@article{HohmuthKhanyareeLangetal.2022, author = {Hohmuth, Nils and Khanyaree, Ifrah and Lang, Anna-Lena and Duering, Ohad and Konigorski, Stefan and Viskovic, Vukasin and Heising, Tobias and Egender, Friedemann and Remschmidt, Cornelius and Leistner, Rasmus}, title = {Participatory disease surveillance for a mass gathering}, series = {BMC public health}, volume = {22}, journal = {BMC public health}, number = {1}, publisher = {BioMed Central}, address = {London}, issn = {1471-2458}, doi = {10.1186/s12889-022-14505-x}, pages = {11}, year = {2022}, abstract = {Background Mass gatherings (MGs) such as music festivals and sports events have been associated with a high risk of SARS-CoV-2 transmission. On-site research can foster knowledge of risk factors for infections and improve risk assessments and precautionary measures at future MGs. We tested a web-based participatory disease surveillance tool to detect COVID-19 infections at and after an outdoor MG by collecting self-reported COVID-19 symptoms and tests. Methods We conducted a digital prospective observational cohort study among fully immunized attendees of a sports festival that took place from September 2 to 5, 2021 in Saxony-Anhalt, Germany. Participants used our study app to report demographic data, COVID-19 tests, symptoms, and their contact behavior. This self-reported data was used to define probable and confirmed COVID-19 cases for the full "study period" (08/12/2021 - 10/31/2021) and within the 14-day "surveillance period" during and after the MG, with the highest likelihood of an MG-related COVID-19 outbreak (09/04/2021 - 09/17/2021). Results A total of 2,808 of 9,242 (30.4\%) event attendees participated in the study. Within the study period, 776 individual symptoms and 5,255 COVID-19 tests were reported. During the 14-day surveillance period around and after the MG, seven probable and seven PCR-confirmed COVID-19 cases were detected. The confirmed cases translated to an estimated seven-day incidence of 125 per 100,000 participants (95\% CI [67.7/100,000, 223/100,000]), which was comparable to the average age-matched incidence in Germany during this time. Overall, weekly numbers of COVID-19 cases were fluctuating over the study period, with another increase at the end of the study period. Conclusion COVID-19 cases attributable to the mass gathering were comparable to the Germany-wide age-matched incidence, implicating that our active participatory disease surveillance tool was able to detect MG-related infections. Further studies are needed to evaluate and apply our participatory disease surveillance tool in other mass gathering settings.}, language = {en} } @inproceedings{HartmannKandilSteckhanetal.2022, author = {Hartmann, Anika M. and Kandil, Farid I. and Steckhan, Nico and H{\"a}upl, Thomas and Kessler, Christian S. and Michalsen, Andreas and Koppold-Liebscher, Daniela A.}, title = {Rheumatoid arthritis benefits from fasting and plant-based diet: an exploratory randomized controlled trial (NUTRIFAST)}, series = {Annals of the rheumatic diseases}, volume = {81}, booktitle = {Annals of the rheumatic diseases}, publisher = {BMJ Publishing Group}, address = {London}, issn = {0003-4967}, doi = {10.1136/annrheumdis-2022-eular.452}, pages = {558 -- 559}, year = {2022}, language = {en} } @inproceedings{MasanneckRaeuberGieseleretal.2022, author = {Masanneck, Lars and R{\"a}uber, S. and Gieseler, Pauline and Ruck, T. and Stern, Ariel Dora and Meuth, S. G. and Pawlitzki, M.}, title = {Geography and a changing technology landscape: analysing coverage of German multiple sclerosis care networks and digital health technology adoption in multiple sclerosis trials}, series = {Multiple sclerosis journal}, volume = {28}, booktitle = {Multiple sclerosis journal}, number = {Supplement 3}, publisher = {Sage}, address = {London}, issn = {1352-4585}, doi = {10.1177/13524585221123687}, pages = {492 -- 493}, year = {2022}, language = {en} } @article{ChromikKlopfensteinPfitzneretal.2022, author = {Chromik, Jonas and Klopfenstein, Sophie Anne Ines and Pfitzner, Bjarne and Sinno, Zeena-Carola and Arnrich, Bert and Balzer, Felix and Poncette, Akira-Sebastian}, title = {Computational approaches to alleviate alarm fatigue in intensive care medicine: a systematic literature review}, series = {Frontiers in digital health}, volume = {4}, journal = {Frontiers in digital health}, publisher = {Frontiers Media}, address = {Lausanne}, issn = {2673-253X}, doi = {10.3389/fdgth.2022.843747}, pages = {15}, year = {2022}, abstract = {Patient monitoring technology has been used to guide therapy and alert staff when a vital sign leaves a predefined range in the intensive care unit (ICU) for decades. However, large amounts of technically false or clinically irrelevant alarms provoke alarm fatigue in staff leading to desensitisation towards critical alarms. With this systematic review, we are following the Preferred Reporting Items for Systematic Reviews (PRISMA) checklist in order to summarise scientific efforts that aimed to develop IT systems to reduce alarm fatigue in ICUs. 69 peer-reviewed publications were included. The majority of publications targeted the avoidance of technically false alarms, while the remainder focused on prediction of patient deterioration or alarm presentation. The investigated alarm types were mostly associated with heart rate or arrhythmia, followed by arterial blood pressure, oxygen saturation, and respiratory rate. Most publications focused on the development of software solutions, some on wearables, smartphones, or headmounted displays for delivering alarms to staff. The most commonly used statistical models were tree-based. In conclusion, we found strong evidence that alarm fatigue can be alleviated by IT-based solutions. However, future efforts should focus more on the avoidance of clinically non-actionable alarms which could be accelerated by improving the data availability.}, language = {en} } @article{PetzoltHoelzleKulliketal.2022, author = {Petzolt, Sophie and H{\"o}lzle, Katharina and Kullik, Oliver and Gergeleit, Wiebke and Radunski, Anne}, title = {Organisational digital transformation of SMEs—development and application of a digital transformation maturity model for business model transformation}, series = {International journal of innovation in management}, volume = {26}, journal = {International journal of innovation in management}, number = {3}, publisher = {World Scientific Publ.}, address = {Singapore}, issn = {1363-9196}, doi = {10.1142/S1363919622400175}, pages = {43}, year = {2022}, abstract = {One of the most challenging difficulties for incumbent organisations, especially small- and medium-sized enterprises (SMEs), is to manage digital transformation driven by technological change. Incumbent organisations' responses to digital transformation have been extensively studied in the current literature. However, most research neglects digital transformation in SMEs. There are hardly any valid developed measures for the maturity of digital transformation. We present a holistic digital transformation maturity model based on an extensive literature review, qualitative computer-assisted data analysis, and empirical findings. The digital transformation maturity model focuses on small- and medium-sized enterprises' unique features and characteristics. We proved the practical applicability and relevance of the digital transformation maturity model in an extensive study involving various organisations, particularly German SMEs (n = 310). Organisations can use this model to assess themselves initially and, through this process, gain a comprehensive understanding of the multiple forms of digital transformation.}, language = {en} } @article{AndjelkovicMarjanovicDraskoetal.2022, author = {Andjelkovic, Marko and Marjanovic, Milos and Drasko, Bojan and Calligaro, Cristiano and Schrape, Oliver and Gatti, Umberto and Kuentzer, Felipe A. and Ilic, Stefan and Ristic, Goran and Krstić, Miloš}, title = {Analysis of single event transient effects in standard delay cells based on decoupling capacitors}, series = {Journal of circuits, systems, and computers : JCSC}, volume = {31}, journal = {Journal of circuits, systems, and computers : JCSC}, number = {18}, publisher = {World Scientific}, address = {Singapore [u.a.]}, issn = {0218-1266}, doi = {10.1142/S0218126622400072}, pages = {24}, year = {2022}, abstract = {Single Event Transients (SETs), i.e., voltage glitches induced in combinational logic as a result of the passage of energetic particles, represent an increasingly critical reliability threat for modern complementary metal oxide semiconductor (CMOS) integrated circuits (ICs) employed in space missions. In rad-hard ICs implemented with standard digital cells, special design techniques should be applied to reduce the Soft Error Rate (SER) due to SETs. To this end, it is essential to consider the SET robustness of individual standard cells. Among the wide range of logic cells available in standard cell libraries, the standard delay cells (SDCs) implemented with the skew-sized inverters are exceptionally vulnerable to SETs. Namely, the SET pulses induced in these cells may be hundreds of picoseconds longer than those in other standard cells. In this work, an alternative design of a SDC based on two inverters and two decoupling capacitors is introduced. Electrical simulations have shown that the propagation delay and SET robustness of the proposed delay cell are strongly influenced by the transistor sizes and supply voltage, while the impact of temperature is moderate. The proposed design is more tolerant to SETs than the SDCs with skew-sized inverters, and occupies less area compared to the hardening configurations based on partial and complete duplication. Due to the low transistor count (only six transistors), the proposed delay cell could also be used as a SET filter.}, language = {en} } @article{BroennekeMuellerMouratisetal.2021, author = {Br{\"o}nneke, Jan Benedikt and M{\"u}ller, Jennifer and Mouratis, Konstantinos and Hagen, Julia and Stern, Ariel Dora}, title = {Regulatory, legal, and market aspects of smart wearables for cardiac monitoring}, series = {Sensors}, volume = {21}, journal = {Sensors}, number = {14}, publisher = {MDPI}, address = {Basel}, issn = {1424-8220}, doi = {10.3390/s21144937}, pages = {19}, year = {2021}, abstract = {In the area of cardiac monitoring, the use of digitally driven technologies is on the rise. While the development of medical products is advancing rapidly, allowing for new use-cases in cardiac monitoring and other areas, regulatory and legal requirements that govern market access are often evolving slowly, sometimes creating market barriers. This article gives a brief overview of the existing clinical studies regarding the use of smart wearables in cardiac monitoring and provides insight into the main regulatory and legal aspects that need to be considered when such products are intended to be used in a health care setting. Based on this brief overview, the article elaborates on the specific requirements in the main areas of authorization/certification and reimbursement/compensation, as well as data protection and data security. Three case studies are presented as examples of specific market access procedures: the USA, Germany, and Belgium. This article concludes that, despite the differences in specific requirements, market access pathways in most countries are characterized by a number of similarities, which should be considered early on in product development. The article also elaborates on how regulatory and legal requirements are currently being adapted for digitally driven wearables and proposes an ongoing evolution of these requirements to facilitate market access for beneficial medical technology in the future.}, language = {en} } @article{OwoyeleTrujillodeMeloetal.2022, author = {Owoyele, Babajide and Trujillo, James and de Melo, Gerard and Pouw, Wim}, title = {Masked-Piper: masking personal identities in visual recordings while preserving multimodal information}, series = {SoftwareX}, volume = {20}, journal = {SoftwareX}, publisher = {Elsevier}, address = {Amsterdam}, issn = {2352-7110}, doi = {10.1016/j.softx.2022.101236}, pages = {4}, year = {2022}, abstract = {In this increasingly data-rich world, visual recordings of human behavior are often unable to be shared due to concerns about privacy. Consequently, data sharing in fields such as behavioral science, multimodal communication, and human movement research is often limited. In addition, in legal and other non-scientific contexts, privacy-related concerns may preclude the sharing of video recordings and thus remove the rich multimodal context that humans recruit to communicate. Minimizing the risk of identity exposure while preserving critical behavioral information would maximize utility of public resources (e.g., research grants) and time invested in audio-visual research. Here we present an open-source computer vision tool that masks the identities of humans while maintaining rich information about communicative body movements. Furthermore, this masking tool can be easily applied to many videos, leveraging computational tools to augment the reproducibility and accessibility of behavioral research. The tool is designed for researchers and practitioners engaged in kinematic and affective research. Application areas include teaching/education, communication and human movement research, CCTV, and legal contexts.}, language = {en} } @article{DattaMorassiSassoKiwitetal.2022, author = {Datta, Suparno and Morassi Sasso, Ariane and Kiwit, Nina and Bose, Subhronil and Nadkarni, Girish and Miotto, Riccardo and B{\"o}ttinger, Erwin P.}, title = {Predicting hypertension onset from longitudinal electronic health records with deep learning}, series = {JAMIA Open}, volume = {5}, journal = {JAMIA Open}, number = {4}, publisher = {Oxford Univ. Press}, address = {Oxford}, issn = {2574-2531}, doi = {10.1093/jamiaopen/ooac097}, pages = {10}, year = {2022}, abstract = {Objective: Hypertension has long been recognized as one of the most important predisposing factors for cardiovascular diseases and mortality. In recent years, machine learning methods have shown potential in diagnostic and predictive approaches in chronic diseases. Electronic health records (EHRs) have emerged as a reliable source of longitudinal data. The aim of this study is to predict the onset of hypertension using modern deep learning (DL) architectures, specifically long short-term memory (LSTM) networks, and longitudinal EHRs. Materials and Methods: We compare this approach to the best performing models reported from previous works, particularly XGboost, applied to aggregated features. Our work is based on data from 233 895 adult patients from a large health system in the United States. We divided our population into 2 distinct longitudinal datasets based on the diagnosis date. To ensure generalization to unseen data, we trained our models on the first dataset (dataset A "train and validation") using cross-validation, and then applied the models to a second dataset (dataset B "test") to assess their performance. We also experimented with 2 different time-windows before the onset of hypertension and evaluated the impact on model performance. Results: With the LSTM network, we were able to achieve an area under the receiver operating characteristic curve value of 0.98 in the "train and validation" dataset A and 0.94 in the "test" dataset B for a prediction time window of 1 year. Lipid disorders, type 2 diabetes, and renal disorders are found to be associated with incident hypertension. Conclusion: These findings show that DL models based on temporal EHR data can improve the identification of patients at high risk of hypertension and corresponding driving factors. In the long term, this work may support identifying individuals who are at high risk for developing hypertension and facilitate earlier intervention to prevent the future development of hypertension.}, language = {en} } @article{BlaesiusFriedrichKatzmannetal.2022, author = {Bl{\"a}sius, Thomas and Friedrich, Tobias and Katzmann, Maximilian and Meyer, Ulrich and Penschuck, Manuel and Weyand, Christopher}, title = {Efficiently generating geometric inhomogeneous and hyperbolic random graphs}, series = {Network Science}, volume = {10}, journal = {Network Science}, number = {4}, publisher = {Cambridge Univ. Press}, address = {New York}, issn = {2050-1242}, doi = {10.1017/nws.2022.32}, pages = {361 -- 380}, year = {2022}, abstract = {Hyperbolic random graphs (HRGs) and geometric inhomogeneous random graphs (GIRGs) are two similar generative network models that were designed to resemble complex real-world networks. In particular, they have a power-law degree distribution with controllable exponent beta and high clustering that can be controlled via the temperature T. We present the first implementation of an efficient GIRG generator running in expected linear time. Besides varying temperatures, it also supports underlying geometries of higher dimensions. It is capable of generating graphs with ten million edges in under a second on commodity hardware. The algorithm can be adapted to HRGs. Our resulting implementation is the fastest sequential HRG generator, despite the fact that we support non-zero temperatures. Though non-zero temperatures are crucial for many applications, most existing generators are restricted to T = 0 . We also support parallelization, although this is not the focus of this paper. Moreover, we note that our generators draw from the correct probability distribution, that is, they involve no approximation. Besides the generators themselves, we also provide an efficient algorithm to determine the non-trivial dependency between the average degree of the resulting graph and the input parameters of the GIRG model. This makes it possible to specify the desired expected average degree as input. Moreover, we investigate the differences between HRGs and GIRGs, shedding new light on the nature of the relation between the two models. Although HRGs represent, in a certain sense, a special case of the GIRG model, we find that a straightforward inclusion does not hold in practice. However, the difference is negligible for most use cases.}, language = {en} } @article{TanKhaliliKarletal.2022, author = {Tan, Jing and Khalili, Ramin and Karl, Holger and Hecker, Artur}, title = {Multi-agent reinforcement learning for long-term network resource allocation through auction: a V2X application}, series = {Computer communications : the international journal for the computer and telecommunications industry}, volume = {194}, journal = {Computer communications : the international journal for the computer and telecommunications industry}, publisher = {Elsevier Science}, address = {Amsterdam [u.a.]}, issn = {0140-3664}, doi = {10.1016/j.comcom.2022.07.047}, pages = {333 -- 347}, year = {2022}, abstract = {We formulate offloading of computational tasks from a dynamic group of mobile agents (e.g., cars) as decentral-ized decision making among autonomous agents. We design an interaction mechanism that incentivizes such agents to align private and system goals by balancing between competition and cooperation. In the static case, the mechanism provably has Nash equilibria with optimal resource allocation. In a dynamic environment, this mechanism's requirement of complete information is impossible to achieve. For such environments, we propose a novel multi-agent online learning algorithm that learns with partial, delayed and noisy state information, thus greatly reducing information need. Our algorithm is also capable of learning from long-term and sparse reward signals with varying delay. Empirical results from the simulation of a V2X application confirm that through learning, agents with the learning algorithm significantly improve both system and individual performance, reducing up to 30\% of offloading failure rate, communication overhead and load variation, increasing computation resource utilization and fairness. Results also confirm the algorithm's good convergence and generalization property in different environments.}, language = {en} } @article{ReimannBuchheimSemmoetal.2022, author = {Reimann, Max and Buchheim, Benito and Semmo, Amir and D{\"o}llner, J{\"u}rgen and Trapp, Matthias}, title = {Controlling strokes in fast neural style transfer using content transforms}, series = {The visual computer : international journal of computer graphics}, volume = {38}, journal = {The visual computer : international journal of computer graphics}, publisher = {Springer}, address = {New York}, issn = {0178-2789}, doi = {10.1007/s00371-077-07518-x}, pages = {4019 -- 4033}, year = {2022}, abstract = {Fast style transfer methods have recently gained popularity in art-related applications as they make a generalized real-time stylization of images practicable. However, they are mostly limited to one-shot stylizations concerning the interactive adjustment of style elements. In particular, the expressive control over stroke sizes or stroke orientations remains an open challenge. To this end, we propose a novel stroke-adjustable fast style transfer network that enables simultaneous control over the stroke size and intensity, and allows a wider range of expressive editing than current approaches by utilizing the scale-variance of convolutional neural networks. Furthermore, we introduce a network-agnostic approach for style-element editing by applying reversible input transformations that can adjust strokes in the stylized output. At this, stroke orientations can be adjusted, and warping-based effects can be applied to stylistic elements, such as swirls or waves. To demonstrate the real-world applicability of our approach, we present StyleTune, a mobile app for interactive editing of neural style transfers at multiple levels of control. Our app allows stroke adjustments on a global and local level. It furthermore implements an on-device patch-based upsampling step that enables users to achieve results with high output fidelity and resolutions of more than 20 megapixels. Our approach allows users to art-direct their creations and achieve results that are not possible with current style transfer applications.}, language = {en} } @article{WenigSchmidlPapenbrock2022, author = {Wenig, Phillip and Schmidl, Sebastian and Papenbrock, Thorsten}, title = {TimeEval: a benchmarking toolkit for time series anomaly detection algorithms}, series = {Proceedings of the VLDB Endowment}, volume = {15}, journal = {Proceedings of the VLDB Endowment}, number = {12}, publisher = {Association for Computing Machinery}, address = {New York, NY}, issn = {2150-8097}, doi = {10.14778/3554821.3554873}, pages = {3678 -- 3681}, year = {2022}, abstract = {Detecting anomalous subsequences in time series is an important task in time series analytics because it serves the identification of special events, such as production faults, delivery bottlenecks, system defects, or heart flicker. Consequently, many algorithms have been developed for the automatic detection of such anomalous patterns. The enormous number of approaches (i.e., more than 158 as of today), the lack of properly labeled test data, and the complexity of time series anomaly benchmarking have, though, led to a situation where choosing the best detection technique for a given anomaly detection task is a difficult challenge. In this demonstration, we present TIMEEVAL, an extensible, scalable and automatic benchmarking toolkit for time series anomaly detection algorithms. TIMEEVAL includes an extensive data generator and supports both interactive and batch evaluation scenarios. With our novel toolkit, we aim to ease the evaluation effort and help the community to provide more meaningful evaluations.}, language = {en} } @article{SimoniniZecchiniBergamaschietal.2022, author = {Simonini, Giovanni and Zecchini, Luca and Bergamaschi, Sonia and Naumann, Felix}, title = {Entity resolution on-demand}, series = {Proceedings of the VLDB Endowment}, volume = {15}, journal = {Proceedings of the VLDB Endowment}, number = {7}, publisher = {Association for Computing Machinery}, address = {New York}, issn = {2150-8097}, doi = {10.14778/3523210.3523226}, pages = {1506 -- 1518}, year = {2022}, abstract = {Entity Resolution (ER) aims to identify and merge records that refer to the same real-world entity. ER is typically employed as an expensive cleaning step on the entire data before consuming it. Yet, determining which entities are useful once cleaned depends solely on the user's application, which may need only a fraction of them. For instance, when dealing with Web data, we would like to be able to filter the entities of interest gathered from multiple sources without cleaning the entire, continuously-growing data. Similarly, when querying data lakes, we want to transform data on-demand and return the results in a timely manner-a fundamental requirement of ELT (Extract-Load-Transform) pipelines. We propose BrewER, a framework to evaluate SQL SP queries on dirty data while progressively returning results as if they were issued on cleaned data. BrewER tries to focus the cleaning effort on one entity at a time, following an ORDER BY predicate. Thus, it inherently supports top-k and stop-and-resume execution. For a wide range of applications, a significant amount of resources can be saved. We exhaustively evaluate and show the efficacy of BrewER on four real-world datasets.}, language = {en} } @article{BensonPapkeRabl2022, author = {Benson, Lawrence and Papke, Leon and Rabl, Tilmann}, title = {PerMA-Bench: benchmarking persistent memory access}, series = {Proceedings of the VLDB Endowment}, volume = {15}, journal = {Proceedings of the VLDB Endowment}, number = {11}, publisher = {Association for Computing Machinery}, address = {New York, NY}, issn = {2150-8097}, doi = {10.14778/3551793.3551807}, pages = {2463 -- 2476}, year = {2022}, abstract = {Persistent memory's (PMem) byte-addressability and persistence at DRAM-like speed with SSD-like capacity have the potential to cause a major performance shift in database storage systems. With the availability of Intel Optane DC Persistent Memory, initial benchmarks evaluate the performance of real PMem hardware. However, these results apply to only a single server and it is not yet clear how workloads compare across different PMem servers. In this paper, we propose PerMA-Bench, a con.gurable benchmark framework that allows users to evaluate the bandwidth, latency, and operations per second for customizable database-related PMem access. Based on PerMA-Bench, we perform an extensive evaluation of PMem performance across four di.erent server configurations, containing both first- and second-generation Optane, with additional parameters such as DIMM power budget and number of DIMMs per server. We validate our results with existing systems and show the impact of low-level design choices. We conduct a price-performance comparison that shows while there are large differences across Optane DIMMs, PMem is generally competitive with DRAM. We discuss our findings and identify eight general and implementation-specific aspects that influence PMem performance and should be considered in future work to improve PMem-aware designs.}, language = {en} } @article{KonakvandeWaterDoeringetal.2023, author = {Konak, Orhan and van de Water, Robin and D{\"o}ring, Valentin and Fiedler, Tobias and Liebe, Lucas and Masopust, Leander and Postnov, Kirill and Sauerwald, Franz and Treykorn, Felix and Wischmann, Alexander and Gjoreski, Hristijan and Luštrek, Mitja and Arnrich, Bert}, title = {HARE}, series = {Sensors}, volume = {23}, journal = {Sensors}, number = {23}, publisher = {MDPI}, address = {Basel}, issn = {1424-8220}, doi = {10.3390/s23239571}, pages = {23}, year = {2023}, abstract = {Sensor-based human activity recognition is becoming ever more prevalent. The increasing importance of distinguishing human movements, particularly in healthcare, coincides with the advent of increasingly compact sensors. A complex sequence of individual steps currently characterizes the activity recognition pipeline. It involves separate data collection, preparation, and processing steps, resulting in a heterogeneous and fragmented process. To address these challenges, we present a comprehensive framework, HARE, which seamlessly integrates all necessary steps. HARE offers synchronized data collection and labeling, integrated pose estimation for data anonymization, a multimodal classification approach, and a novel method for determining optimal sensor placement to enhance classification results. Additionally, our framework incorporates real-time activity recognition with on-device model adaptation capabilities. To validate the effectiveness of our framework, we conducted extensive evaluations using diverse datasets, including our own collected dataset focusing on nursing activities. Our results show that HARE's multimodal and on-device trained model outperforms conventional single-modal and offline variants. Furthermore, our vision-based approach for optimal sensor placement yields comparable results to the trained model. Our work advances the field of sensor-based human activity recognition by introducing a comprehensive framework that streamlines data collection and classification while offering a novel method for determining optimal sensor placement.}, language = {en} } @article{ZhouFischerBrahmsetal.2023, author = {Zhou, Lin and Fischer, Eric and Brahms, Clemens Markus and Granacher, Urs and Arnrich, Bert}, title = {DUO-GAIT}, series = {Scientific data}, volume = {10}, journal = {Scientific data}, number = {1}, publisher = {Nature Publ. Group}, address = {London}, issn = {2052-4463}, doi = {10.1038/s41597-023-02391-w}, pages = {10}, year = {2023}, abstract = {In recent years, there has been a growing interest in developing and evaluating gait analysis algorithms based on inertial measurement unit (IMU) data, which has important implications, including sports, assessment of diseases, and rehabilitation. Multi-tasking and physical fatigue are two relevant aspects of daily life gait monitoring, but there is a lack of publicly available datasets to support the development and testing of methods using a mobile IMU setup. We present a dataset consisting of 6-minute walks under single- (only walking) and dual-task (walking while performing a cognitive task) conditions in unfatigued and fatigued states from sixteen healthy adults. Especially, nine IMUs were placed on the head, chest, lower back, wrists, legs, and feet to record under each of the above-mentioned conditions. The dataset also includes a rich set of spatio-temporal gait parameters that capture the aspects of pace, symmetry, and variability, as well as additional study-related information to support further analysis. This dataset can serve as a foundation for future research on gait monitoring in free-living environments.}, language = {en} } @article{AndersArnrich2022, author = {Anders, Christoph and Arnrich, Bert}, title = {Wearable electroencephalography and multi-modal mental state classification: a systematic literature review}, series = {Computers in biology and medicine : an international journal}, volume = {150}, journal = {Computers in biology and medicine : an international journal}, publisher = {Elsevier Science}, address = {Amsterdam [u.a.]}, issn = {0010-4825}, doi = {10.1016/j.compbiomed.2022.106088}, pages = {18}, year = {2022}, abstract = {Background: Wearable multi-modal time-series classification applications outperform their best uni-modal counterparts and hold great promise. A modality that directly measures electrical correlates from the brain is electroencephalography. Due to varying noise sources, different key brain regions, key frequency bands, and signal characteristics like non-stationarity, techniques for data pre-processing and classification algorithms are task-dependent. Method: Here, a systematic literature review on mental state classification for wearable electroencephalog-raphy is presented. Four search terms in different combinations were used for an in-title search. The search was executed on the 29th of June 2022, across Google Scholar, PubMed, IEEEXplore, and ScienceDirect. 76 most relevant publications were set into context as the current state-of-the-art in mental state time-series classification. Results: Pre-processing techniques, features, and time-series classification models were analyzed. Across publications, a window length of one second was mainly chosen for classification and spectral features were utilized the most. The achieved performance per time-series classification model is analyzed, finding linear discriminant analysis, decision trees, and k-nearest neighbors models outperform support-vector machines by a factor of up to 1.5. A historical analysis depicts future trends while under-reported aspects relevant to practical applications are discussed. Conclusions: Five main conclusions are given, covering utilization of available area for electrode placement on the head, most often or scarcely utilized features and time-series classification model architectures, baseline reporting practices, as well as explainability and interpretability of Deep Learning. The importance of a 'test battery' assessing the influence of data pre-processing and multi-modality on time-series classification performance is emphasized.}, language = {en} } @article{NordmeyerKrausZiehmetal.2023, author = {Nordmeyer, Sarah and Kraus, Milena and Ziehm, Matthias and Kirchner, Marieluise and Schafstedde, Marie and Kelm, Marcus and Niquet, Sylvia and Stephen, Mariet Mathew and Baczko, Istvan and Knosalla, Christoph and Schapranow, Matthieu-Patrick and Dittmar, Gunnar and Gotthardt, Michael and Falcke, Martin and Regitz-Zagrosek, Vera and Kuehne, Titus and Mertins, Philipp}, title = {Disease- and sex-specific differences in patients with heart valve disease}, series = {Life Science Alliance}, volume = {6}, journal = {Life Science Alliance}, number = {3}, publisher = {EMBO Press}, address = {Heidelberg}, issn = {2575-1077}, doi = {10.26508/lsa.202201411}, pages = {18}, year = {2023}, abstract = {Pressure overload in patients with aortic valve stenosis and volume overload in mitral valve regurgitation trigger specific forms of cardiac remodeling; however, little is known about similarities and differences in myocardial proteome regulation. We performed proteome profiling of 75 human left ventricular myocardial biopsies (aortic stenosis = 41, mitral regurgitation = 17, and controls = 17) using high-resolution tandem mass spectrometry next to clinical and hemodynamic parameter acquisition. In patients of both disease groups, proteins related to ECM and cytoskeleton were more abundant, whereas those related to energy metabolism and proteostasis were less abundant compared with controls. In addition, disease group-specific and sex-specific differences have been observed. Male patients with aortic stenosis showed more proteins related to fibrosis and less to energy metabolism, whereas female patients showed strong reduction in proteostasis-related proteins. Clinical imaging was in line with proteomic findings, showing elevation of fibrosis in both patient groups and sex differences. Disease-and sex-specific proteomic profiles provide insight into cardiac remodeling in patients with heart valve disease and might help improve the understanding of molecular mechanisms and the development of individualized treatment strategies.}, language = {en} } @article{TalebRohrerBergneretal.2022, author = {Taleb, Aiham and Rohrer, Csaba and Bergner, Benjamin and De Leon, Guilherme and Rodrigues, Jonas Almeida and Schwendicke, Falk and Lippert, Christoph and Krois, Joachim}, title = {Self-supervised learning methods for label-efficient dental caries classification}, series = {Diagnostics : open access journal}, volume = {12}, journal = {Diagnostics : open access journal}, number = {5}, publisher = {MDPI}, address = {Basel}, issn = {2075-4418}, doi = {10.3390/diagnostics12051237}, pages = {15}, year = {2022}, abstract = {High annotation costs are a substantial bottleneck in applying deep learning architectures to clinically relevant use cases, substantiating the need for algorithms to learn from unlabeled data. In this work, we propose employing self-supervised methods. To that end, we trained with three self-supervised algorithms on a large corpus of unlabeled dental images, which contained 38K bitewing radiographs (BWRs). We then applied the learned neural network representations on tooth-level dental caries classification, for which we utilized labels extracted from electronic health records (EHRs). Finally, a holdout test-set was established, which consisted of 343 BWRs and was annotated by three dental professionals and approved by a senior dentist. This test-set was used to evaluate the fine-tuned caries classification models. Our experimental results demonstrate the obtained gains by pretraining models using self-supervised algorithms. These include improved caries classification performance (6 p.p. increase in sensitivity) and, most importantly, improved label-efficiency. In other words, the resulting models can be fine-tuned using few labels (annotations). Our results show that using as few as 18 annotations can produce >= 45\% sensitivity, which is comparable to human-level diagnostic performance. This study shows that self-supervision can provide gains in medical image analysis, particularly when obtaining labels is costly and expensive.}, language = {en} } @article{TangNakamotoSternetal.2022, author = {Tang, Mitchell and Nakamoto, Carter H. and Stern, Ariel Dora and Mehrotra, Ateev}, title = {Trends in remote patient monitoring use in traditional medicare}, series = {JAMA internal medicine}, volume = {182}, journal = {JAMA internal medicine}, number = {9}, publisher = {American Medical Association}, address = {Chicago, Ill.}, issn = {2168-6106}, doi = {10.1001/jamainternmed.2022.3043}, pages = {1005 -- 1006}, year = {2022}, language = {en} } @article{AltenburgGieseWangetal.2022, author = {Altenburg, Tom and Giese, Sven Hans-Joachim and Wang, Shengbo and Muth, Thilo and Renard, Bernhard Y.}, title = {Ad hoc learning of peptide fragmentation from mass spectra enables an interpretable detection of phosphorylated and cross-linked peptides}, series = {Nature machine intelligence}, volume = {4}, journal = {Nature machine intelligence}, number = {4}, publisher = {Springer Nature Publishing}, address = {London}, issn = {2522-5839}, doi = {10.1038/s42256-022-00467-7}, pages = {378 -- 388}, year = {2022}, abstract = {Fragmentation of peptides leaves characteristic patterns in mass spectrometry data, which can be used to identify protein sequences, but this method is challenging for mutated or modified sequences for which limited information exist. Altenburg et al. use an ad hoc learning approach to learn relevant patterns directly from unannotated fragmentation spectra. Mass spectrometry-based proteomics provides a holistic snapshot of the entire protein set of living cells on a molecular level. Currently, only a few deep learning approaches exist that involve peptide fragmentation spectra, which represent partial sequence information of proteins. Commonly, these approaches lack the ability to characterize less studied or even unknown patterns in spectra because of their use of explicit domain knowledge. Here, to elevate unrestricted learning from spectra, we introduce 'ad hoc learning of fragmentation' (AHLF), a deep learning model that is end-to-end trained on 19.2 million spectra from several phosphoproteomic datasets. AHLF is interpretable, and we show that peak-level feature importance values and pairwise interactions between peaks are in line with corresponding peptide fragments. We demonstrate our approach by detecting post-translational modifications, specifically protein phosphorylation based on only the fragmentation spectrum without a database search. AHLF increases the area under the receiver operating characteristic curve (AUC) by an average of 9.4\% on recent phosphoproteomic data compared with the current state of the art on this task. Furthermore, use of AHLF in rescoring search results increases the number of phosphopeptide identifications by a margin of up to 15.1\% at a constant false discovery rate. To show the broad applicability of AHLF, we use transfer learning to also detect cross-linked peptides, as used in protein structure analysis, with an AUC of up to 94\%.}, language = {en} } @article{KonigorskiWernickeSlosareketal.2022, author = {Konigorski, Stefan and Wernicke, Sarah and Slosarek, Tamara and Zenner, Alexander M. and Strelow, Nils and Ruether, Darius F. and Henschel, Florian and Manaswini, Manisha and Pottb{\"a}cker, Fabian and Edelman, Jonathan A. and Owoyele, Babajide and Danieletto, Matteo and Golden, Eddye and Zweig, Micol and Nadkarni, Girish N. and B{\"o}ttinger, Erwin}, title = {StudyU: a platform for designing and conducting innovative digital N-of-1 trials}, series = {Journal of medical internet research}, volume = {24}, journal = {Journal of medical internet research}, number = {7}, publisher = {Healthcare World}, address = {Richmond, Va.}, issn = {1439-4456}, doi = {10.2196/35884}, pages = {12}, year = {2022}, abstract = {N-of-1 trials are the gold standard study design to evaluate individual treatment effects and derive personalized treatment strategies. Digital tools have the potential to initiate a new era of N-of-1 trials in terms of scale and scope, but fully functional platforms are not yet available. Here, we present the open source StudyU platform, which includes the StudyU Designer and StudyU app. With the StudyU Designer, scientists are given a collaborative web application to digitally specify, publish, and conduct N-of-1 trials. The StudyU app is a smartphone app with innovative user-centric elements for participants to partake in trials published through the StudyU Designer to assess the effects of different interventions on their health. Thereby, the StudyU platform allows clinicians and researchers worldwide to easily design and conduct digital N-of-1 trials in a safe manner. We envision that StudyU can change the landscape of personalized treatments both for patients and healthy individuals, democratize and personalize evidence generation for self-optimization and medicine, and can be integrated in clinical practice.}, language = {en} } @misc{DellepianeVaidJaladankietal.2021, author = {Dellepiane, Sergio and Vaid, Akhil and Jaladanki, Suraj K. and Coca, Steven and Fayad, Zahi A. and Charney, Alexander W. and B{\"o}ttinger, Erwin and He, John Cijiang and Glicksberg, Benjamin S. and Chan, Lili and Nadkarni, Girish}, title = {Acute kidney injury in patients hospitalized with COVID-19 in New York City}, series = {Zweitver{\"o}ffentlichungen der Universit{\"a}t Potsdam : Reihe der Digital Engineering Fakult{\"a}t}, journal = {Zweitver{\"o}ffentlichungen der Universit{\"a}t Potsdam : Reihe der Digital Engineering Fakult{\"a}t}, number = {5}, issn = {2590-0595}, doi = {10.25932/publishup-58541}, url = {http://nbn-resolving.de/urn:nbn:de:kobv:517-opus4-585415}, pages = {5}, year = {2021}, language = {en} } @article{LangenhanJaegerBaumetal.2022, author = {Langenhan, Jennifer and Jaeger, Carsten and Baum, Katharina and Simon, Mareike and Lisec, Jan}, title = {A flexible tool to correct superimposed mass isotopologue distributions in GC-APCI-MS flux experiments}, series = {Metabolites}, volume = {12}, journal = {Metabolites}, number = {5}, publisher = {MDPI}, address = {Basel}, issn = {2218-1989}, doi = {10.3390/metabo12050408}, pages = {10}, year = {2022}, abstract = {The investigation of metabolic fluxes and metabolite distributions within cells by means of tracer molecules is a valuable tool to unravel the complexity of biological systems. Technological advances in mass spectrometry (MS) technology such as atmospheric pressure chemical ionization (APCI) coupled with high resolution (HR), not only allows for highly sensitive analyses but also broadens the usefulness of tracer-based experiments, as interesting signals can be annotated de novo when not yet present in a compound library. However, several effects in the APCI ion source, i.e., fragmentation and rearrangement, lead to superimposed mass isotopologue distributions (MID) within the mass spectra, which need to be corrected during data evaluation as they will impair enrichment calculation otherwise. Here, we present and evaluate a novel software tool to automatically perform such corrections. We discuss the different effects, explain the implemented algorithm, and show its application on several experimental datasets. This adjustable tool is available as an R package from CRAN.}, language = {en} } @article{SinnGieseStuiveretal.2022, author = {Sinn, Ludwig R. and Giese, Sven Hans-Joachim and Stuiver, Marchel and Rappsilber, Juri}, title = {Leveraging parameter dependencies in high-field asymmetric waveform ion-mobility spectrometry and size exclusion chromatography for proteome-wide cross-linking mass spectrometry}, series = {Analytical chemistry : the authoritative voice of the analytical community}, volume = {94}, journal = {Analytical chemistry : the authoritative voice of the analytical community}, number = {11}, publisher = {American Chemical Society}, address = {Columbus, Ohio}, issn = {0003-2700}, doi = {10.1021/acs.analchem.1c04373}, pages = {4627 -- 4634}, year = {2022}, abstract = {Ion-mobility spectrometry shows great promise to tackle analytically challenging research questions by adding another separation dimension to liquid chromatography-mass spectrometry. The understanding of how analyte properties influence ion mobility has increased through recent studies, but no clear rationale for the design of customized experimental settings has emerged. Here, we leverage machine learning to deepen our understanding of field asymmetric waveform ion-mobility spectrometry for the analysis of cross-linked peptides. Knowing that predominantly m/z and then the size and charge state of an analyte influence the separation, we found ideal compensation voltages correlating with the size exclusion chromatography fraction number. The effect of this relationship on the analytical depth can be substantial as exploiting it allowed us to almost double unique residue pair detections in a proteome-wide cross-linking experiment. Other applications involving liquid- and gas-phase separation may also benefit from considering such parameter dependencies.}, language = {en} } @article{GevayRablBressetal.2022, author = {Gevay, Gabor E. and Rabl, Tilmann and Bress, Sebastian and Maclai-Tahy, Lorand and Quiane-Ruiz, Jorge-Arnulfo and Markl, Volker}, title = {Imperative or functional control flow handling}, series = {SIGMOD record}, volume = {51}, journal = {SIGMOD record}, number = {1}, publisher = {Association for Computing Machinery}, address = {New York}, issn = {0163-5808}, doi = {10.1145/3542700.3542715}, pages = {60 -- 67}, year = {2022}, abstract = {Modern data analysis tasks often involve control flow statements, such as the iterations in PageRank and K-means. To achieve scalability, developers usually implement these tasks in distributed dataflow systems, such as Spark and Flink. Designers of such systems have to choose between providing imperative or functional control flow constructs to users. Imperative constructs are easier to use, but functional constructs are easier to compile to an efficient dataflow job. We propose Mitos, a system where control flow is both easy to use and efficient. Mitos relies on an intermediate representation based on the static single assignment form. This allows us to abstract away from specific control flow constructs and treat any imperative control flow uniformly both when building the dataflow job and when coordinating the distributed execution.}, language = {en} } @article{VerweijNeyThompson2022, author = {Verweij, Marco and Ney, Steven and Thompson, Michael}, title = {Cultural Theory's contributions to climate science}, series = {European journal for philosophy of science}, volume = {12}, journal = {European journal for philosophy of science}, number = {2}, publisher = {Springer}, address = {Dordrecht}, issn = {1879-4912}, doi = {10.1007/s13194-022-00464-y}, pages = {13}, year = {2022}, abstract = {In his article, 'Social constructionism and climate science denial', Hansson claims to present empirical evidence that the cultural theory developed by Dame Mary Douglas, Aaron Wildavsky and ourselves (among others) leads to (climate) science denial. In this reply, we show that there is no validity to these claims. First, we show that Hansson's empirical evidence that cultural theory has led to climate science denial falls apart under closer inspection. Contrary to Hansson's claims, cultural theory has made significant contributions to understanding and addressing climate change. Second, we discuss various features of Douglas' cultural theory that differentiate it from other constructivist approaches and make it compatible with the scientific method. Thus, we also demonstrate that cultural theory cannot be accused of epistemic relativism.}, language = {en} } @article{Boissier2021, author = {Boissier, Martin}, title = {Robust and budget-constrained encoding configurations for in-memory database systems}, series = {Proceedings of the VLDB Endowment}, volume = {15}, journal = {Proceedings of the VLDB Endowment}, number = {4}, publisher = {Association for Computing Machinery (ACM)}, address = {[New York]}, issn = {2150-8097}, doi = {10.14778/3503585.3503588}, pages = {780 -- 793}, year = {2021}, abstract = {Data encoding has been applied to database systems for decades as it mitigates bandwidth bottlenecks and reduces storage requirements. But even in the presence of these advantages, most in-memory database systems use data encoding only conservatively as the negative impact on runtime performance can be severe. Real-world systems with large parts being infrequently accessed and cost efficiency constraints in cloud environments require solutions that automatically and efficiently select encoding techniques, including heavy-weight compression. In this paper, we introduce workload-driven approaches to automaticaly determine memory budget-constrained encoding configurations using greedy heuristics and linear programming. We show for TPC-H, TPC-DS, and the Join Order Benchmark that optimized encoding configurations can reduce the main memory footprint significantly without a loss in runtime performance over state-of-the-art dictionary encoding. To yield robust selections, we extend the linear programming-based approach to incorporate query runtime constraints and mitigate unexpected performance regressions.}, language = {en} } @article{BjoerkHoelzleBoer2021, author = {Bj{\"o}rk, Jennie and H{\"o}lzle, Katharina and Boer, Harry}, title = {'What will we learn from the current crisis?'}, series = {Creativity and innovation management}, volume = {30}, journal = {Creativity and innovation management}, number = {2}, publisher = {Wiley-Blackwell}, address = {Oxford [u.a.]}, issn = {0963-1690}, doi = {10.1111/caim.12442}, pages = {231 -- 232}, year = {2021}, language = {en} } @article{BonifatiMiorNaumannetal.2022, author = {Bonifati, Angela and Mior, Michael J. and Naumann, Felix and Noack, Nele Sina}, title = {How inclusive are we?}, series = {SIGMOD record / Association for Computing Machinery, Special Interest Group on Management of Data}, volume = {50}, journal = {SIGMOD record / Association for Computing Machinery, Special Interest Group on Management of Data}, number = {4}, publisher = {Association for Computing Machinery}, address = {New York}, issn = {0163-5808}, doi = {10.1145/3516431.3516438}, pages = {30 -- 35}, year = {2022}, abstract = {ACM SIGMOD, VLDB and other database organizations have committed to fostering an inclusive and diverse community, as do many other scientific organizations. Recently, different measures have been taken to advance these goals, especially for underrepresented groups. One possible measure is double-blind reviewing, which aims to hide gender, ethnicity, and other properties of the authors.
We report the preliminary results of a gender diversity analysis of publications of the database community across several peer-reviewed venues, and also compare women's authorship percentages in both single-blind and double-blind venues along the years. We also obtained a cross comparison of the obtained results in data management with other relevant areas in Computer Science.}, language = {en} } @article{ReimannBuchheimSemmoetal.2022, author = {Reimann, Max and Buchheim, Benito and Semmo, Amir and D{\"o}llner, J{\"u}rgen and Trapp, Matthias}, title = {Controlling strokes in fast neural style transfer using content transforms}, series = {The Visual Computer}, volume = {38}, journal = {The Visual Computer}, number = {12}, publisher = {Springer}, address = {New York}, issn = {0178-2789}, doi = {10.1007/s00371-022-02518-x}, pages = {4019 -- 4033}, year = {2022}, abstract = {Fast style transfer methods have recently gained popularity in art-related applications as they make a generalized real-time stylization of images practicable. However, they are mostly limited to one-shot stylizations concerning the interactive adjustment of style elements. In particular, the expressive control over stroke sizes or stroke orientations remains an open challenge. To this end, we propose a novel stroke-adjustable fast style transfer network that enables simultaneous control over the stroke size and intensity, and allows a wider range of expressive editing than current approaches by utilizing the scale-variance of convolutional neural networks. Furthermore, we introduce a network-agnostic approach for style-element editing by applying reversible input transformations that can adjust strokes in the stylized output. At this, stroke orientations can be adjusted, and warping-based effects can be applied to stylistic elements, such as swirls or waves. To demonstrate the real-world applicability of our approach, we present StyleTune, a mobile app for interactive editing of neural style transfers at multiple levels of control. Our app allows stroke adjustments on a global and local level. It furthermore implements an on-device patch-based upsampling step that enables users to achieve results with high output fidelity and resolutions of more than 20 megapixels. Our approach allows users to art-direct their creations and achieve results that are not possible with current style transfer applications.}, language = {en} } @article{BorchertMockTomczaketal.2021, author = {Borchert, Florian and Mock, Andreas and Tomczak, Aurelie and H{\"u}gel, Jonas and Alkarkoukly, Samer and Knurr, Alexander and Volckmar, Anna-Lena and Stenzinger, Albrecht and Schirmacher, Peter and Debus, J{\"u}rgen and J{\"a}ger, Dirk and Longerich, Thomas and Fr{\"o}hling, Stefan and Eils, Roland and Bougatf, Nina and Sax, Ulrich and Schapranow, Matthieu-Patrick}, title = {Correction to: Knowledge bases and software support for variant interpretation in precision oncology}, series = {Briefings in bioinformatics}, volume = {22}, journal = {Briefings in bioinformatics}, number = {6}, publisher = {Oxford Univ. Press}, address = {Oxford}, issn = {1467-5463}, doi = {10.1093/bib/bbab246}, pages = {1}, year = {2021}, language = {en} } @article{BorchertMockTomczaketal.2021, author = {Borchert, Florian and Mock, Andreas and Tomczak, Aurelie and H{\"u}gel, Jonas and Alkarkoukly, Samer and Knurr, Alexander and Volckmar, Anna-Lena and Stenzinger, Albrecht and Schirmacher, Peter and Debus, J{\"u}rgen and J{\"a}ger, Dirk and Longerich, Thomas and Fr{\"o}hling, Stefan and Eils, Roland and Bougatf, Nina and Sax, Ulrich and Schapranow, Matthieu-Patrick}, title = {Knowledge bases and software support for variant interpretation in precision oncology}, series = {Briefings in bioinformatics}, volume = {22}, journal = {Briefings in bioinformatics}, number = {6}, publisher = {Oxford Univ. Press}, address = {Oxford}, issn = {1467-5463}, doi = {10.1093/bib/bbab134}, pages = {17}, year = {2021}, abstract = {Precision oncology is a rapidly evolving interdisciplinary medical specialty. Comprehensive cancer panels are becoming increasingly available at pathology departments worldwide, creating the urgent need for scalable cancer variant annotation and molecularly informed treatment recommendations. A wealth of mainly academia-driven knowledge bases calls for software tools supporting the multi-step diagnostic process. We derive a comprehensive list of knowledge bases relevant for variant interpretation by a review of existing literature followed by a survey among medical experts from university hospitals in Germany. In addition, we review cancer variant interpretation tools, which integrate multiple knowledge bases. We categorize the knowledge bases along the diagnostic process in precision oncology and analyze programmatic access options as well as the integration of knowledge bases into software tools. The most commonly used knowledge bases provide good programmatic access options and have been integrated into a range of software tools. For the wider set of knowledge bases, access options vary across different parts of the diagnostic process. Programmatic access is limited for information regarding clinical classifications of variants and for therapy recommendations. The main issue for databases used for biological classification of pathogenic variants and pathway context information is the lack of standardized interfaces. There is no single cancer variant interpretation tool that integrates all identified knowledge bases. Specialized tools are available and need to be further developed for different steps in the diagnostic process.}, language = {en} } @article{PrillWalterKrolikowskaetal.2021, author = {Prill, Robert and Walter, Marina and Kr{\´o}likowska, Aleksandra and Becker, Roland}, title = {A systematic review of diagnostic accuracy and clinical applications of wearable movement sensors for knee joint rehabilitation}, series = {Sensors}, volume = {21}, journal = {Sensors}, number = {24}, publisher = {MDPI}, address = {Basel}, issn = {1424-8220}, doi = {10.3390/s21248221}, pages = {14}, year = {2021}, abstract = {In clinical practice, only a few reliable measurement instruments are available for monitoring knee joint rehabilitation. Advances to replace motion capturing with sensor data measurement have been made in the last years. Thus, a systematic review of the literature was performed, focusing on the implementation, diagnostic accuracy, and facilitators and barriers of integrating wearable sensor technology in clinical practices based on a Preferred Reporting Items for Systematic Reviews and Meta-Analyses (PRISMA) statement. For critical appraisal, the COSMIN Risk of Bias tool for reliability and measurement of error was used. PUBMED, Prospero, Cochrane database, and EMBASE were searched for eligible studies. Six studies reporting reliability aspects in using wearable sensor technology at any point after knee surgery in humans were included. All studies reported excellent results with high reliability coefficients, high limits of agreement, or a few detectable errors. They used different or partly inappropriate methods for estimating reliability or missed reporting essential information. Therefore, a moderate risk of bias must be considered. Further quality criterion studies in clinical settings are needed to synthesize the evidence for providing transparent recommendations for the clinical use of wearable movement sensors in knee joint rehabilitation.}, language = {en} } @article{ChanJaladankiSomanietal.2021, author = {Chan, Lili and Jaladanki, Suraj K. and Somani, Sulaiman and Paranjpe, Ishan and Kumar, Arvind and Zhao, Shan and Kaufman, Lewis and Leisman, Staci and Sharma, Shuchita and He, John Cijiang and Murphy, Barbara and Fayad, Zahi A. and Levin, Matthew A. and B{\"o}ttinger, Erwin and Charney, Alexander W. and Glicksberg, Benjamin and Coca, Steven G. and Nadkarni, Girish N.}, title = {Outcomes of patients on maintenance dialysis hospitalized with COVID-19}, series = {Clinical journal of the American Society of Nephrology : CJASN}, volume = {16}, journal = {Clinical journal of the American Society of Nephrology : CJASN}, number = {3}, publisher = {American Society of Nephrology}, address = {Washington}, organization = {Mount Sinai Covid I}, issn = {1555-9041}, doi = {10.2215/CJN.12360720}, pages = {452 -- 455}, year = {2021}, language = {en} } @article{DattaSachsFreitasdaCruzetal.2021, author = {Datta, Suparno and Sachs, Jan Philipp and Freitas da Cruz, Harry and Martensen, Tom and Bode, Philipp and Morassi Sasso, Ariane and Glicksberg, Benjamin S. and B{\"o}ttinger, Erwin}, title = {FIBER}, series = {JAMIA open}, volume = {4}, journal = {JAMIA open}, number = {3}, publisher = {Oxford Univ. Press}, address = {Oxford}, issn = {2574-2531}, doi = {10.1093/jamiaopen/ooab048}, pages = {10}, year = {2021}, abstract = {Objectives: The development of clinical predictive models hinges upon the availability of comprehensive clinical data. Tapping into such resources requires considerable effort from clinicians, data scientists, and engineers. Specifically, these efforts are focused on data extraction and preprocessing steps required prior to modeling, including complex database queries. A handful of software libraries exist that can reduce this complexity by building upon data standards. However, a gap remains concerning electronic health records (EHRs) stored in star schema clinical data warehouses, an approach often adopted in practice. In this article, we introduce the FlexIBle EHR Retrieval (FIBER) tool: a Python library built on top of a star schema (i2b2) clinical data warehouse that enables flexible generation of modeling-ready cohorts as data frames. Materials and Methods: FIBER was developed on top of a large-scale star schema EHR database which contains data from 8 million patients and over 120 million encounters. To illustrate FIBER's capabilities, we present its application by building a heart surgery patient cohort with subsequent prediction of acute kidney injury (AKI) with various machine learning models. Results: Using FIBER, we were able to build the heart surgery cohort (n = 12 061), identify the patients that developed AKI (n = 1005), and automatically extract relevant features (n = 774). Finally, we trained machine learning models that achieved area under the curve values of up to 0.77 for this exemplary use case. Conclusion: FIBER is an open-source Python library developed for extracting information from star schema clinical data warehouses and reduces time-to-modeling, helping to streamline the clinical modeling process.}, language = {en} } @article{DeFreitasJohnsonGoldenetal.2021, author = {De Freitas, Jessica K. and Johnson, Kipp W. and Golden, Eddye and Nadkarni, Girish N. and Dudley, Joel T. and B{\"o}ttinger, Erwin and Glicksberg, Benjamin S. and Miotto, Riccardo}, title = {Phe2vec}, series = {Patterns}, volume = {2}, journal = {Patterns}, number = {9}, publisher = {Elsevier}, address = {Amsterdam}, issn = {2666-3899}, doi = {10.1016/j.patter.2021.100337}, pages = {9}, year = {2021}, abstract = {Robust phenotyping of patients from electronic health records (EHRs) at scale is a challenge in clinical informatics. Here, we introduce Phe2vec, an automated framework for disease phenotyping from EHRs based on unsupervised learning and assess its effectiveness against standard rule-based algorithms from Phenotype KnowledgeBase (PheKB). Phe2vec is based on pre-computing embeddings of medical concepts and patients' clinical history. Disease phenotypes are then derived from a seed concept and its neighbors in the embedding space. Patients are linked to a disease if their embedded representation is close to the disease phenotype. Comparing Phe2vec and PheKB cohorts head-to-head using chart review, Phe2vec performed on par or better in nine out of ten diseases. Differently from other approaches, it can scale to any condition and was validated against widely adopted expert-based standards. Phe2vec aims to optimize clinical informatics research by augmenting current frameworks to characterize patients by condition and derive reliable disease cohorts.}, language = {en} } @inproceedings{AdnanSrsicVenticichetal.2020, author = {Adnan, Hassan Sami and Srsic, Amanda and Venticich, Pete Milos and Townend, David M.R.}, title = {Using AI for mental health analysis and prediction in school surveys}, series = {European journal of public health}, volume = {30}, booktitle = {European journal of public health}, publisher = {Oxford Univ. Press}, address = {Oxford [u.a.]}, issn = {1101-1262}, doi = {10.1093/eurpub/ckaa165.336}, pages = {V125 -- V125}, year = {2020}, abstract = {Background: Childhood and adolescence are critical stages of life for mental health and well-being. Schools are a key setting for mental health promotion and illness prevention. One in five children and adolescents have a mental disorder, about half of mental disorders beginning before the age of 14. Beneficial and explainable artificial intelligence can replace current paper- based and online approaches to school mental health surveys. This can enhance data acquisition, interoperability, data driven analysis, trust and compliance. This paper presents a model for using chatbots for non-obtrusive data collection and supervised machine learning models for data analysis; and discusses ethical considerations pertaining to the use of these models. Methods: For data acquisition, the proposed model uses chatbots which interact with students. The conversation log acts as the source of raw data for the machine learning. Pre-processing of the data is automated by filtering for keywords and phrases. Existing survey results, obtained through current paper-based data collection methods, are evaluated by domain experts (health professionals). These can be used to create a test dataset to validate the machine learning models. Supervised learning can then be deployed to classify specific behaviour and mental health patterns. Results: We present a model that can be used to improve upon current paper-based data collection and manual data analysis methods. An open-source GitHub repository contains necessary tools and components of this model. Privacy is respected through rigorous observance of confidentiality and data protection requirements. Critical reflection on these ethics and law aspects is included in the project. Conclusions: This model strengthens mental health surveillance in schools. The same tools and components could be applied to other public health data. Future extensions of this model could also incorporate unsupervised learning to find clusters and patterns of unknown effects.}, language = {en} } @article{ChanChaudharySahaetal.2021, author = {Chan, Lili and Chaudhary, Kumardeep and Saha, Aparna and Chauhan, Kinsuk and Vaid, Akhil and Zhao, Shan and Paranjpe, Ishan and Somani, Sulaiman and Richter, Felix and Miotto, Riccardo and Lala, Anuradha and Kia, Arash and Timsina, Prem and Li, Li and Freeman, Robert and Chen, Rong and Narula, Jagat and Just, Allan C. and Horowitz, Carol and Fayad, Zahi and Cordon-Cardo, Carlos and Schadt, Eric and Levin, Matthew A. and Reich, David L. and Fuster, Valentin and Murphy, Barbara and He, John C. and Charney, Alexander W. and B{\"o}ttinger, Erwin and Glicksberg, Benjamin and Coca, Steven G. and Nadkarni, Girish N.}, title = {AKI in hospitalized patients with COVID-19}, series = {Journal of the American Society of Nephrology : JASN}, volume = {32}, journal = {Journal of the American Society of Nephrology : JASN}, number = {1}, publisher = {American Society of Nephrology}, address = {Washington}, organization = {Mt Sinai COVID Informatics Ct}, issn = {1046-6673}, doi = {10.1681/ASN.2020050615}, pages = {151 -- 160}, year = {2021}, abstract = {Background: Early reports indicate that AKI is common among patients with coronavirus disease 2019 (COVID-19) and associatedwith worse outcomes. However, AKI among hospitalized patients with COVID19 in the United States is not well described. Methods: This retrospective, observational study involved a review of data from electronic health records of patients aged >= 18 years with laboratory-confirmed COVID-19 admitted to the Mount Sinai Health System from February 27 to May 30, 2020. We describe the frequency of AKI and dialysis requirement, AKI recovery, and adjusted odds ratios (aORs) with mortality. Results: Of 3993 hospitalized patients with COVID-19, AKI occurred in 1835 (46\%) patients; 347 (19\%) of the patientswith AKI required dialysis. The proportionswith stages 1, 2, or 3 AKIwere 39\%, 19\%, and 42\%, respectively. A total of 976 (24\%) patients were admitted to intensive care, and 745 (76\%) experienced AKI. Of the 435 patients with AKI and urine studies, 84\% had proteinuria, 81\% had hematuria, and 60\% had leukocyturia. Independent predictors of severe AKI were CKD, men, and higher serum potassium at admission. In-hospital mortality was 50\% among patients with AKI versus 8\% among those without AKI (aOR, 9.2; 95\% confidence interval, 7.5 to 11.3). Of survivors with AKI who were discharged, 35\% had not recovered to baseline kidney function by the time of discharge. An additional 28 of 77 (36\%) patients who had not recovered kidney function at discharge did so on posthospital follow-up. Conclusions: AKI is common among patients hospitalized with COVID-19 and is associated with high mortality. Of all patients with AKI, only 30\% survived with recovery of kidney function by the time of discharge.}, language = {en} } @article{OliveiraCiabatiLouresdosSantosHsiouSchmaltzetal.2021, author = {Oliveira-Ciabati, Livia and Loures dos Santos, Luciane and Hsiou Schmaltz, Annie and Sasso, Ariane Morassi and Castro, Margaret de and Souza, Jo{\~a}o Paulo}, title = {Scientific sexism}, series = {Revista de sa{\´u}de p{\´u}blica : publication of the Faculdade de Sa{\´u}de P{\´u}blica da Universidade de S{\~a}o Paulo = Journal of public health}, volume = {55}, journal = {Revista de sa{\´u}de p{\´u}blica : publication of the Faculdade de Sa{\´u}de P{\´u}blica da Universidade de S{\~a}o Paulo = Journal of public health}, publisher = {Faculdade de Sa{\´u}de P{\´u}blica da Universidade de S{\~a}o Paulo}, address = {S{\~a}o Paulo}, issn = {1518-8787}, doi = {10.11606/s1518-8787.2021055002939}, pages = {12}, year = {2021}, abstract = {OBJECTIVE: To investigate gender inequity in the scientific production of the University of Sao Paulo. METHODS: Members of the University of Sao Paulo faculty are the study population. The Web of Science repository was the source of the publication metrics. We selected the measures: total publications and citations, average of citations per year and item, H-index, and history of citations between 1950 and 2019. We used the name of the faculty member as a proxy to the gender identity. We use descriptive statistics to characterize the metrics. We evaluated the scissors effect by selecting faculty members with a high H-index. The historical series of citations was projected until 2100. We carry out analyses for the general population and working time subgroups: less than 10 years, 10 to 20 years, and 20 years or more. RESULTS: Of the 8,325 faculty members, we included 3,067 (36.8\%). Among those included, 1,893 (61.7\%) were male and 1,174 (38.28\%) female. The male gender presented higher values in the publication metrics (average of articles: M = 67.0 versus F = 49.7; average of citations/year: M = 53.9 versus F = 35.9), and H-index (M = 14.5 versus F = 12.4). Among the 100 individuals with the highest H-index (>= 37), 83\% are male. The male curve grows faster in the historical series of citations, opening a difference between the groups whose separation is confirmed by the projection. DISCUSSION: Scientific production at the Universidade de Sao Paulo is subject to a gender bias. Two-thirds of the faculty are male, and hiring over the past few decades perpetuates this pattern. The large majority of high impact faculty members are male. CONCLUSION: Our analysis suggests that the Universidade de Sao Paulo will not overcome gender inequality in scientific production without substantive affirmative action. Development does not happen by chance but through choices that are affirmative, decisive, and long-term oriented.}, language = {en} } @article{LongdeMeloHeetal.2020, author = {Long, Xiang and de Melo, Gerard and He, Dongliang and Li, Fu and Chi, Zhizhen and Wen, Shilei and Gan, Chuang}, title = {Purely attention based local feature integration for video classification}, series = {IEEE Transactions on Pattern Analysis and Machine Intelligence}, volume = {44}, journal = {IEEE Transactions on Pattern Analysis and Machine Intelligence}, number = {4}, publisher = {Inst. of Electr. and Electronics Engineers}, address = {Los Alamitos}, issn = {0162-8828}, doi = {10.1109/TPAMI.2020.3029554}, pages = {2140 -- 2154}, year = {2020}, abstract = {Recently, substantial research effort has focused on how to apply CNNs or RNNs to better capture temporal patterns in videos, so as to improve the accuracy of video classification. In this paper, we investigate the potential of a purely attention based local feature integration. Accounting for the characteristics of such features in video classification, we first propose Basic Attention Clusters (BAC), which concatenates the output of multiple attention units applied in parallel, and introduce a shifting operation to capture more diverse signals. Experiments show that BAC can achieve excellent results on multiple datasets. However, BAC treats all feature channels as an indivisible whole, which is suboptimal for achieving a finer-grained local feature integration over the channel dimension. Additionally, it treats the entire local feature sequence as an unordered set, thus ignoring the sequential relationships. To improve over BAC, we further propose the channel pyramid attention schema by splitting features into sub-features at multiple scales for coarse-to-fine sub-feature interaction modeling, and propose the temporal pyramid attention schema by dividing the feature sequences into ordered sub-sequences of multiple lengths to account for the sequential order. Our final model pyramidxpyramid attention clusters (PPAC) combines both channel pyramid attention and temporal pyramid attention to focus on the most important sub-features, while also preserving the temporal information of the video. We demonstrate the effectiveness of PPAC on seven real-world video classification datasets. Our model achieves competitive results across all of these, showing that our proposed framework can consistently outperform the existing local feature integration methods across a range of different scenarios.}, language = {en} } @article{HaarmannHolfterPufahletal.2021, author = {Haarmann, Stephan and Holfter, Adrian and Pufahl, Luise and Weske, Mathias}, title = {Formal framework for checking compliance of data-driven case management}, series = {Journal on data semantics : JoDS}, volume = {10}, journal = {Journal on data semantics : JoDS}, number = {1-2}, publisher = {Springer}, address = {Heidelberg}, issn = {1861-2032}, doi = {10.1007/s13740-021-00120-3}, pages = {143 -- 163}, year = {2021}, abstract = {Business processes are often specified in descriptive or normative models. Both types of models should adhere to internal and external regulations, such as company guidelines or laws. Employing compliance checking techniques, it is possible to verify process models against rules. While traditionally compliance checking focuses on well-structured processes, we address case management scenarios. In case management, knowledge workers drive multi-variant and adaptive processes. Our contribution is based on the fragment-based case management approach, which splits a process into a set of fragments. The fragments are synchronized through shared data but can, otherwise, be dynamically instantiated and executed. We formalize case models using Petri nets. We demonstrate the formalization for design-time and run-time compliance checking and present a proof-of-concept implementation. The application of the implemented compliance checking approach to a use case exemplifies its effectiveness while designing a case model. The empirical evaluation on a set of case models for measuring the performance of the approach shows that rules can often be checked in less than a second.}, language = {en} } @article{DoerrKoetzing2022, author = {Doerr, Benjamin and K{\"o}tzing, Timo}, title = {Lower bounds from fitness levels made easy}, series = {Algorithmica}, journal = {Algorithmica}, publisher = {Springer}, address = {New York}, issn = {0178-4617}, doi = {10.1007/s00453-022-00952-w}, pages = {29}, year = {2022}, abstract = {One of the first and easy to use techniques for proving run time bounds for evolutionary algorithms is the so-called method of fitness levels by Wegener. It uses a partition of the search space into a sequence of levels which are traversed by the algorithm in increasing order, possibly skipping levels. An easy, but often strong upper bound for the run time can then be derived by adding the reciprocals of the probabilities to leave the levels (or upper bounds for these). Unfortunately, a similarly effective method for proving lower bounds has not yet been established. The strongest such method, proposed by Sudholt (2013), requires a careful choice of the viscosity parameters gamma(i), j, 0 <= i < j <= n. In this paper we present two new variants of the method, one for upper and one for lower bounds. Besides the level leaving probabilities, they only rely on the probabilities that levels are visited at all. We show that these can be computed or estimated without greater difficulties and apply our method to reprove the following known results in an easy and natural way. (i) The precise run time of the (1+1) EA on LEADINGONES. (ii) A lower bound for the run time of the (1+1) EA on ONEMAX, tight apart from an O(n) term. (iii) A lower bound for the run time of the (1+1) EA on long k-paths (which differs slightly from the previous result due to a small error in the latter). We also prove a tighter lower bound for the run time of the (1+1) EA on jump functions by showing that, regardless of the jump size, only with probability O(2(-n)) the algorithm can avoid to jump over the valley of low fitness.}, language = {en} } @article{BlaesiusFreibergerFriedrichetal.2022, author = {Bl{\"a}sius, Thomas and Freiberger, Cedric and Friedrich, Tobias and Katzmann, Maximilian and Montenegro-Retana, Felix and Thieffry, Marianne}, title = {Efficient Shortest Paths in Scale-Free Networks with Underlying Hyperbolic Geometry}, series = {ACM Transactions on Algorithms}, volume = {18}, journal = {ACM Transactions on Algorithms}, number = {2}, publisher = {Association for Computing Machinery}, address = {New York}, issn = {1549-6325}, doi = {10.1145/3516483}, pages = {1 -- 32}, year = {2022}, abstract = {A standard approach to accelerating shortest path algorithms on networks is the bidirectional search, which explores the graph from the start and the destination, simultaneously. In practice this strategy performs particularly well on scale-free real-world networks. Such networks typically have a heterogeneous degree distribution (e.g., a power-law distribution) and high clustering (i.e., vertices with a common neighbor are likely to be connected themselves). These two properties can be obtained by assuming an underlying hyperbolic geometry.
To explain the observed behavior of the bidirectional search, we analyze its running time on hyperbolic random graphs and prove that it is (O) over tilde (n(2-1/alpha) + n(1/(2 alpha)) + delta(max)) with high probability, where alpha is an element of (1/2, 1) controls the power-law exponent of the degree distribution, and dmax is the maximum degree. This bound is sublinear, improving the obvious worst-case linear bound. Although our analysis depends on the underlying geometry, the algorithm itself is oblivious to it.}, language = {en} } @article{DoerrKrejca2021, author = {Doerr, Benjamin and Krejca, Martin Stefan}, title = {A simplified run time analysis of the univariate marginal distribution algorithm on LeadingOnes}, series = {Theoretical computer science}, volume = {851}, journal = {Theoretical computer science}, publisher = {Elsevier}, address = {Amsterdam}, issn = {0304-3975}, doi = {10.1016/j.tcs.2020.11.028}, pages = {121 -- 128}, year = {2021}, abstract = {With elementary means, we prove a stronger run time guarantee for the univariate marginal distribution algorithm (UMDA) optimizing the LEADINGONES benchmark function in the desirable regime with low genetic drift. If the population size is at least quasilinear, then, with high probability, the UMDA samples the optimum in a number of iterations that is linear in the problem size divided by the logarithm of the UMDA's selection rate. This improves over the previous guarantee, obtained by Dang and Lehre (2015) via the deep level-based population method, both in terms of the run time and by demonstrating further run time gains from small selection rates. Under similar assumptions, we prove a lower bound that matches our upper bound up to constant factors.}, language = {en} } @article{BanoMichaelRumpeetal.2022, author = {Bano, Dorina and Michael, Judith and Rumpe, Bernhard and Varga, Simon and Weske, Mathias}, title = {Process-aware digital twin cockpit synthesis from event logs}, series = {Journal of computer languages}, volume = {70}, journal = {Journal of computer languages}, publisher = {Elsevier}, address = {Amsterdam [u.a.]}, issn = {2590-1184}, doi = {10.1016/j.cola.2022.101121}, pages = {19}, year = {2022}, abstract = {The engineering of digital twins and their user interaction parts with explicated processes, namely processaware digital twin cockpits (PADTCs), is challenging due to the complexity of the systems and the need for information from different disciplines within the engineering process. Therefore, it is interesting to investigate how to facilitate their engineering by using already existing data, namely event logs, and reducing the number of manual steps for their engineering. Current research lacks systematic, automated approaches to derive process-aware digital twin cockpits even though some helpful techniques already exist in the areas of process mining and software engineering. Within this paper, we present a low-code development approach that reduces the amount of hand-written code needed and uses process mining techniques to derive PADTCs. We describe what models could be derived from event log data, which generative steps are needed for the engineering of PADTCs, and how process mining could be incorporated into the resulting application. This process is evaluated using the MIMIC III dataset for the creation of a PADTC prototype for an automated hospital transportation system. This approach can be used for early prototyping of PADTCs as it needs no hand-written code in the first place, but it still allows for the iterative evolvement of the application. This empowers domain experts to create their PADTC prototypes.}, language = {en} } @article{BlaesiusFriedrichSchirneck2021, author = {Blaesius, Thomas and Friedrich, Tobias and Schirneck, Friedrich Martin}, title = {The complexity of dependency detection and discovery in relational databases}, series = {Theoretical computer science}, volume = {900}, journal = {Theoretical computer science}, publisher = {Elsevier}, address = {Amsterdam}, issn = {0304-3975}, doi = {10.1016/j.tcs.2021.11.020}, pages = {79 -- 96}, year = {2021}, abstract = {Multi-column dependencies in relational databases come associated with two different computational tasks. The detection problem is to decide whether a dependency of a certain type and size holds in a given database, the discovery problem asks to enumerate all valid dependencies of that type. We settle the complexity of both of these problems for unique column combinations (UCCs), functional dependencies (FDs), and inclusion dependencies (INDs). We show that the detection of UCCs and FDs is W[2]-complete when parameterized by the solution size. The discovery of inclusion-wise minimal UCCs is proven to be equivalent under parsimonious reductions to the transversal hypergraph problem of enumerating the minimal hitting sets of a hypergraph. The discovery of FDs is equivalent to the simultaneous enumeration of the hitting sets of multiple input hypergraphs. We further identify the detection of INDs as one of the first natural W[3]-complete problems. The discovery of maximal INDs is shown to be equivalent to enumerating the maximal satisfying assignments of antimonotone, 3-normalized Boolean formulas.}, language = {en} } @article{AndreeIhdeWeskeetal.2022, author = {Andree, Kerstin and Ihde, Sven and Weske, Mathias and Pufahl, Luise}, title = {An exception handling framework for case management}, series = {Software and Systems Modeling}, volume = {21}, journal = {Software and Systems Modeling}, number = {3}, publisher = {Springer}, address = {Heidelberg}, issn = {1619-1366}, doi = {10.1007/s10270-022-00993-3}, pages = {939 -- 962}, year = {2022}, abstract = {In order to achieve their business goals, organizations heavily rely on the operational excellence of their business processes. In traditional scenarios, business processes are usually well-structured, clearly specifying when and how certain tasks have to be executed. Flexible and knowledge-intensive processes are gathering momentum, where a knowledge worker drives the execution of a process case and determines the exact process path at runtime. In the case of an exception, the knowledge worker decides on an appropriate handling. While there is initial work on exception handling in well-structured business processes, exceptions in case management have not been sufficiently researched. This paper proposes an exception handling framework for stage-oriented case management languages, namely Guard Stage Milestone Model, Case Management Model and Notation, and Fragment-based Case Management. The effectiveness of the framework is evaluated with two real-world use cases showing that it covers all relevant exceptions and proposed handling strategies.}, language = {en} } @article{KossmannPapenbrockNaumann2021, author = {Koßmann, Jan and Papenbrock, Thorsten and Naumann, Felix}, title = {Data dependencies for query optimization}, series = {The VLDB journal : the international journal on very large data bases / publ. on behalf of the VLDB Endowment}, volume = {31}, journal = {The VLDB journal : the international journal on very large data bases / publ. on behalf of the VLDB Endowment}, number = {1}, publisher = {Springer}, address = {Berlin ; Heidelberg ; New York}, issn = {1066-8888}, doi = {10.1007/s00778-021-00676-3}, pages = {1 -- 22}, year = {2021}, abstract = {Effective query optimization is a core feature of any database management system. While most query optimization techniques make use of simple metadata, such as cardinalities and other basic statistics, other optimization techniques are based on more advanced metadata including data dependencies, such as functional, uniqueness, order, or inclusion dependencies. This survey provides an overview, intuitive descriptions, and classifications of query optimization and execution strategies that are enabled by data dependencies. We consider the most popular types of data dependencies and focus on optimization strategies that target the optimization of relational database queries. The survey supports database vendors to identify optimization opportunities as well as DBMS researchers to find related work and open research questions.}, language = {en} }