@article{RingEisenmannKandiletal.2022, author = {Ring, Raphaela M. and Eisenmann, Clemens and Kandil, Farid and Steckhan, Nico and Demmrich, Sarah and Klatte, Caroline and Kessler, Christian S. and Jeitler, Michael and Boschmann, Michael and Michalsen, Andreas and Blakeslee, Sarah B. and St{\"o}ckigt, Barbara and Stritter, Wiebke and Koppold-Liebscher, Daniela A.}, title = {Mental and behavioural responses to Bah{\´a}'{\´i} fasting: Looking behind the scenes of a religiously motivated intermittent fast using a mixed methods approach}, series = {Nutrients}, volume = {14}, journal = {Nutrients}, number = {5}, publisher = {MDPI}, address = {Basel}, issn = {2072-6643}, doi = {10.3390/nu14051038}, pages = {23}, year = {2022}, abstract = {Background/Objective: Historically, fasting has been practiced not only for medical but also for religious reasons. Baha'is follow an annual religious intermittent dry fast of 19 days. We inquired into motivation behind and subjective health impacts of Baha'i fasting. Methods: A convergent parallel mixed methods design was embedded in a clinical single arm observational study. Semi-structured individual interviews were conducted before (n = 7), during (n = 8), and after fasting (n = 8). Three months after the fasting period, two focus group interviews were conducted (n = 5/n = 3). A total of 146 Baha'i volunteers answered an online survey at five time points before, during, and after fasting. Results: Fasting was found to play a central role for the religiosity of interviewees, implying changes in daily structures, spending time alone, engaging in religious practices, and experiencing social belonging. Results show an increase in mindfulness and well-being, which were accompanied by behavioural changes and experiences of self-efficacy and inner freedom. Survey scores point to an increase in mindfulness and well-being during fasting, while stress, anxiety, and fatigue decreased. Mindfulness remained elevated even three months after the fast. Conclusion: Baha'i fasting seems to enhance participants' mindfulness and well-being, lowering stress levels and reducing fatigue. Some of these effects lasted more than three months after fasting.}, language = {en} } @book{KubanRottaNolteetal.2023, author = {Kuban, Robert and Rotta, Randolf and Nolte, J{\"o}rg and Chromik, Jonas and Beilharz, Jossekin Jakob and Pirl, Lukas and Friedrich, Tobias and Lenzner, Pascal and Weyand, Christopher and Juiz, Carlos and Bermejo, Belen and Sauer, Joao and Coelh, Leandro dos Santos and Najafi, Pejman and P{\"u}nter, Wenzel and Cheng, Feng and Meinel, Christoph and Sidorova, Julia and Lundberg, Lars and Vogel, Thomas and Tran, Chinh and Moser, Irene and Grunske, Lars and Elsaid, Mohamed Esameldin Mohamed and Abbas, Hazem M. and Rula, Anisa and Sejdiu, Gezim and Maurino, Andrea and Schmidt, Christopher and H{\"u}gle, Johannes and Uflacker, Matthias and Nozza, Debora and Messina, Enza and Hoorn, Andr{\´e} van and Frank, Markus and Schulz, Henning and Alhosseini Almodarresi Yasin, Seyed Ali and Nowicki, Marek and Muite, Benson K. and Boysan, Mehmet Can and Bianchi, Federico and Cremaschi, Marco and Moussa, Rim and Abdel-Karim, Benjamin M. and Pfeuffer, Nicolas and Hinz, Oliver and Plauth, Max and Polze, Andreas and Huo, Da and Melo, Gerard de and Mendes Soares, F{\´a}bio and Oliveira, Roberto C{\´e}lio Lim{\~a}o de and Benson, Lawrence and Paul, Fabian and Werling, Christian and Windheuser, Fabian and Stojanovic, Dragan and Djordjevic, Igor and Stojanovic, Natalija and Stojnev Ilic, Aleksandra and Weidmann, Vera and Lowitzki, Leon and Wagner, Markus and Ifa, Abdessatar Ben and Arlos, Patrik and Megia, Ana and Vendrell, Joan and Pfitzner, Bjarne and Redondo, Alberto and R{\´i}os Insua, David and Albert, Justin Amadeus and Zhou, Lin and Arnrich, Bert and Szab{\´o}, Ildik{\´o} and Fodor, Szabina and Ternai, Katalin and Bhowmik, Rajarshi and Campero Durand, Gabriel and Shevchenko, Pavlo and Malysheva, Milena and Prymak, Ivan and Saake, Gunter}, title = {HPI Future SOC Lab - Proceedings 2019}, number = {158}, editor = {Meinel, Christoph and Polze, Andreas and Beins, Karsten and Strotmann, Rolf and Seibold, Ulrich and R{\"o}dszus, Kurt and M{\"u}ller, J{\"u}rgen}, publisher = {Universit{\"a}tsverlag Potsdam}, address = {Potsdam}, isbn = {978-3-86956-564-4}, issn = {1613-5652}, doi = {10.25932/publishup-59791}, url = {http://nbn-resolving.de/urn:nbn:de:kobv:517-opus4-597915}, publisher = {Universit{\"a}t Potsdam}, pages = {xi, 301}, year = {2023}, abstract = {The "HPI Future SOC Lab" is a cooperation of the Hasso Plattner Institute (HPI) and industry partners. Its mission is to enable and promote exchange and interaction between the research community and the industry partners. The HPI Future SOC Lab provides researchers with free of charge access to a complete infrastructure of state of the art hard and software. This infrastructure includes components, which might be too expensive for an ordinary research environment, such as servers with up to 64 cores and 2 TB main memory. The offerings address researchers particularly from but not limited to the areas of computer science and business information systems. Main areas of research include cloud computing, parallelization, and In-Memory technologies. This technical report presents results of research projects executed in 2019. Selected projects have presented their results on April 9th and November 12th 2019 at the Future SOC Lab Day events.}, language = {en} } @phdthesis{Richly2024, author = {Richly, Keven}, title = {Memory-efficient data management for spatio-temporal applications}, doi = {10.25932/publishup-63547}, url = {http://nbn-resolving.de/urn:nbn:de:kobv:517-opus4-635473}, school = {Universit{\"a}t Potsdam}, pages = {xii, 181}, year = {2024}, abstract = {The wide distribution of location-acquisition technologies means that large volumes of spatio-temporal data are continuously being accumulated. Positioning systems such as GPS enable the tracking of various moving objects' trajectories, which are usually represented by a chronologically ordered sequence of observed locations. The analysis of movement patterns based on detailed positional information creates opportunities for applications that can improve business decisions and processes in a broad spectrum of industries (e.g., transportation, traffic control, or medicine). Due to the large data volumes generated in these applications, the cost-efficient storage of spatio-temporal data is desirable, especially when in-memory database systems are used to achieve interactive performance requirements. To efficiently utilize the available DRAM capacities, modern database systems support various tuning possibilities to reduce the memory footprint (e.g., data compression) or increase performance (e.g., additional indexes structures). By considering horizontal data partitioning, we can independently apply different tuning options on a fine-grained level. However, the selection of cost and performance-balancing configurations is challenging, due to the vast number of possible setups consisting of mutually dependent individual decisions. In this thesis, we introduce multiple approaches to improve spatio-temporal data management by automatically optimizing diverse tuning options for the application-specific access patterns and data characteristics. Our contributions are as follows: (1) We introduce a novel approach to determine fine-grained table configurations for spatio-temporal workloads. Our linear programming (LP) approach jointly optimizes the (i) data compression, (ii) ordering, (iii) indexing, and (iv) tiering. We propose different models which address cost dependencies at different levels of accuracy to compute optimized tuning configurations for a given workload, memory budgets, and data characteristics. To yield maintainable and robust configurations, we further extend our LP-based approach to incorporate reconfiguration costs as well as optimizations for multiple potential workload scenarios. (2) To optimize the storage layout of timestamps in columnar databases, we present a heuristic approach for the workload-driven combined selection of a data layout and compression scheme. By considering attribute decomposition strategies, we are able to apply application-specific optimizations that reduce the memory footprint and improve performance. (3) We introduce an approach that leverages past trajectory data to improve the dispatch processes of transportation network companies. Based on location probabilities, we developed risk-averse dispatch strategies that reduce critical delays. (4) Finally, we used the use case of a transportation network company to evaluate our database optimizations on a real-world dataset. We demonstrate that workload-driven fine-grained optimizations allow us to reduce the memory footprint (up to 71\% by equal performance) or increase the performance (up to 90\% by equal memory size) compared to established rule-based heuristics. Individually, our contributions provide novel approaches to the current challenges in spatio-temporal data mining and database research. Combining them allows in-memory databases to store and process spatio-temporal data more cost-efficiently.}, language = {en} } @article{RosinLaiMouldetal.2022, author = {Rosin, Paul L. and Lai, Yu-Kun and Mould, David and Yi, Ran and Berger, Itamar and Doyle, Lars and Lee, Seungyong and Li, Chuan and Liu, Yong-Jin and Semmo, Amir and Shamir, Ariel and Son, Minjung and Winnem{\"o}ller, Holger}, title = {NPRportrait 1.0: A three-level benchmark for non-photorealistic rendering of portraits}, series = {Computational visual media}, volume = {8}, journal = {Computational visual media}, number = {3}, publisher = {Springer Nature}, address = {London}, issn = {2096-0433}, doi = {10.1007/s41095-021-0255-3}, pages = {445 -- 465}, year = {2022}, abstract = {Recently, there has been an upsurge of activity in image-based non-photorealistic rendering (NPR), and in particular portrait image stylisation, due to the advent of neural style transfer (NST). However, the state of performance evaluation in this field is poor, especially compared to the norms in the computer vision and machine learning communities. Unfortunately, the task of evaluating image stylisation is thus far not well defined, since it involves subjective, perceptual, and aesthetic aspects. To make progress towards a solution, this paper proposes a new structured, three-level, benchmark dataset for the evaluation of stylised portrait images. Rigorous criteria were used for its construction, and its consistency was validated by user studies. Moreover, a new methodology has been developed for evaluating portrait stylisation algorithms, which makes use of the different benchmark levels as well as annotations provided by user studies regarding the characteristics of the faces. We perform evaluation for a wide variety of image stylisation methods (both portrait-specific and general purpose, and also both traditional NPR approaches and NST) using the new benchmark dataset.}, language = {en} } @article{VitaglianoHameedJiangetal.2023, author = {Vitagliano, Gerardo and Hameed, Mazhar and Jiang, Lan and Reisener, Lucas and Wu, Eugene and Naumann, Felix}, title = {Pollock: A Data Loading Benchmark}, series = {Proceedings of the VLDB Endowment}, volume = {16}, journal = {Proceedings of the VLDB Endowment}, number = {8}, publisher = {Association for Computing Machinery}, address = {New York}, issn = {2150-8097}, doi = {10.14778/3594512.3594518}, pages = {1870 -- 1882}, year = {2023}, abstract = {Any system at play in a data-driven project has a fundamental requirement: the ability to load data. The de-facto standard format to distribute and consume raw data is CSV. Yet, the plain text and flexible nature of this format make such files often difficult to parse and correctly load their content, requiring cumbersome data preparation steps. We propose a benchmark to assess the robustness of systems in loading data from non-standard CSV formats and with structural inconsistencies. First, we formalize a model to describe the issues that affect real-world files and use it to derive a systematic lpollutionz process to generate dialects for any given grammar. Our benchmark leverages the pollution framework for the csv format. To guide pollution, we have surveyed thousands of real-world, publicly available csv files, recording the problems we encountered. We demonstrate the applicability of our benchmark by testing and scoring 16 different systems: popular csv parsing frameworks, relational database tools, spreadsheet systems, and a data visualization tool.}, language = {en} } @article{WiemkerBunovaNeufeldetal.2022, author = {Wiemker, Veronika and Bunova, Anna and Neufeld, Maria and Gornyi, Boris and Yurasova, Elena and Konigorski, Stefan and Kalinina, Anna and Kontsevaya, Anna and Ferreira-Borges, Carina and Probst, Charlotte}, title = {Pilot study to evaluate usability and acceptability of the 'Animated Alcohol Assessment Tool' in Russian primary healthcare}, series = {Digital health}, volume = {8}, journal = {Digital health}, publisher = {Sage Publications}, address = {London}, issn = {2055-2076}, doi = {10.1177/20552076211074491}, pages = {11}, year = {2022}, abstract = {Background and aims: Accurate and user-friendly assessment tools quantifying alcohol consumption are a prerequisite to effective prevention and treatment programmes, including Screening and Brief Intervention. Digital tools offer new potential in this field. We developed the 'Animated Alcohol Assessment Tool' (AAA-Tool), a mobile app providing an interactive version of the World Health Organization's Alcohol Use Disorders Identification Test (AUDIT) that facilitates the description of individual alcohol consumption via culturally informed animation features. This pilot study evaluated the Russia-specific version of the Animated Alcohol Assessment Tool with regard to (1) its usability and acceptability in a primary healthcare setting, (2) the plausibility of its alcohol consumption assessment results and (3) the adequacy of its Russia-specific vessel and beverage selection. Methods: Convenience samples of 55 patients (47\% female) and 15 healthcare practitioners (80\% female) in 2 Russian primary healthcare facilities self-administered the Animated Alcohol Assessment Tool and rated their experience on the Mobile Application Rating Scale - User Version. Usage data was automatically collected during app usage, and additional feedback on regional content was elicited in semi-structured interviews. Results: On average, patients completed the Animated Alcohol Assessment Tool in 6:38 min (SD = 2.49, range = 3.00-17.16). User satisfaction was good, with all subscale Mobile Application Rating Scale - User Version scores averaging >3 out of 5 points. A majority of patients (53\%) and practitioners (93\%) would recommend the tool to 'many people' or 'everyone'. Assessed alcohol consumption was plausible, with a low number (14\%) of logically impossible entries. Most patients reported the Animated Alcohol Assessment Tool to reflect all vessels (78\%) and all beverages (71\%) they typically used. Conclusion: High acceptability ratings by patients and healthcare practitioners, acceptable completion time, plausible alcohol usage assessment results and perceived adequacy of region-specific content underline the Animated Alcohol Assessment Tool's potential to provide a novel approach to alcohol assessment in primary healthcare. After its validation, the Animated Alcohol Assessment Tool might contribute to reducing alcohol-related harm by facilitating Screening and Brief Intervention implementation in Russia and beyond.}, language = {en} } @article{FehrPiccininniKurthetal.2023, author = {Fehr, Jana and Piccininni, Marco and Kurth, Tobias and Konigorski, Stefan}, title = {Assessing the transportability of clinical prediction models for cognitive impairment using causal models}, series = {BMC medical research methodology}, volume = {23}, journal = {BMC medical research methodology}, number = {1}, publisher = {BMC}, address = {London}, issn = {1471-2288}, doi = {10.1186/s12874-023-02003-6}, pages = {14}, year = {2023}, abstract = {Background Machine learning models promise to support diagnostic predictions, but may not perform well in new settings. Selecting the best model for a new setting without available data is challenging. We aimed to investigate the transportability by calibration and discrimination of prediction models for cognitive impairment in simulated external settings with different distributions of demographic and clinical characteristics. Methods We mapped and quantified relationships between variables associated with cognitive impairment using causal graphs, structural equation models, and data from the ADNI study. These estimates were then used to generate datasets and evaluate prediction models with different sets of predictors. We measured transportability to external settings under guided interventions on age, APOE \& epsilon;4, and tau-protein, using performance differences between internal and external settings measured by calibration metrics and area under the receiver operating curve (AUC). Results Calibration differences indicated that models predicting with causes of the outcome were more transportable than those predicting with consequences. AUC differences indicated inconsistent trends of transportability between the different external settings. Models predicting with consequences tended to show higher AUC in the external settings compared to internal settings, while models predicting with parents or all variables showed similar AUC. Conclusions We demonstrated with a practical prediction task example that predicting with causes of the outcome results in better transportability compared to anti-causal predictions when considering calibration differences. We conclude that calibration performance is crucial when assessing model transportability to external settings.}, language = {en} } @article{GarrelsKhodabakhshRenardetal.2023, author = {Garrels, Tim and Khodabakhsh, Athar and Renard, Bernhard Y. and Baum, Katharina}, title = {LazyFox: fast and parallelized overlapping community detection in large graphs}, series = {PEERJ Computer Science}, volume = {9}, journal = {PEERJ Computer Science}, publisher = {PeerJ Inc.}, address = {London}, issn = {2376-5992}, doi = {10.7717/peerj-cs.1291}, pages = {30}, year = {2023}, abstract = {The detection of communities in graph datasets provides insight about a graph's underlying structure and is an important tool for various domains such as social sciences, marketing, traffic forecast, and drug discovery. While most existing algorithms provide fast approaches for community detection, their results usually contain strictly separated communities. However, most datasets would semantically allow for or even require overlapping communities that can only be determined at much higher computational cost. We build on an efficient algorithm, FOX, that detects such overlapping communities. FOX measures the closeness of a node to a community by approximating the count of triangles which that node forms with that community. We propose LAZYFOX, a multi-threaded adaptation of the FOX algorithm, which provides even faster detection without an impact on community quality. This allows for the analyses of significantly larger and more complex datasets. LAZYFOX enables overlapping community detection on complex graph datasets with millions of nodes and billions of edges in days instead of weeks. As part of this work, LAZYFOX's implementation was published and is available as a tool under an MIT licence at https://github.com/TimGarrels/LazyFox.}, language = {en} } @article{KappattanavarHeckerMoontahaetal.2023, author = {Kappattanavar, Arpita Mallikarjuna and Hecker, Pascal and Moontaha, Sidratul and Steckhan, Nico and Arnrich, Bert}, title = {Food choices after cognitive load}, series = {Sensors}, volume = {23}, journal = {Sensors}, number = {14}, publisher = {MDPI}, address = {Basel}, issn = {1424-8220}, doi = {10.3390/s23146597}, pages = {22}, year = {2023}, abstract = {Psychology and nutritional science research has highlighted the impact of negative emotions and cognitive load on calorie consumption behaviour using subjective questionnaires. Isolated studies in other domains objectively assess cognitive load without considering its effects on eating behaviour. This study aims to explore the potential for developing an integrated eating behaviour assistant system that incorporates cognitive load factors. Two experimental sessions were conducted using custom-developed experimentation software to induce different stimuli. During these sessions, we collected 30 h of physiological, food consumption, and affective states questionnaires data to automatically detect cognitive load and analyse its effect on food choice. Utilising grid search optimisation and leave-one-subject-out cross-validation, a support vector machine model achieved a mean classification accuracy of 85.12\% for the two cognitive load tasks using eight relevant features. Statistical analysis was performed on calorie consumption and questionnaire data. Furthermore, 75\% of the subjects with higher negative affect significantly increased consumption of specific foods after high-cognitive-load tasks. These findings offer insights into the intricate relationship between cognitive load, affective states, and food choice, paving the way for an eating behaviour assistant system to manage food choices during cognitive load. Future research should enhance system capabilities and explore real-world applications.}, language = {en} } @article{CohenHershcovitchTarazetal.2023, author = {Cohen, Sarel and Hershcovitch, Moshik and Taraz, Martin and Kissig, Otto and Issac, Davis and Wood, Andrew and Waddington, Daniel and Chin, Peter and Friedrich, Tobias}, title = {Improved and optimized drug repurposing for the SARS-CoV-2 pandemic}, series = {PLoS one}, volume = {18}, journal = {PLoS one}, number = {3}, publisher = {PLoS}, address = {San Fransisco}, issn = {1932-6203}, doi = {10.1371/journal.pone.0266572}, pages = {13}, year = {2023}, abstract = {The active global SARS-CoV-2 pandemic caused more than 426 million cases and 5.8 million deaths worldwide. The development of completely new drugs for such a novel disease is a challenging, time intensive process. Despite researchers around the world working on this task, no effective treatments have been developed yet. This emphasizes the importance of drug repurposing, where treatments are found among existing drugs that are meant for different diseases. A common approach to this is based on knowledge graphs, that condense relationships between entities like drugs, diseases and genes. Graph neural networks (GNNs) can then be used for the task at hand by predicting links in such knowledge graphs. Expanding on state-of-the-art GNN research, Doshi et al. recently developed the Dr-COVID model. We further extend their work using additional output interpretation strategies. The best aggregation strategy derives a top-100 ranking of 8,070 candidate drugs, 32 of which are currently being tested in COVID-19-related clinical trials. Moreover, we present an alternative application for the model, the generation of additional candidates based on a given pre-selection of drug candidates using collaborative filtering. In addition, we improved the implementation of the Dr-COVID model by significantly shortening the inference and pre-processing time by exploiting data-parallelism. As drug repurposing is a task that requires high computation and memory resources, we further accelerate the post-processing phase using a new emerging hardware-we propose a new approach to leverage the use of high-capacity Non-Volatile Memory for aggregate drug ranking.}, language = {en} } @article{PiroRenard2023, author = {Piro, Vitor C. and Renard, Bernhard Y.}, title = {Contamination detection and microbiome exploration with GRIMER}, series = {GigaScience}, volume = {12}, journal = {GigaScience}, publisher = {Oxford Univ. Press}, address = {Oxford}, issn = {2047-217X}, doi = {10.1093/gigascience/giad017}, pages = {13}, year = {2023}, abstract = {Background: Contamination detection is a important step that should be carefully considered in early stages when designing and performing microbiome studies to avoid biased outcomes. Detecting and removing true contaminants is challenging, especially in low-biomass samples or in studies lacking proper controls. Interactive visualizations and analysis platforms are crucial to better guide this step, to help to identify and detect noisy patterns that could potentially be contamination. Additionally, external evidence, like aggregation of several contamination detection methods and the use of common contaminants reported in the literature, could help to discover and mitigate contamination. Results: We propose GRIMER, a tool that performs automated analyses and generates a portable and interactive dashboard integrating annotation, taxonomy, and metadata. It unifies several sources of evidence to help detect contamination. GRIMER is independent of quantification methods and directly analyzes contingency tables to create an interactive and offline report. Reports can be created in seconds and are accessible for nonspecialists, providing an intuitive set of charts to explore data distribution among observations and samples and its connections with external sources. Further, we compiled and used an extensive list of possible external contaminant taxa and common contaminants with 210 genera and 627 species reported in 22 published articles. Conclusion: GRIMER enables visual data exploration and analysis, supporting contamination detection in microbiome studies. The tool and data presented are open source and available at https://gitlab.com/dacs-hpi/grimer.}, language = {en} } @article{GaertnerSchneiderArnrichetal.2023, author = {G{\"a}rtner, Thomas and Schneider, Juliana and Arnrich, Bert and Konigorski, Stefan}, title = {Comparison of Bayesian Networks, G-estimation and linear models to estimate causal treatment effects in aggregated N-of-1 trials with carry-over effects}, series = {BMC Medical Research Methodology}, volume = {23}, journal = {BMC Medical Research Methodology}, number = {1}, publisher = {BMC}, address = {London}, issn = {1471-2288}, doi = {10.1186/s12874-023-02012-5}, pages = {12}, year = {2023}, abstract = {Background The aggregation of a series of N-of-1 trials presents an innovative and efficient study design, as an alternative to traditional randomized clinical trials. Challenges for the statistical analysis arise when there is carry-over or complex dependencies of the treatment effect of interest. Methods In this study, we evaluate and compare methods for the analysis of aggregated N-of-1 trials in different scenarios with carry-over and complex dependencies of treatment effects on covariates. For this, we simulate data of a series of N-of-1 trials for Chronic Nonspecific Low Back Pain based on assumed causal relationships parameterized by directed acyclic graphs. In addition to existing statistical methods such as regression models, Bayesian Networks, and G-estimation, we introduce a carry-over adjusted parametric model (COAPM). Results The results show that all evaluated existing models have a good performance when there is no carry-over and no treatment dependence. When there is carry-over, COAPM yields unbiased and more efficient estimates while all other methods show some bias in the estimation. When there is known treatment dependence, all approaches that are capable to model it yield unbiased estimates. Finally, the efficiency of all methods decreases slightly when there are missing values, and the bias in the estimates can also increase. Conclusions This study presents a systematic evaluation of existing and novel approaches for the statistical analysis of a series of N-of-1 trials. We derive practical recommendations which methods may be best in which scenarios.}, language = {en} } @article{LewkowiczBoettingerSiegel2023, author = {Lewkowicz, Daniel and B{\"o}ttinger, Erwin and Siegel, Martin}, title = {Economic evaluation of digital therapeutic care apps for unsupervised treatment of low back pain}, series = {JMIR mhealth and uhealth}, volume = {11}, journal = {JMIR mhealth and uhealth}, publisher = {JMIR Publications}, address = {Toronto}, issn = {2291-5222}, doi = {10.2196/44585}, pages = {14}, year = {2023}, abstract = {Background: Digital therapeutic care (DTC) programs are unsupervised app-based treatments that provide video exercises and educational material to patients with nonspecific low back pain during episodes of pain and functional disability. German statutory health insurance can reimburse DTC programs since 2019, but evidence on efficacy and reasonable pricing remains scarce. This paper presents a probabilistic sensitivity analysis (PSA) to evaluate the efficacy and cost-utility of a DTC app against treatment as usual (TAU) in Germany. Objective: The aim of this study was to perform a PSA in the form of a Monte Carlo simulation based on the deterministic base case analysis to account for model assumptions and parameter uncertainty. We also intend to explore to what extent the results in this probabilistic analysis differ from the results in the base case analysis and to what extent a shortage of outcome data concerning quality-of-life (QoL) metrics impacts the overall results. Methods: The PSA builds upon a state-transition Markov chain with a 4-week cycle length over a model time horizon of 3 years from a recently published deterministic cost-utility analysis. A Monte Carlo simulation with 10,000 iterations and a cohort size of 10,000 was employed to evaluate the cost-utility from a societal perspective. Quality-adjusted life years (QALYs) were derived from Veterans RAND 6-Dimension (VR-6D) and Short-Form 6-Dimension (SF-6D) single utility scores. Finally, we also simulated reducing the price for a 3-month app prescription to analyze at which price threshold DTC would result in being the dominant strategy over TAU in Germany. Results: The Monte Carlo simulation yielded on average a euro135.97 (a currency exchange rate of EUR euro1=US \$1.069 is applicable) incremental cost and 0.004 incremental QALYs per person and year for the unsupervised DTC app strategy compared to in-person physiotherapy in Germany. The corresponding incremental cost-utility ratio (ICUR) amounts to an additional euro34,315.19 per additional QALY. DTC yielded more QALYs in 54.96\% of the iterations. DTC dominates TAU in 24.04\% of the iterations for QALYs. Reducing the app price in the simulation from currently euro239.96 to euro164.61 for a 3-month prescription could yield a negative ICUR and thus make DTC the dominant strategy, even though the estimated probability of DTC being more effective than TAU is only 54.96\%. Conclusions: Decision-makers should be cautious when considering the reimbursement of DTC apps since no significant treatment effect was found, and the probability of cost-effectiveness remains below 60\% even for an infinite willingness-to-pay threshold. More app-based studies involving the utilization of QoL outcome parameters are urgently needed to account for the low and limited precision of the available QoL input parameters, which are crucial to making profound recommendations concerning the cost-utility of novel apps.}, language = {en} } @article{MoontahaSchumannArnrich2023, author = {Moontaha, Sidratul and Schumann, Franziska Elisabeth Friederike and Arnrich, Bert}, title = {Online learning for wearable EEG-Based emotion classification}, series = {Sensors}, volume = {23}, journal = {Sensors}, number = {5}, publisher = {MDPI}, address = {Basel}, issn = {1424-8220}, doi = {10.3390/s23052387}, pages = {23}, year = {2023}, abstract = {Giving emotional intelligence to machines can facilitate the early detection and prediction of mental diseases and symptoms. Electroencephalography (EEG)-based emotion recognition is widely applied because it measures electrical correlates directly from the brain rather than indirect measurement of other physiological responses initiated by the brain. Therefore, we used non-invasive and portable EEG sensors to develop a real-time emotion classification pipeline. The pipeline trains different binary classifiers for Valence and Arousal dimensions from an incoming EEG data stream achieving a 23.9\% (Arousal) and 25.8\% (Valence) higher F1-Score on the state-of-art AMIGOS dataset than previous work. Afterward, the pipeline was applied to the curated dataset from 15 participants using two consumer-grade EEG devices while watching 16 short emotional videos in a controlled environment. Mean F1-Scores of 87\% (Arousal) and 82\% (Valence) were achieved for an immediate label setting. Additionally, the pipeline proved to be fast enough to achieve predictions in real-time in a live scenario with delayed labels while continuously being updated. The significant discrepancy from the readily available labels on the classification scores leads to future work to include more data. Thereafter, the pipeline is ready to be used for real-time applications of emotion classification.}, language = {en} } @article{KirchlerKonigorskiNordenetal.2022, author = {Kirchler, Matthias and Konigorski, Stefan and Norden, Matthias and Meltendorf, Christian and Kloft, Marius and Schurmann, Claudia and Lippert, Christoph}, title = {transferGWAS}, series = {Bioinformatics}, volume = {38}, journal = {Bioinformatics}, number = {14}, publisher = {Oxford Univ. Press}, address = {Oxford}, issn = {1367-4803}, doi = {10.1093/bioinformatics/btac369}, pages = {3621 -- 3628}, year = {2022}, abstract = {Motivation: Medical images can provide rich information about diseases and their biology. However, investigating their association with genetic variation requires non-standard methods. We propose transferGWAS, a novel approach to perform genome-wide association studies directly on full medical images. First, we learn semantically meaningful representations of the images based on a transfer learning task, during which a deep neural network is trained on independent but similar data. Then, we perform genetic association tests with these representations. Results: We validate the type I error rates and power of transferGWAS in simulation studies of synthetic images. Then we apply transferGWAS in a genome-wide association study of retinal fundus images from the UK Biobank. This first-of-a-kind GWAS of full imaging data yielded 60 genomic regions associated with retinal fundus images, of which 7 are novel candidate loci for eye-related traits and diseases.}, language = {en} } @phdthesis{Lorson2024, author = {Lorson, Annalena}, title = {Understanding early stage evolution of digital innovation units in manufacturing companies}, doi = {10.25932/publishup-63914}, url = {http://nbn-resolving.de/urn:nbn:de:kobv:517-opus4-639141}, school = {Universit{\"a}t Potsdam}, pages = {XI, 149}, year = {2024}, abstract = {The dynamic landscape of digital transformation entails an impact on industrial-age manufacturing companies that goes beyond product offerings, changing operational paradigms, and requiring an organization-wide metamorphosis. An initiative to address the given challenges is the creation of Digital Innovation Units (DIUs) - departments or distinct legal entities that use new structures and practices to develop digital products, services, and business models and support or drive incumbents' digital transformation. With more than 300 units in German-speaking countries alone and an increasing number of scientific publications, DIUs have become a widespread phenomenon in both research and practice. This dissertation examines the evolution process of DIUs in the manufacturing industry during their first three years of operation, through an extensive longitudinal single-case study and several cross-case syntheses of seven DIUs. Building on the lenses of organizational change and development, time, and socio-technical systems, this research provides insights into the fundamentals, temporal dynamics, socio-technical interactions, and relational dynamics of a DIU's evolution process. Thus, the dissertation promotes a dynamic understanding of DIUs and adds a two-dimensional perspective to the often one-dimensional view of these units and their interactions with the main organization throughout the startup and growth phases of a DIU. Furthermore, the dissertation constructs a phase model that depicts the early stages of DIU evolution based on these findings and by incorporating literature from information systems research. As a result, it illustrates the progressive intensification of collaboration between the DIU and the main organization. After being implemented, the DIU sparks initial collaboration and instigates change within (parts of) the main organization. Over time, it adapts to the corporate environment to some extent, responding to changing circumstances in order to contribute to long-term transformation. Temporally, the DIU drives the early phases of cooperation and adaptation in particular, while the main organization triggers the first major evolutionary step and realignment of the DIU. Overall, the thesis identifies DIUs as malleable organizational structures that are crucial for digital transformation. Moreover, it provides guidance for practitioners on the process of building a new DIU from scratch or optimizing an existing one.}, language = {en} } @article{CsehFaenzaKavithaetal.2022, author = {Cseh, Agnes and Faenza, Yuri and Kavitha, Telikepalli and Powers, Vladlena}, title = {Understanding popular matchings via stable matchings}, series = {SIAM journal on discrete mathematics}, volume = {36}, journal = {SIAM journal on discrete mathematics}, number = {1}, publisher = {Society for Industrial and Applied Mathematics}, address = {Philadelphia}, issn = {0895-4801}, doi = {10.1137/19M124770X}, pages = {188 -- 213}, year = {2022}, abstract = {An instance of the marriage problem is given by a graph G = (A boolean OR B, E), together with, for each vertex of G, a strict preference order over its neighbors. A matching M of G is popular in the marriage instance if M does not lose a head-to-head election against any matching where vertices are voters. Every stable matching is a min-size popular matching; another subclass of popular matchings that always exists and can be easily computed is the set of dominant matchings. A popular matching M is dominant if M wins the head-to-head election against any larger matching. Thus, every dominant matching is a max-size popular matching, and it is known that the set of dominant matchings is the linear image of the set of stable matchings in an auxiliary graph. Results from the literature seem to suggest that stable and dominant matchings behave, from a complexity theory point of view, in a very similar manner within the class of popular matchings. The goal of this paper is to show that there are instead differences in the tractability of stable and dominant matchings and to investigate further their importance for popular matchings. First, we show that it is easy to check if all popular matchings are also stable; however, it is co-NP hard to check if all popular matchings are also dominant. Second, we show how some new and recent hardness results on popular matching problems can be deduced from the NP-hardness of certain problems on stable matchings, also studied in this paper, thus showing that stable matchings can be employed to show not only positive results on popular matchings (as is known) but also most negative ones. Problems for which we show new hardness results include finding a min-size (resp., max-size) popular matching that is not stable (resp., dominant). A known result for which we give a new and simple proof is the NP-hardness of finding a popular matching when G is nonbipartite.}, language = {en} } @phdthesis{Huegle2024, author = {Huegle, Johannes}, title = {Causal discovery in practice: Non-parametric conditional independence testing and tooling for causal discovery}, doi = {10.25932/publishup-63582}, url = {http://nbn-resolving.de/urn:nbn:de:kobv:517-opus4-635820}, school = {Universit{\"a}t Potsdam}, pages = {xiv, 156}, year = {2024}, abstract = {Knowledge about causal structures is crucial for decision support in various domains. For example, in discrete manufacturing, identifying the root causes of failures and quality deviations that interrupt the highly automated production process requires causal structural knowledge. However, in practice, root cause analysis is usually built upon individual expert knowledge about associative relationships. But, "correlation does not imply causation", and misinterpreting associations often leads to incorrect conclusions. Recent developments in methods for causal discovery from observational data have opened the opportunity for a data-driven examination. Despite its potential for data-driven decision support, omnipresent challenges impede causal discovery in real-world scenarios. In this thesis, we make a threefold contribution to improving causal discovery in practice. (1) The growing interest in causal discovery has led to a broad spectrum of methods with specific assumptions on the data and various implementations. Hence, application in practice requires careful consideration of existing methods, which becomes laborious when dealing with various parameters, assumptions, and implementations in different programming languages. Additionally, evaluation is challenging due to the lack of ground truth in practice and limited benchmark data that reflect real-world data characteristics. To address these issues, we present a platform-independent modular pipeline for causal discovery and a ground truth framework for synthetic data generation that provides comprehensive evaluation opportunities, e.g., to examine the accuracy of causal discovery methods in case of inappropriate assumptions. (2) Applying constraint-based methods for causal discovery requires selecting a conditional independence (CI) test, which is particularly challenging in mixed discrete-continuous data omnipresent in many real-world scenarios. In this context, inappropriate assumptions on the data or the commonly applied discretization of continuous variables reduce the accuracy of CI decisions, leading to incorrect causal structures. Therefore, we contribute a non-parametric CI test leveraging k-nearest neighbors methods and prove its statistical validity and power in mixed discrete-continuous data, as well as the asymptotic consistency when used in constraint-based causal discovery. An extensive evaluation of synthetic and real-world data shows that the proposed CI test outperforms state-of-the-art approaches in the accuracy of CI testing and causal discovery, particularly in settings with low sample sizes. (3) To show the applicability and opportunities of causal discovery in practice, we examine our contributions in real-world discrete manufacturing use cases. For example, we showcase how causal structural knowledge helps to understand unforeseen production downtimes or adds decision support in case of failures and quality deviations in automotive body shop assembly lines.}, language = {en} } @article{CaselFernauGhadikolaeietal.2022, author = {Casel, Katrin and Fernau, Henning and Ghadikolaei, Mehdi Khosravian and Monnot, Jerome and Sikora, Florian}, title = {On the complexity of solution extension of optimization problems}, series = {Theoretical computer science : the journal of the EATCS}, volume = {904}, journal = {Theoretical computer science : the journal of the EATCS}, publisher = {Elsevier}, address = {Amsterdam [u.a.]}, issn = {0304-3975}, doi = {10.1016/j.tcs.2021.10.017}, pages = {48 -- 65}, year = {2022}, abstract = {The question if a given partial solution to a problem can be extended reasonably occurs in many algorithmic approaches for optimization problems. For instance, when enumerating minimal vertex covers of a graph G = (V, E), one usually arrives at the problem to decide for a vertex set U subset of V (pre-solution), if there exists a minimal vertex cover S (i.e., a vertex cover S subset of V such that no proper subset of S is a vertex cover) with U subset of S (minimal extension of U). We propose a general, partial-order based formulation of such extension problems which allows to model parameterization and approximation aspects of extension, and also highlights relationships between extension tasks for different specific problems. As examples, we study a number of specific problems which can be expressed and related in this framework. In particular, we discuss extension variants of the problems dominating set and feedback vertex/edge set. All these problems are shown to be NP-complete even when restricted to bipartite graphs of bounded degree, with the exception of our extension version of feedback edge set on undirected graphs which is shown to be solvable in polynomial time. For the extension variants of dominating and feedback vertex set, we also show NP-completeness for the restriction to planar graphs of bounded degree. As non-graph problem, we also study an extension version of the bin packing problem. We further consider the parameterized complexity of all these extension variants, where the parameter is a measure of the pre-solution as defined by our framework.}, language = {en} } @article{CoupetteHartungBeckedorfetal.2022, author = {Coupette, Corinna and Hartung, Dirk and Beckedorf, Janis and B{\"o}ther, Maximilian and Katz, Daniel Martin}, title = {Law smells}, series = {Artificial intelligence and law}, volume = {31}, journal = {Artificial intelligence and law}, publisher = {Springer}, address = {Dordrecht}, issn = {0924-8463}, doi = {10.1007/s10506-022-09315-w}, pages = {335 -- 368}, year = {2022}, abstract = {Building on the computer science concept of code smells, we initiate the study of law smells, i.e., patterns in legal texts that pose threats to the comprehensibility and maintainability of the law. With five intuitive law smells as running examples-namely, duplicated phrase, long element, large reference tree, ambiguous syntax, and natural language obsession-, we develop a comprehensive law smell taxonomy. This taxonomy classifies law smells by when they can be detected, which aspects of law they relate to, and how they can be discovered. We introduce text-based and graph-based methods to identify instances of law smells, confirming their utility in practice using the United States Code as a test case. Our work demonstrates how ideas from software engineering can be leveraged to assess and improve the quality of legal code, thus drawing attention to an understudied area in the intersection of law and computer science and highlighting the potential of computational legal drafting.}, language = {en} }