@article{EhrigWagnerWolteretal.2023, author = {Ehrig, Lukas and Wagner, Ann-Christin and Wolter, Heike and Correll, Christoph U. and Geisel, Olga and Konigorski, Stefan}, title = {FASDetect as a machine learning-based screening app for FASD in youth with ADHD}, series = {npj Digital Medicine}, volume = {6}, journal = {npj Digital Medicine}, number = {1}, publisher = {Macmillan Publishers Limited}, address = {Basingstoke}, issn = {2398-6352}, doi = {10.1038/s41746-023-00864-1}, pages = {9}, year = {2023}, abstract = {Fetal alcohol-spectrum disorder (FASD) is underdiagnosed and often misdiagnosed as attention-deficit/hyperactivity disorder (ADHD). Here, we develop a screening tool for FASD in youth with ADHD symptoms. To develop the prediction model, medical record data from a German University outpatient unit are assessed including 275 patients aged 0-19 years old with FASD with or without ADHD and 170 patients with ADHD without FASD aged 0-19 years old. We train 6 machine learning models based on 13 selected variables and evaluate their performance. Random forest models yield the best prediction models with a cross-validated AUC of 0.92 (95\% confidence interval [0.84, 0.99]). Follow-up analyses indicate that a random forest model with 6 variables - body length and head circumference at birth, IQ, socially intrusive behaviour, poor memory and sleep disturbance - yields equivalent predictive accuracy. We implement the prediction model in a web-based app called FASDetect - a user-friendly, clinically scalable FASD risk calculator that is freely available at https://fasdetect.dhc-lab.hpi.de.}, language = {en} } @article{SlosarekIbingSchormairetal.2023, author = {Slosarek, Tamara and Ibing, Susanne and Schormair, Barbara and Heyne, Henrike and B{\"o}ttinger, Erwin and Andlauer, Till and Schurmann, Claudia}, title = {Implementation and evaluation of personal genetic testing as part of genomics analysis courses in German universities}, series = {BMC Medical Genomics}, volume = {16}, journal = {BMC Medical Genomics}, number = {1}, publisher = {BMC}, address = {London}, issn = {1755-8794}, doi = {10.1186/s12920-023-01503-0}, pages = {13}, year = {2023}, abstract = {Purpose Due to the increasing application of genome analysis and interpretation in medical disciplines, professionals require adequate education. Here, we present the implementation of personal genotyping as an educational tool in two genomics courses targeting Digital Health students at the Hasso Plattner Institute (HPI) and medical students at the Technical University of Munich (TUM). Methods We compared and evaluated the courses and the students ' perceptions on the course setup using questionnaires. Results During the course, students changed their attitudes towards genotyping (HPI: 79\% [15 of 19], TUM: 47\% [25 of 53]). Predominantly, students became more critical of personal genotyping (HPI: 73\% [11 of 15], TUM: 72\% [18 of 25]) and most students stated that genetic analyses should not be allowed without genetic counseling (HPI: 79\% [15 of 19], TUM: 70\% [37 of 53]). Students found the personal genotyping component useful (HPI: 89\% [17 of 19], TUM: 92\% [49 of 53]) and recommended its inclusion in future courses (HPI: 95\% [18 of 19], TUM: 98\% [52 of 53]). Conclusion Students perceived the personal genotyping component as valuable in the described genomics courses. The implementation described here can serve as an example for future courses in Europe.}, language = {en} } @phdthesis{Taleb2024, author = {Taleb, Aiham}, title = {Self-supervised deep learning methods for medical image analysis}, doi = {10.25932/publishup-64408}, url = {http://nbn-resolving.de/urn:nbn:de:kobv:517-opus4-644089}, school = {Universit{\"a}t Potsdam}, pages = {xii, 171}, year = {2024}, abstract = {Deep learning has seen widespread application in many domains, mainly for its ability to learn data representations from raw input data. Nevertheless, its success has so far been coupled with the availability of large annotated (labelled) datasets. This is a requirement that is difficult to fulfil in several domains, such as in medical imaging. Annotation costs form a barrier in extending deep learning to clinically-relevant use cases. The labels associated with medical images are scarce, since the generation of expert annotations of multimodal patient data at scale is non-trivial, expensive, and time-consuming. This substantiates the need for algorithms that learn from the increasing amounts of unlabeled data. Self-supervised representation learning algorithms offer a pertinent solution, as they allow solving real-world (downstream) deep learning tasks with fewer annotations. Self-supervised approaches leverage unlabeled samples to acquire generic features about different concepts, enabling annotation-efficient downstream task solving subsequently. Nevertheless, medical images present multiple unique and inherent challenges for existing self-supervised learning approaches, which we seek to address in this thesis: (i) medical images are multimodal, and their multiple modalities are heterogeneous in nature and imbalanced in quantities, e.g. MRI and CT; (ii) medical scans are multi-dimensional, often in 3D instead of 2D; (iii) disease patterns in medical scans are numerous and their incidence exhibits a long-tail distribution, so it is oftentimes essential to fuse knowledge from different data modalities, e.g. genomics or clinical data, to capture disease traits more comprehensively; (iv) Medical scans usually exhibit more uniform color density distributions, e.g. in dental X-Rays, than natural images. Our proposed self-supervised methods meet these challenges, besides significantly reducing the amounts of required annotations. We evaluate our self-supervised methods on a wide array of medical imaging applications and tasks. Our experimental results demonstrate the obtained gains in both annotation-efficiency and performance; our proposed methods outperform many approaches from related literature. Additionally, in case of fusion with genetic modalities, our methods also allow for cross-modal interpretability. In this thesis, not only we show that self-supervised learning is capable of mitigating manual annotation costs, but also our proposed solutions demonstrate how to better utilize it in the medical imaging domain. Progress in self-supervised learning has the potential to extend deep learning algorithms application to clinical scenarios.}, language = {en} } @article{ShamsWangRoineetal.2022, author = {Shams, Boshra and Wang, Ziqian and Roine, Timo and Aydogan, Dogu Baran and Vajkoczy, Peter and Lippert, Christoph and Picht, Thomas and Fekonja, Lucius Samo}, title = {Machine learning-based prediction of motor status in glioma patients using diffusion MRI metrics along the corticospinal tract}, series = {Brain communications}, volume = {4}, journal = {Brain communications}, number = {3}, publisher = {Oxford University Press}, address = {Oxford}, issn = {2632-1297}, doi = {10.1093/braincomms/fcac141}, pages = {17}, year = {2022}, abstract = {Shams et al. report that glioma patients' motor status is predicted accurately by diffusion MRI metrics along the corticospinal tract based on support vector machine method, reaching an overall accuracy of 77\%. They show that these metrics are more effective than demographic and clinical variables. Along tract statistics enables white matter characterization using various diffusion MRI metrics. These diffusion models reveal detailed insights into white matter microstructural changes with development, pathology and function. Here, we aim at assessing the clinical utility of diffusion MRI metrics along the corticospinal tract, investigating whether motor glioma patients can be classified with respect to their motor status. We retrospectively included 116 brain tumour patients suffering from either left or right supratentorial, unilateral World Health Organization Grades II, III and IV gliomas with a mean age of 53.51 +/- 16.32 years. Around 37\% of patients presented with preoperative motor function deficits according to the Medical Research Council scale. At group level comparison, the highest non-overlapping diffusion MRI differences were detected in the superior portion of the tracts' profiles. Fractional anisotropy and fibre density decrease, apparent diffusion coefficient axial diffusivity and radial diffusivity increase. To predict motor deficits, we developed a method based on a support vector machine using histogram-based features of diffusion MRI tract profiles (e.g. mean, standard deviation, kurtosis and skewness), following a recursive feature elimination method. Our model achieved high performance (74\% sensitivity, 75\% specificity, 74\% overall accuracy and 77\% area under the curve). We found that apparent diffusion coefficient, fractional anisotropy and radial diffusivity contributed more than other features to the model. Incorporating the patient demographics and clinical features such as age, tumour World Health Organization grade, tumour location, gender and resting motor threshold did not affect the model's performance, revealing that these features were not as effective as microstructural measures. These results shed light on the potential patterns of tumour-related microstructural white matter changes in the prediction of functional deficits.}, language = {en} } @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} }