@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} } @misc{KonigorskiWernickeSlosareketal.2023, author = {Konigorski, Stefan and Wernicke, Sarah and Slosarek, Tamara and Zenner, Alexander Maximilian and Strelow, Nils and Ruether, Darius Ferenc and Henschel, Florian and Manaswini, Manisha and Pottb{\"a}cker, Fabian and Edelman, Jonathan Antonio 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 = {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 = {12}, doi = {10.25932/publishup-58037}, url = {http://nbn-resolving.de/urn:nbn:de:kobv:517-opus4-580370}, pages = {12}, year = {2023}, 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} } @article{FreitasdaCruzPfahringerMartensenetal.2021, author = {Freitas da Cruz, Harry and Pfahringer, Boris and Martensen, Tom and Schneider, Frederic and Meyer, Alexander and B{\"o}ttinger, Erwin and Schapranow, Matthieu-Patrick}, title = {Using interpretability approaches to update "black-box" clinical prediction models}, series = {Artificial intelligence in medicine : AIM}, volume = {111}, journal = {Artificial intelligence in medicine : AIM}, publisher = {Elsevier}, address = {Amsterdam}, issn = {0933-3657}, doi = {10.1016/j.artmed.2020.101982}, pages = {13}, year = {2021}, abstract = {Despite advances in machine learning-based clinical prediction models, only few of such models are actually deployed in clinical contexts. Among other reasons, this is due to a lack of validation studies. In this paper, we present and discuss the validation results of a machine learning model for the prediction of acute kidney injury in cardiac surgery patients initially developed on the MIMIC-III dataset when applied to an external cohort of an American research hospital. To help account for the performance differences observed, we utilized interpretability methods based on feature importance, which allowed experts to scrutinize model behavior both at the global and local level, making it possible to gain further insights into why it did not behave as expected on the validation cohort. The knowledge gleaned upon derivation can be potentially useful to assist model update during validation for more generalizable and simpler models. We argue that interpretability methods should be considered by practitioners as a further tool to help explain performance differences and inform model update in validation studies.}, language = {en} } @book{AdrianoBleifussChengetal.2019, author = {Adriano, Christian and Bleifuß, Tobias and Cheng, Lung-Pan and Diba, Kiarash and Fricke, Andreas and Grapentin, Andreas and Jiang, Lan and Kovacs, Robert and Krejca, Martin Stefan and Mandal, Sankalita and Marwecki, Sebastian and Matthies, Christoph and Mattis, Toni and Niephaus, Fabio and Pirl, Lukas and Quinzan, Francesco and Ramson, Stefan and Rezaei, Mina and Risch, Julian and Rothenberger, Ralf and Roumen, Thijs and Stojanovic, Vladeta and Wolf, Johannes}, title = {Technical report}, number = {129}, editor = {Meinel, Christoph and Plattner, Hasso and D{\"o}llner, J{\"u}rgen Roland Friedrich and Weske, Mathias and Polze, Andreas and Hirschfeld, Robert and Naumann, Felix and Giese, Holger and Baudisch, Patrick and Friedrich, Tobias and B{\"o}ttinger, Erwin and Lippert, Christoph}, publisher = {Universit{\"a}tsverlag Potsdam}, address = {Potsdam}, isbn = {978-3-86956-465-4}, issn = {1613-5652}, doi = {10.25932/publishup-42753}, url = {http://nbn-resolving.de/urn:nbn:de:kobv:517-opus4-427535}, publisher = {Universit{\"a}t Potsdam}, pages = {vi, 267}, year = {2019}, abstract = {Design and Implementation of service-oriented architectures imposes a huge number of research questions from the fields of software engineering, system analysis and modeling, adaptability, and application integration. Component orientation and web services are two approaches for design and realization of complex web-based system. Both approaches allow for dynamic application adaptation as well as integration of enterprise application. Commonly used technologies, such as J2EE and .NET, form de facto standards for the realization of complex distributed systems. Evolution of component systems has lead to web services and service-based architectures. This has been manifested in a multitude of industry standards and initiatives such as XML, WSDL UDDI, SOAP, etc. All these achievements lead to a new and promising paradigm in IT systems engineering which proposes to design complex software solutions as collaboration of contractually defined software services. Service-Oriented Systems Engineering represents a symbiosis of best practices in object-orientation, component-based development, distributed computing, and business process management. It provides integration of business and IT concerns. The annual Ph.D. Retreat of the Research School provides each member the opportunity to present his/her current state of their research and to give an outline of a prospective Ph.D. thesis. Due to the interdisciplinary structure of the research school, this technical report covers a wide range of topics. These include but are not limited to: Human Computer Interaction and Computer Vision as Service; Service-oriented Geovisualization Systems; Algorithm Engineering for Service-oriented Systems; Modeling and Verification of Self-adaptive Service-oriented Systems; Tools and Methods for Software Engineering in Service-oriented Systems; Security Engineering of Service-based IT Systems; Service-oriented Information Systems; Evolutionary Transition of Enterprise Applications to Service Orientation; Operating System Abstractions for Service-oriented Computing; and Services Specification, Composition, and Enactment.}, 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{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{UlrichLutfiRutzenetal.2022, author = {Ulrich, Jens-Uwe and Lutfi, Ahmad and Rutzen, Kilian and Renard, Bernhard Y.}, title = {ReadBouncer}, series = {Bioinformatics}, volume = {38}, journal = {Bioinformatics}, number = {SUPPL 1}, publisher = {Oxford Univ. Press}, address = {Oxford}, issn = {1367-4803}, doi = {10.1093/bioinformatics/btac223}, pages = {153 -- 160}, year = {2022}, abstract = {Motivation: Nanopore sequencers allow targeted sequencing of interesting nucleotide sequences by rejecting other sequences from individual pores. This feature facilitates the enrichment of low-abundant sequences by depleting overrepresented ones in-silico. Existing tools for adaptive sampling either apply signal alignment, which cannot handle human-sized reference sequences, or apply read mapping in sequence space relying on fast graphical processing units (GPU) base callers for real-time read rejection. Using nanopore long-read mapping tools is also not optimal when mapping shorter reads as usually analyzed in adaptive sampling applications. Results: Here, we present a new approach for nanopore adaptive sampling that combines fast CPU and GPU base calling with read classification based on Interleaved Bloom Filters. ReadBouncer improves the potential enrichment of low abundance sequences by its high read classification sensitivity and specificity, outperforming existing tools in the field. It robustly removes even reads belonging to large reference sequences while running on commodity hardware without GPUs, making adaptive sampling accessible for in-field researchers. Readbouncer also provides a user-friendly interface and installer files for end-users without a bioinformatics background.}, 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} } @inproceedings{MarxBruenkerMirbabaieetal.2024, author = {Marx, Julian and Br{\"u}nker, Felix and Mirbabaie, Milad and Stieglitz, Stefan}, title = {Digital activism on social media}, series = {Proceedings of the 57th Annual Hawaii International Conference on System Sciences}, booktitle = {Proceedings of the 57th Annual Hawaii International Conference on System Sciences}, editor = {Bui, Tung X.}, publisher = {Department of IT Management Shidler College of Business University of Hawaii}, address = {Honolulu, HI}, isbn = {978-0-99813-317-1}, pages = {7205 -- 7214}, year = {2024}, abstract = {Social media constitute an important arena for public debates and steady interchange of issues relevant to society. To boost their reputation, commercial organizations also engage in political, social, or environmental debates on social media. To engage in this type of digital activism, organizations increasingly utilize the social media profiles of executive employees and other brand ambassadors. However, the relationship between brand ambassadors' digital activism and corporate reputation is only vaguely understood. The results of a qualitative inquiry suggest that digital activism via brand ambassadors can be risky (e.g., creating additional surface for firestorms, financial loss) and rewarding (e.g., emitting authenticity, employing 'megaphones' for industry change) at the same time. The paper informs both scholarship and practitioners about strategic trade-offs that need to be considered when employing brand ambassadors for digital activism.}, language = {en} } @article{FandinoLaferriereRomeroetal.2021, author = {Fandi{\~n}o, Jorge and Laferriere, Francois and Romero, Javier and Schaub, Torsten H. and Son, Tran Cao}, title = {Planning with incomplete information in quantified answer set programming}, series = {Theory and practice of logic programming}, volume = {21}, journal = {Theory and practice of logic programming}, number = {5}, publisher = {Cambridge University Press}, address = {Cambridge}, issn = {1471-0684}, doi = {10.1017/S1471068421000259}, pages = {663 -- 679}, year = {2021}, abstract = {We present a general approach to planning with incomplete information in Answer Set Programming (ASP). More precisely, we consider the problems of conformant and conditional planning with sensing actions and assumptions. We represent planning problems using a simple formalism where logic programs describe the transition function between states, the initial states and the goal states. For solving planning problems, we use Quantified Answer Set Programming (QASP), an extension of ASP with existential and universal quantifiers over atoms that is analogous to Quantified Boolean Formulas (QBFs). We define the language of quantified logic programs and use it to represent the solutions different variants of conformant and conditional planning. On the practical side, we present a translation-based QASP solver that converts quantified logic programs into QBFs and then executes a QBF solver, and we evaluate experimentally the approach on conformant and conditional planning benchmarks.}, language = {en} } @inproceedings{MirbabaieRieskampHofeditzetal.2024, author = {Mirbabaie, Milad and Rieskamp, Jonas and Hofeditz, Lennart and Stieglitz, Stefan}, title = {Breaking down barriers}, series = {Proceedings of the 57th Annual Hawaii International Conference on System Sciences}, booktitle = {Proceedings of the 57th Annual Hawaii International Conference on System Sciences}, editor = {Bui, Tung X.}, publisher = {Department of IT Management Shidler College of Business University of Hawaii}, address = {Honolulu, HI}, isbn = {978-0-99813-317-1}, pages = {672 -- 681}, year = {2024}, abstract = {Many researchers hesitate to provide full access to their datasets due to a lack of knowledge about research data management (RDM) tools and perceived fears, such as losing the value of one's own data. Existing tools and approaches often do not take into account these fears and missing knowledge. In this study, we examined how conversational agents (CAs) can provide a natural way of guidance through RDM processes and nudge researchers towards more data sharing. This work offers an online experiment in which researchers interacted with a CA on a self-developed RDM platform and a survey on participants' data sharing behavior. Our findings indicate that the presence of a guiding and enlightening CA on an RDM platform has a constructive influence on both the intention to share data and the actual behavior of data sharing. Notably, individual factors do not appear to impede or hinder this effect.}, language = {en} }