@phdthesis{Allgaier2024, author = {Allgaier, Johannes}, title = {Machine Learning Explainability on Multi-Modal Data using Ecological Momentary Assessments in the Medical Domain}, doi = {10.25972/OPUS-35118}, url = {http://nbn-resolving.de/urn:nbn:de:bvb:20-opus-351189}, school = {Universit{\"a}t W{\"u}rzburg}, year = {2024}, abstract = {Introduction. Mobile health (mHealth) integrates mobile devices into healthcare, enabling remote monitoring, data collection, and personalized interventions. Machine Learning (ML), a subfield of Artificial Intelligence (AI), can use mHealth data to confirm or extend domain knowledge by finding associations within the data, i.e., with the goal of improving healthcare decisions. In this work, two data collection techniques were used for mHealth data fed into ML systems: Mobile Crowdsensing (MCS), which is a collaborative data gathering approach, and Ecological Momentary Assessments (EMA), which capture real-time individual experiences within the individual's common environments using questionnaires and sensors. We collected EMA and MCS data on tinnitus and COVID-19. About 15 \% of the world's population suffers from tinnitus. Materials \& Methods. This thesis investigates the challenges of ML systems when using MCS and EMA data. It asks: How can ML confirm or broad domain knowledge? Domain knowledge refers to expertise and understanding in a specific field, gained through experience and education. Are ML systems always superior to simple heuristics and if yes, how can one reach explainable AI (XAI) in the presence of mHealth data? An XAI method enables a human to understand why a model makes certain predictions. Finally, which guidelines can be beneficial for the use of ML within the mHealth domain? In tinnitus research, ML discerns gender, temperature, and season-related variations among patients. In the realm of COVID-19, we collaboratively designed a COVID-19 check app for public education, incorporating EMA data to offer informative feedback on COVID-19-related matters. This thesis uses seven EMA datasets with more than 250,000 assessments. Our analyses revealed a set of challenges: App user over-representation, time gaps, identity ambiguity, and operating system specific rounding errors, among others. Our systematic review of 450 medical studies assessed prior utilization of XAI methods. Results. ML models predict gender and tinnitus perception, validating gender-linked tinnitus disparities. Using season and temperature to predict tinnitus shows the association of these variables with tinnitus. Multiple assessments of one app user can constitute a group. Neglecting these groups in data sets leads to model overfitting. In select instances, heuristics outperform ML models, highlighting the need for domain expert consultation to unveil hidden groups or find simple heuristics. Conclusion. This thesis suggests guidelines for mHealth related data analyses and improves estimates for ML performance. Close communication with medical domain experts to identify latent user subsets and incremental benefits of ML is essential.}, subject = {Maschinelles Lernen}, language = {en} } @article{AllgaierSchleeProbstetal.2022, author = {Allgaier, Johannes and Schlee, Winfried and Probst, Thomas and Pryss, R{\"u}diger}, title = {Prediction of tinnitus perception based on daily life mHealth data using country origin and season}, series = {Journal of Clinical Medicine}, volume = {11}, journal = {Journal of Clinical Medicine}, number = {15}, issn = {2077-0383}, doi = {10.3390/jcm11154270}, url = {http://nbn-resolving.de/urn:nbn:de:bvb:20-opus-281812}, year = {2022}, abstract = {Tinnitus is an auditory phantom perception without external sound stimuli. This chronic perception can severely affect quality of life. Because tinnitus symptoms are highly heterogeneous, multimodal data analyses are increasingly used to gain new insights. MHealth data sources, with their particular focus on country- and season-specific differences, can provide a promising avenue for new insights. Therefore, we examined data from the TrackYourTinnitus (TYT) mHealth platform to create symptom profiles of TYT users. We used gradient boosting engines to classify momentary tinnitus and regress tinnitus loudness, using country of origin and season as features. At the daily assessment level, tinnitus loudness can be regressed with a mean absolute error rate of 7.9\% points. In turn, momentary tinnitus can be classified with an F1 score of 93.79\%. Both results indicate differences in the tinnitus of TYT users with respect to season and country of origin. The significance of the features was evaluated using statistical and explainable machine learning methods. It was further shown that tinnitus varies with temperature in certain countries. The results presented show that season and country of origin appear to be valuable features when combined with longitudinal mHealth data at the level of daily assessment.}, language = {en} } @article{AllgaierSchleeLangguthetal.2021, author = {Allgaier, Johannes and Schlee, Winfried and Langguth, Berthold and Probst, Thomas and Pryss, R{\"u}diger}, title = {Predicting the Gender of Individuals with Tinnitus based on Daily Life Data of the TrackYourTinnitus mHealth Platform}, series = {Scientific Reports}, volume = {11}, journal = {Scientific Reports}, number = {1}, doi = {10.1038/s41598-021-96731-8}, url = {http://nbn-resolving.de/urn:nbn:de:bvb:20-opus-261753}, year = {2021}, abstract = {Tinnitus is an auditory phantom perception in the absence of an external sound stimulation. People with tinnitus often report severe constraints in their daily life. Interestingly, indications exist on gender differences between women and men both in the symptom profile as well as in the response to specific tinnitus treatments. In this paper, data of the TrackYourTinnitus platform (TYT) were analyzed to investigate whether the gender of users can be predicted. In general, the TYT mobile Health crowdsensing platform was developed to demystify the daily and momentary variations of tinnitus symptoms over time. The goal of the presented investigation is a better understanding of gender-related differences in the symptom profiles of users from TYT. Based on two questionnaires of TYT, four machine learning based classifiers were trained and analyzed. With respect to the provided daily answers, the gender of TYT users can be predicted with an accuracy of 81.7\%. In this context, worries, difficulties in concentration, and irritability towards the family are the three most important characteristics for predicting the gender. Note that in contrast to existing studies on TYT, daily answers to the worst symptom question were firstly investigated in more detail. It was found that results of this question significantly contribute to the prediction of the gender of TYT users. Overall, our findings indicate gender-related differences in tinnitus and tinnitus-related symptoms. Based on evidence that gender impacts the development of tinnitus, the gathered insights can be considered relevant and justify further investigations in this direction.}, language = {en} } @article{BeierleSchobelVogeletal.2021, author = {Beierle, Felix and Schobel, Johannes and Vogel, Carsten and Allgaier, Johannes and Mulansky, Lena and Haug, Fabian and Haug, Julian and Schlee, Winfried and Holfelder, Marc and Stach, Michael and Schickler, Marc and Baumeister, Harald and Cohrdes, Caroline and Deckert, J{\"u}rgen and Deserno, Lorenz and Edler, Johanna-Sophie and Eichner, Felizitas A. and Greger, Helmut and Hein, Grit and Heuschmann, Peter and John, Dennis and Kestler, Hans A. and Krefting, Dagmar and Langguth, Berthold and Meybohm, Patrick and Probst, Thomas and Reichert, Manfred and Romanos, Marcel and St{\"o}rk, Stefan and Terhorst, Yannik and Weiß, Martin and Pryss, R{\"u}diger}, title = {Corona Health — A Study- and Sensor-Based Mobile App Platform Exploring Aspects of the COVID-19 Pandemic}, series = {International Journal of Environmental Research and Public Health}, volume = {18}, journal = {International Journal of Environmental Research and Public Health}, number = {14}, issn = {1660-4601}, doi = {10.3390/ijerph18147395}, url = {http://nbn-resolving.de/urn:nbn:de:bvb:20-opus-242658}, year = {2021}, abstract = {Physical and mental well-being during the COVID-19 pandemic is typically assessed via surveys, which might make it difficult to conduct longitudinal studies and might lead to data suffering from recall bias. Ecological momentary assessment (EMA) driven smartphone apps can help alleviate such issues, allowing for in situ recordings. Implementing such an app is not trivial, necessitates strict regulatory and legal requirements, and requires short development cycles to appropriately react to abrupt changes in the pandemic. Based on an existing app framework, we developed Corona Health, an app that serves as a platform for deploying questionnaire-based studies in combination with recordings of mobile sensors. In this paper, we present the technical details of Corona Health and provide first insights into the collected data. Through collaborative efforts from experts from public health, medicine, psychology, and computer science, we released Corona Health publicly on Google Play and the Apple App Store (in July 2020) in eight languages and attracted 7290 installations so far. Currently, five studies related to physical and mental well-being are deployed and 17,241 questionnaires have been filled out. Corona Health proves to be a viable tool for conducting research related to the COVID-19 pandemic and can serve as a blueprint for future EMA-based studies. The data we collected will substantially improve our knowledge on mental and physical health states, traits and trajectories as well as its risk and protective factors over the course of the COVID-19 pandemic and its diverse prevention measures.}, language = {en} } @article{KammererHoppenstedtPryssetal.2019, author = {Kammerer, Klaus and Hoppenstedt, Burkhard and Pryss, R{\"u}diger and St{\"o}kler, Steffen and Allgaier, Johannes and Reichert, Manfred}, title = {Anomaly Detections for Manufacturing Systems Based on Sensor Data—Insights into Two Challenging Real-World Production Settings}, series = {Sensors}, volume = {19}, journal = {Sensors}, number = {24}, issn = {1424-8220}, doi = {10.3390/s19245370}, url = {http://nbn-resolving.de/urn:nbn:de:bvb:20-opus-193885}, pages = {5370}, year = {2019}, abstract = {o build, run, and maintain reliable manufacturing machines, the condition of their components has to be continuously monitored. When following a fine-grained monitoring of these machines, challenges emerge pertaining to the (1) feeding procedure of large amounts of sensor data to downstream processing components and the (2) meaningful analysis of the produced data. Regarding the latter aspect, manifold purposes are addressed by practitioners and researchers. Two analyses of real-world datasets that were generated in production settings are discussed in this paper. More specifically, the analyses had the goals (1) to detect sensor data anomalies for further analyses of a pharma packaging scenario and (2) to predict unfavorable temperature values of a 3D printing machine environment. Based on the results of the analyses, it will be shown that a proper management of machines and their components in industrial manufacturing environments can be efficiently supported by the detection of anomalies. The latter shall help to support the technical evangelists of the production companies more properly.}, language = {en} }