Predicting the Health Condition of mHealth App Users with Large Differences in the Number of Recorded Observations - Where to Learn from?

Unnikrishnan, Vishnu; Shah, Yash; Schleicher, Miro; Strandzheva, Mirela; Dimitrov, Plamen; Velikova, Doroteya; Pryss, Rüdiger; Schobel, Johannes; Schlee, Winfried; Spiliopoulou, Myra

doi:10.1007/978-3-030-61527-7_43

Cited by 8 publications

(5 citation statements)

References 17 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…As TYT was able to gather more than 100,000 EMA questionnaires since 2013, which are comprised of many dimensions, we decided to answer RQ1 and RQ2 based on machine learning algorithms. As we already revealed interesting results on TYT EMA data based on machine learning [ 38 ], including the fact that the use of machine learning has been generally recognized in the context of mHealth data in the last years with much attention and valuable results [ 39 , 40 , 41 , 42 ], the present paper links these findings.…”

Section: Introductionsupporting

confidence: 61%

Prediction of Tinnitus Perception Based on Daily Life MHealth Data Using Country Origin and Season

Allgaier

Schlee

Probst

et al. 2022

JCM

Self Cite

View full text Add to dashboard Cite

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.

show abstract

Section: Introductionsupporting

confidence: 61%

Prediction of Tinnitus Perception Based on Daily Life MHealth Data Using Country Origin and Season

Allgaier

Schlee

Probst

et al. 2022

JCM

Self Cite

View full text Add to dashboard Cite

show abstract

“…This means that if the population of users were larger and more EMA were available for some of them, then the aforementioned finding might be reversed. There are indeed indications in that direction: our earlier analyses on users of EMA-based mHealth apps for tinnitus (Unnikrishnan et al, 2019 , 2020a , 2021 ) and diabetes (Unnikrishnan et al, 2020b ) demonstrate that it is possible to exploit the data of users who deliver many EMA in order to do high-quality predictions for users who deliver few EMA (or are at the beginning of their interaction with the app). Nonetheless, choosing appropriate data to inform a neighborhood-based predictor is challenging (Unnikrishnan et al, 2021 ), not least because dependencies between past and current recordings do not generalize for the whole population of users.…”

Section: Discussionmentioning

confidence: 94%

Predicting Ecological Momentary Assessments in an App for Tinnitus by Learning From Each User's Stream With a Contextual Multi-Armed Bandit

et al. 2022

Self Cite

View full text Add to dashboard Cite

Ecological Momentary Assessments (EMA) deliver insights on how patients perceive tinnitus at different times and how they are affected by it. Moving to the next level, an mHealth app can support users more directly by predicting a user's next EMA and recommending personalized services based on these predictions. In this study, we analyzed the data of 21 users who were exposed to an mHealth app with non-personalized recommendations, and we investigate ways of predicting the next vector of EMA answers. We studied the potential of entity-centric predictors that learn for each user separately and neighborhood-based predictors that learn for each user separately but take also similar users into account, and we compared them to a predictor that learns from all past EMA indiscriminately, without considering which user delivered which data, i.e., to a “global model.” Since users were exposed to two versions of the non-personalized recommendations app, we employed a Contextual Multi-Armed Bandit (CMAB), which chooses the best predictor for each user at each time point, taking each user's group into account. Our analysis showed that the combination of predictors into a CMAB achieves good performance throughout, since the global model was chosen at early time points and for users with few data, while the entity-centric, i.e., user-specific, predictors were used whenever the user had delivered enough data—the CMAB chose itself when the data were “enough.” This flexible setting delivered insights on how user behavior can be predicted for personalization, as well as insights on the specific mHealth data. Our main findings are that for EMA prediction the entity-centric predictors should be preferred over a user-insensitive global model and that the choice of EMA items should be further investigated because some items are answered more rarely than others. Albeit our CMAB-based prediction workflow is robust to differences in exposition and interaction intensity, experimentators that design studies with mHealth apps should be prepared to quantify and closely monitor differences in the intensity of user-app interaction, since users with many interactions may have a disproportionate influence on global models.

show abstract

“…In addition to a digital data collection procedure, TrackYourTinnitus uses smartphone-internal sensing capabilities to enrich the dataset with contextual data, like the current GPS position or environmental sound level.Most importantly, the TrackYourTinnitus platform and its generic API ( 45 ) have been adapted to other diseases as well. For example, the same technology stack is used to support researchers in assessing data in the context of stress ( 46 ), diabetes ( 47 ) or hearing loss. The study presented in Beierle et al ( 48 ) examines physical and mental well-being during the COVID-19 pandemic using an app that combines questionnaire-based surveys with mobile sensor recordings.…”

Section: Conceptmentioning

confidence: 99%

Enhancing mHealth data collection applications with sensing capabilities

Karthan

Martin

Holl

et al. 2022

Front. Public Health

Self Cite

View full text Add to dashboard Cite

Smart mobile devices such as smartphones or tablets have become an important factor for collecting data in complex health scenarios (e.g., psychological studies, medical trials), and are more and more replacing traditional pen-and-paper instruments. However, simply digitizing such instruments does not yet realize the full potential of mobile devices: most modern smartphones have a variety of di erent sensor technologies (e.g., microphone, GPS data, camera, ...) that can also provide valuable data and potentially valuable insights for the medical purpose or the researcher. In this context, a significant development e ort is required to integrate sensing capabilities into (existing) data collection applications. Developers may have to deal with platform-specific peculiarities (e.g., Android vs. iOS) or proprietary sensor data formats, resulting in unnecessary development e ort to support researchers with such digital solutions. Therefore, a cross-platform mobile data collection framework has been developed to extend existing data collection applications with sensor capabilities and address the aforementioned challenges in the process. This framework will enable researchers to collect additional information from participants and environment, increasing the amount of data collected and drawing new insights from existing data.

show abstract

Predicting the Health Condition of mHealth App Users with Large Differences in the Number of Recorded Observations - Where to Learn from?

Cited by 8 publications

References 17 publications

Prediction of Tinnitus Perception Based on Daily Life MHealth Data Using Country Origin and Season

Prediction of Tinnitus Perception Based on Daily Life MHealth Data Using Country Origin and Season

Predicting Ecological Momentary Assessments in an App for Tinnitus by Learning From Each User's Stream With a Contextual Multi-Armed Bandit

Enhancing mHealth data collection applications with sensing capabilities

Contact Info

Product

Resources

About