Predicting the gender of individuals with tinnitus based on daily life data of the TrackYourTinnitus mHealth platform

A comparison of self-reported COVID-19 symptoms between android and iOS CoronaCheck app users

This study explored differences in COVID-19 infections and symptoms between Android and iOS users using data from the CoronaCheck app. This cross-sectional analysis included 23,063 global users (20,753 Android and 2310 iOS) from April 2020 to February 2023. Participants reported COVID-19 symptoms and contact risks, with data analyzed to adjust for age, sex, education, and country. Android users were generally younger, more often male, had a lower educational level, and reported more symptoms on average (2.1 vs. 1.6) than iOS users. Android users also had higher suspected COVID-19 infection rates (24% vs. 11%), with an adjusted odds ratio of 2.21 (95% CI: 1.93-2.54). These findings suggest platform-based differences in COVID-19 infection rates and symptom reporting, highlighting potential biases in mobile health research. Adjusting for device operating systems may be crucial in improving the reliability of population-based health data collected through mobile platforms.

Process mining in mHealth data analysis

This perspective article explores how process mining can extract clinical insights from mobile health data and complement data-driven techniques like machine learning. Despite technological advances, challenges such as selection bias and the complex dynamics of health data require advanced approaches. Process mining focuses on analyzing temporal process patterns and provides complementary insights into health condition variability. The article highlights the potential of process mining for analyzing mHealth data and beyond.

Practical approaches in evaluating validation and biases of machine learning applied to mobile health studies

BACKGROUND

Machine learning (ML) models are evaluated in a test set to estimate model performance after deployment. The design of the test set is therefore of importance because if the data distribution after deployment differs too much, the model performance decreases. At the same time, the data often contains undetected groups. For example, multiple assessments from one user may constitute a group, which is usually the case in mHealth scenarios.

METHODS

In this work, we evaluate a model's performance using several cross-validation train-test-split approaches, in some cases deliberately ignoring the groups. By sorting the groups (in our case: Users) by time, we additionally simulate a concept drift scenario for better external validity. For this evaluation, we use 7 longitudinal mHealth datasets, all containing Ecological Momentary Assessments (EMA). Further, we compared the model performance with baseline heuristics, questioning the essential utility of a complex ML model.

RESULTS

Hidden groups in the dataset leads to overestimation of ML performance after deployment. For prediction, a user's last completed questionnaire is a reasonable heuristic for the next response, and potentially outperforms a complex ML model. Because we included 7 studies, low variance appears to be a more fundamental phenomenon of mHealth datasets.

CONCLUSIONS

The way mHealth-based data are generated by EMA leads to questions of user and assessment level and appropriate validation of ML models. Our analysis shows that further research needs to follow to obtain robust ML models. In addition, simple heuristics can be considered as an alternative for ML. Domain experts should be consulted to find potentially hidden groups in the data.

Conceptual framework for tinnitus: a cognitive model in practice

Tinnitus is a conscious attended awareness perception of sourceless sound. Widespread theoretical and evidence-based neurofunctional and psychological models have tried to explain tinnitus-related distress considering the influence of psychological and cognitive factors. However, tinnitus models seem to be less focused on causality, thereby easily misleading interpretations. Also, they may be incapable of individualization. This study proposes a Conceptual Cognitive Framework (CCF) providing insight into cognitive mechanisms involved in the predisposition, precipitation, and perpetuation of tinnitus and consequent cognitive-emotional disturbances. The current CCF for tinnitus relies on evaluative conditional learning and appraisal, generating negative valence (emotional value) and arousal (cognitive value) to annoyance, distress, and distorted perception. The suggested methodology is well-defined, reproducible, and accessible, which can help foster future high-quality clinical databases. Perceived tinnitus through the perpetual-learning process can always lead to annoyance, but only in the clinical stage directly cause annoyance. In the clinical stage, tinnitus perception can lead indirectly to distress only with experiencing annoyance either with ("I n d - 1 C " = 1.87; 95% CI 1.18-2.72)["1st indirect path in the Clinical stage model": Tinnitus Loudness → Attention Bias → Cognitive-Emotional Value → Annoyance → Clinical Distress]or without ("I n d - 2 C "= 2.03; 95% CI 1.02-3.32)[ "2nd indirect path in the Clinical stage model": Tinnitus Loudness → Annoyance → Clinical Distress] the perpetual-learning process. Further real-life testing of the CCF is expected to express a meticulous, decision-supporting platform for cognitive rehabilitation and clinical interventions. Furthermore, the suggested methodology offers a reliable platform for CCF development in other cognitive impairments and supports the causal clinical data models. It may also enhance our knowledge of psychological disorders and complicated comorbidities by supporting the design of different rehabilitation interventions and comprehensive frameworks in line with the "preventive medicine" policy.

Predicting the presence of tinnitus using ecological momentary assessments

Mobile applications have gained popularity in healthcare in recent years. These applications are an increasingly important pillar of public health care, as they open up new possibilities for data collection and can lead to new insights into various diseases and disorders thanks to modern data analysis approaches. In this context, Ecological Momentary Assessment (EMA) is a commonly used research method that aims to assess phenomena with a focus on ecological validity and to help both the user and the researcher observe these phenomena over time. One phenomenon that benefits from this capability is the chronic condition tinnitus. TrackYourTinnitus (TYT) is an EMA-based mobile crowdsensing platform designed to provide more insight into tinnitus by repeatedly assessing various dimensions of tinnitus, including perception (i.e., perceived presence). Because the presence of tinnitus is the dimension that is of great importance to chronic tinnitus patients and changes over time in many tinnitus patients, we seek to predict the presence of tinnitus based on the not directly related dimensions of mood, stress level, arousal, and concentration level that are captured in TYT. In this work, we analyzed a dataset of 45,935 responses to a harmonized EMA questionnaire using different machine learning techniques. In addition, we considered five different subgroups after consultation with clinicians to further validate our results. Finally, we were able to predict the presence of tinnitus with an accuracy of up to 78% and an AUC of up to 85.7%.

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

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.