When Can I Expect the mHealth User to Return? Prediction Meets Time Series with Gaps

Abstract

With mHealth apps, data can be recorded in real life, which makes them useful, for example, as an accompanying tool in treatments. However, such datasets, especially those based on apps with usage on a voluntary basis, are often affected by fluctuating engagement and by high user dropout rates. This makes it difficult to exploit the data using machine learning techniques and raises the question of whether users have stopped using the app. In this paper, we present a method to identify phases with varying dropout rates in a dataset and predict for each. We also present an approach to predict what period of inactivity can be expected for a user in the current state. We use change point detection to identify the phases, show how to deal with uneven misaligned time series and predict the user’s phase using time series classification. We evaluated our method on the data of an mHealth app for tinnitus, and show that our approach is appropriate for the study of adherence in datasets with uneven, unaligned time series of different lengths and with missing values.

Appendix

Fig. 4.

Three exemplary attrition curves to illustrate the shape of a (a) logarithmic-shaped curve, (b) a sigmoid-shaped curve and (c) a L-shaped curve.

Table 2. This table shows the precision, recall, and f1-score as evaluation metrics for each class and each fold of the 10-fold stratified cross-validation as well as the averages for the 1-NN classifier (Pre–Precision, Rec–Recall, F1–F1-score, Sup–Support, Avg–Average & Acc–Accuracy)