Personalised depression forecasting using mobile sensor data and ecological momentary assessment

Alexander Kathan, Mathias Harrer, Ludwig Küster, Andreas Triantafyllopoulos, Xiangheng He, Manuel Milling, Maurice Gerczuk, Tianhao Yan, Srividya Tirunellai Rajamani, Elena Heber, Inga Grossmann, David D. Ebert, Björn W. Schuller

Research output: Contribution to JournalArticleAcademicpeer-review

Abstract

Introduction: Digital health interventions are an effective way to treat depression, but it is still largely unclear how patients’ individual symptoms evolve dynamically during such treatments. Data-driven forecasts of depressive symptoms would allow to greatly improve the personalisation of treatments. In current forecasting approaches, models are often trained on an entire population, resulting in a general model that works overall, but does not translate well to each individual in clinically heterogeneous, real-world populations. Model fairness across patient subgroups is also frequently overlooked. Personalised models tailored to the individual patient may therefore be promising. Methods: We investigate different personalisation strategies using transfer learning, subgroup models, as well as subject-dependent standardisation on a newly-collected, longitudinal dataset of depression patients undergoing treatment with a digital intervention ((Formula presented.) patients recruited). Both passive mobile sensor data as well as ecological momentary assessments were available for modelling. We evaluated the models’ ability to predict symptoms of depression (Patient Health Questionnaire-2; PHQ-2) at the end of each day, and to forecast symptoms of the next day. Results: In our experiments, we achieve a best mean-absolute-error (MAE) of (Formula presented.) (25% improvement) for predicting PHQ-2 values at the end of the day with subject-dependent standardisation compared to a non-personalised baseline ((Formula presented.)). For one day ahead-forecasting, we can improve the baseline of (Formula presented.) by (Formula presented.) to a MAE of (Formula presented.) using a transfer learning approach with shared common layers. In addition, personalisation leads to fairer models at group-level. Discussion: Our results suggest that personalisation using subject-dependent standardisation and transfer learning can improve predictions and forecasts, respectively, of depressive symptoms in participants of a digital depression intervention. We discuss technical and clinical limitations of this approach, avenues for future investigations, and how personalised machine learning architectures may be implemented to improve existing digital interventions for depression.
Original languageEnglish
Article number964582
JournalFrontiers in Digital Health
Volume4
DOIs
Publication statusPublished - 18 Nov 2022
Externally publishedYes

Funding

Data analysed in this publication were collected as part of the MAIKI project, which was funded by the German Federal Ministry of Education and Research (grant No. 113GW0254). The responsibility for the content of this publication lies with the authors. MH is supported by a fellowship of the Bavarian Research Institute for Digital Transformation (BIDT). Acknowledgment

FundersFunder number
Bavarian Research Institute for Digital Transformation
Bundesministerium für Bildung und Forschung113GW0254

    Fingerprint

    Dive into the research topics of 'Personalised depression forecasting using mobile sensor data and ecological momentary assessment'. Together they form a unique fingerprint.

    Cite this