Personalized machine learning of depressed mood using wearables

Abstract

Depression is a multifaceted illness with large interindividual variability in clinical response to treatment. In the era of digital medicine and precision therapeutics, new personalized treatment approaches are warranted for depression. Here, we use a combination of longitudinal ecological momentary assessments of depression, neurocognitive sampling synchronized with electroencephalography, and lifestyle data from wearables to generate individualized predictions of depressed mood over a 1-month time period. This study, thus, develops a systematic pipeline for N-of-1 personalized modeling of depression using multiple modalities of data. In the models, we integrate seven types of supervised machine learning (ML) approaches for each individual, including ensemble learning and regression-based methods. All models were verified using fourfold nested cross-validation. The best-fit as benchmarked by the lowest mean absolute percentage error, was obtained by a different type of ML model for each individual, demonstrating that there is no one-size-fits-all strategy. The voting regressor, which is a composite strategy across ML models, was best performing on-average across subjects. However, the individually selected best-fit models still showed significantly less error than the voting regressor performance across subjects. For each individual’s best-fit personalized model, we further extracted top-feature predictors using Shapley statistics. Shapley values revealed distinct feature determinants of depression over time for each person ranging from co-morbid anxiety, to physical exercise, diet, momentary stress and breathing performance, sleep times, and neurocognition. In future, these personalized features can serve as targets for a personalized ML-guided, multimodal treatment strategy for depression.

Managing Perceived Loneliness and Social-Isolation Levels for Older Adults: A Survey with Focus on Wearables-Based Solutions

“…Ensemble learning [142,143] Recommendation systems and prediction of loneliness levels Improves the generalization capacity of the model and makes predictions using data-fusion techniques for multiple data sources…”

Smart Consumer Wearables as Digital Diagnostic Tools: A Review

“…Wearable device data equipped with ML algorithms are helpful for extracting the highly personalized nature of psychological conditions such as depression and mood swings. A recent study on 14 young people using EEG data, neurocognitive assessments, and lifestyle data from wearable devices revealed that each person had distinct depression determinants [ 90 ]. Hence, highly personalized diagnoses and treatments are required.…”

Modulation Spectral Signal Representation for Quality Measurement and Enhancement of Wearable Device Data: A Technical Note

“…In addition to COVID-19 infection monitoring, wearables have shown to disrupt numerous healthcare domains, including cardiology [5], gait analysis [6], sleep quality [7], clinical trials during cancer treatment [8], stress management [9], and emotion/depression [10], just to name a few. In addition to healthcare, wearables have also seen applications in smart vehicles [11], pedestrian tracking [12], gaming [13] and extended reality [14], smart homes and robots [15], construction safety [16], and Industry 4.0 applications [17].…”