Geriatric depression and anxiety screening via deep learning using activity tracking and sleep data

• Published in: International journal of geriatric psychiatry Vol. 39; no. 2; pp. e6071 - n/a
• Main Authors: Lee, Tae‐Rim, Kim, Geon Ha, Choi, Mun‐Taek
• Format: Journal Article
• Language: English
• Published: England Wiley Subscription Services, Inc 01.02.2024
• Subjects: activity tracking; Anxiety; Classification; Comorbidity; Deep learning; Dementia disorders; depression; Diagnosis; Feasibility studies; Functional magnetic resonance imaging; Geriatrics; Magnetic resonance imaging; Mental depression; Mental disorders; mixed input model; multi‐label classification; Neural networks; Older people; Sleep; step counts; Time series; time‐series data; Wrist; sleep; anxiety; deep learning; mixed input model; activity tracking; time-series data; step counts; depression; multi-label classification
• ISSN: 0885-6230; 1099-1166
• DOI: 10.1002/gps.6071

Background Geriatric depression and anxiety have been identified as mood disorders commonly associated with the onset of dementia. Currently, the diagnosis of geriatric depression and anxiety relies on self‐reported assessments for primary screening purposes, which is uncomfortable for older adults and can be prone to misreporting. When a more precise diagnosis is needed, additional methods such as in‐depth interviews or functional magnetic resonance imaging are used. However, these methods can not only be time‐consuming and costly but also require systematic and cost‐effective approaches. Objective The main objective of this study was to investigate the feasibility of training an end‐to‐end deep learning (DL) model by directly inputting time‐series activity tracking and sleep data obtained from consumer‐grade wrist‐worn activity trackers to identify comorbid depression and anxiety. Methods To enhance accuracy, the input of the DL model consisted of step counts and sleep stages as time series data, along with minimal depression and anxiety assessment scores as non‐time‐series data. The basic structure of the DL model was designed to process mixed‐input data and perform multi‐label‐based classification for depression and anxiety. Various DL models, including the convolutional neural network (CNN) and long short‐term memory (LSTM), were applied to process the time‐series data, and model selection was conducted by comparing the performances of the hyperparameters. Results This study achieved significant results in the multi‐label classification of depression and anxiety, with a Hamming loss score of 0.0946 in the Residual Network (ResNet), by applying a mixed‐input DL model based on activity tracking data. The comparison of hyper‐parameter performance and the development of various DL models, such as CNN, LSTM, and ResNet contributed to the optimization of time series data processing and achievement of meaningful results. Conclusions This study can be considered as the first to develop a mixed‐input DL model based on activity tracking data for the multi‐label identification of late‐life depression and anxiety. The findings of the study demonstrate the feasibility and potential of using consumer‐grade wrist‐worn activity trackers in conjunction with DL models to improve the identification of comorbid mental health conditions in older adults. The study also established a multi‐label classification framework for identifying the complex symptoms of depression and anxiety. Key points Deep learning (DL) models, notably ResNet, significantly enhance depression and anxiety classification using activity tracking data, outperforming traditional models in accuracy. Mixed‐input models that combine activity tracking with minimal assessment data demonstrate superior performance, underscoring the advantages of integrating diverse data types for mental health diagnosis. This study confirms the practicality of employing consumer‐grade wearable devices for the multi‐label classification of geriatric mood disorders, presenting an affordable and effective tool for healthcare