Prediction of depressive symptoms severity based on sleep quality, anxiety, and gray matter volume: a generalizable machine learning approach across three datasets

Background Depressive symptoms are rising in the general population, but their associated factors are unclear. Although the link between sleep disturbances and depressive symptoms severity (DSS) is reported, the predictive role of sleep on DSS and the impact of anxiety and the brain on their relationship remained obscure. Methods Using three population-based datasets (N = 1813), we trained the machine learning models in the primary dataset (N = 1101) to assess the predictive role of sleep quality, anxiety problems, and brain structural (and functional) measurements on DSS, then we tested our models' performance in two independent datasets (N = 378, N = 334) to test the generalizability of our findings. Furthermore, we applied our model to a smaller longitudinal subsample (N = 66). In addition, we performed a mediation analysis to identify the role of anxiety and brain measurements on the sleep quality and DSS association. Findings Sleep quality could predict individual DSS (r = 0.43, R-2 = 0.18, rMSE = 2.73), and adding anxiety, contrary to brain measurements, strengthened its prediction performance (r = 0.67, R-2 = 0.45, rMSE = 2.25). Importantly, out-of-cohort validations in other cross-sectional datasets and a longitudinal subsample provided robust similar results. Furthermore, anxiety scores, contrary to brain measurements, mediated the association between sleep quality and DSS. Interpretation Poor sleep quality could predict DSS at the individual subject level across three datasets. Anxiety scores not only increased the predictive model's performance but also mediated the link between sleep quality and DSS. Copyright (c) 2024 The Author(s). Published by Elsevier B.V. This is an open access article under the CC BY license (http://creativecommons.org/licenses/by/4.0/). 2024;108: Published September https://doi.org/10. 1016/j.ebiom.2024. 105313