A Multi-Method Machine Learning Analysis of Sleep Disturbances’ Determinants During COVID-19.

Publication date: Jun 26, 2025

Sleep disturbances are a major issue, nowadays, make the whole scientific community to be alert, utilizing machine learning techniques to predict its underlying determinants. The main purpose of this paper is to test the accuracy of machine learning algorithms in interpretation of sleep problems. A public dataset was used and multiple feature selection techniques were addressed to identify the most influential predictors in sleep disturbances. Explainable AI was used to further interpret how each predictor impacts individual predictions. Results from model performance show that AdaBoost outperformed other models (71. 27% accuracy) and sleep quality is the dominant predictor (with SHAP value 0. 01586), indicating the strongest influence on model. The incorporation of explainable AI methods (e. g., SHAP) enhances the clinical and public health value of these models, enabling healthcare providers to target specific interventions and potentially improve patients’ sleep health outcomes.

Open Access PDF

Concepts Keywords
Healthcare Algorithms
Outperformed COVID-19
Scientific explainable AI (XAI)
Sleep Female
Humans
interpretable machine learning
Machine Learning
SARS-CoV-2
sleep disturbances
Sleep Wake Disorders

Semantics

Type Source Name
disease MESH COVID-19
disease MESH sleep quality
disease MESH insomnia
disease MESH mental disorder
pathway REACTOME Metabolism
disease MESH sleep disorders
disease MESH hypersomnia
disease MESH sleep apnea
disease MESH anxiety
disease MESH depression
drug DRUGBANK Diethylstilbestrol
drug DRUGBANK Methionine
drug DRUGBANK Flunarizine
disease MESH sleep debt
disease IDO quality
disease MESH lifestyle

Original Article

(Visited 3 times, 1 visits today)