summary: By analyzing demographics, lifestyle data, physical exam results, and lab values, new machine learning algorithms can accurately predict whether a person is at risk for sleep disorders. Age, weight, and depression are three factors that AI technology has identified as significant predictors of insomnia.
Machine learning models can use demographic and lifestyle data, physical examination results, and laboratory values to effectively predict a patient’s risk of sleep problems, according to a new study published this week in an open-access journal. and, pro swan By Samuel Y. Huang, Virginia Commonwealth University School of Medicine and Alexander A. Huang, Northwestern Feinberg University School of Medicine, USA.
The prevalence of diagnosed sleep disorders among American patients has increased significantly over the past decade. Sleep disorders are a significant risk factor for diabetes, heart disease, obesity and depression, so it is important to better understand and reverse this trend.
In a new study, researchers used the machine learning model XGBoost to analyze public data on 7,929 US patients who completed the National Health and Nutrition Examination Survey. Data included 684 variables per patient and included demographic, diet, exercise, and mental health questionnaire responses, as well as clinical and physical examination information.
Overall, 2,302 patients in the study were diagnosed with sleep disorders by their physicians. XGBoost was able to predict the risk of sleep disorder diagnosis with high accuracy (AUROC=0.87, sensitivity=0.74, specificity=0.77) using a total of 64 variables in the full dataset. The greatest predictors of sleep disturbance based on machine learning models were depression, weight, age and waist circumference.
The authors conclude that machine learning methods may be an effective first step to screen patients for sleep disorder risk without relying on physician judgment or bias.
Samuel Y. Huang adds: Fifty-seven other variables are associated with insomnia, but the contribution of each is visualized in a highly predictive model. ”
About this machine learning and sleep disorder research news
author: Hannah Abdalla
contact: Hannah Abdalla – PLOS
image: image is public domain
Original research: open access.
“Using Machine Learning to Identify Risk Factors for Insomnia,” Samuel Y. Huang et al. pro swan
Using machine learning to identify risk factors for insomnia
Although sleep is important to a person’s physical and mental health, few studies have systematically evaluated risk factors for sleep disorders.
The aim of this study was to identify risk factors for sleep disorders through machine learning and to evaluate this methodology.
design, setting, participants
A retrospective, cross-sectional cohort study using the publicly available National Health and Nutrition Examination Survey (NHANES) completed questionnaires on demographic, diet, exercise, and mental health, followed by clinical and physical examinations. It was performed in patients with available data.
A doctor’s diagnosis of insomnia was the result of this study. A univariate logistic model of insomnia outcomes was used to identify covariates associated with insomnia. Covariates with p < 0.0001 in univariate analysis were included in the final machine learning model. The machine learning model XGBoost was used because of its prevalence in the literature and its improved prediction accuracy in healthcare prediction. Covariates in the model were ranked according to cover statistics to identify risk factors for insomnia. We utilized Shapely Additive Explanations (SHAP) to visualize the relationship between these potential risk factors and insomnia.
Of the 7,929 patients who met the inclusion criteria in this study, 4,055 (51% were female and 3,874 (49%) were male. Mean age was 49.2 years (SD = 18.4), and 2,885 (36 %) Caucasian patients, 2,144 ( 27%) Black patients, 1,639 (21%) Hispanic patients, 1,261 (16%) patients of another race. There were 64 out of a total of 684 features for which P Machine learning models can effectively predict the risk of sleep disorders using demographic, clinical, physical, and lifestyle covariates to identify key risk factors.
Machine learning models can effectively predict the risk of sleep disorders using demographic, clinical, physical, and lifestyle covariates to identify key risk factors.