Development and Validation of a Sleep Disorder Risk Prediction Model in Young and Middle-Aged Adults With Anemia
- 1Shandong Public Health Clinical Center
Abstract
ObjectiveThis study aimed to develop and validate a predictive model for sleep disorders in young and middle-aged adults with anemia, providing evidence for early identification, risk stratification, and individualized sleep management.
MethodsData in the NHANES were analyzed and randomly divided into development and validation cohorts. LASSO regression was used to screen optimal predictors in the development cohort, followed by univariate and multivariate logistic regression to identify independent predictors and construct a nomogram. Model performance was evaluated using receiver operating characteristic curves, calibration curves, Brier scores, and decision curve analysis.
ResultsThe weighted prevalence of sleep disorders among young and middle-aged adults with anemia was 10.19%. Multivariate logistic regression identified seven independent predictors: sex, monocyte count, asthma, overweight, arthritis, congestive heart failure, and hypertension. The model showed good discrimination, with area under the curve values of 0.817 in the development cohort and 0.791 in the validation cohort. Calibration was satisfactory, with Brier scores of 0.074 and 0.075, respectively. Decision curve analysis indicated favorable clinical net benefit in both cohorts.
ConclusionThe proposed predictive model demonstrated good discrimination, calibration, and may help healthcare providers identify young and middle-aged adults with anemia who are at high risk for sleep disorders.
Related
- Interpretable prediction model for severe community-acquired pneumonia in adults: machine learning development and validation using routine laboratory parameters
- Development and internal validation of a baseline prediction model for ≥10-point Oswestry Disability Index improvement by episode end among adults receiving outpatient physical therapy for low back pain : A retrospective cohort study
- Development and validation of a prediction model for subsequent fractures after hip fracture surgery in older adults: a retrospective cohort study.
- Development and external validation of a preoperative prediction model for in-hospital major adverse cardiovascular events after hip fracture surgery in older adults: a retrospective two-center study.
- Pain as a predictor of incident frailty in middle-aged and older adults with metabolic dysfunction-associated steatotic liver disease: a prospective cohort study using machine learning and external validation
BibTeX
@misc{liu2026development,
title = {{Development and Validation of a Sleep Disorder Risk Prediction Model in Young and Middle-Aged Adults With Anemia}},
author = {Y. Liu and C. Zhang},
howpublished = {medRxiv},
year = {2026},
month = oct,
doi = {10.64898/2026.10.12.26365352},
url = {https://www.medrxiv.org/content/10.64898/2026.10.12.26365352v1},
note = {CC BY},
}
RIS
TY - UNPB
TI - Development and Validation of a Sleep Disorder Risk Prediction Model in Young and Middle-Aged Adults With Anemia
AU - Y. Liu
AU - C. Zhang
PY - 2026
DA - 2026/10/12
PB - medRxiv
DO - 10.64898/2026.10.12.26365352
UR - https://www.medrxiv.org/content/10.64898/2026.10.12.26365352v1
AB - ObjectiveThis study aimed to develop and validate a predictive model for sleep disorders in young and middle-aged adults with anemia, providing evidence for early identification, risk stratification, and individualized sleep management. MethodsData in the NHANES were analyzed and randomly divided into development and validation cohorts. LASSO regression was used to screen optimal predictors in the development cohort, followed by univariate and multivariate logistic regression to identify independent predictors and construct a nomogram. Model performance was evaluated using receiver operating characteristic curves, calibration curves, Brier scores, and decision curve analysis. ResultsThe weighted prevalence of sleep disorders among young and middle-aged adults with anemia was 10.19%. Multivariate logistic regression identified seven independent predictors: sex, monocyte count, asthma, overweight, arthritis, congestive heart failure, and hypertension. The model showed good discrimination, with area under the curve values of 0.817 in the development cohort and 0.791 in the validation cohort. Calibration was satisfactory, with Brier scores of 0.074 and 0.075, respectively. Decision curve analysis indicated favorable clinical net benefit in both cohorts. ConclusionThe proposed predictive model demonstrated good discrimination, calibration, and may help healthcare providers identify young and middle-aged adults with anemia who are at high risk for sleep disorders.
ER -