cohort·nutrition, dietetics, clinical nutrition, public health, epidemiology·PMC10620836
Deep neural network for prediction of diet quality among doctors and nurses in North China during the COVID-19 pandemic
Frontiers in Public Health · 10 authors, 5 centres
AI SUMMARY
FIDELITY 100%
This summary was generated by AI from a single paper. It has not been reviewed by a clinician and is not clinical advice. Verify against the source before acting on it.
The DNN model achieved high prediction efficacy (R² = 0.928), with BMI, poor sleep quality, work–family conflict, negative emotional eating, and nutrition knowledge as the top five predictors.
Full summary
833 CHARS
Participants completed questionnaires assessing sociodemographic characteristics, lifestyles, sleep quality, personality traits, burnout, work-related conflicts, and diet quality. A Deep Neural Network with a 21–30–28-1 architecture was developed using 21 input features across two hidden layers. The model achieved high prediction efficacy with R² of 0.928, MAE of 0.048, MSE of 0.004, and RMSE of 0.065. The mean diet quality score was 46.14 ± 15.08 out of 100, indicating poor diet quality. BMI was the strongest predictor, followed by poor sleep quality, work–family conflict, negative emotional eating, and nutrition knowledge. The findings suggest that integrated interventions targeting weight management, sleep, work–family balance, emotional eating, and nutrition knowledge may improve diet quality among healthcare workers.
