BMC Psychol. 2025 Dec 27. doi: 10.1186/s40359-025-03894-4. Online ahead of print.
ABSTRACT
OBJECTIVE: To assess the prevalence of depression among uninsured middle-aged food delivery riders, to identify occupational and psychosocial determinants, and to develop a predictive nomogram for early risk detection.
METHODS: We conducted a cross-sectional survey of 1,333 uninsured riders aged 40-59 years in China between January 2022 and December 2024. Depressive symptoms were evaluated using the CESD-10 scale. Data on sociodemographic, behavioral, health, and occupational characteristics were collected. Predictors were identified through least absolute shrinkage and selection operator (LASSO) regression and entered into a multivariable logistic regression to construct a predictive model. Model performance was assessed using the area under the receiver operating characteristic curve (AUC), calibration plots, Brier scores, and decision curve analysis.
RESULTS: In total, 516 riders (38.7%) met the criteria for depression. Riders with depression were more often female and rural residents and reported poor self-rated health. Key occupational risk factors included frequent near-miss traffic events, higher algorithmic pressure, adverse weather exposure, and a greater number of customer complaints. Protective factors include male sex, better self-rated health, and greater organizational justice. The predictive nomogram demonstrated strong discrimination (AUC 0.828 in the training cohort and 0.853 in the test cohort) and satisfactory calibration.
CONCLUSION: This study developed and validated one of the first nomograms to predict depression in uninsured middle-aged food delivery riders. The model underscores the critical role of occupational stressors and psychosocial resources and provides a practical tool for risk identification.
PMID:41454401 | DOI:10.1186/s40359-025-03894-4
