Development and validation of a multimodal nomogram predicting anxiety and depression in Parkinson’s disease: integrating plasma biomarkers and clinical phenotypes
Introduction Anxiety and depression are prevalent, disabling, yet frequently underdiagnosed non-motor symptoms in Parkinson’s disease (PD). This study aimed to develop and validate a non-invasive model predicting these affective disorders by integrating peripheral blood biomarkers with standardized clinical scales to facilitate early screening. Methods We retrospectively analyzed data from 290 patients with PD, who were randomly allocated into a training cohort (n = 203) and a validation cohort (n = 87). Baseline plasma neurofilament light chain (NfL) levels and clinical phenotypes were assessed. Independent risk factors were determined via multivariate logistic regression analysis to construct the clinical prediction nomogram. Model performance was comprehensively evaluated using the area under the receiver operating characteristic curve (AUC) for discrimination, calibration curves for risk consistency, and decision curve analysis (DCA) for clinical utility. Results Multivariate logistic regression identified plasma NfL, Hoehn and Yahr stage, MMSE score, and MDS-UPDRS Part III score as independent predictors for anxiety and depression in PD patients (all p < 0.05). The established model exhibited high discriminative power, achieving an AUC of 0.94 (95% CI: 0.873–0.964) in the training cohort and 0.84 (95% CI: 0.782–0.879) in the validation cohort. Calibration curves demonstrated excellent consistency between predicted and actual probabilities, and DCA confirmed strong clinical net benefits. Discussion In conclusion, combining peripheral plasma NfL levels with standard clinical phenotypes provides an objective, quantifiable, and non-invasive tool for early risk stratification of affective disorders in PD. This multimodal nomogram effectively expands the therapeutic window for timely personalized psychiatric interventions, potentially improving long-term quality of life and clinical outcomes for PD patients.