Objective To explore the predictive value of neutrophil/lymphocyte ratio (NLR) and prognostic nutritional index (PNI) for Parkinson"s disease (PD) patients with depressive symptoms, and to construct and verify a nomogram prediction model for the risk of PD patients with depression. Methods One hundred and eighty-two patients with PD were recruited, and 175 healthy controls (HCs) matched for age and sex were admitted simultaneously. According to the HAMD-24 score, the patients with PD were divided into two groups: PD without depression group and PD with depression group. The differences in clinical data between the groups were compared, and a multivariate logistic regression analysis was used to explore the influencing factors of PD patients with depression, And based on this, construct and validate a column chart model for personalized prediction of the risk of depression in PD patients. Results (1) Compared with HCs, patients with PD showed lower PNI but higher NLR (P<0.05). (2) Compared with PD patients without depression, PD patients with depression showed higher levels of NLR, LED, H-Y stage, course of disease, and UPDRS-III; but lower level of PNI (P<0.05). (3) The results of multivariate logistic regression analysis showed that NLR, LED and UPDRS-III were independent risk factors for PD patients with depression; while PNI was an independent protective factor for PD patients with depression. (4) Based on the results of multivariate logistic regression analysis, a nomogram model was constructed to predict the risk of depression in PD patients. The area under the ROC curve (AUC) of the nomogram model was 0.835 (95%CI: 0.776-0.893, P<0.01). The Hosmer- Leme show test showed χ2=11.576 (P>0.05). Combining the calibration curve and decision curve, it was found that the nomogram model had good clinical consistency and clinical applicability. Conclusions The individualized nomogram model based on PNI, NLR, LED and UPDRS-III can effectively predict the risk of depression in patients with PD, and has certain clinical application value.