Early Detection and Management of Cognitive Impairment in Parkinson's Disease: A Predictive Model Approach

Abstract

Objective

The study aims to identify risk factors associated with cognitive impairment in Parkinson's disease and to develop a predictive model to facilitate early clinical detection, diagnosis, and management, thereby enhancing patient prognosis and quality of life.

Methods

A total of 351 PD patients were enrolled from the Department of Neurology at the First Hospital of Shanxi Medical University between January 2022 and December 2023. Cognitive function was evaluated using the Montreal Cognitive Assessment (MoCA) scale, and patients were subsequently categorized into cognitively normal (PD-NC) and cognitively impaired (PD-CI) groups. A logistic regression analysis was conducted to identify risk factors, and a predictive model was constructed and validated.

Results

Among the 351 patients with PD, 188 cases were in the PD⁃NC group and 163 cases were in the PD⁃CI group, with an incidence of cognitive impairment of 46.4%. Logistic regression analysis indicated that H–Y classification, HAMA score, homocysteine, uric acid, and folic acid were significant predictors and were incorporated into the regression equation. The constructed prediction model had an area under the receiver operating characteristic curve of 0.738.

Conclusions

The cognitive function of PD patients is influenced by H–Y classification, HAMA score, homocysteine, uric acid, and folic acid. The constructed prediction model demonstrates good discrimination and calibration, providing a reference basis for early clinical identification and intervention of cognitive impairment in Parkinson's disease patients.