In European journal of neurology
BACKGROUND : A broad list of variables associated with mild cognitive impairment (MCI) in Parkinson's Disease (PD) has been investigated separately. However, there is no study including all of them to assess variable importance yet. Shapley variable importance cloud (ShapleyVIC) can robustly assesses variable importance while accounting for correlation between variables.
OBJECTIVE : 1) To prioritise the important variables associated with PD-MCI; 2) To explore new blood biomarkers related to PD-MCI.
METHODS : ShapleyVIC-assisted variable selection was used to identify a subset of variables from 41 variables potentially associated with PD-MCI in a cross-sectional study. Backward selection was used to further identify the variables that associated with PD-MCI. Relative risk was used to quantify the association of final predictors and PD-MCI in the final multivariable log-binomial regression model.
RESULTS : Among 41 variables analysed, 22 variables were identified as significantly important variables associated with PD-MCI and 8 variables were subsequently selected in the final model, indicating shorter education year, history of hypertension, higher MDS-UPDRS motor score, higher levels of TG, APOA1, and SNCA rs6826785 non-carrier were associated with increased risk of PD-MCI (p<0.05).
CONCLUSIONS : Our study highlighted the strong association between TG, APOA1, SNCA rs6826785 and PD-MCI by machine learning approach. Screening and management of high TG and ApoA1 levels might help prevent the cognitive impairment in early PD patients. SNCA rs6826785 could be a novel therapeutic target for PD-MCI. ShapleyVIC-assisted variable selection is a novel and robust alternative to traditional approaches for future clinical study to prioritize the variables of interests.
Deng Xiao, Ning Yilin, Saffari Seyed Ehsan, Xiao Bin, Niu Chenglin, Ng Samuel Yong Ern, Chia Nicole, Choi Xinyi, Heng Dede Liana, Tan Yi Jayne, Ng Ebonne, Xu Zheyu, Tay Kay-Yaw, Au Wing-Lok, Ng Adeline, Tan Eng-King, Liu Nan, Tan Louis C S
2023-Mar-13
