2026-10-14T01:57:45Z https://www.scidb.cn/oai

10.57760/sciencedb.j00150.00009 2022-09-29T14:03:38Z

2022-09-29 Application of metaPRS and APOEε4 to optimize genetic risk prediction modeling strategy for mild cognitive impairment doi:10.57760/sciencedb.j00150.00009 en Background Mild cognitive impairment (MCI) is an important stage to intervene and delay the progression of dementia, and studies have shown that it is closely associated with genetic factors, among which APOEε4 is known to be an important risk allele of MCI in the medical community. Due to the lack of genome-wide association study (GWAS) summary data of MCI, existing studies calculate the polygenic risk score (PRS) of MCI based on GWAS summary data of Alzheimer's disease, which leads to the unsatisfactory effect of the existing statistical modeling of genetic risk of MCI. Objective In this study, meta-polygenic risk score (metaPRS) and APOEε4 were used as important predictors to explore and optimize the statistical modeling strategy of genetic risk in MCI from the perspective of generalized linear model and machine learning. Methods PRS for the 12 MCI-related traits were calculated and integrated into metaPRS for MCI by elastic-net logistic regression model. SCOREAPOE is calculated by weighting the APOEε4 effect size with age correction. In this study, XGBoost, GBM, Logistic regression and Lasso regression were used as statistical modeling methods to verify the inclusion strategies of different predictors based on metaPRS, SCOREAPOE and basic demographic information (age, gender, education level). AUC and F-measure were used to evaluate the predictive effect of statistical modeling of genetic risk of MCI. Results For the genetic risk of MCI, metaPRS and SCOREAPOE have high predictive value. After including metaPRS, SCOREAPOE and basic demographic information (age, gender, education level), the predictive effect of each statistical modeling method is as follows: XGBoost (AUC=0.69, F-measure=0.88), GBM (AUC=0.76, F-measure=0.87), logistic regression (AUC=0.77, F-measure=0.89), and lasso regression (AUC=0.76, F-measure=0.92). Conclusion When the sample size is not high (less than 500), the lasso regression model constructed by including metaPRS, SCOREAPOE and basic demographic information (age, gender, education level) has the best effect on MCI genetic risk prediction, which provided a new idea and perspective for statistical modeling of genetic risk of MCI and other complex diseases. Mild cognitive impairment; Polygenic risk score; MetaPRS; APOEε4; Genetic risk prediction; Statistical modeling optimization li zi meng wang rong cheng shuai zhao cai li wang xiao cong wen ya lu liu long PUBLIC https://creativecommons.org/publicdomain/zero/1.0/ dataset Science Data Bank