Construction of nomogram prediction model for risk of mild cognitive impairment in elderly people
10.3969/j.issn.1671-8348.2024.11.006
- VernacularTitle:老年人轻度认知障碍风险列线图预测模型的构建
- Author:
Dongmei HUANG
1
;
Huiqiao HUANG
;
Jinjin WEI
;
Caili LI
;
Yanfei PAN
;
Lichong LAI
;
Shujie LONG
Author Information
1. 广西医科大学第二附属医院康复医学科,南宁 530005
- Keywords:
mild cognitive impairment;
nomogram prediction model;
influencing factors;
older adults
- From:
Chongqing Medicine
2024;53(11):1630-1635
- CountryChina
- Language:Chinese
-
Abstract:
Objective To construct a nomogram prediction model for the risk of mild cognitive impair-ment (MCI) in elderly people aged ≥ 60-year-old.Methods A total of 502 elderly permanent residents in Guangxi were selected as the research subjects by the multi-stage stratified random sampling method,and the general situation questionnaire and the Beijing edition of MoCA-BJ scale were used to investigate the elderly people,and their anthropometric indicators were collected.The minimum absolute shrinkage rate and selection operator (LASSO) regression were used to screen the characteristic variables.The MCI risk nomogram pre-diction model was constructed.The receiver operating characteristic (ROC) curve and calibration curve were adopted to conduct the fitting effect test on the prediction model.Results Among the 502 elderly people,244 cases (46.04％) had the normal cognition and 258 cases (48.68％) had MCI.The logistic regression analysis showed that the age,education background,month income,children support,calf circumference,BMI and body fat index were the influencing factors of MCI in the elderly people,and the nomogram prediction model of the MCI risk in the elderly people was constructed by these seven variables.The area under the ROC curve (AUC) of the model was 0.790 (95％CI:0.750-0.829),the sensitivity was 0.64,the specificity was 0.62,the C-index index was 0.790,and the model fitting x2=8.111,P=0.454,the predictive value was basically consistent with the actual value.Conclusion The nomogram prediction model of MCI risk in the elderly peo-ple is successfully constructed with good predictive effect.
