基于XGBoost算法的面部特征对轻度认知障碍风险的预测作用  

Predictive role of facial features in mild cognitive impairment risk based on XGBoost algorithm

作　　者：戚馨如 宋玉磊[1] 吕玉婵 殷海燕[1] 张薛晴 张洁昕 徐桂华[1] 柏亚妹[1] Qi Xinru;Song Yulei;LüYuchan;Yin Haiyan;Zhang Xueqing;Zhang Jiexin;Xu Guihua;Bai Yamei(School of Nursing,Nanjing University of Traditional Chinese Medicine,Nanjing 210023,China)

机构地区：[1]南京中医药大学护理学院,江苏南京210023 [2]东南大学仪器与工程学院

出　　处：《护理学杂志》2025年第7期95-99,共5页Journal of Nursing Science

基　　金：国家重点研发计划项目(2023YFC3603600);国家自然科学基金面上项目(72174095);江苏省社会发展面上项目(BE2022802);2024年江苏省研究生实践创新计划项目(SJCX24_0847)。

摘　　要：目的初步构建预测轻度认知障碍(MCI)风险的机器学习模型,为医护人员早期快速筛查轻度认知障碍提供参考。方法2024年7-9月,采用便利采样法选取南京市2个街道老年人294人,通过OpenFace 3.0提取受试者观看快乐、中性、悲伤视频的面部特征,将其显著性面部特征分别归类为快乐、中性、悲伤、快乐+中性、快乐+悲伤、中性+悲伤、快乐+中性+悲伤7种面部特征组合。以特征组合作为输入变量,是否患有MCI作为结局变量,按照7∶3的比例分为训练集和测试集构建XGBoost的机器学习模型。运用准确率、精确率、召回率、F1得分和曲线下面积(AUC-ROC)值评价判别效能,并对预测效果较优的面部特征组合模型进行SHAP分析。结果两组面部特征比较,MCI组在观看快乐视频产生的面部特征AU04_AUI、AU06_AUI、AU10_AUP和AU12_AUP与非MCI组有显著差异;MCI组在观看中性、悲伤视频分别产生的9种、8种面部特征与非MCI组有显著差异(均P<0.05)。各面部特征组合构建的XGBoost模型受试者工作特征曲线下面积(AUC)均大于0.6,其中悲伤最高(0.71)。悲伤视频的面部特征构建的XGBoost模型SHAP结果显示排名前3的预测因子是AU04_AUI、AU20_AUP、AU07_AUI。结论初步构建基于面部特征的XGBoost机器学习模型,旨在辅助早期阶段识别MCI的风险,实现MCI风险的早期预警与干预。Objective To preliminarily construct a machine learning model,aimed at predicting the risk of mild cognitive impairment(MCI),and to provide a reference for healthcare professionals in early and rapid screening of MCI.Methods From July to September 2024,a convenience sampling method was employed to select 294 elderly individuals from two neighborhoods in Nanjing.Facial features were extracted using OpenFace 3.0 while subjects viewed happy,neutral,and sad videos.Significant facial features were categorized into seven combinations:happy,neutral,sad,happy+neutral,happy+sad,neutral+sad,and happy+neutral+sad.The feature combinations were used as input variables,and the presence of MCI was the outcome variable.The dataset was split into training and testing sets in a 7∶3 ratio to construct the XGBoost machine learning model.The model′s discriminative perfor-mance was evaluated using accuracy,precision,recall,F1 score,and area under the curve(AUC-ROC)values,with SHAP analysis conducted on the best-performing facial feature combination model.Results Comparison of facial features revealed significant differences in AU04_AUI,AU06_AUI,AU10_AUP,and AU12_AUP among the MCI group while watching happy videos compared to the non-MCI group.The MCI group also exhibited significant differences in nine facial features when watching neutral videos and eight features when watching sad videos.All XGBoost models constructed from facial feature combinations showed AUC values greater than 0.6,with the sad video model achieving the highest AUC of 0.71.SHAP analysis of the sad video model indicated that the top three predictive factors were AU04_AUI,AU20_AUP,and AU07_AUI.Conclusion A preliminary XGBoost machine learning model based on facial features has been constructed to assist in the early identification of MCI risk,providing a refe-rence for early warning and intervention strategies for MCI.

关 键 词：老年人 轻度认知障碍 面部特征 面部动作单元 机器学习模型 XGBoost算法 老年护理 

分 类 号：R473.2[医药卫生—护理学]