南方医科大学学报

南方医科大学学报 ›› 2026, Vol. 46 ›› Issue (9): 2091-2100.doi: 10.12122/j.issn.1673-4254.2026.09.09

• • 上一篇    

基于机器学习算法构建老年患者肺功能智能评估模型

陈翠妍1,2(), 张文娴1,2, 蔡依琳1,2, 欧阳媚1,2, 梁叶2,3, 梁铭标2, 梁会营1,2()   

  1. 1.南方医科大学公共卫生学院，广东 广州 510515
    2.南方医科大学附属广东省人民医院（广东省医学科学院），广东 广州 510000
    3.广东省心血管病研究所，广东 广州 510000
  • 收稿日期:2026-02-13 出版日期:2026-09-20 发布日期:2026-09-30
  • 通讯作者: 梁会营 E-mail:17675629838@163.com;lianghuiying@gdph.org.cn
  • 作者简介:陈翠妍，在读硕士研究生，E-mail: 17675629838@163.com
  • 基金资助:
    广东省科技计划项目重点领域研发计划(2025B0101120008)

Development of a machine learning-based model for assessing pulmonary function in elderly patients

Cuiyan CHEN1,2(), Wenxian ZHANG1,2, Yilin CAI1,2, Mei OUYANG1,2, Ye LIANG2,3, Mingbiao LIANG2, Huiying LIANG1,2()   

  1. 1.School of Public Health, Southern Medical University, Guangzhou 510515, China
    2.Guangdong Provincial People's Hospital (Guangdong Academy of Medical Sciences), Southern Medical University, Guangzhou 510000, China
    3.Guangdong Provincial Cardiovascular Institute, Guangzhou 510000, China
  • Received:2026-02-13 Online:2026-09-20 Published:2026-09-30
  • Contact: Huiying LIANG E-mail:17675629838@163.com;lianghuiying@gdph.org.cn

RichHTML

1

PDF

19

摘要：

目的 利用常规临床资料，构建接受度强、普适性广的肺功能智能评估模型，为老年患者肺功能异常的早期识别与诊疗提供参考。 方法 选取2020年9月1日~2024年12月31日于广东省人民医院完成肺功能检查（PFT）的7720例老年患者，整合临床资料，经单因素分析及LASSO回归筛选变量，按8∶2比例随机分为训练集（n=6176）和测试集（n=1544），分别构建线性回归、随机森林、极端梯度提升（XGBoost）、梯度提升机及支持向量回归模型以预测用力肺活量（FVC）和1秒用力呼气量（FEV1），采用Pearson相关系数（r）、组内相关系数（ICC）等评估性能，确定最优模型。结合沙普利加性解释方法分析特征贡献，并评估模型对呼吸高危人群的分类性能。 结果 XGBoost为最优模型，FVC和FEV1的r值分别为0.733、0.711，ICC为0.694、0.668。性别与年龄为核心预测变量，男性与低龄对肺功能指标呈正向效应，女性与高龄呈负向效应。FVC%、FEV1%最佳截断值分别为82.93%、85.46%，AUC为0.700、0.706。 结论 本研究构建的模型简便易行、适用性强，可辅助老年患者肺功能评估，具备良好的临床应用前景。

关键词: 机器学习, 老年人, 肺功能, 评估模型, 极端梯度提升

Abstract:

Objective To develop a machine learning-based model with good generalization ability for pulmonary function assessment in elderly patients with impaired pulmonary function. Methods A total of 7720 elderly patients undergoing pulmonary function testing (PFT) in Guangdong Provincial People's Hospital between September 1, 2020 and December 31, 2024 were enrolled. After variable screening by univariate analysis and LASSO regression, the patients were randomly assigned in an 8:2 ratio to the training set (n=6176) and test set (n=1544). Five regression models were constructed for predicting forced vital capacity (FVC) and forced expiratory volume in one second (FEV1), and their performance was evaluated based on Pearson correlation coefficient (r) and intraclass correlation coefficient (ICC). Feature contributions were interpreted using Shapley additive explanations, and the classification performance of the models for high-risk populations was assessed. Results XGBoost showed the best predictive performance in the elderly patients (r=0.733 for FVC and 0.711 for FEV1; ICC=0.694 for FVCand 0.668 for FEV1). Male gender and a younger age showed positive effects on pulmonary function, while female gender and an advanced age showed negative effects. The optimal cut-off values of FVC% and FEV1% were 82.93% and 85.46%, with AUC of 0.700 and 0.706, respectively. Conclusion The XGBoost-based model developed in this study is simple and reliable with good generalization ability for pulmonary function assessment in elderly patients.

Key words: machine learning, elderly, pulmonary function, model evaluation, extreme gradient boosting