Loeloe Mohammad Sadegh, Sefidkar Reyhane, Tabatabaei Seyyed Mohammad, Mehrparvar Amir Houshang, Jambarsang Sara
Center for Healthcare Data Modeling, Department of Biostatistics and Epidemiology, School of Public Health, Shahid Sadoughi University of Medical Sciences, Yazd, Iran.
Department of Medical Informatics, Faculty of Medicine, Mashhad University of Medical Sciences, Mashhad, Iran.
Front Med (Lausanne). 2025 Mar 10;12:1480931. doi: 10.3389/fmed.2025.1480931. eCollection 2025.
This study aimed to determine spirometric norm values for the healthy Iranian adult population and compare them with established norm equations, specifically the GLI-Caucasian and Iranian equations.
During the recruitment phase of the Shahedieh Prospective Epidemiological Research Studies in Iran (PERSIAN) in 2016, spirometric parameters of 998 participants were obtained. KNN regression was used to extract reference values for spirometric parameters FEV, FVC, FEV/FVC, and FEF, considering height and age as features. The performance of KNN regression was compared with conventional models used in previous studies, such as the multiple linear regression (MLR) model and the Lambda-Mu-Sigma (LMS) model. The predicted values were compared with those obtained from the GLI-Caucasian and Iranian equations. The validation criterion was the mean squared error (MSE) based on 5-fold cross-validation.
This study included 473 female participants and 525 male participants. KNN regression provided more accurate predictions for four spirometric parameters than MLR and LMS. The MSE for predicting FVC in female participants was 0.159, 0.169, and 0.165 in KNN regression, MLR, and LMS, respectively. The predictions of the present study were closer to the actual values of the reference population for four indicators compared to the prediction values using two sets of reference equations. The MSE of predicted FVC for female participants was 0.159 in the present study, which was less than the Iranian (MSE = 0.344) and GLI-Caucasian (MSE = 0.397) equations.
Using a flexible machine learning approach, this study established spirometry reference values specifically for the Iranian population. Recognizing that spirometry reference values vary among different populations, the Excel calculator developed in this research can be a valuable tool in healthcare centers for assessing lung function in Iranian adults.
本研究旨在确定伊朗健康成年人群的肺功能测定标准值，并将其与既定的标准方程进行比较，特别是GLI - 高加索人方程和伊朗方程。
在2016年伊朗沙赫迪耶前瞻性流行病学研究（PERSIAN）的招募阶段，获取了998名参与者的肺功能测定参数。考虑身高和年龄作为特征，使用K近邻回归来提取肺功能测定参数FEV、FVC、FEV/FVC和FEF的参考值。将K近邻回归的性能与先前研究中使用的传统模型进行比较，如多元线性回归（MLR）模型和Lambda - Mu - Sigma（LMS）模型。将预测值与从GLI - 高加索人方程和伊朗方程获得的预测值进行比较。验证标准是基于5折交叉验证的均方误差（MSE）。
本研究包括473名女性参与者和525名男性参与者。与MLR和LMS相比，K近邻回归对四个肺功能测定参数提供了更准确的预测。在K近邻回归、MLR和LMS中，女性参与者预测FVC的MSE分别为0.159、0.169和0.165。与使用两组参考方程的预测值相比，本研究对四个指标的预测更接近参考人群的实际值。本研究中女性参与者预测FVC的MSE为0.159，低于伊朗方程（MSE = 0.344）和GLI - 高加索人方程（MSE = 0.397）。
本研究使用灵活的机器学习方法，专门为伊朗人群建立了肺功能测定参考值。认识到不同人群的肺功能测定参考值存在差异，本研究开发的Excel计算器可成为医疗中心评估伊朗成年人肺功能的宝贵工具。
