Development of an Ensemble Screening Model for Chronic Obstructive Pulmonary Disease Using Multimodal Data

Corresponding author: Liang Huiying, lianghuiying@gdph.org.cn

DOI: 10.12201/bmr.202604.00086

•  

  Abstract: Purpose/Significance To integrate chest X-ray images and clinical data to construct an integrated screening model for chronic obstructive pulmonary disease (COPD), and provide a supplementary tool for patients unable to cooperate with pulmonary function test (PFT). Method/Process A total of 15,414 patients who underwent chest X-ray examination at Guangdong Provincial Peoples Hospital from September 2020 to December 2024 were enrolled, and randomly divided into a training set (8,892 cases, 57.7%), a validation set (1,134 cases, 7.3%) and a test set (5,388 cases, 35.0%) for model construction. The model performance was evaluated by indicators including the area under the curve (AUC), with supplementary analyses performed via calibration curve, decision curve analysis (DCA) and SHapley Additive exPlanations (SHAP). Result/Conclusion In the test set, the model achieved an AUC of 0.922, a sensitivity of 0.979 and a specificity of 0.823, with favorable calibration and clinical benefit. SHAP analysis identified comorbidity combination, age and hypertension as key features, among which pulmonary infection plus hypertension had the strongest predictive efficiency (OR=19.42, 95%CI: 5.04-74.87, P=0.006). This integrated model can complete COPD screening without relying on PFT, and is expected to provide a supplementary approach for patients unable to cooperate with PFT.

  Key words: Chronic Obstructive Pulmonary Disease; Screening; Machine Learning; Deep Learning; Integrated Model

  Submit time: 10 April 2026

  Copyright: The copyright holder for this preprint is the author/funder, who has granted biomedRxiv a license to display the preprint in perpetuity.
• html

• 图表

• Hongying Ma. Advances in Exhaled Breath Condensate for Chronic Obstructive Pulmonary Disease. 2025. doi: 10.12201/bmr.202512.00038

  LI LinHao, WANG Kun, LI Peng, XU XiaoChen, HAN Ping. Study on Chronic Obstructive Pulmonary Disease Complicated with Malnutrition Based on the TCM Theory of Child Consumes Qi of Mother. 2026. doi: 10.12201/bmr.202601.00090

  Zhou Jie², Xiao Wei², Sun Zengtao. Understanding the Mechanism and Therapeutic Strategies of the Gut-Lung Axis in Chronic Obstructive Pulmonary Disease from the Perspective of. 2026. doi: 10.12201/bmr.202601.00005

  guolianmei, sunxiaohong, zhangzhe, tianye. Construction of a Prediction Model for Lower Limb Deep Vein Thrombosis in Patients with Hemorrhagic Stroke Based on Machine Learning. 2025. doi: 10.12201/bmr.202510.00023

  Shen Si, Zhu Jiahui, Xia Senlin, Xu Hua. A predictive model and performance evaluation for acute respiratory distress syndrome in the elderly patients with severe trauma based on interpretable machine learning. 2026. doi: 10.12201/bmr.202602.00094

  WANG Jie, WANG Zhi-cheng, LOU Shuai, DONG Jian-cheng, CAO Xin-zhi. Research on thyroid nodule detection model based on deep learning algorithm Mask R-CNN. 2024. doi: 10.12201/bmr.202411.00085

  HONG Suru, CHEN Yushuang, WU Xiayang. Mortality risk assessment and interpretability analysis of preterm infants in the NICU using machine learning models. 2025. doi: 10.12201/bmr.202503.00066

  SHEN Rong, Li Jiayu, SHENG Boyang, ZHONG Liqin, JING Xiaoshuo, YAN Junfeng. Research on the Construction of an Intelligent Syndrome Differentiation Model for Traditional Chinese Medicine in Lung Cancer Based on Ensemble Learning.. 2026. doi: 10.12201/bmr.202604.00093

  SuFeiyu, HuHongpu. Research on a Diabetic Retinopathy Risk Prediction Model Integrating Health Profiles and Machine LearningSu Feiyu1, Feng Qishun2, Zeng Qingjia1, Gao Shuyao3, Xi Huinan1, Wu Wenxin1, Wang Yingshuai1, Hu Hongpu1. 2026. doi: 10.12201/bmr.202601.00077

  ZHU ZHIWEN, QI GUOQIANG, YANG KAIYI, ZHAO YONGGEN, YU ZHUO, YU GANG. Children Cough as Chief Complaint Date Sharing Model Based on Multi-center Horizontal Federated Learning. 2022. doi: 10.12201/bmr.202207.00004

• ID	Submit time	Number	Download
  1	2026-01-22	10.12201/bmr.202604.00086V1	Download

• Public  Anonymous  To author only Submit Comments