Development and validation of a machine learning-based diagnostic model for identifying nonneutropenic invasive pulmonary aspergillosis in suspected patients: a multicenter cohort study

作者：Xinyu Wang, Yajie Lu, Chao Sun, Huanhuan Zhong, Yuchen Cai, Min Cao, Xuefan Cui, Wenkui Sun, Li Wang, Xin Lu, Cheng Chen, Yanbin Chen, Chunlai Feng, Yujian Tao, Jun Zhou, Jiaxin Shi, Guoer Ma, Yuanqin Li, Xin Su · 发表于：Microbiology Spectrum · 年份：2025 · DOI：10.1128/spectrum.00607-25 · 被引用次数：7 · 研究领域：Antifungal resistance and susceptibility、Lung Cancer Diagnosis and Treatment、Interstitial Lung Diseases and Idiopathic Pulmonary Fibrosis

ABSTRACT This study aims to develop and validate an optimized diagnostic model for nonneutropenic invasive pulmonary aspergillosis (IPA) among suspected cases. A cohort of 344 nonneutropenic suspected cases from 13 medical centers (August 2020 to February 2024) was analyzed. The cohort was divided into a training data set (70%) and a testing data set (30%) using stratified sampling based on the IPA diagnosis. Three machine learning models (a regularized logistic regression model, a support vector machine model, and a weighted ensemble model) were developed. SHapley Additive explanation (SHAP) method was used for model interpretation. Six predictor variables were finally selected: sputum Aspergillus culture, Aspergillus -specific IgG, imaging feature of cavity, serum galactomannan, critical condition, and plasma pentraxin 3. The weighted ensemble model, exhibiting the significantly higher specificity of 95.1% in internal cross-validation and 95.7% in testing among the three models, was selected as the optimal prediction model despite comparable discrimination capacity, calibration ability, and clinical applicability across all models. The risk score derived from SHAP values showed a highly significant correlation with the predicted probability of the weighted ensemble model (Spearman ρ = 0.974), achieving an area under the curve of 0.857 in internal cross-validation and 0.871 in external testing. Using the optimal cut-off value of 3, the risk score demonstrated sensitivity (68...