Development of a machine learning model for predicting pneumothorax risk in coaxial core needle biopsy (≤3 cm)

• Published in: European journal of radiology 2024-07, Vol.176, p.111508, Article 111508
• Main Authors: Zou, Xugong, Cui, Ning, Ma, Qiang, Lin, Zhipeng, Zhang, Jian, Li, Xiaoqun
• Format: Article
• Language: English
• Subjects: Adult; Aged; Biopsy, Large-Core Needle; Coaxial core needle lung biopsy (CCNB); Female; Humans; Image-Guided Biopsy; Lung Neoplasms - diagnostic imaging; Lung Neoplasms - pathology; Machine Learning; Machine learning (ML); Male; Middle Aged; Pneumothorax; Pneumothorax - diagnostic imaging; Pneumothorax - etiology; Prediction model; Retrospective Studies; Risk Assessment; Risk factor; Risk Factors; Sensitivity and Specificity
• ISSN: 0720-048X; 1872-7727; 1872-7727
• DOI: 10.1016/j.ejrad.2024.111508

•Developed ML model to predict post-CCNB pneumothorax risk.•Collected data on ≤3 cm lung nodules.•Gaussian Naive Bayes classifier achieved an AUC of 0.82.•Algorithm enhances perioperative care and clinical decision-making. The aim is to devise a machine learning algorithm exploiting preoperative clinical data to forecast the hazard of pneumothorax post-coaxial needle lung biopsy (CCNB), thereby informing clinical decision-making and enhancing perioperative care. This retrospective analysis aggregated clinical and imaging data from patients with lung nodules (≤3 cm) biopsies. Variable selection was done using univariate analysis and LASSO regression, with the dataset subsequently divided into training (80 %) and validation (20 %) subsets. Various machine learning (ML) classifiers were employed in a consolidated approach to ascertain the paramount model, which was followed by individualized risk profiling showcased through Shapley Additive eXplanations (SHAP). Out of the 325 patients included in the study, 19.6% (64/325) experienced postoperative pneumothorax. High-risk factors determined were Cancer, Lesion_type, GOLD, Size, and Depth. The Gaussian Naive Bayes (GNB) classifier demonstrated superior prediction with an Area Under the Curve (AUC) of 0.82 (95% CI 0.71–0.94), complemented by an accuracy rate of 0.8, sensitivity of 0.71, specificity of 0.84, and an F1 score of 0.61 in the test cohort. The formulated prognostic algorithm exhibited commendable efficacy in preoperatively prognosticating CCNB-induced pneumothorax, harboring the potential to refine personalized risk appraisals, steer clinical judgment, and ameliorate perioperative patient stewardship.