PLOS ONE Medicine&Health

Construction of an automated machine learning-based predictive model for postoperative pulmonary complications risk in non-small cell lung cancer patients undergoing thoracoscopic surgery

by Xie Qiu, Shuo Hu, Shumin Dong, Haijun Sun

Objective

To develop a predictive framework integrating machine learning and clinical parameters for postoperative pulmonary complications (PPCs) in non-small cell lung cancer (NSCLC) patients undergoing video-assisted thoracic surgery (VATS).

Methods

This retrospective study analyzed 286 NSCLC patients (2022–2024), incorporating 13 demographic, metabolic-inflammatory, and surgical variables. An Improved Blood-Sucking Leech Optimizer (IBSLO) enhanced via Cubic mapping and opposition-based learning was developed. Model performance was evaluated using AUC-ROC, F1-score, and decision curve analysis (DCA). SHAP interpretation identified key predictors.

Results

The IBSLO demonstrated significantly superior convergence performance versus original BSLO, ant lion optimizer (ALO), Harris hawks optimization (HHO), and whale optimization algorithm (WOA) across all 12 CEC2022 test functions. Subsequently, the IBSLO-optimized automated machine learning (AutoML) model achieved ROC-AUC/PR-AUC values of 0.9038/0.8091 (training set) and 0.8775/0.8175 (testing set), significantly outperforming four baseline models: logistic regression (LR), support vector machine (SVM), XGBoost, and LightGBM. SHAP interpretability identified six key predictors: preoperative leukocyte count, body mass index (BMI), surgical approach, age, intraoperative blood loss, and C-reactive protein (CRP). Decision curve analysis demonstrated significantly higher net clinical benefit of the AutoML model compared to conventional methods across expanded threshold probability ranges (training set: 8–99%; testing set: 3–80%).

Conclusion

This study establishes an interpretable machine learning framework that improves preoperative risk stratification for NSCLC patients, offering actionable guidance for thoracic oncology practice.

International Wound Journal

Effect of transconjunctival sutureless vitrectomy versus 20‐G vitrectomy on surgical wound closure in patients: A meta‐analysis

Abstract

A meta-analysis was conducted to evaluate the impact of transconjunctival sutureless vitrectomy (TSV) over 20 G vitrectomy on wound healing, as well as the requirements for closing the wound in order to treat vitreoretinal diseases. Among the 500 cases who had been treated with vitrectomy to September 2023, 250 were treated by transconjunctiva without vitrectomy and 250 were treated with 20 G vitrectomy. The odds ratio (OR) and mean difference (MD) of 95% confidence interval (CI) were computed to evaluate the influence of wound opening and closing on vitrectomy diseases. The evaluation of vitreoretinal diseases was performed with either a random-or fixed-effect model, which involved TSV compared to 20 G vitrectomy. Compared to 20 G vitrectomy, the opening time of the wound in TSV was less (MD, −2.03; 95% CI, −2.87, −1.19; p < 0.0001); Compared to 20 G vitrectomy, the closing time of the wound was less (MD, −4.84; 95% CI, −6.38, −3.03; p < 0.0001); Nevertheless, there were no statistically significant differences in the incidence of vitreous haemorrhage after TSV surgery compared with 20 G vitrectomy (OR, 0.74; 95% CI, 0.25, 2.18; p = 0.59). TSV vitrectomy can shorten the duration of the operation and speed up the healing of the wound. It is suggested that additional studies be carried out with a larger sample size in order to verify this conclusion.