Prediction and calibration performance of the five algorithms in the training cohort of the model.
| Algorithm | AUC (95% CI) | Sensitivity | Specificity | Accuracy | Precision | Brier score |
|---|---|---|---|---|---|---|
| LR | 0.854 (0.808–0.900) | 0.826 | 0.73 | 0.761 | 0.597 | 0.145 |
| XGB | 0.933 (0.903–0.962) | 0.849 | 0.865 | 0.86 | 0.753 | 0.107 |
| RFC | 0.918 (0.884–0.952) | 0.872 | 0.831 | 0.845 | 0.714 | 0.131 |
| SVM | 0.850 (0.803–0.898) | 0.767 | 0.798 | 0.788 | 0.647 | 0.146 |
| LGBM | 0.936 (0.907–0.964) | 0.942 | 0.764 | 0.822 | 0.659 | 0.12 |
AUC: area under the curve; CI: confidence interval; LR: logistic regression; XGB: extreme gradient boosting; RFC: random forest classifier; SVM: support vector machine; LGBM: light gradient boosting machine.
The supplementary figures and tables for this article are available at: https://www.explorationpub.com/uploads/Article/file/1012111_sup_1.pdf.
EDKF and JW: Conceptualization, Data curation, Formal analysis, Methodology, Software, Writing—original draft. SHS: Writing—original draft. TF: Conceptualization, Data curation, Formal analysis, Methodology, Software. ZGK, DKN, ESN, and EJI: Writing—review & editing. WY, LH, and JZ: Writing—review & editing, Supervision, Funding acquisition. All authors read and approved the submitted version.
The authors declare that there are no conflicts of interest.
Our study adhered to the Declaration of Helsinki and postoperative ethical standards. The ethics committee of the Nanjing First Hospital approved this study (Grant No. KY20220518-KS-01).
As a retrospective study, the need for written informed consent of participants was waived by the ethics committee of the Nanjing First Hospital. Our study did not border on confidential information as pertains to patients.
As a retrospective study, the need for written informed consent of participants was waived by the ethics committee of the Nanjing First Hospital. Our study did not border on confidential information as pertains to patients.
The data supporting this studyʼs findings are available from the corresponding author, [Jianjun Zou], upon reasonable request.
This work was supported by the National Natural Science Foundation of China [81873954, 82173899], Natural Science Foundation of Jiangsu Province of China [BK20241730], the Six Talent Peaks Project of Jiangsu [WSW-106], Nanjing Medical Science and Technical Development Foundation [ZKX22030], and Jiangsu Pharmaceutical Association [H202108, A2021024, Q202202, and JY202207]. The funders had no role in study design, data collection and analysis, decision to publish, or preparation of the manuscript.
© The Author(s) 2026.
Open Exploration maintains a neutral stance on jurisdictional claims in published institutional affiliations and maps. All opinions expressed in this article are the personal views of the author(s) and do not represent the stance of the editorial team or the publisher.