Correction: Validation and Development of an Explainable Machine Learning Approach

Overview

This correction addresses errors in the reported P-values for anticoagulant and chemotherapy drugs in a study predicting venous thromboembolism (VTE) risk in lung cancer patients. The corrected P-values are now both 1.000, indicating no statistically significant differences between training and validation cohorts.

Background

Venous thromboembolism (VTE) is a significant complication in lung cancer patients. Machine learning approaches offer potential for improved prediction and understanding of VTE risk factors. Ensuring the accuracy of reported data in such studies is crucial.

Data Highlights

The correction pertains specifically to Table 1, which now accurately reflects the P-values for anticoagulant and chemotherapy drugs as 1.000.

Key Findings

• The correction only affects the accuracy of reported P-values in Table 1.
• Both corrected P-values indicate no statistically significant differences between cohorts.
• The model construction and overall conclusions of the original study remain unchanged.
• The study utilizes machine learning for VTE risk prediction in lung cancer patients.
• Statistical interpretation of the baseline characteristics is unaffected by the correction.

Clinical Implications

Accurate reporting is essential for the application of machine learning models in predicting VTE risk in lung cancer patients.

Conclusion

The correction clarifies the statistical analysis without altering the study's conclusions.

Related Resources & Content

1. Xia A., Liu J., Song J., et al., Front. Med., 2026 -- Validation and Development of an Explainable Machine Learning Approach for Predicting Venous Thromboembolism Risk in Lung Cancer Patients
2. Frontiers in Medicine — Construction and validation of a machine learning-based prediction model for venous thromboembolism in lung transplant recipients supported by ECMO
3. Frontiers in Immunology — Explainable machine learning for predicting venous thromboembolism in septic shock patients
4. Frontiers in Oncology — Risk prediction models for venous thromboembolism in lung cancer patients after surgery: a systematic review and meta-analysis
5. Journal of Hospital Medicine — Comparison of machine learning methods for prediction of venous thromboembolism among hospitalized adults
6. NCCN Guidelines Version 3.2025
7. Thromboembolism in ALK+ and ROS1+ NSCLC patients: A systematic review and meta-analysis - ScienceDirect