Development of Machine Learning Models for Predicting the 1-Year Risk of Reoperation After Lower Limb Oncological Resection and Endoprosthetic Reconstruction Based on Data From the PARITY Trial.

BACKGROUND: Oncological resection and reconstruction involving the lower extremities commonly lead to reoperations that impact patient outcomes and healthcare resources. This study aimed to develop a machine learning (ML) model to predict this reoperation risk. METHODS: This study was conducted according to TRIPOD + AI. Data from the PARITY trial was used to develop ML models to predict the 1-year reoperation risk following lower extremity oncological resection and reconstruction. Six ML algorithms were tuned and calibrated based on fivefold cross-validation. The best-performing model was identified using classification and calibration metrics. RESULTS: The polynomial support vector machine (SVM) model was chosen as the best-performing model. During internal validation, the SVM exhibited an AUC-ROC of 0.73 and a Brier score of 0.17. Using an optimal threshold that balances all quadrants of the confusion matrix, the SVM exhibited a sensitivity of 0.45 and a specificity of 0.81. Using a high-sensitivity threshold, the SVM exhibited a sensitivity of 0.68 and a specificity of 0.68. Total operative time was the most important feature for reoperation risk prediction. CONCLUSION: The models may facilitate reoperation risk stratification, allowing for better patient counseling and for physicians to implement measures that reduce surgical risks.

Immune-based classification of HPV-associated oropharyngeal cancer with implications for biomarker-driven treatment de-intensification.

BACKGROUND: There is significant interest in treatment de-escalation for human papillomavirus-associated (HPV+) oropharyngeal squamous cell carcinoma (OPSCC) patients given the generally favourable prognosis. However, 15-30% of patients recur after primary treatment, reflecting a need for improved risk-stratification tools. We sought to develop a molecular test to risk stratify HPV+ OPSCC patients. METHODS: We created an immune score (UWO3) associated with survival outcomes in six independent cohorts comprising 906 patients, including blinded retrospective and prospective external validations. Two aggressive radiation de-escalation cohorts were used to assess the ability of UWO3 to identify patients who recur. Multivariate Cox models were used to assess the associations between the UWO3 immune class and outcomes. FINDINGS: A three-gene immune score classified patients into three immune classes (immune rich, mixed, or immune desert) and was strongly associated with disease-free survival in six datasets, including large retrospective and prospective datasets. Pooled analysis demonstrated that the immune rich group had superior disease-free survival compared to the immune desert (HR = 9.0, 95% CI: 3.2-25.5, P = 3.6 × 10-5) and mixed (HR = 6.4, 95% CI: 2.2-18.7, P = 0.006) groups after adjusting for age, sex, smoking status, and AJCC8 clinical stage. Finally, UWO3 was able to identify patients from two small treatment de-escalation cohorts who remain disease-free after aggressive de-escalation to 30 Gy radiation. INTERPRETATION: With additional prospective validation, the UWO3 score could enable biomarker-driven clinical decision-making for patients with HPV+ OPSCC based on robust outcome prediction across six independent cohorts. Prospective de-escalation and intensification clinical trials are currently being planned. FUNDING: CIHR, European Union, and the NIH.