29 Molecular markers predict long-term recurrence following resection of clival and spinal chordomas: A multi-center study

Abstract

OBJECTIVES/GOALS: We aimed to find the histology-specific markers that were predictive of post-operative long-term chordoma recurrence (≤1 year) using trained multiple tree-based machine learning (ML) algorithms. METHODS/STUDY POPULATION: We reviewed the records of patients who had treatment for clival and spinal chordomas between January 2017 and June 2021 across the Mayo Clinic enterprise (Minnesota, Florida, and Arizona). Patients were excluded if they had no histopathology or recurrence as an outcome. Demographics, type of treatment, clinical and radiological follow-up duration, histopathology, and other relevant clinical factors were abstracted from each patient record. Decision tree and random forest classifiers were trained and tested to predict the long-term recurrence based on unseen data using an 80/20 split. The performance of the model was optimized using tenfold cross-validation. RESULTS/ANTICIPATED RESULTS: One hundred fifty-one patients were identified: 58 chordomas from the clivus, 48 chordomas of the mobile spine, and 45 sacrococcygeal. Subtotal Resection followed by radiation therapy, was the most common treatment modality, followed by Gross Total resection, then radiation therapy. The multivariate analysis defines the molecular predictors of recurrence following resection. S100 and pan-cytokeratin is more likely to increase the risk of post-operative recurrence (OR= 3.67; CI= [1.09,12.42], p=0.03). In the decision tree analysis, a clinical follow-up > 1897 days was found in 37 % of encounters and a 90% chance of being classified for recurrence (Accuracy= 77%). Factors predicting long-term recurrence are the patient’s age, type of surgical treatment, location of the tumor, S100, pan-cytokeratin, and EMA. DISCUSSION/SIGNIFICANCE: Our molecular and clinicopathological variables combined with tree-based ML tools successfully demonstrate a high capacity to individually identify the patient’s recurrence pattern with an accuracy of 77%. S100, pan-cytokeratin, and EMA were the histologic drivers of recurrence.