Machine Learning Predictability of Clinical Next Generation Sequencing for Hematologic Malignancies to Guide High-Value Precision Medicine

Advancing diagnostic testing capabilities such as clinical next generation sequencing methods offer the potential to diagnose, risk stratify, and guide specialized treatment, but must be balanced against the escalating costs of healthcare to identify patient cases most likely to benefit from them. Heme-STAMP (Stanford Actionable Mutation Panel for Hematopoietic and Lymphoid Malignancies) is one such next generation sequencing test. Our objective is to assess how well Heme-STAMP pathological variants can be predicted given electronic health records data available at the time of test ordering. The model demonstrated AUROC 0.74 (95% CI: [0.72, 0.76]) with 99% negative predictive value at 6% specificity. A benchmark for comparison is the prevalence of positive results in the dataset at 58.7%. Identifying patients with very low or very high predicted probabilities of finding actionable mutations (positive result) could guide more precise high-value selection of patient cases to test.