Abstract
Accurate survival prediction for Non-Small Cell Lung Cancer (NSCLC) patients remains a significant challenge for the scientific and clinical community despite decades of advanced analytics. Addressing this challenge not only helps inform the critical aspects of clinical study design and biomarker discovery but also ensures that the 'right patient' receives the 'right treatment'. However, survival prediction is a highly complex task, given the large number of 'omics; and clinical features, as well as the high degree of freedom that drive patient survival. Prior knowledge could play a critical role in uncovering the complexity of a disease and understanding the driving factors affecting a patient's survival. We introduce a methodology for incorporating prior knowledge into machine learning-based models for prediction of patient survival through Knowledge Graphs, demonstrating the advantage of such an approach for NSCLC patients. Using data from patients treated with immuno-oncologic therapies in the POPLAR (NCT01903993) and OAK (NCT02008227) clinical trials, we found that the use of knowledge graphs yielded significantly improved hazard ratios, including in the POPLAR cohort, for models based on biomarker tumor mutation burden compared with those based on knowledge graphs. Use of a model-defined mutational 10-gene signature led to significant overall survival differentiation for both trials. We provide parameterized code for incorporating knowledge graphs into survival analyses for use by the wider scientific community.