Predicting Cancer Relapse with Clinical Data: A Survey of Current Techniques

Abstract

While cancer treatments are constantly advancing, there is still a real risk of relapse after potentially curative treatments. At the risk of adverse side effects, certain adjuvant treatments can be given to patients that are at high risk of recurrence. The challenge, however, is in finding the best tradeoff between these two extremes. Patients that are given more potent treatments, such as chemotherapy, radiation, or systemic treatment, can suffer unnecessary consequences, especially if the cancer does not return. Predictive modeling of recurrence can help inform patients and practitioners on a case-by-case basis, personalized for each patient. For large-scale predictive models to be built, structured data must be captured for a wide range of diverse patients. This paper explores current methods for building cancer recurrence risk models using structured clinical patient data.