Background: Patients undergoing screening for early detection of cancer have serial biomarker measurements that are not traditionally being incorporated into decision making when evaluating biomarkers.
Objective: We discuss statistical learning algorithms that have the ability to learn from patient history to make personalized decision rules to improve the early detection of cancer. These artificial intelligence algorithms are able to learn in real time from data collected on the patient to identify changes in the patient that could signal asymptomatic cancer.
Methods: We discuss the parametric empirical Bayes (PEB) algorithm for a single biomarker and a Bayesian screening algorithm for multiple biomarkers.
Results: We provide tools to implement these algorithms and discuss their clinical utility for the early detection of hepatocellular carcinoma (HCC). The PEB algorithm is a robust, easily implemented algorithm for defining patient specific thresholds that can improve the patient-level sensitivity of a biomarker in many settings, including HCC. The fully Bayesian algorithm, while more complex, can accommodate multiple biomarkers and further improve the clinical utility of the algorithms.
Conclusions: These algorithms could be used in many clinical settings and we aim to guide the reader on how these algorithms may improve the detection performance of their biomarkers.
Keywords: Bayesian changepoint models; Statistical learning algorithms; cancer biomarkers; early detection; parametric empirical Bayes.