Identification of patients at risk for pancreatic cancer in a 3-year timeframe based on machine learning algorithms

Background and Aims: Early detection of pancreatic cancer (PC) remains challenging largely due to the low population incidence and few known risk factors. However, screening in at-risk populations and detection of early cancer has the potential to significantly alter survival. In this study, we aim to develop a predictive model to identify patients at risk for developing new-onset PC at two and a half to three year time frame. Methods We used the Electronic Health Records (EHR) of a large medical system from 2000 to 2021 (N = 537,410). The EHR data analyzed in this work consists of patients’ demographic information, diagnosis records, and lab values, which are used to identify patients who were diagnosed with pancreatic cancer and the risk factors used in the machine learning algorithm for prediction. We identified 73 risk factors of pancreatic cancer with the Phenome-wide Association Study (PheWAS) on a matched case-control cohort. Based on them, we built a large-scale machine learning algorithm based on EHR. A temporally stratified validation based on patients not included in any stage of the training of the model was performed. Results This model showed an AUROC at 0.742 [0.727, 0.757] which was similar in both the general population and in a subset of the population who has had prior cross-sectional imaging. The prevalence of pancreatic cancer in those in the top 5 percentile of the risk score was 6 folds higher than the general population. Conclusions Our model leverages data extracted from a 6-month window of time in the electronic health record to identify patients at nearly 6-fold higher than baseline risk of developing pancreatic cancer 2.5 to 3 years from evaluation. This approach offers an opportunity to define an enriched population entirely based on static data, where current screening may be recommended.