The use of individual and multilevel data in the development of a risk prediction model to predict patients’ likelihood of completing colorectal cancer screening

Abstract

Promotion of colorectal cancer (CRC) screening can be expensive and unnecessary for many patients. The use of predictive analytics promises to help health systems target the right services to the right patients at the right time while improving population health. Multilevel data at the interpersonal, organizational, community, and policy levels, is rarely considered in clinical decision making but may be used to improve CRC screening risk prediction. We compared the effectiveness of a CRC screening risk prediction model that uses multilevel data with a more conventional model that uses only individual patient data.We used a retrospective cohort to ascertain the one-year occurrence of CRC screening. The cohort was determined from a Health Maintenance Organization, in Oregon. Eligible patients were 50–75 years old, health plan members for at least one year before their birthday in 2018 and were due for screening. We created a risk model using logistic regression first with data available in the electronic health record (EHR), and then added multilevel data.In a cohort of 59,249 patients, 36.1% completed CRC screening. The individual level model included 14 demographic, clinical and encounter based characteristics, had a bootstrap-corrected C-statistic of 0.722 and sufficient calibration. The multilevel model added 9 variables from clinical setting and community characteristics, and the bootstrap-corrected C-statistic remained the same with continued sufficient calibration.The predictive power of the CRC screening model did not improve after adding multilevel data. Our findings suggest that multilevel data added no improvement to the prediction of the likelihood of CRC screening.