000009308 001__ 9308 000009308 005__ 20240124114320.0 000009308 0247_ $$2DOI$$a10.6083/s4655h26g 000009308 037__ $$aETD 000009308 245__ $$aThe use of predictive analytics for population health management, integrating multilevel data to predict colorectal cancer screening 000009308 260__ $$bOregon Health and Science University 000009308 269__ $$a2021 000009308 336__ $$aDissertation 000009308 502__ $$bPh.D. 000009308 520__ $$aThe use of predictive analytics can help health systems target the right services to the right patients at the right time, while improving population health. Multilevel data, or data at the interpersonal, organizational, community and policy levels, is rarely sought after but may be used to improve risk prediction by providing information about a patient and the many groups to which they belong. Colorectal cancer screening promotion can be expensive and not all patients need it. This study assessed the availability of multilevel data for use in a colorectal cancer screening risk prediction model in accordance with the Social-ecological Model (SEM) and assessed its ability to improve prediction over standard models based on individual level data. 000009308 542__ $$fIn copyright - single owner 000009308 650__ $$aColonic Neoplasms$$016905 000009308 650__ $$aPopulation Health$$012483 000009308 650__ $$aMultilevel Analysis$$038265 000009308 650__ $$aColorectal Neoplasms$$028197 000009308 650__ $$aEarly Detection of Cancer$$038151 000009308 650__ $$aPrognosis$$024646 000009308 650__ $$aPolicy$$038967 000009308 6531_ $$apreventative care 000009308 6531_ $$ahealth care outcome assessment 000009308 691__ $$aOHSU-PSU School of Public Health$$041366 000009308 7001_ $$aPetrik, Amanda F. 000009308 8564_ $$950a8af44-e87f-454b-8c06-f24633299d7e$$s1536077$$uhttps://digitalcollections.ohsu.edu/record/9308/files/Petrik.Amanda.2021.pdf 000009308 905__ $$a/rest/prod/s4/65/5h/26/s4655h26g 000009308 909CO $$ooai:digitalcollections.ohsu.edu:9308$$pstudent-work 000009308 980__ $$aTheses and Dissertations 000009308 980__ $$aDual Author Affiliations Cleanup