Development of a Large Colonoscopy-Based Longitudinal Cohort for Integrated Research of Colorectal Cancer: Partners Colonoscopy Cohort

Mathew Vithayathil; Scott Smith; Sergey Goryachev; Jennifer Nayor; Mingyang Song

doi:10.1007/s10620-021-06882-x

Development of a Large Colonoscopy-Based Longitudinal Cohort for Integrated Research of Colorectal Cancer: Partners Colonoscopy Cohort

Dig Dis Sci. 2022 Feb;67(2):473-480. doi: 10.1007/s10620-021-06882-x. Epub 2021 Feb 16.

Authors

Mathew Vithayathil¹, Scott Smith¹, Sergey Goryachev², Jennifer Nayor³, Mingyang Song^{4

5

6}

Affiliations

¹ Departments of Epidemiology and Nutrition, Harvard T. H. Chan School of Public Health, 667 Huntington Avenue, Kresge 906A, Boston, MA, 02115, USA.
² Research Information Science and Computing (RISC), Partners Healthcare, Boston, MA, USA.
³ Division of Gastroenterology, Emerson Hospital, Concord, MA, USA.
⁴ Departments of Epidemiology and Nutrition, Harvard T. H. Chan School of Public Health, 667 Huntington Avenue, Kresge 906A, Boston, MA, 02115, USA. mingyangsong@mail.harvard.edu.
⁵ Clinical and Translational Epidemiology Unit, Massachusetts General Hospital and Harvard Medical School, Boston, MA, USA. mingyangsong@mail.harvard.edu.
⁶ Division of Gastroenterology, Massachusetts General Hospital and Harvard Medical School, Boston, MA, USA. mingyangsong@mail.harvard.edu.

PMID: 33590405
DOI: 10.1007/s10620-021-06882-x

Abstract

Background and aims: Conventional adenomas (CAs) and serrated polyps (SPs) are precursors to colorectal cancer (CRC). Understanding metachronous cancer risk is poor due to lack of accurate large-volume datasets. We outline the use of natural language processing (NLP) in forming the Partners Colonoscopy Cohort, an integrated longitudinal cohort of patients undergoing colonoscopies.

Methods: We identified endoscopy quality data from endoscopy reports for colonoscopies performed from 2007 to 2018 in a large integrated healthcare system, Mass General Brigham). Through modification of an established NLP pipeline, we extracted histopathological data (polyp location, histology and dysplasia) from corresponding pathology reports. Pathology and endoscopy data were merged by polyp location using a four-stage algorithm. NLP and merging procedures were validated by manual review of 500 pathology reports.

Results: 305,656 colonoscopies in 213,924 patients were identified. After merging, 76,137 patients had matched polyp data for 334,750 polyps. CAs and SPs were present in 86,707 (28.5%) and 55,373 (18.2%) colonoscopies. Among patients with polyps at index screening colonoscopy, 14,931 (33.4%) had follow-up colonoscopy (median 46.4, interquartile range 33.8-62.4 months); 91 (0.2%) and 1127 (2.5%) patients developed metachronous CRC and high-risk polyps (polyps ≥ 10 mm or CAs having high-grade dysplasia/villous/tublovillous histology or SPs with dysplasia). Genetic data were available for 23,787 (31.7%) patients with polyps from the Partners Biobank. The validation study showed a positive predictive value of 100% for polyp histology and locations.

Conclusion: We created the Partners Colonoscopy Cohort providing essential infrastructure for future studies to better understand the natural history of CRC and improve screening and post-polypectomy strategies.

Keywords: Advanced adenoma; Molecular epidemiology; Natural language processing; Precision screening; Serrated polyp.

MeSH terms

Adenoma*
Adenomatous Polyps
Adult
Aged
Cohort Studies
Colonic Polyps*
Colonoscopy*
Colorectal Neoplasms*
Datasets as Topic*
Female
Humans
Longitudinal Studies
Male
Middle Aged
Natural Language Processing