Computationally Assisted Patient Finding for Navigation to Optimize Pancreatic Cancer Care Access

King, Daniel A, John, Kristen M, Tenner, Joseph, Nadella, Sandeep, Zavadsky, Tiffany, Carvino, Anthony, Khan, Shama, Croocks, Rolando, McEvoy, Tara, Beyer, Kristen, Mercieca, Rita, Valente, Cristina, Bingham, Bernadette, Cohn, Elizabeth G, Habowski, Amber N, Tuveson, David A, Barish, Matthew A, Carvajal, Richard (February 2026) Computationally Assisted Patient Finding for Navigation to Optimize Pancreatic Cancer Care Access. Oncologist. oyag037. ISSN 1083-7159

PDF 10.1093.oncolo.oyag037.pdf - Published Version Available under License Creative Commons Attribution Non-commercial. Download (1MB)

Abstract

BACKGROUND: Patient navigators are increasingly utilized in cancer care but ensuring patients are properly identified and referred to navigators is a significant challenge. The primary objective was to compare time from radiographic report to biopsy, oncology visit, and treatment before versus after implementation of a computationally assisted navigation referral stream. Secondary objectives included evaluating care delivery across demographic groups and assessing survival outcomes. MATERIALS AND METHODS: A quality initiative at Northwell Health compared care delivery metrics between two cohorts of patients with suspected pancreatic cancer: those identified retrospectively using computational methods in January 2023 and those identified and navigated prospectively in June 2023. Radiology reports from a centralized health information exchange were analyzed by an ML-based NLP model to detect findings suspicious of pancreatic cancer. Participants deemed eligible for navigation were contacted by a navigator to improve the likelihood and expediency of follow-up care. RESULTS: 71 patients were included, with 38 patients in the retrospective cohort and 33 patients in the prospective cohort. The prospective cohort showed numeric reduction in time to biopsy (12 to 6 days, p = 0.173), oncology appointment (27 to 17 days, p = 0.192), and treatment (56 to 35 days, p = 0.136), though these results were not statistically significant. These metrics showed a significant reduction in standard deviation (p < 0.001), including among racial and ethnic minorities. The survival of patients in both cohorts was comparable (HR = 0.82, p = 0.66). CONCLUSION: This study provides promising evidence that an NLP-assisted identification workflow can improve care delivery and investigation in a larger study is warranted to validate these findings.

Item Type:	Paper
Subjects:	diseases & disorders > cancer diseases & disorders diseases & disorders > cancer > cancer types > pancreatic cancer diseases & disorders > cancer > cancer types
CSHL Authors:	Tuveson, David A. Habowski, Amber N.
Communities:	CSHL labs > Tuveson lab CSHL Post Doctoral Fellows
SWORD Depositor:	CSHL Elements
Depositing User:	CSHL Elements
Date:	26 February 2026
Date Deposited:	25 Mar 2026 15:41
Last Modified:	25 Mar 2026 15:41
Related URLs:	Publisher
URI:	https://repository.cshl.edu/id/eprint/42122

Actions (login required)

Administrator's edit/view item