Deploying a national clinical text processing infrastructure.

OBJECTIVES: Clinical text processing offers a promising avenue for improving multiple aspects of healthcare, though operational deployment remains a substantial challenge. This case report details the implementation of a national clinical text processing infrastructure within the Department of Veterans Affairs (VA). METHODS: Two foundational use cases, cancer case management and suicide and overdose prevention, illustrate how text processing can be practically implemented at scale for diverse clinical applications using shared services. RESULTS: Insights from these use cases underline both commonalities and differences, providing a replicable model for future text processing applications. CONCLUSIONS: This project enables more efficient initiation, testing, and future deployment of text processing models, streamlining the integration of these use cases into healthcare operations. This project implementation is in a large integrated health delivery system in the United States, but we expect the lessons learned to be relevant to any health system, including smaller local and regional health systems in the United States.

A Clinical Decision Support System for Monitoring Post-Colonoscopy Patient Follow-Up and Scheduling.

This paper describes a natural language processing (NLP)-based clinical decision support (CDS) system that is geared towards colon cancer care coordinators as the end users. The system is implemented using a metadata- driven Structured Query Language (SQL) function (discriminant function). For our pilot study, we have developed a training corpus consisting of 2,085 pathology reports from the VA Connecticut Health Care System (VACHS). We categorized reports as "actionable"- requiring close follow up, or "non-actionable"- requiring standard or no follow up. We then used 600 distinct pathology reports from 6 different VA sites as our test corpus. Analysis of our test corpus shows that our NLP approach yields 98.5% accuracy in identifying cases that required close clinical follow up. By integrating this into our cancer care tracking system, our goal is to ensure that patients with worrisome pathology receive appropriate and timely follow-up and care.

Pilot of decision support to individualize colorectal cancer screening recommendations.

OBJECTIVES: To test the feasibility of using an electronic medical record (EMR)-based decision support system (DSS) that incorporates morbidity and frailty information to individualize colorectal cancer (CRC) screening recommendations. STUDY DESIGN: Our framework used the payoff time, defined as the minimum time until the benefits of screening exceed the harms. METHODS: Subjects were 24 patients eligible for CRC screening and 22 primary care providers (PCPs). Measures included PCP satisfaction with existing reminder systems and with decision support. RESULTS: The run-in phase, during which the intervention was inactive but its performance was verified, had 14 patients enrolled. The intervention phase, during which payoff time and life expectancy calculations were used to recommend for or against CRC screening, had 10 patients enrolled. Of the 10 patients enrolled in the intervention phase, the DSS recommended in favor of CRC screening for 6 patients. (The PCPs also recommended it for those 6 patients, although 3 refused the screening.) The DSS recommended against CRC screening for 4 patients, while the PCPs recommended against it for 3 of those 4 and ordered the screening for 1 patient. PCPs who had patients enrolled in the intervention phase indicated interest in having payoff time information for all patients eligible for CRC screening. This pilot study was small and was not powered to determine the effect of the intervention on screening behavior. CONCLUSIONS: Colorectal cancer screening involves balancing immediate harms with longer-term benefits; EMR decision support may facilitate personalized benefit/harm assessment. The payoff time framework is feasible for implementation in EMR decision support.