1. The UCSF Health Problem
The UCSF Health problem
At UCSF and other leading academic medical centers, the referral intake and triage process for new patients is strained, leading to long delays and high rates of incomplete referrals.
Early-stage or covert hepatic encephalopathy (CHE), which can be present in up to 60% of patients with cirrhosis, often goes unrecognized by both patients and clinicians. Without timely identification and intervention, such as initiating or titrating lactulose or rifaximin, patients can rapidly progress to overt HE. This is strong emerging evidence that suggest a patient’s voice can serve as a biomarker for CHE (PMID 35861546, PMID 39264936). This proposal seeks to leverage ambient AI scribe recordings obtained through routine clinical care as a voice-based biomarker for CHE detection.
We have previously constructed a liver disease specific Large Language Model (LLM) called “LiVersa” using Retrieval Augmented Generation (PMID 38451962, PMID 38935858). We have also constructed “CirrhosisRx,” which is a rule-based (non-AI) clinical decision support system for guideline adherent inpatient cirrhosis care, built on the EngageRx platform using SMART-on-FHIR (NCT05967273, PMID 38407255). In this proposal, we plan to integrate LiVersa into CirrhosisRx via Fast Healthcare Interoperability Resources (FHIR) application progressing interface (API) calls to provide a patient-personalized dynamic information retrieval system to provide guideline-based clinical recommendations to clinician end-users.
Patients with chronic liver diseases, including those with cirrhosis and those awaiting transplantation, have unique and often stringent nutritional requirements. There is an unmet need to provide treating clinicians with culturally-appropriate, evidence-based, and patient-specific nutritional recommendations that resonates with that person’s dietary norms and preferences. This proposal seeks to bridge this gap through a culturally appropriate and personalized RAG-LLM assistant that supports nutritional counseling in liver diseases.
Plain knee radiographs are a cornerstone in evaluating osteoarthritis (OA), and at UCSF, nearly all such studies include Kellgren-Lawrence (KL) grading to assess severity. While essential, this grading task is repetitive, time-consuming, and inherently subjective—especially in borderline cases. In fact, studies show only moderate inter-reader reliability in KL grading, creating inconsistencies in diagnosis and downstream care decisions. KL grading adds to radiologist workload, reducing time available for complex cases and clinical consults. We propose integrating an automated AI model for KL grading directly into the radiology workflow at UCSF. By deploying this AI system at the point of care, we can support more efficient workflows, better diagnostic consistency, and enhanced trainee learning.
The UCSF Health Problem
We aim to automate specialty-specific chart review, a high provider burden, error-prone process that costs clinicians 15–45 minutes per patient, leading to 6–12 hours of weekly administrative overhead contributing to pajama time. This burden impairs clinic throughput, contributes to burnout, and compromises care quality, especially in specialties like Gastroenterology where fragmented, longitudinal data including scanned outside records are the norm.
Section 1. The UCSF Health Problem
Diagnostic error, the failure to establish or communicate an accurate and timely explanation of a patient’s health problem, affects 12 million people in the U.S. annually, leading to delays in treatment, potentially avoidable healthcare utilization, and increased morbidity and mortality.1