Popular searches
Not sure where to start?Talk to our team about running sovereign AI in your environment.
↑ ↓ Navigate↵ OpenEsc Close
UCSF Health used H2O Document AI to intake e-faxes automatically, saving 25,000+ hours of access-center staff time and 5,000 hours of clinician time.
UCSF Health receives over 1.4 million faxed documents a year, from referrals and prescription refills to DME requests and lab results. Each one required manual handling to identify the document type, the patient, and the action needed. That manual processing carried costs equivalent to more than 100 full-time employees and delayed patient access to care.
Referral coordinators manually extracted demographics and insurance information and re-entered it across multiple EHR screens. The work delayed patient access to care and carried operational costs equivalent to more than 100 full-time employees across the health system.
UCSF built an "Intake Automation" application powered by H2O Document AI. The system automatically classifies document pages, extracts the relevant information through API calls, and stores the results in the application database.
H2O Document AI uses Intelligent Character Recognition with learning algorithms for character and word recognition, document layout understanding, and Natural Language Processing. That approach reads the semi-structured, variable-quality faxes that traditional rules-driven OCR could not handle. Incoming faxes were digitized through a RightFax service and passed to the backend for processing.
The Intake Automation application saved more than 25,000 hours of access-center staff time, roughly 12 full-time-equivalent positions, and 5,000 hours of clinician time, roughly 2.5 FTE.
Staff redirected that time toward personalized patient experiences, care navigation, and absorbing year-over-year growth in referral volume, work that directly improves patient access to care.
“When we started this journey, we were hopeful that information extraction from semi-structured documents was possible, but we weren't sure. Some in the industry told us it couldn't be done. Now that the UCSF-H2O.ai collaboration team has delivered, it opens up many possibilities.”Bob Rogers, PhDExpert in Residence for AI
UCSF Health is the academic health system of the University of California, San Francisco, a renowned health system and world leader in patient care and biomedical research. It provides adult and pediatric care across the San Francisco Bay Area, with principal components including UCSF Medical Center at Parnassus Heights, Mission Bay, and Mount Zion, the UCSF Benioff Children's Hospitals in San Francisco and Oakland, Langley Porter Psychiatric Hospital, and UCSF Health Hyde and Stanyan hospitals.
UCSF Health is ranked among the top hospitals nationally by U.S. News, holds a five-star CMS rating, an "A" Leapfrog safety rating, and Magnet designation for nursing excellence. More information is available at https://www.ucsfhealth.org/about.