C-QODE Use Case: Ambiscribe Partnership
In partnership with the U of M’s Department of Electrical and Computer Engineering and the Program for Clinical AI within the Center for Learning Health Systems Sciences, the Center for Quality Outcomes, Discovery and Evaluation (C-QODE) within the Medical School’s Department of Surgery have partnered on an ‘AmbiScribe’ project to develop an AI-enabled medical assistant.
John Sartori, PhD, assistant professor in the Department of Electrical and Computer Engineering and C-QODE Director and Co-Investigator, Christopher J. Tignanelli, MD MS FACS FAMIA of the Department of Surgery, are embarking on a large research project to develop a dataset for retrospective model training. Spearheading technical expertise, the Department of Electrical and Computer Engineering will be responsible for developing and validating the AI medical assistant with the Medical School serving as the clinical subject matter expert.
The electronic medical record (EMR) is an integral part of our healthcare system designed to improve the quality and efficiency of medical care provided to patients. Despite its advantages in providing streamlined access to patient data, however, the means of data entry into the EMR can actually detract from the care that patients receive from a medical provider. Multiple studies have shown that doctors are increasingly spending more time in front of a screen, navigating the EMR, than face to face with their patients.
Frustration with the EMR is consistently cited as a contributor to the epidemic of physician burnout. The process of documenting the details of an encounter is tedious and time-consuming, and when done in the patient room, often leads to “doc-in-a-box” lines of questioning, as providers attempt to fill out an electronic form in real-time. Physicians who use medical scribes show greater job satisfaction, decreased burnout, and increased efficiency. Medical scribe support is expensive, however, as it requires a 1:1 ratio of additional medical staffing. In parallel, the team will provide an IRB protocol for a prospective study to integrate real-time audio data going forward.
This research aims to create software – AmbiScribe – to address this gap by providing the benefits of an in-person scribe via ambient speech recognition and classification technology built into the provider’s computer.
Goal and Significance
Our research aims to create software that provides the benefits of an in-person scribe via ambient speech recognition and classification technology. The software will have the ability to automatically navigate and populate the EHR based on a patient-provider conversation and structured EHR data. The software will also provide data-driven decision support to providers based on the same data. The goals of these software tools include improving clinical outcomes, reducing healthcare costs and improving patient and provider satisfaction.
