FactsR: A Safer Method for Producing High Quality Healthcare Documentation

TL;DR

FactsR introduces a real-time, clinician-in-the-loop method for healthcare documentation that enhances accuracy and safety by reducing hallucinations and misrepresentation in AI-generated notes.

Contribution

The paper presents FactsR, a novel real-time information extraction and recursive note generation method that improves healthcare documentation quality and safety.

Findings

More accurate and concise notes produced.

Reduced hallucinations and misrepresentation.

Enhanced real-time decision support capabilities.

Abstract

There are now a multitude of AI-scribing solutions for healthcare promising the utilization of large language models for ambient documentation. However, these AI scribes still rely on one-shot, or few-shot prompts for generating notes after the consultation has ended, employing little to no reasoning. This risks long notes with an increase in hallucinations, misrepresentation of the intent of the clinician, and reliance on the proofreading of the clinician to catch errors. A dangerous combination for patient safety if vigilance is compromised by workload and fatigue. In this paper, we introduce a method for extracting salient clinical information in real-time alongside the healthcare consultation, denoted Facts, and use that information recursively to generate the final note. The FactsR method results in more accurate and concise notes by placing the clinician-in-the-loop of note generation, while opening up new use cases within real-time decision support.