Appl Clin Inform 2020; 11(03): 427-432
DOI: 10.1055/s-0040-1713134
Research Article
Georg Thieme Verlag KG Stuttgart · New York

A Randomized Trial of Voice-Generated Inpatient Progress Notes: Effects on Professional Fee Billing

Andrew A. White
1  Department of Medicine, University of Washington School of Medicine, Seattle, Washington, United States
,
Tyler Lee
1  Department of Medicine, University of Washington School of Medicine, Seattle, Washington, United States
,
Michelle M. Garrison
2  Department of Health Services, University of Washington School of Public Health, and Department of Psychiatry and Behavioral Sciences, University of Washington School of Medicine, Seattle, Washington, United States
,
Thomas H. Payne
1  Department of Medicine, University of Washington School of Medicine, Seattle, Washington, United States
› Author Affiliations
Further Information

Publication History

18 November 2019

01 May 2020

Publication Date:
10 June 2020 (online)

Abstract

Background Prior evaluations of automated speech recognition (ASR) to create hospital progress notes have not analyzed its effect on professional revenue billing codes. As ASR becomes a more common method of entering clinical notes, clinicians, hospital administrators, and payers should understand whether this technology alters charges associated with inpatient physician services.

Objectives This study aimed to measure the difference in professional fee charges between using voice and keyboard to create inpatient progress notes.

Methods In a randomized trial of a novel voice with ASR system, called voice-generated enhanced electronic note system (VGEENS), to generate physician notes, we compared 1,613 notes created using intervention (VGEENS) or control (keyboard with template) created by 31 physicians. We measured three outcomes, as follows: (1) professional fee billing levels assigned by blinded coders, (2) number of elements within each note domain, and (3) frequency of organ system evaluations documented in review of systems (ROS) and physical exam.

Results Participants using VGEENS generated a greater portion of high-level (99233) notes than control users (31.8 vs. 24.3%, p < 0.01). After adjustment for clustering by author, the finding persisted; intervention notes were 1.43 times more likely (95% confidence interval [CI]: 1.14–1.79) to receive a high-level code. Notes created using voice contained an average of 1.34 more history of present illness components (95% CI: 0.14–2.54) and 1.62 more review of systems components (95% CI: 0.48–2.76). The number of physical exam components was unchanged.

Conclusion Using this voice with ASR system as tested slightly increases documentation of patient symptom details without reliance on copy and paste and may raise physician charges. Increased provider reimbursement may encourage hospital and provider group to offer use of voice and ASR to create hospital progress notes as an alternative to usual methods.

Protection of Human and Animal Subjects

This study was performed in compliance with the World Medical Association Declaration of Helsinki on Ethical Principles for Medical Research Involving Human Subjects and was reviewed by the University of Washington Institutional Review Board.


a In the United States, for a given encounter, the selection of the appropriate level of evaluation and management (E/M) services is determined according to the code of definitions in the American Medical Association’s Current Procedural Terminology (CPT) book and any applicable documentation guidelines. For hospital physician professional fees, 99231 99232, 99233 are used for subsequent care progress notes. Professional fees are lowest for 99231, intermediate for 99232, and highest for 99233. See reference 8 for more detail.


b Hospital physicians make at least daily visits to their hospitalized patients; these visits are referred to as “rounds.”