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

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.

Effect of Ambient Voice Technology, Natural Language Processing, and Artificial Intelligence on the Patient–Physician Relationship

“…There may also be financial incentives as one recent randomized controlled trial demonstrated an increase in professional fee billing levels when providers used automated speech recognition for documentation as compared to traditional typing notes into the EHR. 26 Technologies such as DAX which utilize ambient recording, natural language processing, and artificial intelligence may plausibly hold advantages in some of these areas.…”

A retrospective look at the predictions and recommendations from the 2009 AMIA policy meeting: did we see EHR-related clinician burnout coming?

“… 16 Subsequent research has addressed the documentation burden. 17 Research by the informatics community has quantified the EHR factors contributing to burnout. 18 Other work has focused on reducing the burden created by excessive alerts.…”

Conversational Artificial Intelligence for Spinal Pain Questionnaire: Validation and User Satisfaction

“…Recently, hospitals have been actively introducing a doctor appointment service using chatbots [ 13 ]. Currently, the most actively researched field is document automation through voice recognition [ 7 , 14 ]. Speech recognition technology can dramatically reduce the time required to write medical records for doctors and nurses by automatically inputting data in the medical records.…”