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.

Keywords

encounter notes - billing - speech recognition - inpatient care

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.”

• References

• 1 Henry J, Pylypchuk Y, Searcy T, Patel V. . Adoption of electronic health record systems among u.s. non-federal acute care hospitals: 2008–2015. ONC data brief, no.35, 2016. Available at: https://dashboard.healthit.gov/evaluations/data-briefs/non-federal-acute-care-hospital-ehr-adoption-2008-2015.php . Accessed May 15, 2020
• 2 Amarasingham R, Plantinga L, Diener-West M, Gaskin DJ, Powe NR. Clinical information technologies and inpatient outcomes: a multiple hospital study. Arch Intern Med 2009; 169 (02) 108-114
• 3 Chaudhry B, Wang J, Wu S. , et al. Systematic review: impact of health information technology on quality, efficiency, and costs of medical care. Ann Intern Med 2006; 144 (10) 742-752
• 4 Friedberg MW, Chen PG, Van Busum KR. , et al. Factors affecting physician professional satisfaction and their implications for patient care, health systems, and health policy. Rand Health Q 2014; 3 (04) 1
• 5 Sinsky CA, Willard-Grace R, Schutzbank AM, Sinsky TA, Margolius D, Bodenheimer T. In search of joy in practice: a report of 23 high-functioning primary care practices. Ann Fam Med 2013; 11 (03) 272-278
• 6 Tsou AY, Lehmann CU, Michel J, Solomon R, Possanza L, Gandhi T. Safe practices for copy and paste in the EHR. Systematic review, recommendations, and novel model for health IT collaboration. Appl Clin Inform 2017; 8 (01) 12-34
• 7 Abelson R, Creswell J. . US warning to hospitals on Medicare bill abuses. Available at: http://www.nytimes.com/2012/09/25/business/us-warns-hospitals-on-medicare-billing.html . Accessed May 15, 2020
• 8 Centers for Medicare & Medicate Services, Department of Health and Human Services. Evaluation and management services guide. Available at: https://www.cms.gov/Outreach-and-Education/Medicare-Learning-Network-MLN/MLNProducts/Downloads/eval-mgmt-serv-guide-ICN006764.pdf . Accessed May 24, 2019
• 9 Al Hadidi S, Upadhaya S, Shastri R, Alamarat Z. Use of dictation as a tool to decrease documentation errors in electronic health records. J Community Hosp Intern Med Perspect 2017; 7 (05) 282-286
• 10 Johnson M, Lapkin S, Long V. , et al. A systematic review of speech recognition technology in health care. BMC Med Inform Decis Mak 2014; 14: 94
• 11 Blackley SV, Huynh J, Wang L, Korach Z, Zhou L. Speech recognition for clinical documentation from 1990 to 2018: a systematic review. J Am Med Inform Assoc 2019; 26 (04) 324-338
• 12 Payne TH, Alonso WD, Markiel JA. , et al. Using voice to create hospital progress notes: description of a mobile application and supporting system integrated with a commercial electronic health record. J Biomed Inform 2017; 77: 91-96
• 13 Payne TH, Alonso WD, Markiel JA. , et al. Using voice to create inpatient progress notes: effects on note timeliness, quality, and physician satisfaction. JAMIA Open 2018; 1 (02) 218-226
• 14 Office of Inspector General, Department of Health and Human Services. Not All Recommended Fraud Safeguards Have Been Implemented In Hospital EHR Technology. Available at: http://oig.hhs.gov/oei/reports/oei-01-11-00570.pdf . Accessed April 29, 2019
• 15 Payne TH, Perkins M, Kalus R, Reilly D. The transition to electronic documentation on a teaching hospital medical service. AMIA Annu Symp Proc 2006; 629-633
• 16 Lybarger KJ, Ostendorf M, Riskin E, Payne TH, White AA, Yetisgen M. Asynchronous speech recognition affects physician editing of notes. Appl Clin Inform 2018; 9 (04) 782-790
• 17 Payne TH, Garver-Hume A, Kirkegaard S. , et al. Natural language processing improves coding accuracy. MGMA Connex 2011; 11 (09) 15-17
• 18 Zigmond J.HHS. , Justice Department warn hospitals on EHR-related payment fraud. Available at: https://www.modernhealthcare.com/article/20120924/NEWS/309249968/hhs-justice-department-warn-hospitals-on-ehr-related-payment-fraud . Accessed January 25, 2020
• 19 Obtaining robust variance estimates” Stata Corp. Stata 16 Base Reference Manual. College Station, TX: Stata Press; 2019
• 20 Correlated errors: Cluster–robust standard errors” Stata Corp. Stata 16 Base Reference Manual. College Station, TX: Stata Press; 2019
• 21 Graubard BI, Korn EL. Regression analysis with clustered data. Stat Med 1994; 13 (5–7): 509-522
• 22 Watterson JL, Rodriguez HP, Aguilera A, Shortell SM. Ease of use of electronic health records and relational coordination among primary care team members. Health Care Manage Rev 2018 . Doi: 10.1097/HMR.0000000000000222
• 23 McNeish D, Stapleton LM, Silverman RD. On the unnecessary ubiquity of hierarchical linear modeling. Psychol Methods 2017; 22 (01) 114-140