Using ChatGPT-4 to Create Structured Medical Notes From Audio Recordings of Physician-Patient Encounters: Comparative Study

BACKGROUND

Medical documentation plays a crucial role in clinical practice, facilitating accurate patient management and communication among health care professionals. However, inaccuracies in medical notes can lead to miscommunication and diagnostic errors. Additionally, the demands of documentation contribute to physician burnout. Although intermediaries like medical scribes and speech recognition software have been used to ease this burden, they have limitations in terms of accuracy and addressing provider-specific metrics. The integration of ambient artificial intelligence (AI)-powered solutions offers a promising way to improve documentation while fitting seamlessly into existing workflows.

OBJECTIVE

This study aims to assess the accuracy and quality of Subjective, Objective, Assessment, and Plan (SOAP) notes generated by ChatGPT-4, an AI model, using established transcripts of History and Physical Examination as the gold standard. We seek to identify potential errors and evaluate the model's performance across different categories.

METHODS

We conducted simulated patient-provider encounters representing various ambulatory specialties and transcribed the audio files. Key reportable elements were identified, and ChatGPT-4 was used to generate SOAP notes based on these transcripts. Three versions of each note were created and compared to the gold standard via chart review; errors generated from the comparison were categorized as omissions, incorrect information, or additions. We compared the accuracy of data elements across versions, transcript length, and data categories. Additionally, we assessed note quality using the Physician Documentation Quality Instrument (PDQI) scoring system.

RESULTS

Although ChatGPT-4 consistently generated SOAP-style notes, there were, on average, 23.6 errors per clinical case, with errors of omission (86%) being the most common, followed by addition errors (10.5%) and inclusion of incorrect facts (3.2%). There was significant variance between replicates of the same case, with only 52.9% of data elements reported correctly across all 3 replicates. The accuracy of data elements varied across cases, with the highest accuracy observed in the "Objective" section. Consequently, the measure of note quality, assessed by PDQI, demonstrated intra- and intercase variance. Finally, the accuracy of ChatGPT-4 was inversely correlated to both the transcript length (P=.05) and the number of scorable data elements (P=.05).

CONCLUSIONS

Our study reveals substantial variability in errors, accuracy, and note quality generated by ChatGPT-4. Errors were not limited to specific sections, and the inconsistency in error types across replicates complicated predictability. Transcript length and data complexity were inversely correlated with note accuracy, raising concerns about the model's effectiveness in handling complex medical cases. The quality and reliability of clinical notes produced by ChatGPT-4 do not meet the standards required for clinical use. Although AI holds promise in health care, caution should be exercised before widespread adoption. Further research is needed to address accuracy, variability, and potential errors. ChatGPT-4, while valuable in various applications, should not be considered a safe alternative to human-generated clinical documentation at this time.

Conducting high-value secondary dataset analysis: an introductory guide and resources

Secondary analyses of large datasets provide a mechanism for researchers to address high impact questions that would otherwise be prohibitively expensive and time-consuming to study. This paper presents a guide to assist investigators interested in conducting secondary data analysis, including advice on the process of successful secondary data analysis as well as a brief summary of high-value datasets and online resources for researchers, including the SGIM dataset compendium ( www.sgim.org/go/datasets ). The same basic research principles that apply to primary data analysis apply to secondary data analysis, including the development of a clear and clinically relevant research question, study sample, appropriate measures, and a thoughtful analytic approach. A real-world case description illustrates key steps: (1) define your research topic and question; (2) select a dataset; (3) get to know your dataset; and (4) structure your analysis and presentation of findings in a way that is clinically meaningful. Secondary dataset analysis is a well-established methodology. Secondary analysis is particularly valuable for junior investigators, who have limited time and resources to demonstrate expertise and productivity.