Improving Patient Communication by Simplifying AI-Generated Dental Radiology Reports With ChatGPT: Comparative Study

Abstract

Background: Medical reports, particularly radiology findings, are often written for professional communication, making them difficult for patients to understand. This communication barrier can reduce patient engagement and lead to misinterpretation. Artificial intelligence (AI), especially large language models such as ChatGPT, offers new opportunities for simplifying medical documentation to improve patient comprehension.

Objective: We aimed to evaluate whether AI-generated radiology reports simplified by ChatGPT improve patient understanding, readability, and communication quality compared to original AI-generated reports.

Methods: In total, 3 versions of radiology reports were created using ChatGPT: an original AI-generated version (text 1), a patient-friendly, simplified version (text 2), and a further simplified and accessibility-optimized version (text 3). A total of 300 patients (n=100, 33.3% per group), excluding patients with medical education, were randomly assigned to review one text version and complete a standardized questionnaire. Readability was assessed using the Flesch Reading Ease (FRE) score and LIX indices.

Results: Both simplified texts showed significantly higher readability scores (text 1: FRE score=51.1; text 2: FRE score=55.0; and text 3: FRE score=56.4; P<.001) and lower LIX scores, indicating enhanced clarity. Text 3 had the shortest sentences, had the fewest long words, and scored best on all patient-rated dimensions. Questionnaire results revealed significantly higher ratings for texts 2 and 3 across clarity (P<.001), tone (P<.001), structure, and patient engagement. For example, patients rated the ability to understand findings without help highest for text 3 (mean 1.5, SD 0.7) and lowest for text 1 (mean 3.1, SD 1.4). Both simplified texts significantly improved patients' ability to prepare for clinical conversations and promoted shared decision-making.

Conclusions: AI-generated simplification of radiology reports significantly enhances patient comprehension and engagement. These findings highlight the potential of ChatGPT as a tool to improve patient-centered communication. While promising, future research should focus on ensuring clinical accuracy and exploring applications across diverse patient populations to support equitable and effective integration of AI in health care communication.

Keywords: clinical communication; health literacy; medical accessibility; natural language processing; patient comprehension; patient-centered care; radiology report.

Figure 1

Analysis of (A) sentence count, (B) word count, and (C) proportion of long words in artificial intelligence (AI)–simplified radiology reports compared to original AI-generated reports (n=100). Data represent mean (SD). *P<.05.

Figure 2

Metric evaluation of readability of artificial intelligence (AI)–simplified reports and original AI-generated reports assessed with (A) the Flesch Reading Ease score and (B) the LIX score (n=100). Data represent mean (SD). *P<.05.

Figure 3

Patient ratings of their comprehension of radiology reports for original artificial intelligence (AI)–generated (text 1), patient-friendly, simplified AI-generated (text 2), and accessibility-optimized AI-generated (text 3) reports. Responses were assessed for (A) ease of understanding the radiology reports, (B) clarity of the medical terms, and (C) ability to understand the findings without additional help (n=100). Data are presented as box-and-whisker plots with medians and IQRs. *P<.05.

Figure 4

Patient ratings comparing original artificial intelligence (AI)–generated (text 1), patient-friendly simplified AI-generated (text 2), and accessibility-optimized AI-generated (text 3) radiology reports. Ratings were assessed for (A) how the structure of the report helped in understanding the information and (B) whether the information in the report was detailed enough to answer patients’ questions (n=100). Data are presented as box-and-whisker plots, showing medians and IQRs. *P<.05.

Figure 5

Patient ratings comparing original artificial intelligence (AI)–generated (text 1), patient-friendly simplified AI-generated (text 2), and accessibility-optimized AI-generated (text 3) radiology reports. Ratings were assessed for (A) whether the tone of the report was respectful and took the patient’s situation into account, and (B) whether the report conveyed an empathetic attitude toward the patient’s level of understanding (n=100). Data are presented as box-and-whisker plots, showing medians and IQRs. *P<.05.

Figure 6

Patient ratings comparing original artificial intelligence (AI)–generated (text 1), patient-friendly simplified AI-generated (text 2), and accessibility-optimized AI-generated (text 3) radiology reports. Ratings were assessed for (A) whether the report helps patients ask the right questions to their physician or dentist, (B) whether the report enables a discussion on equal terms with their physician or dentist, and (C) whether the report motivates patients to focus more on oral hygiene and health in the future (n=100). Data are presented as box-and-whisker plots, showing medians and IQRs. *P<.05.

Figure 7

Patient ratings comparing original artificial intelligence (AI)–generated (text 1), patient-friendly simplified AI-generated (text 2), and accessibility-optimized AI-generated (text 3) radiology reports. Ratings reflect the preference for all medical reports to be as understandable as the radiology reports presented (n=100). Data are shown as box-and-whisker plots, displaying medians and IQRs. *P<.05.