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

• DOI: 10.2196/preprints.73337
• Publication Date: 2025-03-02T16:15:06Z
• Authors: Daniel Stephan; Annika S Bertsch; Sophia Schumacher; Behrus Puladi; Matthias Burwinkel; Bilal Al-Nawas; Peer W Kämmerer; Daniel GE Thiem
• Keywords: Preprint

<sec> <title>UNSTRUCTURED</title> Objectives: Artificial intelligence (AI) has emerged as a transformative tool in healthcare, particularly improving medical documentation and communication. This study investigates the potential of ChatGPT, an AI language model, to enhance patient comprehension radiology reports through simplification. Materials Methods: Three versions were evaluated: original AI-generated, simplified, further simplified versions. Patient feedback 300 patients was collected via structured questionnaires assessing clarity, tone, structure, engagement. Results: The results demonstrated that both significantly outperformed AI-generated across all dimensions, with version receiving highest ratings. Patients consistently reported greater improved enhanced engagement texts. Readability analysis confirmed these findings, achieved higher Flesch Reading Ease scores lower LIX indices (readability index), indicating accessibility without compromising clinical relevance. Conclusion: Overall, effectively empower understand their conditions actively engage healthcare decisions. Clinical Relevance: therefore highlights ChatGPT advancing patient-centered communication while emphasizing need for cautious collaborative approach integration workflows. </sec>