PRECISE Framework: GPT-based Text For Improved Readability, Reliability, and Understandability of Radiology Reports For Patient-Centered Care

arXiv:2403.00788v1 Announce Type: cross
Abstract: This study introduces and evaluates the PRECISE framework, utilizing OpenAI's GPT-4 to enhance patient engagement by providing clearer and more accessible chest X-ray reports at a sixth-grade reading level. The framework was tested on 500 reports, demonstrating significant improvements in readability, reliability, and understandability. Statistical analyses confirmed the effectiveness of the PRECISE approach, highlighting its potential to foster patient-centric care delivery in healthcare decision-making.

abstract arxiv cs.ai cs.cl cs.hc cs.lg engagement framework gpt gpt-4 improvements openai openai's gpt-4 patient patient engagement radiology ray readability reading reliability reports study text type x-ray