ChestX-ray14 is a medical imaging dataset which comprises 112,120 frontal-view X-ray images of 30,805 (collected from the year of 1992 to 2015) unique patients with the text-mined fourteen common disease labels, mined from the text radiological reports via NLP techniques. It expands on ChestX-ray8 by adding six additional thorax diseases: Edema, Emphysema, Fibrosis, Pleural Thickening and Hernia.

This paper introduces CPIR-MR (Chained Prompting for Improved Readability of Medical Reports), a method designed to simplify complex chest X-ray reports for better patient understanding. The authors extend the IU X-Ray dataset with Simplified Medical Reports (SMRs) generated via chained prompting and propose a multi-modal text decoder (MTD) that integrates BLIP embeddings with classification outputs to generate Simplified Medical Explanations (SMEs).

Key highlights:
- Uses few-shot and Chain-of-Thought (CoT) prompting for generating structured, readable outputs.
- Maintains medical accuracy while improving readability and sentiment consistency.
- Introduces CPMK-E, a chained prompting system for keyword extraction and evaluation using Gemini 1.5 Flash.
- Shows strong performance in text complexity reduction and semantic similarity preservation.