Integrating ChatGPT into Secure Hospital Networks: A Case Study on Improving Radiology Report Analysis

Kyungsu Kim, Junhyun Park, Saul Langarica, Adham Mahmoud Alkhadrawi, Synho Do

View paper (PDF)

Abstract: This study demonstrates the first in-hospital adaptation of a cloud-based AI, similar to ChatGPT, into a secure model for analyzing radiology reports, prioritizing patient data privacy. By employing a unique sentence-level knowledge distillation method through contrastive learning, we achieve over 95% accuracy in detecting anomalies. The model also accurately flags uncertainties in its predictions, enhancing its reliability and interpretability for physicians with certainty indicators. Despite limitations in data privacy during the training phase, such as requiring de-identification or IRB permission, our study is significant in addressing this issue in the inference phase (once the local model is trained), without the need for human annotation throughout the entire process. These advancements represent a new direction for developing secure and efficient AI tools for healthcare with minimal supervision, paving the way for a promising future of in-hospital AI applications.