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
Proceedings of the fifth Conference on Health, Inference, and Learning, PMLR 248:72-87, 2024.

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.

Cite this Paper

BibTeX
@InProceedings{pmlr-v248-kim24a, title = {Integrating ChatGPT into Secure Hospital Networks: A Case Study on Improving Radiology Report Analysis}, author = {Kim, Kyungsu and Park, Junhyun and Langarica, Saul and Mahmoud Alkhadrawi, Adham and Do, Synho}, booktitle = {Proceedings of the fifth Conference on Health, Inference, and Learning}, pages = {72--87}, year = {2024}, editor = {Pollard, Tom and Choi, Edward and Singhal, Pankhuri and Hughes, Michael and Sizikova, Elena and Mortazavi, Bobak and Chen, Irene and Wang, Fei and Sarker, Tasmie and McDermott, Matthew and Ghassemi, Marzyeh}, volume = {248}, series = {Proceedings of Machine Learning Research}, month = {27--28 Jun}, publisher = {PMLR}, pdf = {https://raw.githubusercontent.com/mlresearch/v248/main/assets/kim24a/kim24a.pdf}, url = {https://proceedings.mlr.press/v248/kim24a.html}, 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.} }
Endnote
%0 Conference Paper %T Integrating ChatGPT into Secure Hospital Networks: A Case Study on Improving Radiology Report Analysis %A Kyungsu Kim %A Junhyun Park %A Saul Langarica %A Adham Mahmoud Alkhadrawi %A Synho Do %B Proceedings of the fifth Conference on Health, Inference, and Learning %C Proceedings of Machine Learning Research %D 2024 %E Tom Pollard %E Edward Choi %E Pankhuri Singhal %E Michael Hughes %E Elena Sizikova %E Bobak Mortazavi %E Irene Chen %E Fei Wang %E Tasmie Sarker %E Matthew McDermott %E Marzyeh Ghassemi %F pmlr-v248-kim24a %I PMLR %P 72--87 %U https://proceedings.mlr.press/v248/kim24a.html %V 248 %X 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.
APA
Kim, K., Park, J., Langarica, S., Mahmoud Alkhadrawi, A. & Do, S.. (2024). Integrating ChatGPT into Secure Hospital Networks: A Case Study on Improving Radiology Report Analysis. Proceedings of the fifth Conference on Health, Inference, and Learning, in Proceedings of Machine Learning Research 248:72-87 Available from https://proceedings.mlr.press/v248/kim24a.html.

Related Material