MedAutoCorrect: Image-Conditioned Autocorrection in Medical Reporting

Arnold Caleb Asiimwe, Didac Suris Coll-Vinent, Pranav Rajpurkar, Carl Vondrick
Proceedings of the 9th Machine Learning for Healthcare Conference, PMLR 252, 2024.

Abstract

In medical reporting, the accuracy of radiological reports, whether generated by humans or machine learning algorithms, is critical. We tackle a new task in this paper: image- conditioned autocorrection of inaccuracies within these reports. Using the MIMIC-CXR dataset, we first intentionally introduce a diverse range of errors into reports. Subsequently, we propose a two-stage framework capable of pinpointing these errors and then making corrections, simulating an autocorrection process. This method aims to address the short- comings of existing automated medical reporting systems, like factual errors and incorrect conclusions, enhancing report reliability in vital healthcare applications. Importantly, our approach could serve as a guardrail, ensuring the accuracy and trustworthiness of automated report generation. Experiments on established datasets and state of the art report generation models validate this method’s potential in correcting medical reporting errors.

Cite this Paper

BibTeX
@InProceedings{pmlr-v252-asiimwe24a, title = {MedAutoCorrect: Image-Conditioned Autocorrection in Medical Reporting}, author = {Asiimwe, Arnold Caleb and Coll-Vinent, Didac Suris and Rajpurkar, Pranav and Vondrick, Carl}, booktitle = {Proceedings of the 9th Machine Learning for Healthcare Conference}, year = {2024}, editor = {Deshpande, Kaivalya and Fiterau, Madalina and Joshi, Shalmali and Lipton, Zachary and Ranganath, Rajesh and Urteaga, Iñigo}, volume = {252}, series = {Proceedings of Machine Learning Research}, month = {16--17 Aug}, publisher = {PMLR}, pdf = {https://raw.githubusercontent.com/mlresearch/v252/main/assets/asiimwe24a/asiimwe24a.pdf}, url = {https://proceedings.mlr.press/v252/asiimwe24a.html}, abstract = {In medical reporting, the accuracy of radiological reports, whether generated by humans or machine learning algorithms, is critical. We tackle a new task in this paper: image- conditioned autocorrection of inaccuracies within these reports. Using the MIMIC-CXR dataset, we first intentionally introduce a diverse range of errors into reports. Subsequently, we propose a two-stage framework capable of pinpointing these errors and then making corrections, simulating an autocorrection process. This method aims to address the short- comings of existing automated medical reporting systems, like factual errors and incorrect conclusions, enhancing report reliability in vital healthcare applications. Importantly, our approach could serve as a guardrail, ensuring the accuracy and trustworthiness of automated report generation. Experiments on established datasets and state of the art report generation models validate this method’s potential in correcting medical reporting errors.} }
Endnote
%0 Conference Paper %T MedAutoCorrect: Image-Conditioned Autocorrection in Medical Reporting %A Arnold Caleb Asiimwe %A Didac Suris Coll-Vinent %A Pranav Rajpurkar %A Carl Vondrick %B Proceedings of the 9th Machine Learning for Healthcare Conference %C Proceedings of Machine Learning Research %D 2024 %E Kaivalya Deshpande %E Madalina Fiterau %E Shalmali Joshi %E Zachary Lipton %E Rajesh Ranganath %E Iñigo Urteaga %F pmlr-v252-asiimwe24a %I PMLR %U https://proceedings.mlr.press/v252/asiimwe24a.html %V 252 %X In medical reporting, the accuracy of radiological reports, whether generated by humans or machine learning algorithms, is critical. We tackle a new task in this paper: image- conditioned autocorrection of inaccuracies within these reports. Using the MIMIC-CXR dataset, we first intentionally introduce a diverse range of errors into reports. Subsequently, we propose a two-stage framework capable of pinpointing these errors and then making corrections, simulating an autocorrection process. This method aims to address the short- comings of existing automated medical reporting systems, like factual errors and incorrect conclusions, enhancing report reliability in vital healthcare applications. Importantly, our approach could serve as a guardrail, ensuring the accuracy and trustworthiness of automated report generation. Experiments on established datasets and state of the art report generation models validate this method’s potential in correcting medical reporting errors.
APA
Asiimwe, A.C., Coll-Vinent, D.S., Rajpurkar, P. & Vondrick, C.. (2024). MedAutoCorrect: Image-Conditioned Autocorrection in Medical Reporting. Proceedings of the 9th Machine Learning for Healthcare Conference, in Proceedings of Machine Learning Research 252 Available from https://proceedings.mlr.press/v252/asiimwe24a.html.

Related Material