{"id":985488,"date":"2023-11-27T09:00:00","date_gmt":"2023-11-27T17:00:00","guid":{"rendered":"https:\/\/www.microsoft.com\/en-us\/research\/?p=985488"},"modified":"2023-11-29T08:18:22","modified_gmt":"2023-11-29T16:18:22","slug":"gpt-4s-potential-in-shaping-the-future-of-radiology","status":"publish","type":"post","link":"https:\/\/www.microsoft.com\/en-us\/research\/blog\/gpt-4s-potential-in-shaping-the-future-of-radiology\/","title":{"rendered":"GPT-4&#8217;s potential in shaping the future of radiology"},"content":{"rendered":"\n<p class=\"has-text-align-center\"><strong><em>This research paper is being presented at the <\/em><\/strong><a class=\"msr-external-link glyph-append glyph-append-open-in-new-tab glyph-append-xsmall\" href=\"https:\/\/2023.emnlp.org\/\" target=\"_blank\" rel=\"noreferrer noopener\"><strong><em>2023 Conference on Empirical Methods in Natural Language Processing<\/em><\/strong><span class=\"sr-only\"> (opens in new tab)<\/span><\/a><strong><em> (EMNLP 2023), the premier conference on natural language processing and artificial intelligence.<\/em><\/strong><\/p>\n\n\n\n<figure class=\"wp-block-image aligncenter size-full\"><img loading=\"lazy\" decoding=\"async\" width=\"1400\" height=\"788\" src=\"https:\/\/www.microsoft.com\/en-us\/research\/uploads\/prod\/2023\/11\/MAIRA_feature_1400x788.jpg\" alt=\"EMNLP 2023 blog hero - female radiologist analyzing an MRI image of the head\" class=\"wp-image-984078\" srcset=\"https:\/\/www.microsoft.com\/en-us\/research\/uploads\/prod\/2023\/11\/MAIRA_feature_1400x788.jpg 1400w, https:\/\/www.microsoft.com\/en-us\/research\/uploads\/prod\/2023\/11\/MAIRA_feature_1400x788-300x169.jpg 300w, https:\/\/www.microsoft.com\/en-us\/research\/uploads\/prod\/2023\/11\/MAIRA_feature_1400x788-1024x576.jpg 1024w, https:\/\/www.microsoft.com\/en-us\/research\/uploads\/prod\/2023\/11\/MAIRA_feature_1400x788-768x432.jpg 768w, https:\/\/www.microsoft.com\/en-us\/research\/uploads\/prod\/2023\/11\/MAIRA_feature_1400x788-1066x600.jpg 1066w, https:\/\/www.microsoft.com\/en-us\/research\/uploads\/prod\/2023\/11\/MAIRA_feature_1400x788-655x368.jpg 655w, https:\/\/www.microsoft.com\/en-us\/research\/uploads\/prod\/2023\/11\/MAIRA_feature_1400x788-343x193.jpg 343w, https:\/\/www.microsoft.com\/en-us\/research\/uploads\/prod\/2023\/11\/MAIRA_feature_1400x788-240x135.jpg 240w, https:\/\/www.microsoft.com\/en-us\/research\/uploads\/prod\/2023\/11\/MAIRA_feature_1400x788-640x360.jpg 640w, https:\/\/www.microsoft.com\/en-us\/research\/uploads\/prod\/2023\/11\/MAIRA_feature_1400x788-960x540.jpg 960w, https:\/\/www.microsoft.com\/en-us\/research\/uploads\/prod\/2023\/11\/MAIRA_feature_1400x788-1280x720.jpg 1280w\" sizes=\"(max-width: 1400px) 100vw, 1400px\" \/><\/figure>\n\n\n\n<div class=\"annotations \" data-bi-aN=\"margin-callout\">\n\t<ul class=\"annotations__list card depth-16 bg-body p-4 annotations__list--right\">\n\t\t<li class=\"annotations__list-item\">\n\t\t\t\t\t\t<span class=\"annotations__type d-block text-uppercase font-weight-semibold text-neutral-300 small\">Project<\/span>\n\t\t\t<a href=\"https:\/\/aka.ms\/maira\" target=\"_blank\" class=\"annotations__link font-weight-semibold text-decoration-none\" data-bi-type=\"annotated-link\" aria-label=\"Project MAIRA\" data-bi-aN=\"margin-callout\" data-bi-cN=\"Project MAIRA\">\n\t\t\t\tProject MAIRA&nbsp;<span class=\"glyph-append glyph-append-share glyph-append-xsmall\"><\/span>\n\t\t\t<\/a>\n\t\t\t\t\t<\/li>\n\t<\/ul>\n<\/div>\n\n\n\n<p>In recent years, AI has been increasingly integrated into healthcare, bringing about new areas of focus and priority, such as diagnostics, treatment planning, patient engagement. While AI\u2019s contribution in certain fields like image analysis and drug interaction is widely recognized, its potential in natural language tasks with these newer areas presents an intriguing research opportunity.&nbsp;<\/p>\n\n\n\n<p>One notable advancement in this area involves <a href=\"https:\/\/www.microsoft.com\/en-us\/research\/publication\/capabilities-of-gpt-4-on-medical-challenge-problems\/\">GPT-4&#8217;s impressive performance<span class=\"sr-only\"> (opens in new tab)<\/span><\/a> on medical competency exams and benchmark datasets. GPT-4 has also demonstrated <a class=\"msr-external-link glyph-append glyph-append-open-in-new-tab glyph-append-xsmall\" href=\"https:\/\/www.nejm.org\/doi\/full\/10.1056\/NEJMsr2214184\" target=\"_blank\" rel=\"noreferrer noopener\">potential utility<span class=\"sr-only\"> (opens in new tab)<\/span><\/a> in medical consultations, providing a promising outlook for healthcare innovation.<\/p>\n\n\n\n<h2 class=\"wp-block-heading\" id=\"progressing-radiology-ai-for-real-problems\">Progressing radiology AI for real problems<\/h2>\n\n\n\n<p>Our paper, \u201c<a href=\"https:\/\/www.microsoft.com\/en-us\/research\/publication\/exploring-the-boundaries-of-gpt-4-in-radiology\/\" target=\"_blank\" rel=\"noreferrer noopener\">Exploring the Boundaries of GPT-4 in Radiology<span class=\"sr-only\"> (opens in new tab)<\/span><\/a>,\u201d which we are presenting at <a class=\"msr-external-link glyph-append glyph-append-open-in-new-tab glyph-append-xsmall\" href=\"https:\/\/2023.emnlp.org\/\" target=\"_blank\" rel=\"noreferrer noopener\">EMNLP 2023<span class=\"sr-only\"> (opens in new tab)<\/span><\/a>, further explores GPT-4\u2019s potential in healthcare, focusing on its abilities and limitations in radiology\u2014a field that is crucial in disease diagnosis and treatment through imaging technologies like x-rays, computed tomography (CT) and magnetic resonance imaging (MRI). We collaborated with our colleagues at <a class=\"msr-external-link glyph-append glyph-append-open-in-new-tab glyph-append-xsmall\" href=\"https:\/\/www.nuance.com\/en-gb\/healthcare.html\" target=\"_blank\" rel=\"noreferrer noopener\">Nuance<span class=\"sr-only\"> (opens in new tab)<\/span><\/a>, a Microsoft company, whose solution, PowerScribe, is used by more than 80 percent of US radiologists. Together, we aimed to better understand technology\u2019s impact on radiologists\u2019 workflow.<\/p>\n\n\n\n<p>Our research included a comprehensive evaluation and error analysis framework to rigorously assess GPT-4\u2019s ability to process radiology reports, including common language understanding and generation tasks in radiology, such as disease classification and findings summarization. This framework was developed in collaboration with a board-certified radiologist to tackle more intricate and challenging real-world scenarios in radiology and move beyond mere metric scores.<\/p>\n\n\n\n<p>We also explored various effective zero-, few-shot, and chain-of-thought (CoT) prompting techniques for GPT-4 across different radiology tasks and experimented with approaches to improve the reliability of GPT-4 outputs. For each task, GPT-4 performance was benchmarked against prior GPT-3.5 models and respective state-of-the-art radiology models.&nbsp;<\/p>\n\n\n\n<p>We found that GPT-4 demonstrates new state-of-the-art performance in some tasks, achieving about a 10-percent absolute improvement over existing models, as shown in Table 1. Surprisingly, we found radiology report summaries generated by GPT-4 to be comparable and, in some cases, even preferred over those written by experienced radiologists, with one example illustrated in Table 2.<\/p>\n\n\n\n<figure class=\"wp-block-image aligncenter size-full\"><img loading=\"lazy\" decoding=\"async\" width=\"1400\" height=\"369\" src=\"https:\/\/www.microsoft.com\/en-us\/research\/uploads\/prod\/2023\/11\/EMNLP-Blog_Table1.png\" alt=\"Table 1: Table showing GPT-4 either outperforms or is on par with previous state-of-the-art multimodal LLMs.\" class=\"wp-image-985512\" srcset=\"https:\/\/www.microsoft.com\/en-us\/research\/uploads\/prod\/2023\/11\/EMNLP-Blog_Table1.png 1400w, https:\/\/www.microsoft.com\/en-us\/research\/uploads\/prod\/2023\/11\/EMNLP-Blog_Table1-300x79.png 300w, https:\/\/www.microsoft.com\/en-us\/research\/uploads\/prod\/2023\/11\/EMNLP-Blog_Table1-1024x270.png 1024w, https:\/\/www.microsoft.com\/en-us\/research\/uploads\/prod\/2023\/11\/EMNLP-Blog_Table1-768x202.png 768w, https:\/\/www.microsoft.com\/en-us\/research\/uploads\/prod\/2023\/11\/EMNLP-Blog_Table1-240x63.png 240w\" sizes=\"(max-width: 1400px) 100vw, 1400px\" \/><figcaption class=\"wp-element-caption\">Table 1: Results overview. GPT-4 either outperforms or is on par with previous state-of-the-art (SOTA) multimodal LLMs.<\/figcaption><\/figure>\n\n\n\n<figure class=\"wp-block-image aligncenter size-full\"><img loading=\"lazy\" decoding=\"async\" width=\"1400\" height=\"585\" src=\"https:\/\/www.microsoft.com\/en-us\/research\/uploads\/prod\/2023\/11\/EMNLP-Blog_Table2.png\" alt=\"Table 2. Table showing examples where GPT-4 impressions, or findings summaries, are favored over existing manually written impressions on the Open-i dataset. In both examples, GPT-4 outputs are more faithful and provide more complete details on the findings.\" class=\"wp-image-985515\" srcset=\"https:\/\/www.microsoft.com\/en-us\/research\/uploads\/prod\/2023\/11\/EMNLP-Blog_Table2.png 1400w, https:\/\/www.microsoft.com\/en-us\/research\/uploads\/prod\/2023\/11\/EMNLP-Blog_Table2-300x125.png 300w, https:\/\/www.microsoft.com\/en-us\/research\/uploads\/prod\/2023\/11\/EMNLP-Blog_Table2-1024x428.png 1024w, https:\/\/www.microsoft.com\/en-us\/research\/uploads\/prod\/2023\/11\/EMNLP-Blog_Table2-768x321.png 768w, https:\/\/www.microsoft.com\/en-us\/research\/uploads\/prod\/2023\/11\/EMNLP-Blog_Table2-240x100.png 240w\" sizes=\"(max-width: 1400px) 100vw, 1400px\" \/><figcaption class=\"wp-element-caption\">Table 2. Examples where GPT-4 findings summaries are favored over existing manually written ones on the Open-i dataset. In both examples, GPT-4 outputs are more faithful and provide more complete details on the findings.<\/figcaption><\/figure>\n\n\n\n<p>Another encouraging prospect for GPT-4 is its ability to automatically structure radiology reports, as schematically illustrated in Figure 1. These reports, based on a radiologist\u2019s interpretation of medical images like x-rays and include patients\u2019 clinical history, are often complex and unstructured, making them difficult to interpret. <a class=\"msr-external-link glyph-append glyph-append-open-in-new-tab glyph-append-xsmall\" href=\"https:\/\/pubs.rsna.org\/doi\/pdf\/10.1148\/rg.2019190182\" target=\"_blank\" rel=\"noreferrer noopener\">Research shows<\/a> that structuring these reports can improve standardization and consistency in disease descriptions, making them easier to interpret by other healthcare providers and more easily searchable for research and quality improvement initiatives. Additionally, using GPT-4 to structure and standardize radiology reports can further support efforts to augment real-world data (RWD) and its use for <a href=\"https:\/\/www.microsoft.com\/en-us\/research\/group\/real-world-evidence\/\" target=\"_blank\" rel=\"noreferrer noopener\">real-world evidence<\/a> (RWE). This can complement more robust and comprehensive clinical trials and, in turn, accelerate the application of research findings into clinical practice.<\/p>\n\n\n\n<figure class=\"wp-block-video aligncenter\"><video controls poster=\"https:\/\/www.microsoft.com\/en-us\/research\/uploads\/prod\/2023\/11\/Maira-Diagram-2-6565b8475c936.png\" src=\"https:\/\/www.microsoft.com\/en-us\/research\/uploads\/prod\/2023\/11\/Maira-Diagram-2-V2.mp4\"><\/video><\/figure>\n\n\n\n<p>Beyond radiology, GPT-4\u2019s potential extends to translating medical reports into more <a class=\"msr-external-link glyph-append glyph-append-open-in-new-tab glyph-append-xsmall\" href=\"https:\/\/www.ihi.org\/insights\/artificial-intelligence-health-care-peter-lee-empathy-empowerment-and-equity\" target=\"_blank\" rel=\"noreferrer noopener\">empathetic<span class=\"sr-only\"> (opens in new tab)<\/span><\/a> and understandable formats for patients and other health professionals. This innovation could revolutionize patient engagement and education, making it easier for them and their carers to actively participate in their healthcare.<\/p>\n\n\n\n\t<div class=\"border-bottom border-top border-gray-300 mt-5 mb-5 msr-promo text-center text-md-left alignwide\" data-bi-aN=\"promo\" data-bi-id=\"1085496\">\n\t\t\n\n\t\t<p class=\"msr-promo__label text-gray-800 text-center text-uppercase\">\n\t\t<span class=\"px-4 bg-white display-inline-block font-weight-semibold small\">Spotlight: Blog post<\/span>\n\t<\/p>\n\t\n\t<div class=\"row pt-3 pb-4 align-items-center\">\n\t\t\t\t\t\t<div class=\"msr-promo__media col-12 col-md-5\">\n\t\t\t\t<a class=\"bg-gray-300\" href=\"https:\/\/www.microsoft.com\/en-us\/research\/blog\/eureka-evaluating-and-understanding-progress-in-ai\/\" aria-label=\"Eureka: Evaluating and understanding progress in AI\" data-bi-cN=\"Eureka: Evaluating and understanding progress in AI\" target=\"_blank\">\n\t\t\t\t\t<img decoding=\"async\" class=\"w-100 display-block\" src=\"https:\/\/www.microsoft.com\/en-us\/research\/uploads\/prod\/2024\/09\/NEWEureka-2024-BlogHeroFeature-1400x788-1-66e90c195464d.jpg\" alt=\"White icons representing the Eureka Experiment Pipeline -- PromptProcessing, Inference, PromptProcessing, Inference, DataProcessing, EvalReporting -- on blue to green gradient background.\" \/>\n\t\t\t\t<\/a>\n\t\t\t<\/div>\n\t\t\t\n\t\t\t<div class=\"msr-promo__content p-3 px-5 col-12 col-md\">\n\n\t\t\t\t\t\t\t\t\t<h2 class=\"h4\">Eureka: Evaluating and understanding progress in AI<\/h2>\n\t\t\t\t\n\t\t\t\t\t\t\t\t<p class=\"large\">How can we rigorously evaluate and understand state-of-the-art progress in AI? Eureka is an open-source framework for standardizing evaluations of large foundation models, beyond single-score reporting and rankings. Learn more about the extended findings.\u00a0<\/p>\n\t\t\t\t\n\t\t\t\t\t\t\t\t<div class=\"wp-block-buttons justify-content-center justify-content-md-start\">\n\t\t\t\t\t<div class=\"wp-block-button\">\n\t\t\t\t\t\t<a href=\"https:\/\/www.microsoft.com\/en-us\/research\/blog\/eureka-evaluating-and-understanding-progress-in-ai\/\" class=\"btn btn-brand glyph-append glyph-append-chevron-right\" aria-label=\"Read more\" data-bi-cN=\"Eureka: Evaluating and understanding progress in AI\" target=\"_blank\">\n\t\t\t\t\t\t\tRead more\t\t\t\t\t\t<\/a>\n\t\t\t\t\t<\/div>\n\t\t\t\t<\/div>\n\t\t\t\t\t\t\t<\/div><!--\/.msr-promo__content-->\n\t<\/div><!--\/.msr-promo__inner-wrap-->\n\t<\/div><!--\/.msr-promo-->\n\t\n\n\n<h2 class=\"wp-block-heading\" id=\"a-promising-path-toward-advancing-radiology-and-beyond\">A promising path toward advancing radiology and beyond<\/h2>\n\n\n\n<p>When used with human oversight, GPT-4 also has the potential to transform radiology by assisting professionals in their day-to-day tasks. As we continue to explore this cutting-edge technology, there is great promise in improving our evaluation results of GPT-4 by investigating how it can be verified more thoroughly and finding ways to improve its accuracy and reliability.&nbsp;<\/p>\n\n\n\n<p>Our research highlights GPT-4\u2019s potential in advancing radiology and other medical specialties, and while our results are encouraging, they require further validation through extensive research and clinical trials. Nonetheless, the emergence of GPT-4 heralds an exciting future for radiology. It will take the entire medical community working alongside other stakeholders in technology and policy to determine the appropriate use of these tools and responsibly realize the opportunity to transform healthcare. We eagerly anticipate its transformative impact towards improving patient care and safety.<\/p>\n\n\n\n<p>Learn more about this work by visiting the <a class=\"msr-external-link glyph-append glyph-append-open-in-new-tab glyph-append-xsmall\" href=\"https:\/\/aka.ms\/maira\">Project MAIRA<span class=\"sr-only\"> (opens in new tab)<\/span><\/a> (Multimodal AI for Radiology Applications) page.<\/p>\n\n\n\n<h3 class=\"wp-block-heading\" id=\"acknowledgements\">Acknowledgements&nbsp;<\/h3>\n\n\n\n<p>We\u2019d like to thank our coauthors: Qianchu Liu,\u202f<a href=\"https:\/\/www.microsoft.com\/en-us\/research\/people\/sthyland\/\" target=\"_blank\" rel=\"noreferrer noopener\">Stephanie Hyland<\/a>,\u202f<a href=\"https:\/\/www.microsoft.com\/en-us\/research\/people\/shbannur\/\" target=\"_blank\" rel=\"noreferrer noopener\">Shruthi Bannur<\/a>,\u202f<a href=\"https:\/\/www.microsoft.com\/en-us\/research\/people\/t-kbouzid\/\" target=\"_blank\" rel=\"noreferrer noopener\">Kenza Bouzid<\/a>,\u202f<a href=\"https:\/\/www.microsoft.com\/en-us\/research\/people\/dacoelh\/\" target=\"_blank\" rel=\"noreferrer noopener\">Daniel C. Castro<\/a>,\u202fMaria Teodora Wetscherek,\u202fRobert Tinn,\u202f<a href=\"https:\/\/www.microsoft.com\/en-us\/research\/people\/harssharma\/\" target=\"_blank\" rel=\"noreferrer noopener\">Harshita Sharma<\/a>,\u202f<a href=\"https:\/\/www.microsoft.com\/en-us\/research\/people\/fperezgarcia\/\" target=\"_blank\" rel=\"noreferrer noopener\">Fernando Perez-Garcia<\/a>,\u202f<a href=\"https:\/\/www.microsoft.com\/en-us\/research\/people\/antonsc\/\" target=\"_blank\" rel=\"noreferrer noopener\">Anton Schwaighofer<\/a>,\u202fPranav Rajpurkar,\u202fSameer Tajdin Khanna,\u202f<a href=\"https:\/\/www.microsoft.com\/en-us\/research\/people\/hoifung\/\" target=\"_blank\" rel=\"noreferrer noopener\">Hoifung Poon<\/a>,\u202f<a href=\"https:\/\/www.microsoft.com\/en-us\/research\/people\/naotous\/\" target=\"_blank\" rel=\"noreferrer noopener\">Naoto Usuyama<\/a>,\u202f<a href=\"https:\/\/www.microsoft.com\/en-us\/research\/people\/anthie\/\" target=\"_blank\" rel=\"noreferrer noopener\">Anja Thieme<\/a>,\u202f<a href=\"https:\/\/www.microsoft.com\/en-us\/research\/people\/adityan\/\" target=\"_blank\" rel=\"noreferrer noopener\">Aditya V. Nori<\/a>,\u202f<a href=\"https:\/\/www.microsoft.com\/en-us\/research\/people\/ozoktay\/\" target=\"_blank\" rel=\"noreferrer noopener\">Ozan Oktay<\/a>&nbsp;<\/p>\n","protected":false},"excerpt":{"rendered":"<p>This research paper is being presented at the 2023 Conference on Empirical Methods in Natural Language Processing (opens in new tab) (EMNLP 2023), the premier conference on natural language processing and artificial intelligence. In recent years, AI has been increasingly integrated into healthcare, bringing about new areas of focus and priority, such as diagnostics, treatment [&hellip;]<\/p>\n","protected":false},"author":42735,"featured_media":984078,"comment_status":"closed","ping_status":"closed","sticky":false,"template":"","format":"standard","meta":{"msr-url-field":"","msr-podcast-episode":"","msrModifiedDate":"","msrModifiedDateEnabled":false,"ep_exclude_from_search":false,"_classifai_error":"","footnotes":""},"categories":[1],"tags":[],"research-area":[13556,13553],"msr-region":[],"msr-event-type":[],"msr-locale":[268875],"msr-post-option":[243984],"msr-impact-theme":[261673],"msr-promo-type":[],"msr-podcast-series":[],"class_list":["post-985488","post","type-post","status-publish","format-standard","has-post-thumbnail","hentry","category-research-blog","msr-research-area-artificial-intelligence","msr-research-area-medical-health-genomics","msr-locale-en_us","msr-post-option-blog-homepage-featured"],"msr_event_details":{"start":"","end":"","location":""},"podcast_url":"","podcast_episode":"","msr_research_lab":[849856],"msr_impact_theme":["Health"],"related-publications":[],"related-downloads":[],"related-videos":[],"related-academic-programs":[],"related-groups":[952050,780706],"related-projects":[978063],"related-events":[],"related-researchers":[{"type":"user_nicename","value":"Javier Alvarez-Valle","user_id":32137,"display_name":"Javier Alvarez-Valle","author_link":"<a href=\"https:\/\/www.microsoft.com\/en-us\/research\/people\/jaalvare\/\" aria-label=\"Visit the profile page for Javier Alvarez-Valle\">Javier Alvarez-Valle<\/a>","is_active":false,"last_first":"Alvarez-Valle, Javier","people_section":0,"alias":"jaalvare"},{"type":"user_nicename","value":"Matthew Lungren","user_id":42792,"display_name":"Matthew Lungren","author_link":"<a href=\"https:\/\/www.microsoft.com\/en-us\/research\/people\/mlungren\/\" aria-label=\"Visit the profile page for Matthew Lungren\">Matthew Lungren<\/a>","is_active":false,"last_first":"Lungren, Matthew","people_section":0,"alias":"mlungren"}],"msr_type":"Post","featured_image_thumbnail":"<img width=\"960\" height=\"540\" src=\"https:\/\/www.microsoft.com\/en-us\/research\/uploads\/prod\/2023\/11\/MAIRA_feature_1400x788-960x540.jpg\" class=\"img-object-cover\" alt=\"EMNLP 2023 blog hero - female radiologist analyzing an MRI image of the head\" decoding=\"async\" loading=\"lazy\" srcset=\"https:\/\/www.microsoft.com\/en-us\/research\/uploads\/prod\/2023\/11\/MAIRA_feature_1400x788-960x540.jpg 960w, https:\/\/www.microsoft.com\/en-us\/research\/uploads\/prod\/2023\/11\/MAIRA_feature_1400x788-300x169.jpg 300w, https:\/\/www.microsoft.com\/en-us\/research\/uploads\/prod\/2023\/11\/MAIRA_feature_1400x788-1024x576.jpg 1024w, https:\/\/www.microsoft.com\/en-us\/research\/uploads\/prod\/2023\/11\/MAIRA_feature_1400x788-768x432.jpg 768w, https:\/\/www.microsoft.com\/en-us\/research\/uploads\/prod\/2023\/11\/MAIRA_feature_1400x788-1066x600.jpg 1066w, https:\/\/www.microsoft.com\/en-us\/research\/uploads\/prod\/2023\/11\/MAIRA_feature_1400x788-655x368.jpg 655w, https:\/\/www.microsoft.com\/en-us\/research\/uploads\/prod\/2023\/11\/MAIRA_feature_1400x788-343x193.jpg 343w, https:\/\/www.microsoft.com\/en-us\/research\/uploads\/prod\/2023\/11\/MAIRA_feature_1400x788-240x135.jpg 240w, https:\/\/www.microsoft.com\/en-us\/research\/uploads\/prod\/2023\/11\/MAIRA_feature_1400x788-640x360.jpg 640w, https:\/\/www.microsoft.com\/en-us\/research\/uploads\/prod\/2023\/11\/MAIRA_feature_1400x788-1280x720.jpg 1280w, https:\/\/www.microsoft.com\/en-us\/research\/uploads\/prod\/2023\/11\/MAIRA_feature_1400x788.jpg 1400w\" sizes=\"(max-width: 960px) 100vw, 960px\" \/>","byline":"<a href=\"https:\/\/www.microsoft.com\/en-us\/research\/people\/jaalvare\/\" title=\"Go to researcher profile for Javier Alvarez-Valle\" aria-label=\"Go to researcher profile for Javier Alvarez-Valle\" data-bi-type=\"byline author\" data-bi-cN=\"Javier Alvarez-Valle\">Javier Alvarez-Valle<\/a> and <a href=\"https:\/\/www.microsoft.com\/en-us\/research\/people\/mlungren\/\" title=\"Go to researcher profile for Matthew Lungren\" aria-label=\"Go to researcher profile for Matthew Lungren\" data-bi-type=\"byline author\" data-bi-cN=\"Matthew Lungren\">Matthew Lungren<\/a>","formattedDate":"November 27, 2023","formattedExcerpt":"This research paper is being presented at the 2023 Conference on Empirical Methods in Natural Language Processing (opens in new tab) (EMNLP 2023), the premier conference on natural language processing and artificial intelligence. In recent years, AI has been increasingly integrated into healthcare, bringing about&hellip;","locale":{"slug":"en_us","name":"English","native":"","english":"English"},"_links":{"self":[{"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/posts\/985488"}],"collection":[{"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/posts"}],"about":[{"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/types\/post"}],"author":[{"embeddable":true,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/users\/42735"}],"replies":[{"embeddable":true,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/comments?post=985488"}],"version-history":[{"count":33,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/posts\/985488\/revisions"}],"predecessor-version":[{"id":988098,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/posts\/985488\/revisions\/988098"}],"wp:featuredmedia":[{"embeddable":true,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/media\/984078"}],"wp:attachment":[{"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/media?parent=985488"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/categories?post=985488"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/tags?post=985488"},{"taxonomy":"msr-research-area","embeddable":true,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/research-area?post=985488"},{"taxonomy":"msr-region","embeddable":true,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-region?post=985488"},{"taxonomy":"msr-event-type","embeddable":true,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-event-type?post=985488"},{"taxonomy":"msr-locale","embeddable":true,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-locale?post=985488"},{"taxonomy":"msr-post-option","embeddable":true,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-post-option?post=985488"},{"taxonomy":"msr-impact-theme","embeddable":true,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-impact-theme?post=985488"},{"taxonomy":"msr-promo-type","embeddable":true,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-promo-type?post=985488"},{"taxonomy":"msr-podcast-series","embeddable":true,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-podcast-series?post=985488"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}