Chest radiography has been a recommended procedure for patient triaging and resource management in intensive care units (ICUs) throughout the COVID-19 pandemic. The machine learning efforts to augment this workflow have been long challenged due to deficiencies in reporting, model evaluation, and failure mode analysis. To address some of those shortcomings, we model radiological features with a human-interpretable class hierarchy that aligns with the radiological decision process. Also, we propose the use of a data-driven error analysis methodology to uncover the blind spots of our model, providing further transparency on its clinical utility. For example, our experiments show that model failures highly correlate with ICU imaging conditions and with the inherent difficulty in distinguishing certain types of radiological features. Also, our hierarchical interpretation and analysis facilitates the comparison with respect to radiologists’ findings and inter-variability, which in return helps us to better assess the clinical applicability of models.<\/p>\n","protected":false},"excerpt":{"rendered":"
Chest radiography has been a recommended procedure for patient triaging and resource management in intensive care units (ICUs) throughout the COVID-19 pandemic. The machine learning efforts to augment this workflow have been long challenged due to deficiencies in reporting, model evaluation, and failure mode analysis. To address some of those shortcomings, we model radiological features […]<\/p>\n","protected":false},"featured_media":0,"template":"","meta":{"msr-url-field":"","msr-podcast-episode":"","msrModifiedDate":"","msrModifiedDateEnabled":false,"ep_exclude_from_search":false,"_classifai_error":"","msr-author-ordering":null,"msr_publishername":"","msr_publisher_other":"","msr_booktitle":"","msr_chapter":"","msr_edition":"","msr_editors":"","msr_how_published":"","msr_isbn":"","msr_issue":"","msr_journal":"","msr_number":"","msr_organization":"","msr_pages_string":"","msr_page_range_start":"","msr_page_range_end":"","msr_series":"","msr_volume":"","msr_copyright":"","msr_conference_name":"ICML 2021 Workshop on Interpretable Machine Learning in Healthcare","msr_doi":"","msr_arxiv_id":"","msr_s2_paper_id":"","msr_mag_id":"","msr_pubmed_id":"","msr_other_authors":"","msr_other_contributors":"","msr_speaker":"","msr_award":"","msr_affiliation":"","msr_institution":"","msr_host":"","msr_version":"","msr_duration":"","msr_original_fields_of_study":"","msr_release_tracker_id":"","msr_s2_match_type":"","msr_citation_count_updated":"","msr_published_date":"2021-7-1","msr_highlight_text":"","msr_notes":"","msr_longbiography":"","msr_publicationurl":"","msr_external_url":"","msr_secondary_video_url":"","msr_conference_url":"https:\/\/sites.google.com\/view\/imlh2021","msr_journal_url":"","msr_s2_pdf_url":"","msr_year":0,"msr_citation_count":0,"msr_influential_citations":0,"msr_reference_count":0,"msr_s2_match_confidence":0,"msr_microsoftintellectualproperty":true,"msr_s2_open_access":false,"msr_s2_author_ids":[],"msr_pub_ids":[],"msr_hide_image_in_river":0,"footnotes":""},"msr-research-highlight":[],"research-area":[13556,13562,13553],"msr-publication-type":[193716],"msr-publisher":[],"msr-focus-area":[],"msr-locale":[268875],"msr-post-option":[],"msr-field-of-study":[247039,246685],"msr-conference":[],"msr-journal":[],"msr-impact-theme":[],"msr-pillar":[],"class_list":["post-759400","msr-research-item","type-msr-research-item","status-publish","hentry","msr-research-area-artificial-intelligence","msr-research-area-computer-vision","msr-research-area-medical-health-genomics","msr-locale-en_us","msr-field-of-study-health-care","msr-field-of-study-machine-learning"],"msr_publishername":"","msr_edition":"","msr_affiliation":"","msr_published_date":"2021-7-1","msr_host":"","msr_duration":"","msr_version":"","msr_speaker":"","msr_other_contributors":"","msr_booktitle":"","msr_pages_string":"","msr_chapter":"","msr_isbn":"","msr_journal":"","msr_volume":"","msr_number":"","msr_editors":"","msr_series":"","msr_issue":"","msr_organization":"","msr_how_published":"","msr_notes":"","msr_highlight_text":"","msr_release_tracker_id":"","msr_original_fields_of_study":"","msr_download_urls":"","msr_external_url":"","msr_secondary_video_url":"","msr_longbiography":"","msr_microsoftintellectualproperty":1,"msr_main_download":"","msr_publicationurl":"","msr_doi":"","msr_publication_uploader":[{"type":"file","viewUrl":"https:\/\/cm-edgetun.pages.dev\/en-us\/research\/wp-content\/uploads\/2021\/07\/UHB_COVID_19_Workshop_Paper-full.pdf","id":"760684","title":"uhb_covid_19_workshop_paper-full","label_id":"243132","label":0},{"type":"url","viewUrl":"false","id":"false","title":"https:\/\/arxiv.org\/abs\/2107.06618","label_id":"252679","label":0}],"msr_related_uploader":"","msr_citation_count":0,"msr_citation_count_updated":"","msr_s2_paper_id":"","msr_influential_citations":0,"msr_reference_count":0,"msr_arxiv_id":"","msr_s2_author_ids":[],"msr_s2_open_access":false,"msr_s2_pdf_url":null,"msr_attachments":[{"id":760684,"url":"https:\/\/cm-edgetun.pages.dev\/en-us\/research\/wp-content\/uploads\/2021\/07\/UHB_COVID_19_Workshop_Paper-full.pdf"}],"msr-author-ordering":[{"type":"user_nicename","value":"Shruthi Bannur","user_id":39213,"rest_url":"https:\/\/cm-edgetun.pages.dev\/en-us\/research\/wp-json\/microsoft-research\/v1\/researchers?person=Shruthi Bannur"},{"type":"user_nicename","value":"Ozan Oktay","user_id":38706,"rest_url":"https:\/\/cm-edgetun.pages.dev\/en-us\/research\/wp-json\/microsoft-research\/v1\/researchers?person=Ozan Oktay"},{"type":"user_nicename","value":"Melanie Bernhardt","user_id":39033,"rest_url":"https:\/\/cm-edgetun.pages.dev\/en-us\/research\/wp-json\/microsoft-research\/v1\/researchers?person=Melanie Bernhardt"},{"type":"user_nicename","value":"Anton Schwaighofer","user_id":31059,"rest_url":"https:\/\/cm-edgetun.pages.dev\/en-us\/research\/wp-json\/microsoft-research\/v1\/researchers?person=Anton Schwaighofer"},{"type":"user_nicename","value":"Rajesh Jena","user_id":38350,"rest_url":"https:\/\/cm-edgetun.pages.dev\/en-us\/research\/wp-json\/microsoft-research\/v1\/researchers?person=Rajesh Jena"},{"type":"user_nicename","value":"Besmira Nushi","user_id":36975,"rest_url":"https:\/\/cm-edgetun.pages.dev\/en-us\/research\/wp-json\/microsoft-research\/v1\/researchers?person=Besmira Nushi"},{"type":"text","value":"Sharan Wadhwani","user_id":0,"rest_url":false},{"type":"user_nicename","value":"Aditya Nori","user_id":30829,"rest_url":"https:\/\/cm-edgetun.pages.dev\/en-us\/research\/wp-json\/microsoft-research\/v1\/researchers?person=Aditya Nori"},{"type":"text","value":"Kal Natarajan","user_id":0,"rest_url":false},{"type":"text","value":"Shazad Ashraf","user_id":0,"rest_url":false},{"type":"user_nicename","value":"Javier Alvarez-Valle","user_id":32137,"rest_url":"https:\/\/cm-edgetun.pages.dev\/en-us\/research\/wp-json\/microsoft-research\/v1\/researchers?person=Javier Alvarez-Valle"},{"type":"user_nicename","value":"Daniel Coelho de Castro","user_id":39811,"rest_url":"https:\/\/cm-edgetun.pages.dev\/en-us\/research\/wp-json\/microsoft-research\/v1\/researchers?person=Daniel Coelho de Castro"}],"msr_impact_theme":[],"msr_research_lab":[199561],"msr_event":[740803],"msr_group":[669339,780706,916890,1143270],"msr_project":[918249,778522,740356,169659],"publication":[],"video":[],"msr-tool":[],"msr_publication_type":"inproceedings","related_content":{"projects":[{"ID":918249,"post_title":"Treatment & diagnostics","post_name":"treatment-diagnostics","post_type":"msr-project","post_date":"2023-10-25 20:49:14","post_modified":"2023-12-13 11:17:07","post_status":"publish","permalink":"https:\/\/cm-edgetun.pages.dev\/en-us\/research\/project\/treatment-diagnostics\/","post_excerpt":"\"The T-Detect COVID Test is a novel technology that assesses the T cell immune response to COVID-19. Information and scientific data that deepen our understanding of SARS-CoV-2 remain important keys to get ahead of this global pandemic.\" In March 2020, Microsoft and Adaptive Biotechnologies expanded their existing collaboration to map and measure the immune response to multiple diseases and started applying their combined capabilities to COVID-19. In May, Adaptive started enrollment for a virtual clinical…","_links":{"self":[{"href":"https:\/\/cm-edgetun.pages.dev\/en-us\/research\/wp-json\/wp\/v2\/msr-project\/918249"}]}},{"ID":778522,"post_title":"AI for Health","post_name":"ai-for-health","post_type":"msr-project","post_date":"2023-05-16 14:26:13","post_modified":"2024-10-14 15:42:21","post_status":"publish","permalink":"https:\/\/cm-edgetun.pages.dev\/en-us\/research\/project\/ai-for-health\/","post_excerpt":"AI for Health is a philanthropic program launched by Microsoft, which aims to support nonprofits, researchers, and organizations working on global health challenges. The program provides access to artificial intelligence (AI) technology and expertise in three main areas: population health, imaging analytics, genomics & proteomics.","_links":{"self":[{"href":"https:\/\/cm-edgetun.pages.dev\/en-us\/research\/wp-json\/wp\/v2\/msr-project\/778522"}]}},{"ID":740356,"post_title":"Project InnerEye Open-Source Software for Medical Imaging AI","post_name":"project-innereye-open-source-software-for-medical-imaging-ai","post_type":"msr-project","post_date":"2021-07-01 07:14:35","post_modified":"2026-04-30 06:56:59","post_status":"publish","permalink":"https:\/\/cm-edgetun.pages.dev\/en-us\/research\/project\/project-innereye-open-source-software-for-medical-imaging-ai\/","post_excerpt":"Project InnerEye open-source tools are created and used by the medical imaging researchers at Microsoft Research. They are released at no-cost under an MIT open-source license to make them widely available for the global medical imaging community.","_links":{"self":[{"href":"https:\/\/cm-edgetun.pages.dev\/en-us\/research\/wp-json\/wp\/v2\/msr-project\/740356"}]}},{"ID":169659,"post_title":"Project InnerEye - Democratizing Medical Imaging AI","post_name":"medical-image-analysis","post_type":"msr-project","post_date":"2008-10-07 05:22:18","post_modified":"2026-04-30 06:56:43","post_status":"publish","permalink":"https:\/\/cm-edgetun.pages.dev\/en-us\/research\/project\/medical-image-analysis\/","post_excerpt":"InnerEye is a research project that uses state of the art\u00a0machine learning\u00a0technology to build innovative tools for the automatic, quantitative analysis of three-dimensional medical images.","_links":{"self":[{"href":"https:\/\/cm-edgetun.pages.dev\/en-us\/research\/wp-json\/wp\/v2\/msr-project\/169659"}]}}]},"_links":{"self":[{"href":"https:\/\/cm-edgetun.pages.dev\/en-us\/research\/wp-json\/wp\/v2\/msr-research-item\/759400","targetHints":{"allow":["GET"]}}],"collection":[{"href":"https:\/\/cm-edgetun.pages.dev\/en-us\/research\/wp-json\/wp\/v2\/msr-research-item"}],"about":[{"href":"https:\/\/cm-edgetun.pages.dev\/en-us\/research\/wp-json\/wp\/v2\/types\/msr-research-item"}],"version-history":[{"count":1,"href":"https:\/\/cm-edgetun.pages.dev\/en-us\/research\/wp-json\/wp\/v2\/msr-research-item\/759400\/revisions"}],"predecessor-version":[{"id":759403,"href":"https:\/\/cm-edgetun.pages.dev\/en-us\/research\/wp-json\/wp\/v2\/msr-research-item\/759400\/revisions\/759403"}],"wp:attachment":[{"href":"https:\/\/cm-edgetun.pages.dev\/en-us\/research\/wp-json\/wp\/v2\/media?parent=759400"}],"wp:term":[{"taxonomy":"msr-research-highlight","embeddable":true,"href":"https:\/\/cm-edgetun.pages.dev\/en-us\/research\/wp-json\/wp\/v2\/msr-research-highlight?post=759400"},{"taxonomy":"msr-research-area","embeddable":true,"href":"https:\/\/cm-edgetun.pages.dev\/en-us\/research\/wp-json\/wp\/v2\/research-area?post=759400"},{"taxonomy":"msr-publication-type","embeddable":true,"href":"https:\/\/cm-edgetun.pages.dev\/en-us\/research\/wp-json\/wp\/v2\/msr-publication-type?post=759400"},{"taxonomy":"msr-publisher","embeddable":true,"href":"https:\/\/cm-edgetun.pages.dev\/en-us\/research\/wp-json\/wp\/v2\/msr-publisher?post=759400"},{"taxonomy":"msr-focus-area","embeddable":true,"href":"https:\/\/cm-edgetun.pages.dev\/en-us\/research\/wp-json\/wp\/v2\/msr-focus-area?post=759400"},{"taxonomy":"msr-locale","embeddable":true,"href":"https:\/\/cm-edgetun.pages.dev\/en-us\/research\/wp-json\/wp\/v2\/msr-locale?post=759400"},{"taxonomy":"msr-post-option","embeddable":true,"href":"https:\/\/cm-edgetun.pages.dev\/en-us\/research\/wp-json\/wp\/v2\/msr-post-option?post=759400"},{"taxonomy":"msr-field-of-study","embeddable":true,"href":"https:\/\/cm-edgetun.pages.dev\/en-us\/research\/wp-json\/wp\/v2\/msr-field-of-study?post=759400"},{"taxonomy":"msr-conference","embeddable":true,"href":"https:\/\/cm-edgetun.pages.dev\/en-us\/research\/wp-json\/wp\/v2\/msr-conference?post=759400"},{"taxonomy":"msr-journal","embeddable":true,"href":"https:\/\/cm-edgetun.pages.dev\/en-us\/research\/wp-json\/wp\/v2\/msr-journal?post=759400"},{"taxonomy":"msr-impact-theme","embeddable":true,"href":"https:\/\/cm-edgetun.pages.dev\/en-us\/research\/wp-json\/wp\/v2\/msr-impact-theme?post=759400"},{"taxonomy":"msr-pillar","embeddable":true,"href":"https:\/\/cm-edgetun.pages.dev\/en-us\/research\/wp-json\/wp\/v2\/msr-pillar?post=759400"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}