Retrieving, reviewing, and synthesizing technical information can be time-consuming and
\nchallenging, particularly when requiring specialized expertise, as is the case of variant assessment
\nfor rare disease diagnostics. To address this challenge, we developed the Evidence Aggregator
\n(EvAgg), a generative AI tool designed for rare disease diagnosis that systematically extracts
\nrelevant information from the scientific literature for any human gene. EvAgg provides a thorough
\nand current summary of observed genetic variants and their associated clinical features, enabling
\nrapid synthesis of evidence concerning gene-disease relationships. EvAgg demonstrates strong
\nbenchmark performance, achieving 97% recall in identifying relevant papers, 92% recall in
\ndetecting instances of genetic variation within those papers, and ~80% accuracy in extracting
\nindividual case and variant-level content (e.g. zygosity, inheritance, variant type, and phenotype).
\nFurther, EvAgg complemented the process of manual literature review by identifying a substantial
\nnumber of additional relevant pieces of information. When tested with analysts in rare disease case
\nanalysis, EvAgg reduced review time by 34% (p-value < 0.002) and increased the number of papers,
\nvariants, and cases evaluated per unit time. These savings have the potential to reduce diagnostic
\nlatency and increase solve rates for challenging rare disease cases.<\/p>\n","protected":false},"excerpt":{"rendered":"
Retrieving, reviewing, and synthesizing technical information can be time-consuming and challenging, particularly when requiring specialized expertise, as is the case of variant assessment for rare disease diagnostics. To address this challenge, we developed the Evidence Aggregator (EvAgg), a generative AI tool designed for rare disease diagnosis that systematically extracts relevant information from the scientific literature […]<\/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":"","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":"2025-3-13","msr_highlight_text":"","msr_notes":"","msr_longbiography":"","msr_publicationurl":"","msr_external_url":"","msr_secondary_video_url":"","msr_conference_url":"","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":null,"footnotes":""},"msr-research-highlight":[],"research-area":[13556,13553],"msr-publication-type":[193726],"msr-publisher":[],"msr-focus-area":[],"msr-locale":[268875],"msr-post-option":[269148,269142],"msr-field-of-study":[246694,258262,246985],"msr-conference":[],"msr-journal":[],"msr-impact-theme":[],"msr-pillar":[],"class_list":["post-1150302","msr-research-item","type-msr-research-item","status-publish","hentry","msr-research-area-artificial-intelligence","msr-research-area-medical-health-genomics","msr-locale-en_us","msr-post-option-approved-for-river","msr-post-option-include-in-river","msr-field-of-study-artificial-intelligence","msr-field-of-study-medical-diagnosis","msr-field-of-study-medicine"],"msr_publishername":"","msr_edition":"","msr_affiliation":"","msr_published_date":"2025-3-13","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:\/\/www.microsoft.com\/en-us\/research\/wp-content\/uploads\/2025\/09\/Evidence-Aggregator.pdf","id":"1150303","title":"evidence-aggregator","label_id":"243109","label":0}],"msr_related_uploader":[{"type":"url","viewUrl":"false","id":"false","title":"https:\/\/www.biorxiv.org\/content\/10.1101\/2025.03.10.642480v1","label_id":"243118","label":0}],"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":1150303,"url":"https:\/\/www.microsoft.com\/en-us\/research\/wp-content\/uploads\/2025\/09\/Evidence-Aggregator.pdf"}],"msr-author-ordering":[{"type":"user_nicename","value":"Hope Twede","user_id":40747,"rest_url":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/microsoft-research\/v1\/researchers?person=Hope Twede"},{"type":"user_nicename","value":"Ashley Conard","user_id":42849,"rest_url":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/microsoft-research\/v1\/researchers?person=Ashley Conard"},{"type":"text","value":"Lynn Pais","user_id":0,"rest_url":false},{"type":"text","value":"Samantha Brye","user_id":0,"rest_url":false},{"type":"text","value":"Emily O’Heir","user_id":0,"rest_url":false},{"type":"user_nicename","value":"Greg Smith","user_id":31910,"rest_url":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/microsoft-research\/v1\/researchers?person=Greg Smith"},{"type":"user_nicename","value":"Ron Paulsen","user_id":33450,"rest_url":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/microsoft-research\/v1\/researchers?person=Ron Paulsen"},{"type":"text","value":"Christina A. Austin-Tse","user_id":0,"rest_url":false},{"type":"text","value":"Alex Bloemendal","user_id":0,"rest_url":false},{"type":"text","value":"Cas Simons","user_id":0,"rest_url":false},{"type":"user_nicename","value":"Scott Saponas","user_id":33715,"rest_url":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/microsoft-research\/v1\/researchers?person=Scott Saponas"},{"type":"text","value":"Miah Wander","user_id":0,"rest_url":false},{"type":"text","value":"Daniel G. MacArthur","user_id":0,"rest_url":false},{"type":"text","value":"Heidi Rehm","user_id":0,"rest_url":false}],"msr_impact_theme":[],"msr_research_lab":[],"msr_event":[],"msr_group":[],"msr_project":[],"publication":[],"video":[],"msr-tool":[],"msr_publication_type":"unpublished","related_content":[],"_links":{"self":[{"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-research-item\/1150302","targetHints":{"allow":["GET"]}}],"collection":[{"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-research-item"}],"about":[{"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/types\/msr-research-item"}],"version-history":[{"count":1,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-research-item\/1150302\/revisions"}],"predecessor-version":[{"id":1150304,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-research-item\/1150302\/revisions\/1150304"}],"wp:attachment":[{"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/media?parent=1150302"}],"wp:term":[{"taxonomy":"msr-research-highlight","embeddable":true,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-research-highlight?post=1150302"},{"taxonomy":"msr-research-area","embeddable":true,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/research-area?post=1150302"},{"taxonomy":"msr-publication-type","embeddable":true,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-publication-type?post=1150302"},{"taxonomy":"msr-publisher","embeddable":true,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-publisher?post=1150302"},{"taxonomy":"msr-focus-area","embeddable":true,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-focus-area?post=1150302"},{"taxonomy":"msr-locale","embeddable":true,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-locale?post=1150302"},{"taxonomy":"msr-post-option","embeddable":true,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-post-option?post=1150302"},{"taxonomy":"msr-field-of-study","embeddable":true,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-field-of-study?post=1150302"},{"taxonomy":"msr-conference","embeddable":true,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-conference?post=1150302"},{"taxonomy":"msr-journal","embeddable":true,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-journal?post=1150302"},{"taxonomy":"msr-impact-theme","embeddable":true,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-impact-theme?post=1150302"},{"taxonomy":"msr-pillar","embeddable":true,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-pillar?post=1150302"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}