{"672550":{"#nid":"672550","#data":{"type":"news","title":"Researchers Leverage AI to Develop Early Diagnostic Test for Ovarian Cancer","body":[{"value":"\u003Cp\u003EFor over three decades, a highly accurate early diagnostic test for ovarian cancer has eluded physicians. Now, scientists in the \u003Ca href=\u0022https:\/\/icrc.gatech.edu\u0022\u003EGeorgia Tech Integrated Cancer Research Center (ICRC)\u003C\/a\u003E have combined machine learning with information on blood metabolites to develop a new test able to detect ovarian cancer with 93 percent accuracy among samples from the team\u2019s study group.\u003C\/p\u003E\r\n\r\n\u003Cp\u003E\u003Ca href=\u0022https:\/\/biosciences.gatech.edu\/people\/john-mcdonald\u0022\u003EJohn McDonald\u003C\/a\u003E, professor emeritus in the \u003Ca href=\u0022https:\/\/biosciences.gatech.edu\u0022\u003ESchool of Biological Sciences\u003C\/a\u003E, founding director of the ICRC, and the study\u2019s corresponding author, explains that the new test\u2019s accuracy is better in detecting ovarian cancer than existing tests for women clinically classified as normal, with a particular improvement in detecting early-stage ovarian disease in that cohort.\u003C\/p\u003E\r\n\r\n\u003Cp\u003EThe team\u2019s results and methodologies are detailed\u0026nbsp;in a new paper, \u003Ca href=\u0022https:\/\/www.sciencedirect.com\/science\/article\/pii\/S0090825823016360?via%3Dihub\u0022\u003E\u201cA Personalized Probabilistic Approach to Ovarian Cancer Diagnostics,\u201d\u003C\/a\u003E published in the March 2024 online issue of the medical journal \u003Ca href=\u0022https:\/\/www.sciencedirect.com\/journal\/gynecologic-oncology\u0022\u003E\u003Cem\u003EGynecologic Oncology\u003C\/em\u003E\u003C\/a\u003E. Based on their computer models, the researchers have developed what they believe will be a more clinically useful approach to ovarian cancer diagnosis \u2014 whereby a patient\u2019s individual metabolic profile can be used to assign a more accurate probability of the presence or absence of the disease.\u003C\/p\u003E\r\n\r\n\u003Cp\u003E\u201cThis personalized, probabilistic approach to cancer diagnostics is more clinically informative and accurate than traditional binary (yes\/no) tests,\u201d McDonald says. \u201cIt represents a promising new direction in the early detection of ovarian cancer, and perhaps other cancers as well.\u201d\u003C\/p\u003E\r\n\r\n\u003Cp\u003EThe study co-authors also include \u003Ca href=\u0022https:\/\/mcdonaldlab.biology.gatech.edu\/dongjo-ban\/\u0022\u003E\u003Cstrong\u003EDongjo Ban\u003C\/strong\u003E\u003C\/a\u003E, a Bioinformatics Ph.D. student in McDonald\u2019s lab; Research Scientists \u003Cstrong\u003E\u003Ca href=\u0022https:\/\/cos.gatech.edu\/news\/postdoctoral-scientist-named-first-mccallum-early-career-fellow\u0022\u003EStephen N. Housley\u003C\/a\u003E,\u003C\/strong\u003E \u003Ca href=\u0022https:\/\/mcdonaldlab.biology.gatech.edu\/lilya-matyunina\/\u0022\u003E\u003Cstrong\u003ELilya V. Matyunina\u003C\/strong\u003E\u003C\/a\u003E, and \u003Ca href=\u0022https:\/\/mcdonaldlab.biology.gatech.edu\/l-deette-walker\/\u0022\u003E\u003Cstrong\u003EL.DeEtte (Walker) McDonald\u003C\/strong\u003E\u003C\/a\u003E; Regents\u2019 Professor \u003Ca href=\u0022https:\/\/biosciences.gatech.edu\/people\/jeffrey-skolnick\u0022\u003E\u003Cstrong\u003EJeffrey Skolnick\u003C\/strong\u003E\u003C\/a\u003E, who also serves as Mary and Maisie Gibson Chair in the School of Biological Sciences and Georgia Research Alliance Eminent Scholar in Computational Systems Biology; and two collaborating physicians: University of North Carolina Professor \u003Ca href=\u0022https:\/\/unclineberger.org\/directory\/victoria-l-bae-jump\/\u0022\u003E\u003Cstrong\u003EVictoria L. Bae-Jump\u003C\/strong\u003E \u003C\/a\u003Eand Ovarian Cancer Institute of Atlanta Founder and Chief Executive Officer\u003Cstrong\u003E \u003Ca href=\u0022https:\/\/www.ovariancancerinstitute.org\/about-us\/#leadership\u0022\u003EBenedict B. Benigno\u003C\/a\u003E\u003C\/strong\u003E.\u0026nbsp;Members of the research team are forming a startup to transfer and commercialize the technology, and plan to seek requisite trials and FDA approval for the test.\u003C\/p\u003E\r\n\r\n\u003Cp\u003E\u003Cstrong\u003ESilent killer \u003C\/strong\u003E\u003C\/p\u003E\r\n\r\n\u003Cp\u003EOvarian cancer is often referred to as the silent killer because the disease is typically asymptomatic when it first arises \u2014 and is usually not detected until later stages of development, when it is difficult to treat.\u003C\/p\u003E\r\n\r\n\u003Cp\u003EMcDonald explains that while the average five-year survival rate for late-stage ovarian cancer patients, even after treatment, is around 31 percent \u2014 but that if ovarian cancer is detected and treated early, the average five-year survival rate is more than 90 percent.\u003C\/p\u003E\r\n\r\n\u003Cp\u003E\u201cClearly, there is a tremendous need for an accurate early diagnostic test for this insidious disease,\u201d McDonald says.\u003C\/p\u003E\r\n\r\n\u003Cp\u003EAnd although development of an early detection test for ovarian cancer has been vigorously pursued for more than three decades, the development of early, accurate diagnostic tests has proven elusive. Because cancer begins on the molecular level, McDonald explains, there are multiple possible pathways capable of leading to even the same cancer type.\u003C\/p\u003E\r\n\r\n\u003Cp\u003E\u201cBecause of this high-level molecular heterogeneity among patients, the identification of a single universal diagnostic biomarker of ovarian cancer has not been possible,\u201d McDonald says. \u201cFor this reason, we opted to use a branch of artificial intelligence \u2014 machine learning \u2014 to develop an alternative probabilistic approach to the challenge of ovarian cancer diagnostics.\u201d\u003C\/p\u003E\r\n\r\n\u003Cp\u003E\u003Cstrong\u003EMetabolic profiles\u003C\/strong\u003E\u003C\/p\u003E\r\n\r\n\u003Cp\u003EGeorgia Tech co-author Dongjo Ban, whose thesis research contributed to the study, explains that \u201cbecause end-point changes on the metabolic level are known to be reflective of underlying changes operating collectively on multiple molecular levels, we chose metabolic profiles as the backbone of our analysis.\u201d\u003C\/p\u003E\r\n\r\n\u003Cp\u003E\u201cThe set of human metabolites is a collective measure of the health of cells,\u201d adds coauthor Jeffrey Skolnick, \u201cand by not arbitrary choosing any subset in advance, one lets the artificial intelligence figure out which are the key players for a given individual.\u201d\u003C\/p\u003E\r\n\r\n\u003Cp\u003EMass spectrometry can identify the presence of metabolites in the blood by detecting their mass and charge signatures. However, Ban says, the precise chemical makeup of a metabolite requires much more extensive characterization.\u003C\/p\u003E\r\n\r\n\u003Cp\u003EBan explains that because the precise chemical composition of less than seven percent of the metabolites circulating in human blood have, thus far, been chemically characterized, it is currently impossible to accurately pinpoint the specific molecular processes contributing to an individual\u0027s metabolic profile.\u003C\/p\u003E\r\n\r\n\u003Cp\u003EHowever, the research team recognized that, even without knowing the precise chemical make-up of each individual metabolite, the mere presence of different metabolites in the blood of different individuals, as detected by mass spectrometry, can be incorporated as features in the building of accurate machine learning-based predictive models (similar to the use of individual facial features in the building of facial pattern recognition algorithms).\u003C\/p\u003E\r\n\r\n\u003Cp\u003E\u201cThousands of metabolites are known to be circulating in the human bloodstream, and they can be readily and accurately detected by mass spectrometry and combined with machine learning to establish an accurate ovarian cancer diagnostic,\u201d Ban says.\u003C\/p\u003E\r\n\r\n\u003Cp\u003E\u003Cstrong\u003EA new probabilistic approach\u003C\/strong\u003E\u003C\/p\u003E\r\n\r\n\u003Cp\u003EThe researchers developed their integrative approach by combining metabolomic profiles and machine learning-based classifiers to establish a diagnostic test with 93 percent accuracy when tested on 564 women from Georgia, North Carolina, Philadelphia and Western Canada. 431 of the study participants were active ovarian cancer patients, and while the remaining 133 women in the study did not have ovarian cancer.\u003C\/p\u003E\r\n\r\n\u003Cp\u003EFurther studies have been initiated to study the possibility that the test is able to detect very early-stage disease in women displaying no clinical symptoms, McDonald says.\u003C\/p\u003E\r\n\r\n\u003Cp\u003EMcDonald anticipates a clinical future where a person with a metabolic profile that falls within a score range that makes cancer highly unlikely would only require yearly monitoring. But someone with a metabolic score that lies in a range where a majority (say, 90%) have previously been diagnosed with ovarian cancer would likely be monitored more frequently \u2014 or perhaps immediately referred for advanced screening.\u003C\/p\u003E\r\n\r\n\u003Cp\u003E\u003Cstrong\u003E\u003Cem\u003ECitation\u003C\/em\u003E\u003C\/strong\u003E:\u003Cem\u003E https:\/\/doi.org\/10.1016\/j.ygyno.2023.12.030\u003C\/em\u003E\u003C\/p\u003E\r\n\r\n\u003Cp\u003E\u003Cem\u003E\u003Cstrong\u003EFunding\u003C\/strong\u003E\u003C\/em\u003E\u003C\/p\u003E\r\n\r\n\u003Cp\u003E\u003Cem\u003EThis research was funded by the Ovarian Cancer Institute (Atlanta), the Laura Crandall Brown Foundation, the Deborah Nash Endowment Fund, Northside Hospital (Atlanta), and the Mark Light Integrated Cancer Research Student Fellowship. \u003C\/em\u003E\u003C\/p\u003E\r\n\r\n\u003Cp\u003E\u003Cem\u003E\u003Cstrong\u003EDisclosure\u003C\/strong\u003E \u003C\/em\u003E\u003C\/p\u003E\r\n\r\n\u003Cp\u003E\u003Cem\u003EStudy co-authors John McDonald, Stephen N. Housley, Jeffrey Skolnick, and Benedict B. Benigno are the co-founders of MyOncoDx, Inc., formed to support further research, technology transfer, and commercialization for the team\u2019s new clinical tool for the diagnosis of ovarian cancer.\u003C\/em\u003E\u003C\/p\u003E\r\n","summary":"","format":"limited_html"}],"field_subtitle":[{"value":"The Georgia Tech Integrated Cancer Research Center has combined machine learning with information on blood metabolites to develop a new early diagnostic test that detects ovarian cancer with 93 percent accuracy. "}],"field_summary":[{"value":"\u003Cp\u003EThe Georgia Tech Integrated Cancer Research Center has combined machine learning with information on blood metabolites to develop a new early diagnostic test that detects ovarian cancer with 93 percent accuracy. The team\u2019s results are detailed in the medical journal \u003Cem\u003EGynecologic Oncology\u003C\/em\u003E.\u003C\/p\u003E\r\n","format":"limited_html"}],"field_summary_sentence":[{"value":"The Georgia Tech Integrated Cancer Research Center has combined machine learning with information on blood metabolites to develop a new early diagnostic test that detects ovarian cancer with 93 percent accuracy. "}],"uid":"34434","created_gmt":"2024-01-29 18:36:23","changed_gmt":"2024-01-30 15:54:58","author":"Renay San Miguel","boilerplate_text":"","field_publication":"","field_article_url":"","dateline":{"date":"2024-01-29T00:00:00-05:00","iso_date":"2024-01-29T00:00:00-05:00","tz":"America\/New_York"},"extras":[],"hg_media":{"672894":{"id":"672894","type":"image","title":"Micrograph of a mucinous ovarian tumor (Photo National Institutes of Health)","body":"\u003Cp\u003EMicrograph of a mucinous ovarian tumor (Photo National Institutes of Health)\u003C\/p\u003E\r\n","created":"1706553548","gmt_created":"2024-01-29 18:39:08","changed":"1706553548","gmt_changed":"2024-01-29 18:39:08","alt":"Micrograph of a mucinous ovarian tumor (Photo National Institutes of Health)","file":{"fid":"256221","name":"Micrograph of a mucinous ovarian tumor (Photo National Institutes of Health).jpg","image_path":"\/sites\/default\/files\/2024\/01\/29\/Micrograph%20of%20a%20mucinous%20ovarian%20tumor%20%28Photo%20National%20Institutes%20of%20Health%29.jpg","image_full_path":"http:\/\/www.tlwarc.hg.gatech.edu\/\/sites\/default\/files\/2024\/01\/29\/Micrograph%20of%20a%20mucinous%20ovarian%20tumor%20%28Photo%20National%20Institutes%20of%20Health%29.jpg","mime":"image\/jpeg","size":282037,"path_740":"http:\/\/www.tlwarc.hg.gatech.edu\/sites\/default\/files\/styles\/740xx_scale\/public\/2024\/01\/29\/Micrograph%20of%20a%20mucinous%20ovarian%20tumor%20%28Photo%20National%20Institutes%20of%20Health%29.jpg?itok=uhPOY1x_"}}},"media_ids":["672894"],"related_links":[{"url":"https:\/\/www.insideprecisionmedicine.com\/topics\/oncology\/diagnosing-the-silent-killer-ai-tackles-early-stage-ovarian-cancer\/","title":"Diagnosing the \u201cSilent Killer\u201d: AI Tackles Early Stage Ovarian Cancer"},{"url":"https:\/\/www.ajmc.com\/view\/machine-learning-based-classifier-accurately-identifies-ovarian-cancer","title":"Machine Learning\u2013Based Classifier Accurately Identifies Ovarian Cancer"}],"groups":[{"id":"1278","name":"College of Sciences"},{"id":"1188","name":"Research Horizons"},{"id":"1275","name":"School of Biological Sciences"}],"categories":[{"id":"140","name":"Cancer Research"},{"id":"146","name":"Life Sciences and Biology"},{"id":"135","name":"Research"},{"id":"134","name":"Student and Faculty"}],"keywords":[{"id":"4896","name":"College of Sciences"},{"id":"166882","name":"School of Biological Sciences"},{"id":"2371","name":"John McDonald"},{"id":"193470","name":"Dongio Ban"},{"id":"11937","name":"Jeffrey Skolnick"},{"id":"193450","name":"Stephen N. Housley"},{"id":"193451","name":"Lilya Matyunina"},{"id":"193471","name":"LeDette Walker McDonald"},{"id":"2372","name":"ovarian cancer"},{"id":"2373","name":"Ovarian Cancer Institute"},{"id":"193472","name":"Benedict Benigno"},{"id":"193473","name":"diagnostic tests"},{"id":"9167","name":"machine learning"},{"id":"192250","name":"cos-microbial"},{"id":"193266","name":"cos-research"},{"id":"187423","name":"go-bio"},{"id":"192863","name":"go-ai"},{"id":"187915","name":"go-researchnews"}],"core_research_areas":[{"id":"39441","name":"Bioengineering and Bioscience"},{"id":"39501","name":"People and Technology"}],"news_room_topics":[{"id":"71891","name":"Health and Medicine"}],"event_categories":[],"invited_audience":[],"affiliations":[],"classification":[],"areas_of_expertise":[],"news_and_recent_appearances":[],"phone":[],"contact":[{"value":"\u003Cp\u003EWriter: Renay San Miguel\u003Cbr \/\u003E\r\nCommunications Officer II\/Science Writer\u003Cbr \/\u003E\r\nCollege of Sciences\u003Cbr \/\u003E\r\n404-894-5209\u003C\/p\u003E\r\n\r\n\u003Cp\u003EEditor: Jess Hunt-Ralston\u003C\/p\u003E\r\n\r\n\u003Cp\u003E\u0026nbsp;\u003C\/p\u003E\r\n","format":"limited_html"}],"email":["renay.san@cos.gatech.edu"],"slides":[],"orientation":[],"userdata":""}}}