{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,11,7]],"date-time":"2026-11-07T01:37:05Z","timestamp":1794015425693,"version":"4.8.0"},"reference-count":20,"publisher":"BMJ","issue":"1","license":[{"start":{"date-parts":[[2025,12,31]],"date-time":"2025-12-31T00:00:00Z","timestamp":1767139200000},"content-version":"unspecified","delay-in-days":30,"URL":"https:\/\/creativecommons.org\/licenses\/by-nc\/4.0\/"}],"funder":[{"DOI":"10.13039\/501100003196","name":"Ministero della Salute","doi-asserted-by":"publisher","award":["RC-2025-2797528"],"award-info":[{"award-number":["RC-2025-2797528"]}],"id":[{"id":"10.13039\/501100003196","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["bmj.com"],"crossmark-restriction":true},"short-container-title":["BMJ Health Care Inform"],"accepted":{"date-parts":[[2025,12,14]]},"published-print":{"date-parts":[[2025,12]]},"abstract":"<jats:sec>\n                    <jats:title>Objectives<\/jats:title>\n                    <jats:p>\n                      To assess the performance of machine learning (ML) algorithms to predict the presence of germline\n                      <jats:italic>BRCA1\/2<\/jats:italic>\n                      pathogenic variants in ovarian cancer (OC) patients based on clinical\u2013pathological features.\n                    <\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Methods<\/jats:title>\n                    <jats:p>\n                      Clinical\u2013pathological features of 648 patients with OC tested for\n                      <jats:italic>BRCA1\/2<\/jats:italic>\n                      were analysed using three supervised ML algorithms: random forest, boosting and support vector machine.\n                    <\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Results<\/jats:title>\n                    <jats:p>In the \u2018test\u2019 sample, boosting proved to be the most effective algorithm (accuracy: 84.5%; precision: 80.0%; recall: 3.1%; area under the curve (AUC): 78.8%), followed by support vector machine (accuracy: 81.4%; precision: 72.7%; recall: 27.6%; AUC: 62.3%) and random forest (accuracy: 74.4%; precision: 55.6%; recall: 14.7%; AUC: 71.3%). In the \u2018validation\u2019 sample, accuracy was 79.8% for boosting, 81.7% for support vector machine, 80.8% for random forest.<\/jats:p>\n                    <jats:p>In the most effective algorithm (boosting), family history of OC showed the highest relative influence (52.9), followed by histotype (19.5), personal history of breast cancer (BC) (17.1), age at diagnosis (8.4) and family history of BC (2.2), while Federation of Gynecology and Obstetrics stage had no influence.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Discussion<\/jats:title>\n                    <jats:p>\n                      We identified the predictive algorithm that best estimates the a priori likelihood of being a carrier of germline\n                      <jats:italic>BRCA1\/2<\/jats:italic>\n                      pathogenic variants in patients with OC. These findings support a role for ML approaches in predicting\n                      <jats:italic>BRCA1\/2<\/jats:italic>\n                      status in patients with OC, but accuracy and precision are still suboptimal for clinical use, suggesting the need for additional research.\n                    <\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Conclusions<\/jats:title>\n                    <jats:p>Results support the selection of relevant clinical features for predictive purposes, which could have significant implications for the clinical management of patients with OC.<\/jats:p>\n                  <\/jats:sec>","DOI":"10.1136\/bmjhci-2025-101751","type":"journal-article","created":{"date-parts":[[2025,12,31]],"date-time":"2025-12-31T11:35:13Z","timestamp":1767180913000},"page":"e101751","update-policy":"https:\/\/doi.org\/10.1136\/crossmarkpolicy","source":"Crossref","is-referenced-by-count":2,"title":["Machine learning prediction of germline\n                    <i>BRCA1\/2<\/i>\n                    pathogenic variants in patients with ovarian cancer"],"prefix":"10.1136","volume":"32","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-6909-2412","authenticated-orcid":false,"given":"Giovanni","family":"Innella","sequence":"first","affiliation":[{"name":"Medical Genetics Unit, IRCCS Azienda Ospedaliero-Universitaria di Bologna, Bologna, Italy"},{"name":"Department of Medical and Surgical Sciences, University of Bologna, Bologna, Italy"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Giulia","family":"Erini","sequence":"additional","affiliation":[{"name":"Department of Medical and Surgical Sciences, University of Bologna, Bologna, Italy"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Antonio","family":"De Leo","sequence":"additional","affiliation":[{"name":"Department of Experimental, Diagnostics and Specialty Medicine, University of Bologna, Bologna, Italy"},{"name":"IRCCS Azienda Ospedaliero-Universitaria di Bologna, Bologna, Italy"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Lea","family":"Godino","sequence":"additional","affiliation":[{"name":"Medical Genetics Unit, IRCCS Azienda Ospedaliero-Universitaria di Bologna, Bologna, Italy"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Luca","family":"Caramanna","sequence":"additional","affiliation":[{"name":"Department of Medical and Surgical Sciences, University of Bologna, Bologna, Italy"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Simona","family":"Ferrari","sequence":"additional","affiliation":[{"name":"Medical Genetics Unit, IRCCS Azienda Ospedaliero-Universitaria di Bologna, Bologna, Italy"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Sara","family":"Miccoli","sequence":"additional","affiliation":[{"name":"Medical Genetics Unit, IRCCS Azienda Ospedaliero-Universitaria di Bologna, Bologna, Italy"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Anna Myriam","family":"Perrone","sequence":"additional","affiliation":[{"name":"Department of Medical and Surgical Sciences, University of Bologna, Bologna, Italy"},{"name":"Division of Oncologic Gynecology, IRCCS Azienda Ospedaliero-Universitaria di Bologna, Bologna, Italy"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Claudio","family":"Zamagni","sequence":"additional","affiliation":[{"name":"Breast and Gynecological Medical Oncology, IRCCS Azienda Ospedaliero-Universitaria di Bologna, Bologna, Italy"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Pierandrea","family":"De Iaco","sequence":"additional","affiliation":[{"name":"Department of Medical and Surgical Sciences, University of Bologna, Bologna, Italy"},{"name":"Division of Oncologic Gynecology, IRCCS Azienda Ospedaliero-Universitaria di Bologna, Bologna, Italy"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Daniela","family":"Turchetti","sequence":"additional","affiliation":[{"name":"Medical Genetics Unit, IRCCS Azienda Ospedaliero-Universitaria di Bologna, Bologna, Italy"},{"name":"Department of Medical and Surgical Sciences, University of Bologna, Bologna, Italy"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Paola","family":"Rucci","sequence":"additional","affiliation":[{"name":"Department of Biomedical and Neuromotor Sciences, University of Bologna, Bologna, Italy"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"239","published-online":{"date-parts":[[2025,12,31]]},"reference":[{"key":"2025123103350840000_32.1.e101751.1","doi-asserted-by":"crossref","DOI":"10.1016\/j.heliyon.2024.e36994","article-title":"Machine-learning diagnostic models for ovarian tumors","volume":"10","author":"Sun","year":"2024","journal-title":"Heliyon"},{"key":"2025123103350840000_32.1.e101751.2","doi-asserted-by":"crossref","first-page":"66","DOI":"10.1007\/s44337-025-00260-6","article-title":"Machine learning use in early ovarian cancer detection","volume":"2","author":"Kokori","year":"2025","journal-title":"Discov Med"},{"key":"2025123103350840000_32.1.e101751.3","doi-asserted-by":"crossref","first-page":"10","DOI":"10.1186\/s13040-020-00222-x","article-title":"Deep learning-based ovarian cancer subtypes identification using multi-omics data","volume":"13","author":"Guo","year":"2020","journal-title":"BioData Min"},{"key":"2025123103350840000_32.1.e101751.4","doi-asserted-by":"crossref","first-page":"345","DOI":"10.1186\/s12911-022-02087-y","article-title":"Application of machine learning techniques for predicting survival in ovarian cancer","volume":"22","author":"Sorayaie Azar","year":"2022","journal-title":"BMC Med Inform Decis Mak"},{"key":"2025123103350840000_32.1.e101751.5","doi-asserted-by":"crossref","first-page":"113532","DOI":"10.1016\/j.ejca.2024.113532","article-title":"Prediction of prognosis and treatment response in ovarian cancer patients from histopathology images using graph deep learning: a multicenter retrospective study","volume":"199","author":"Yang","year":"2024","journal-title":"Eur J Cancer"},{"key":"2025123103350840000_32.1.e101751.6","doi-asserted-by":"crossref","first-page":"1571193","DOI":"10.3389\/fonc.2025.1571193","article-title":"Multimodal data integration with machine learning for predicting PARP inhibitor efficacy and prognosis in ovarian cancer","volume":"15","author":"Xiong","year":"2025","journal-title":"Front Oncol"},{"key":"2025123103350840000_32.1.e101751.7","doi-asserted-by":"crossref","first-page":"105300","DOI":"10.1016\/j.esmoop.2025.105300","article-title":"Development of a risk score based on clinical-pathological features to predict the presence of germline BRCA1\/2 pathogenic variants in ovarian cancer patients","volume":"10","author":"Innella","year":"2025","journal-title":"ESMO Open"},{"key":"2025123103350840000_32.1.e101751.8","unstructured":"Liu S , Wu X . n.d. Letter Re: \u2018Development of a risk score based on clinicalepathological features to predict the presence of germline BRCA1\/2 pathogenic variants in ovarian cancer patients."},{"key":"2025123103350840000_32.1.e101751.9","doi-asserted-by":"publisher","DOI":"10.1136\/jcp-2022-208753"},{"key":"2025123103350840000_32.1.e101751.10","doi-asserted-by":"publisher","DOI":"10.1038\/s41591-018-0177-5"},{"key":"2025123103350840000_32.1.e101751.11","doi-asserted-by":"crossref","first-page":"423","DOI":"10.1111\/bjd.18880","article-title":"What is AI? Applications of artificial intelligence to dermatology","volume":"183","author":"Du-Harpur","year":"2020","journal-title":"Br J Dermatol"},{"key":"2025123103350840000_32.1.e101751.12","doi-asserted-by":"crossref","first-page":"56","DOI":"10.1038\/s42256-019-0138-9","article-title":"From Local Explanations to Global Understanding with Explainable AI for Trees","volume":"2","author":"Lundberg","year":"2020","journal-title":"Nat Mach Intell"},{"key":"2025123103350840000_32.1.e101751.13","doi-asserted-by":"crossref","unstructured":"Collins GS , Moons KGM , Dhiman P , et al . TRIPOD+AI statement: updated guidance for reporting clinical prediction models that use regression or machine learning methods. BMJ 2024;385. doi:10.1136\/bmj.q902","DOI":"10.1136\/bmj.q902"},{"key":"2025123103350840000_32.1.e101751.14","doi-asserted-by":"crossref","first-page":"83","DOI":"10.1038\/s41698-023-00432-6","article-title":"Artificial intelligence in ovarian cancer histopathology: a systematic review","volume":"7","author":"Breen","year":"2023","journal-title":"NPJ Precis Oncol"},{"key":"2025123103350840000_32.1.e101751.15","doi-asserted-by":"crossref","first-page":"276","DOI":"10.1186\/s12874-023-02103-3","article-title":"Multiclass risk models for ovarian malignancy: an illustration of prediction uncertainty due to the choice of algorithm","volume":"23","author":"Ledger","year":"2023","journal-title":"BMC Med Res Methodol"},{"key":"2025123103350840000_32.1.e101751.16","doi-asserted-by":"crossref","unstructured":"Mercioni MA , Holban S . Ovarian cancer detection with popular ai algorithms: a brief review. In: Costin HN , Magjarevi\u0107 R , Petroiu GG , eds. Advances in Digital Health and Medical Bioengineering. EHB 2023. IFMBE Proceedings; 2024 doi:10.1007\/978-3-031-62502-2_54","DOI":"10.1007\/978-3-031-62502-2_54"},{"key":"2025123103350840000_32.1.e101751.17","doi-asserted-by":"crossref","DOI":"10.3390\/diagnostics15040406","article-title":"Early Diagnosis of Ovarian Cancer: A Comprehensive Review of the Advances, Challenges, and Future Directions","volume":"15","author":"Hong","year":"2025","journal-title":"Diagnostics (Basel)"},{"key":"2025123103350840000_32.1.e101751.18","doi-asserted-by":"crossref","first-page":"4093","DOI":"10.1007\/s11831-025-10268-x","article-title":"Artificial Intelligence for Ovarian Cancer Detection with Medical Images: A Review of the Last Decade (2013\u20132023)","volume":"32","author":"Naderi Yaghouti","year":"2025","journal-title":"Arch Computat Methods Eng"},{"key":"2025123103350840000_32.1.e101751.19","doi-asserted-by":"crossref","unstructured":"Acosta-Jim\u00e9nez S , Mendoza-Mendoza MM , Galv\u00e1n-Tejada CE , et al . Detection of ovarian cancer using a methodology with feature extraction and selection with genetic algorithms and machine learning. Netw Model Anal Health Inform Bioinforma 2025;14. doi:10.1007\/s13721-024-00497-8","DOI":"10.1007\/s13721-024-00497-8"},{"key":"2025123103350840000_32.1.e101751.20","doi-asserted-by":"crossref","first-page":"105762","DOI":"10.1016\/j.esmoop.2025.105762","article-title":"Response to: Re: \u2018Development of a risk score based on clinical\u2013pathological features to predict the presence of germline BRCA1\/2 pathogenic variants in ovarian cancer patients\u2019","volume":"10","author":"Innella","year":"2025","journal-title":"ESMO Open"}],"container-title":["BMJ Health &amp; Care Informatics"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/syndication.highwire.org\/content\/doi\/10.1136\/bmjhci-2025-101751","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,12,31]],"date-time":"2025-12-31T11:35:16Z","timestamp":1767180916000},"score":1,"resource":{"primary":{"URL":"https:\/\/informatics.bmj.com\/lookup\/doi\/10.1136\/bmjhci-2025-101751"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,12]]},"references-count":20,"journal-issue":{"issue":"1","published-online":{"date-parts":[[2025,12,31]]},"published-print":{"date-parts":[[2025,12]]}},"alternative-id":["10.1136\/bmjhci-2025-101751"],"URL":"https:\/\/doi.org\/10.1136\/bmjhci-2025-101751","relation":{},"ISSN":["2632-1009"],"issn-type":[{"value":"2632-1009","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,12]]}}}