{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,27]],"date-time":"2026-03-27T00:50:27Z","timestamp":1774572627620,"version":"3.50.1"},"reference-count":47,"publisher":"CSIRO Publishing","issue":"5","license":[{"start":{"date-parts":[[2026,3,2]],"date-time":"2026-03-02T00:00:00Z","timestamp":1772409600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/doi.org\/10.1071\/journalslicense"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2026,3,31]]},"abstract":"<jats:sec>\n                    <jats:title>Context<\/jats:title>\n                    <jats:p>Overcoming the disconnect between efficient Machine Learning (ML) techniques and its therapeutic applicability necessitates frameworks that provide clear, contextualized evidence.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Aims<\/jats:title>\n                    <jats:p>The present work examines the efficacy of a conceptually-enhanced framework that combines biological domain expertise, knowledge graphs, and probabilistic inference with ML predictions. We employed this innovative strategy for predicting polycystic ovary syndrome (PCOS).<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Methods<\/jats:title>\n                    <jats:p>PCOS clinical data (541 patients) was sourced from Kaggle. Clinically relevant conceptual characteristics were developed and integrated with raw data using a knowledge graph (KG) employing TransE-based semantic proximity scoring and a Bayesian network (BN) to characterize conditional dependencies. Knowledge-driven concepts were included in subsequent ML procedures, including LazyPredict for model screening, and ensemble model construction from top 10 models based on accuracy using soft-voting ensemble classifier. Patient-specific, guideline-compliant explanations were designed to accompany all model predictions for improved interpretability.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Key results<\/jats:title>\n                    <jats:p>The approach demonstrated robust predictive abilities, with the concept-integrated ensemble model demonstrating the strongest performance, with a five-fold stratified cross-validation accuracy of 93.65% (95% CI: 91.59\u201395.63%) and a ROC-AUC of 0.98 (95% CI: 0.96\u20131.00%). In addition to predicting accurately, the incorporation of features obtained from KG and BN significantly improved interpretability, with causal probabilities based on BN proving to be the most important feature. The framework facilitated patient-specific, concept-based interpretations consistent with clinical guidelines.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Conclusion<\/jats:title>\n                    <jats:p>The integration of biomedically-relevant concepts improves the interpretability of PCOS predictions while maintaining predictive performance.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Implications<\/jats:title>\n                    <jats:p>Our work proposes the use of clinician-aligned PCOS screening tools that provide transparent risk classification and informed treatment decisions.<\/jats:p>\n                  <\/jats:sec>","DOI":"10.1071\/rd25145","type":"journal-article","created":{"date-parts":[[2026,3,26]],"date-time":"2026-03-26T23:51:26Z","timestamp":1774569086000},"source":"Crossref","is-referenced-by-count":0,"title":["A concept-enhanced, knowledge graph-guided framework for interpretable PCOS prediction: a case study in explainable biomedical artificial intelligence"],"prefix":"10.1071","volume":"38","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-1214-3362","authenticated-orcid":true,"given":"Sudeepti","family":"Kulshrestha","sequence":"first","affiliation":[{"name":"AInformatics and Data Centre, Indian Council of Medical Research (ICMR) Headquarters, New Delhi, India."}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0149-0000","authenticated-orcid":true,"given":"Neeraj","family":"Kumar","sequence":"additional","affiliation":[{"name":"AInformatics and Data Centre, Indian Council of Medical Research (ICMR) Headquarters, New Delhi, India."}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5162-4863","authenticated-orcid":true,"given":"Pulkit","family":"Verma","sequence":"additional","affiliation":[{"name":"AInformatics and Data Centre, Indian Council of Medical Research (ICMR) Headquarters, New Delhi, India."}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0814-9486","authenticated-orcid":true,"given":"Kriti","family":"Sikri","sequence":"additional","affiliation":[{"name":"BDivision of Descriptive Research, Indian Council of Medical Research (ICMR) Headquarters, New Delhi, India."}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6950-5208","authenticated-orcid":true,"given":"Mayank","family":"Gangwar","sequence":"additional","affiliation":[{"name":"CClinical Studies and Trials Unit, Division of Development Research, Indian Council of Medical Research (ICMR) Headquarters, New Delhi, India."}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3958-3675","authenticated-orcid":true,"given":"Abhishek","family":"Sengupta","sequence":"additional","affiliation":[{"name":"DAmity Institute of Biotechnology, Amity University, Uttar Pradesh, Noida, India."}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3921-321X","authenticated-orcid":true,"given":"Suruchi","family":"Aggarwal","sequence":"additional","affiliation":[{"name":"EDivision of Development Research, Indian Council of Medical Research (ICMR) Headquarters, New Delhi, India."}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7317-654X","authenticated-orcid":true,"given":"Priyanka","family":"Narad","sequence":"additional","affiliation":[{"name":"EDivision of Development Research, Indian Council of Medical Research (ICMR) Headquarters, New Delhi, India."}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"67","published-online":{"date-parts":[[2026,3,27]]},"reference":[{"issue":"12","key":"2026032619512361100_R1","doi-asserted-by":"publisher","first-page":"4961","DOI":"10.1210\/jc.2009-0839","article-title":"Criteria for polycystic ovarian morphology in polycystic ovary syndrome as a function of age.","volume":"94","author":"Alsamarai","year":"2009","journal-title":"The Journal of Clinical Endocrinology & Metabolism"},{"issue":"1","key":"2026032619512361100_R2","doi-asserted-by":"publisher","DOI":"10.1186\/s12911-020-01332-6","article-title":"Explainability for artificial intelligence in healthcare: a multidisciplinary perspective.","volume":"20","author":"Amann","year":"2020","journal-title":"BMC Medical Informatics and Decision Making"},{"issue":"09","key":"2026032619512361100_R3","doi-asserted-by":"publisher","first-page":"727","DOI":"10.55489\/njcm.151020243905","article-title":"A study of psychological distress among women with polycystic ovarian syndrome in Kashmir.","volume":"15","author":"Bashir","year":"2024","journal-title":"National Journal of Community Medicine"},{"key":"2026032619512361100_R4","unstructured":"Bobby (2022) pcos-data: polycystic ovary syndrome sample dataset based on machine learning algorithm. Available at https:\/\/www.kaggle.com\/datasets\/prasadbobby\/pcosdata [accessed 28 July 2025]"},{"issue":"1","key":"2026032619512361100_R5","doi-asserted-by":"publisher","DOI":"10.1186\/s12967-024-05067-0","article-title":"Tribulations and future opportunities for artificial intelligence in precision medicine.","volume":"22","author":"Carini","year":"2024","journal-title":"Journal of Translational Medicine"},{"key":"2026032619512361100_R6","unstructured":"CDC (2024) Adult BMI categories. Available at https:\/\/www.cdc.gov\/bmi\/adult-calculator\/bmi-categories.html [accessed 29 July 2025]"},{"key":"2026032619512361100_R7","doi-asserted-by":"publisher","DOI":"10.2196\/49724","article-title":"Task-specific transformer-based language models in health care: scoping review.","volume":"12","author":"Cho","year":"2024","journal-title":"JMIR Medical Informatics"},{"issue":"1","key":"2026032619512361100_R8","doi-asserted-by":"publisher","DOI":"10.1186\/s40561-024-00292-y","article-title":"Using an adaptive learning tool to improve student performance and satisfaction in online and face-to-face education for a more personalized approach.","volume":"11","author":"Contrino","year":"2024","journal-title":"Smart Learning Environments"},{"key":"2026032619512361100_R9"},{"issue":"1","key":"2026032619512361100_R10","doi-asserted-by":"publisher","DOI":"10.1186\/s12905-025-03617-2","article-title":"Cardiometabolic markers and serum amh levels in PCOS: can AMH serve as a surrogate cardiometabolic markeR?","volume":"25","author":"Ganie","year":"2025","journal-title":"BMC Women\u2019s Health"},{"key":"2026032619512361100_R11","doi-asserted-by":"publisher","DOI":"10.1016\/j.endmts.2025.100228","article-title":"The last update on polycystic ovary syndrome(PCOS), diagnosis criteria, and novel treatment.","volume":"17","author":"Ghafari","year":"2025","journal-title":"Endocrine and Metabolic Science"},{"key":"2026032619512361100_R12","unstructured":"Google (2023) Introducing Gemini: our largest and most capable AI model. Available at https:\/\/blog.google\/technology\/ai\/google-gemini-ai\/ [accessed 2 May 2025]"},{"issue":"9","key":"2026032619512361100_R13","doi-asserted-by":"publisher","first-page":"2613","DOI":"10.1038\/s41591-024-03097-1","article-title":"Evaluation and mitigation of the limitations of large language models in clinical decision-making.","volume":"30","author":"Hager","year":"2024","journal-title":"Nature Medicine"},{"key":"2026032619512361100_R14","unstructured":"Ho J, Jain A, Abbeel P (2020) Denoising diffusion probabilistic models. arXiv. Available at https:\/\/arxiv.org\/abs\/2006.11239 [accessed 27 January 2026]"},{"key":"2026032619512361100_R15"},{"key":"2026032619512361100_R16","unstructured":"LCM Team, Barrault L, Duquenne P-A, et al. (2024) Large concept models: language modeling in a sentence representation space. arXiv. Available at https:\/\/arxiv.org\/abs\/2412.08821 [accessed 2 May 2025]"},{"issue":"2","key":"2026032619512361100_R17","doi-asserted-by":"publisher","first-page":"194","DOI":"10.1128\/CMR.15.2.194-222.2002","article-title":"Lung infections associated with cystic fibrosis.","volume":"15","author":"Lyczak","year":"2002","journal-title":"Clinical Microbiology Reviews"},{"issue":"11","key":"2026032619512361100_R18","doi-asserted-by":"publisher","DOI":"10.4329\/wjr.v17.i11.114754","article-title":"Large language models and large concept models in radiology: present challenges, future directions, and critical perspectives.","volume":"17","author":"Merchant","year":"2025","journal-title":"World Journal of Radiology"},{"key":"2026032619512361100_R19","unstructured":"Misha Bilenko (2024) Introducing Phi-3: redefining what\u2019s possible with SLMs. Available at https:\/\/azure.microsoft.com\/en-us\/blog\/introducing-phi-3-redefining-whats-possible-with-slms\/ [accessed 2 May 2025]"},{"issue":"1","key":"2026032619512361100_R20","doi-asserted-by":"publisher","DOI":"10.1002\/edm2.70022","article-title":"Exploring the predictive role of 11-oxyandrogens in diagnosing polycystic ovary syndrome.","volume":"8","author":"Mody","year":"2025","journal-title":"Endocrinology, Diabetes & Metabolism"},{"issue":"Supplement_1","key":"2026032619512361100_R21","doi-asserted-by":"publisher","first-page":"S279","DOI":"10.1093\/ofid\/ofab466.551","article-title":"Joint Modeling of EHR and CXR Data to Predict COVID-19 Deterioration.","volume":"8","author":"Mu","year":"2021","journal-title":"Open Forum Infectious Diseases"},{"issue":"12","key":"2026032619512361100_R22","doi-asserted-by":"publisher","first-page":"408","DOI":"10.6026\/97320630012408","article-title":"Net2Align: an algorithm for pairwise global alignment of biological networks.","volume":"12","author":"Narad","year":"2016","journal-title":"Bioinformation"},{"key":"2026032619512361100_R23","doi-asserted-by":"publisher","DOI":"10.1016\/j.ejrai.2025.100014","article-title":"The future of radiology: the path towards multimodal AI and superdiagnostics.","volume":"2","author":"Nensa","year":"2025","journal-title":"European Journal of Radiology Artificial Intelligence"},{"key":"2026032619512361100_R24","unstructured":"nference (2025a) nference \u2013 unlocking real-world data with clinical AI. Available at https:\/\/nference.com\/ [accessed 5 May 2025]"},{"key":"2026032619512361100_R25","unstructured":"nference (2025b) nference: augmenting intelligence, transforming health care. Biopharma Dealmakers || Advertisement Feature. Epub ahead of print 2025."},{"key":"2026032619512361100_R26","unstructured":"Pandala SR (2025) shankarpandala\/lazypredict. Python. Available at https:\/\/github.com\/shankarpandala\/lazypredict [accessed 23 April 2025]"},{"issue":"1","key":"2026032619512361100_R27","doi-asserted-by":"publisher","DOI":"10.1007\/s10462-025-11435-z","article-title":"A systematic review of generative AI: importance of industry and startup-centered perspectives, agentic AI, ethical considerations & challenges, and future directions.","volume":"59","author":"Patel","year":"2025","journal-title":"Artificial Intelligence Review"},{"key":"2026032619512361100_R46","unstructured":"pgmpy (2025) Discrete Bayesian Network. Pgmpy. Available at https:\/\/pgmpy.org\/models\/models\/bayesiannetwork.html"},{"key":"2026032619512361100_R28","unstructured":"Pipeline (n.d.) pykeen 1.11.2-dev documentation. Available at https:\/\/pykeen.readthedocs.io\/en\/latest\/reference\/pipeline.html [accessed 28 July 2025]"},{"key":"2026032619512361100_R29","unstructured":"pykeen (2025) TransE \u2014 pykeen 1.11.2-dev documentation. Available at https:\/\/pykeen.readthedocs.io\/en\/latest\/api\/pykeen.models.TransE.html [accessed 28 July 2025]"},{"issue":"21","key":"2026032619512361100_R30","doi-asserted-by":"publisher","first-page":"1981","DOI":"10.1056\/NEJMra2301725","article-title":"The current and future state of AI interpretation of medical images.","volume":"388","author":"Rajpurkar","year":"2023","journal-title":"New England Journal of Medicine"},{"key":"2026032619512361100_R31","doi-asserted-by":"crossref","unstructured":"Reese JT, Danis D, Caufield JH, et al. (2023) On the limitations of large language models in clinical diagnosis. Available at http:\/\/medrxiv.org\/lookup\/doi\/10.1101\/2023.07.13.23292613 [accessed 2 May 2025]","DOI":"10.1101\/2023.07.13.23292613"},{"issue":"1","key":"2026032619512361100_R32","doi-asserted-by":"publisher","DOI":"10.1038\/s41746-020-00323-1","article-title":"The future of digital health with federated learning.","volume":"3","author":"Rieke","year":"2020","journal-title":"npj Digital Medicine"},{"issue":"16","key":"2026032619512361100_R33","doi-asserted-by":"publisher","DOI":"10.3390\/cancers16162882","article-title":"The genetic analysis and clinical therapy in lung cancer: current advances and future directions.","volume":"16","author":"Rina","year":"2024","journal-title":"Cancers"},{"issue":"4","key":"2026032619512361100_R34","first-page":"289","article-title":"Follicle stimulating hormone (LH: FSH) ratio in polycystic ovary syndrome (PCOS) \u2013 obese vs. non- obese women.","volume":"74","author":"Saadia","year":"2020","journal-title":"Medical Archives (Sarajevo, Bosnia and Herzegovina)"},{"key":"2026032619512361100_R35","unstructured":"Science Direct \u2013 Information Fusion (2025) Knowledge graph \u2013 an overview. ScienceDirect Topics. Available at https:\/\/www.sciencedirect.com\/topics\/social-sciences\/knowledge-graph [accessed 29 July 2025]"},{"key":"2026032619512361100_R36","unstructured":"Scikit-learn.org (2025a) SimpleImputer \u2014 scikit-learn 1.7.1 documentation. Available at https:\/\/scikit-learn.org\/stable\/modules\/generated\/sklearn.impute.SimpleImputer.html [accessed 28 July 2025]"},{"key":"2026032619512361100_R37","unstructured":"Scikit-learn.org (2025b) LabelEncoder. Available at https:\/\/scikit-learn\/stable\/modules\/generated\/sklearn.preprocessing.LabelEncoder.html [accessed 28 July 2025)"},{"key":"2026032619512361100_R47","unstructured":"Scikit-Learn.org (2025c) Feature Importances with a Forest of Trees. Scikit-Learn. Available at https:\/\/scikit-learn\/stable\/auto_examples\/ensemble\/plot_forest_importances.html"},{"key":"2026032619512361100_R38"},{"key":"2026032619512361100_R39","unstructured":"SMOTE (2025) SMOTE \u2014 version 0.13.0. Available at https:\/\/imbalanced-learn.org\/stable\/references\/generated\/imblearn.over_sampling.SMOTE.html [accessed 2 June 2025)"},{"key":"2026032619512361100_R40","doi-asserted-by":"crossref","unstructured":"Tong S, Mao K, Huang Z, et al. (2024) Automating psychological hypothesis generation with AI: when large language models meet causal graph. arXiv. Epub ahead of print 2024. Available at https:\/\/doi.org\/10.1057\/s41599-024-03407-5","DOI":"10.31234\/osf.io\/7ck9m"},{"issue":"1","key":"2026032619512361100_R41","doi-asserted-by":"publisher","first-page":"3","DOI":"10.1007\/s11604-023-01474-3","article-title":"Fairness of artificial intelligence in healthcare: review and recommendations.","volume":"42","author":"Ueda","year":"2024","journal-title":"Japanese Journal of Radiology"},{"key":"2026032619512361100_R42"},{"issue":"6","key":"2026032619512361100_R43","doi-asserted-by":"publisher","first-page":"765","DOI":"10.1080\/17460441.2025.2490835","article-title":"Natural language processing in drug discovery: bridging the gap between text and therapeutics with artificial intelligence.","volume":"20","author":"Withers","year":"2025","journal-title":"Expert Opinion on Drug Discovery"},{"key":"2026032619512361100_R44","unstructured":"World Health Organization (WHO) (2025) Polycystic ovary syndrome. Available at https:\/\/www.who.int\/news-room\/fact-sheets\/detail\/polycystic-ovary-syndrome [accessed 11 April 2025]"},{"issue":"2","key":"2026032619512361100_R45","doi-asserted-by":"publisher","first-page":"130","DOI":"10.1097\/CM9.0000000000003456","article-title":"Application of large language models in disease diagnosis and treatment.","volume":"138","author":"Yang","year":"2025","journal-title":"Chinese Medical Journal"}],"container-title":["Reproduction, Fertility and Development"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/connectsci.au\/rd\/article-pdf\/doi\/10.1071\/RD25145\/1861251\/rd25145.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"syndication"},{"URL":"https:\/\/connectsci.au\/rd\/article-pdf\/doi\/10.1071\/RD25145\/1861251\/rd25145.pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,3,26]],"date-time":"2026-03-26T23:51:29Z","timestamp":1774569089000},"score":1,"resource":{"primary":{"URL":"https:\/\/connectsci.au\/rd\/article\/38\/5\/RD25145\/271874\/A-concept-enhanced-knowledge-graph-guided"}},"subtitle":[],"editor":[{"given":"Jennifer","family":"Juengel","sequence":"additional","affiliation":[],"role":[{"role":"editor","vocabulary":"crossref"}]}],"short-title":[],"issued":{"date-parts":[[2026,3,27]]},"references-count":47,"journal-issue":{"issue":"5","published-print":{"date-parts":[[2026,3,31]]}},"URL":"https:\/\/doi.org\/10.1071\/rd25145","relation":{},"ISSN":["1031-3613","1448-5990"],"issn-type":[{"value":"1031-3613","type":"print"},{"value":"1448-5990","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,3,27]]},"article-number":"RD25145"}}