{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,23]],"date-time":"2026-04-23T21:24:46Z","timestamp":1776979486283,"version":"3.51.4"},"reference-count":49,"publisher":"CSIRO Publishing","issue":"16","license":[{"start":{"date-parts":[[2025,10,23]],"date-time":"2025-10-23T00:00:00Z","timestamp":1761177600000},"content-version":"vor","delay-in-days":16,"URL":"https:\/\/doi.org\/10.1071\/journalslicense"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2025,10,23]]},"abstract":"<jats:sec>\n                    <jats:title>Context<\/jats:title>\n                    <jats:p>Despite diagnostic advancements in India, the scarcity of Indian polycystic ovary syndrome (PCOS) data and varied diagnostic standards contribute to delays in PCOS detection, particularly in rural areas.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Aims<\/jats:title>\n                    <jats:p>We aim to build a predictive model based on an extensive dataset derived from Indian studies and perform risk-based stratification of samples.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Methods<\/jats:title>\n                    <jats:p>The PubMed database was queried for studies focused on the pathophysiology of PCOS in Indian women. Based on inclusion and exclusion criteria, six studies were selected. Corresponding clinical data was statistically synthesised based on study-specific baseline characteristics. The integrated dataset consisted of 11,258 samples (nPCOS\u00a0=\u00a07342; nControl\u00a0=\u00a03916) with 14 attributes: disease (PCOS vs control), age, body mass index, cholesterol, triglycerides, high-density and low-density lipoproteins, LH, FSH, testosterone, menarche age, systolic and diastolic blood pressure, and yearly menstrual cycles. After data pre-processing, missing values imputation, and feature engineering, model benchmarking was conducted using LazyPredict. LightGBM was selected for further hyperparameter tuning based on performance metrics. Lastly, feature importance analysis was performed, and predictive probabilities were utilised to categorise samples into different risk categories.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Key results<\/jats:title>\n                    <jats:p>The optimised LightGBM model achieved 96.18% accuracy, 97.51% precision, 96.65% recall, and 99.31% receiver operating characteristic area under curve (ROC-AUC) score. Further, testosterone, menstrual cycles per year, triglycerides, LH, and diastolic blood pressure were the top five key attributes in PCOS. Risk categorisation of samples demonstrated substantial alignment with real diagnoses, validating the model\u2019s clinical significance.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Conclusions<\/jats:title>\n                    <jats:p>This study introduces the first comprehensively synthesised PCOS dataset for Indian women.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Implications<\/jats:title>\n                    <jats:p>Our framework facilitates prompt risk detection, providing an adaptable methodology for decision-making in PCOS management.<\/jats:p>\n                  <\/jats:sec>","DOI":"10.1071\/rd25081","type":"journal-article","created":{"date-parts":[[2025,10,7]],"date-time":"2025-10-07T02:30:07Z","timestamp":1759804207000},"source":"Crossref","is-referenced-by-count":2,"title":["Data-driven biomarker discovery and risk profiling for polycystic ovary syndrome in Indian women using ensemble learning"],"prefix":"10.1071","volume":"37","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-5162-4863","authenticated-orcid":true,"given":"Pulkit","family":"Verma","sequence":"first","affiliation":[{"name":"AIndian Council of Medical Research (ICMR) Headquarters, New Delhi, India. Email: pulkit.verma@icmr.gov.in"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1946-8792","authenticated-orcid":true,"given":"Rekha","family":"Agarwal","sequence":"additional","affiliation":[{"name":"BAmity Institute of Information Technology (AIIT), Amity University, Noida, Uttar Pradesh, India. Email: nsindhwani@amity.edu"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Lokesh Kumar","family":"Sharma","sequence":"additional","affiliation":[{"name":"CICMR - National Institute of Occupational Health (ICMR-NIOH), Gujarat, Ahmadabad, India. Email: sharma.lk@icmr.gov.in"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Nidhi","family":"Sindwani","sequence":"additional","affiliation":[{"name":"BAmity Institute of Information Technology (AIIT), Amity University, Noida, Uttar Pradesh, India. Email: nsindhwani@amity.edu"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"67","published-online":{"date-parts":[[2025,10,7]]},"reference":[{"key":"2025110222444071000_R1","doi-asserted-by":"publisher","DOI":"10.3390\/diagnostics14192225","article-title":"SMOTE-based automated PCOS prediction using lightweight deep learning models.","volume":"14","author":"Ahmad","year":"2024","journal-title":"Diagnostics"},{"key":"2025110222444071000_R2","doi-asserted-by":"publisher","DOI":"10.1016\/j.heliyon.2023.e14518","article-title":"Exploring the dominant features and data-driven detection of polycystic ovary syndrome through modified stacking ensemble machine learning technique.","volume":"9","author":"Alam Suha","year":"2023","journal-title":"Heliyon"},{"key":"2025110222444071000_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":"2025110222444071000_R4","doi-asserted-by":"publisher","first-page":"1121","DOI":"10.1002\/ohn.1081","article-title":"Association of polycystic ovary syndrome with sensorineural hearing loss: a systematic review and meta-analysis.","volume":"172","author":"Chen","year":"2025","journal-title":"Otolaryngology\u2013Head and Neck Surgery"},{"key":"2025110222444071000_R5","doi-asserted-by":"publisher","first-page":"288","DOI":"10.1111\/ahg.12020","article-title":"The role of epistasis in the etiology of polycystic ovary syndrome among Indian women: SNP-SNP and SNP-environment interactions.","volume":"77","author":"Dasgupta","year":"2013","journal-title":"Annals of Human Genetics"},{"key":"2025110222444071000_R6","doi-asserted-by":"publisher","DOI":"10.1080\/09513590.2024.2435469","article-title":"Hyperandrogenemia impairs endometrial vitamin D receptor expression in polycystic ovary syndrome.","volume":"40","author":"D. Gungor","year":"2024","journal-title":"Gynecological Endocrinology"},{"key":"2025110222444071000_R7","doi-asserted-by":"publisher","first-page":"280","DOI":"10.1016\/j.tem.2007.07.004","article-title":"Pathophysiology and types of dyslipidemia in PCOS.","volume":"18","author":"Diamanti-Kandarakis","year":"2007","journal-title":"Trends in Endocrinology & Metabolism"},{"key":"2025110222444071000_R8","doi-asserted-by":"publisher","DOI":"10.3389\/fendo.2021.741764","article-title":"Resistance to the insulin and elevated level of androgen: a major cause of polycystic ovary syndrome.","volume":"12","author":"Ding","year":"2021","journal-title":"Frontiers in Endocrinology"},{"key":"2025110222444071000_R9","doi-asserted-by":"publisher","DOI":"10.1136\/bmjmed-2023-000548","article-title":"Polycystic ovary syndrome: pathophysiology and therapeutic opportunities.","volume":"2","author":"Dong","year":"2023","journal-title":"BMJ Medicine"},{"key":"2025110222444071000_R10"},{"key":"2025110222444071000_R12","doi-asserted-by":"publisher","first-page":"566","DOI":"10.1111\/cen.14964","article-title":"Pre-polycystic ovary syndrome and polymenorrhoea as new facets of polycystic ovary syndrome (PCOS): evidences from a single centre data set.","volume":"99","author":"Ganie","year":"2023","journal-title":"Clinical Endocrinology"},{"key":"2025110222444071000_R13","doi-asserted-by":"publisher","DOI":"10.1001\/jamanetworkopen.2024.40583","article-title":"Prevalence, phenotypes, and comorbidities of polycystic ovary syndrome among Indian women.","volume":"7","author":"Ganie","year":"2024","journal-title":"JAMA Network Open"},{"key":"2025110222444071000_R14","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":"2025110222444071000_R15","doi-asserted-by":"publisher","DOI":"10.3389\/fendo.2022.892125","article-title":"The lipid profiles in different characteristics of women with PCOS and the interaction between dyslipidemia and metabolic disorder states: a retrospective study in Chinese population.","volume":"13","author":"Guo","year":"2022","journal-title":"Frontiers in Endocrinology"},{"key":"2025110222444071000_R16","doi-asserted-by":"publisher","first-page":"512","DOI":"10.1159\/000539361","article-title":"The relationship between thyroid hormones and insulin resistance in polycystic ovary syndrome women.","volume":"89","author":"Hao","year":"2024","journal-title":"Gynecologic and Obstetric Investigation"},{"key":"2025110222444071000_R17","doi-asserted-by":"publisher","first-page":"357","DOI":"10.1038\/s41586-020-2649-2","article-title":"Array programming with NumPy.","volume":"585","author":"Harris","year":"2020","journal-title":"Nature"},{"key":"2025110222444071000_R18","doi-asserted-by":"publisher","first-page":"2907","DOI":"10.1016\/j.dsx.2019.08.001","article-title":"Assessment of PON1 activity and circulating TF levels in relation to BMI, testosterone, HOMA-IR, HDL-C, LDL-C, CHO, SOD activity and TAC in women with PCOS: an observational study.","volume":"13","author":"Jeelani","year":"2019","journal-title":"Diabetes & Metabolic Syndrome: Clinical Research & Reviews"},{"key":"2025110222444071000_R19","first-page":"208","article-title":"Endothelial progenitor cell dysfunction in polycystic ovary syndrome: implications for the genesis of cardiovascular diseases.","volume":"6","author":"Kao","year":"2013","journal-title":"International Journal of Fertility & Sterility"},{"key":"2025110222444071000_R20","doi-asserted-by":"publisher","first-page":"2587","DOI":"10.1007\/s12011-024-04435-7","article-title":"Serum selenium levels and their relationship with insulin resistance in individuals with polycystic ovary syndrome.","volume":"203","author":"Karami","year":"2025","journal-title":"Biological Trace Element Research"},{"key":"2025110222444071000_R21","doi-asserted-by":"publisher","first-page":"518","DOI":"10.1093\/humrep\/deae270","article-title":"The reproductive tract microbiome in women with polycystic ovary syndrome and across different menstrual cycle phases.","volume":"40","author":"Lee","year":"2025","journal-title":"Human Reproduction"},{"key":"2025110222444071000_R22","doi-asserted-by":"publisher","first-page":"447","DOI":"10.1016\/j.tjog.2019.05.003","article-title":"Dyslipidemia involvement in the development of polycystic ovary syndrome.","volume":"58","author":"Liu","year":"2019","journal-title":"Taiwanese Journal of Obstetrics and Gynecology"},{"key":"2025110222444071000_R23","doi-asserted-by":"crossref","unstructured":"McKinney W (2010) Data structures for statistical computing in python. In \u2018Proceedings of the 9th Python in science conference\u2019. pp. 56\u201361. (Proceedings of the Python in Science Conference) 10.25080\/Majora-92bf1922-00a","DOI":"10.25080\/Majora-92bf1922-00a"},{"key":"2025110222444071000_R24","doi-asserted-by":"publisher","DOI":"10.3390\/nu16142238","article-title":"Association between coffee consumption and polycystic ovary syndrome: an exploratory case\u2013control study.","volume":"16","author":"Meliani-Rodr\u00edguez","year":"2024","journal-title":"Nutrients"},{"key":"2025110222444071000_R25","unstructured":"Microsoft Corporation (2025) Welcome to LightGBM\u2019s documentation! \u2014 LightGBM 4.5.0 documentation. Available at https:\/\/lightgbm.readthedocs.io\/en\/stable\/ [accessed 2 July 2025]"},{"key":"2025110222444071000_R26","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"},{"key":"2025110222444071000_R27","doi-asserted-by":"publisher","DOI":"10.3390\/s25041166","article-title":"optimized machine learning for the early detection of polycystic ovary syndrome in women.","volume":"25","author":"Panjwani","year":"2025","journal-title":"Sensors"},{"key":"2025110222444071000_R28","doi-asserted-by":"publisher","first-page":"883","DOI":"10.1016\/j.fertnstert.2024.12.009","article-title":"Sexual response in women with polycystic ovary syndrome: a case-control study.","volume":"123","author":"Pastoor","year":"2025","journal-title":"Fertility and Sterility"},{"key":"2025110222444071000_R29","unstructured":"Prasoon Kottarathil (2020) Polycystic ovary syndrome (PCOS) \u2013 Kaggle Dataset. Available at https:\/\/www.kaggle.com\/datasets\/prasoonkottarathil\/polycystic-ovary-syndrome-pcos [accessed 21 July 2025]"},{"key":"2025110222444071000_R30","doi-asserted-by":"publisher","first-page":"138","DOI":"10.4103\/2230-8210.107858","article-title":"Clinical characteristics of polycystic ovary syndrome in Indian women.","volume":"17","author":"Ramanand","year":"2013","journal-title":"Indian Journal of Endocrinology and Metabolism"},{"key":"2025110222444071000_R31","doi-asserted-by":"publisher","first-page":"343","DOI":"10.1111\/jocd.12235","article-title":"The role of antimullerian hormone in the hormonal workup of women with persistent acne.","volume":"15","author":"Sardana","year":"2016","journal-title":"Journal of Cosmetic Dermatology"},{"key":"2025110222444071000_R32","doi-asserted-by":"publisher","first-page":"611","DOI":"10.5812\/ijem.4020","article-title":"Cardiovascular risk in women with PCOS.","volume":"10","author":"Scicchitano","year":"2012","journal-title":"International Journal of Endocrinology and Metabolism"},{"key":"2025110222444071000_R33","unstructured":"Scikit-learn.org (2025a) 6.4. Imputation of missing values. scikit-learn. Available at https:\/\/scikit-learn\/stable\/modules\/impute.html [accessed 21 April 2025]"},{"key":"2025110222444071000_R34","unstructured":"Scikit-learn.org (2025b) KNNImputer. scikit-learn. Available at https:\/\/scikit-learn\/stable\/modules\/generated\/sklearn.impute.KNNImputer.html [accessed 21April 2025]"},{"key":"2025110222444071000_R35","unstructured":"Scikit-optimize (2025) skopt.BayesSearchCV \u2013 scikit-optimize 0.8.1 documentation. Available at https:\/\/scikit-optimize.github.io\/stable\/modules\/generated\/skopt.BayesSearchCV.html [accessed 21 April 2025]"},{"key":"2025110222444071000_R36"},{"key":"2025110222444071000_R37","unstructured":"Shankarpandala B (2025) lazypredict: Lazy Predict help build a lot of basic models without much code and helps understand which models works better without any parameter tuning. Available at https:\/\/github.com\/shankarpandala\/lazypredict"},{"key":"2025110222444071000_R38","doi-asserted-by":"publisher","DOI":"10.1186\/s12911-024-02688-9","article-title":"Optimized polycystic ovarian disease prognosis and classification using AI based computational approaches on multi-modality data.","volume":"24","author":"Shanmugavadivel","year":"2024","journal-title":"BMC Medical Informatics and Decision Making"},{"key":"2025110222444071000_R39","doi-asserted-by":"publisher","DOI":"10.3389\/fendo.2022.951938","article-title":"Kisspeptin-neuron control of LH pulsatility and ovulation.","volume":"13","author":"Stevenson","year":"2022","journal-title":"Frontiers in Endocrinology"},{"key":"2025110222444071000_R40","doi-asserted-by":"publisher","DOI":"10.1186\/s13048-025-01621-6","article-title":"Physiopathology of polycystic ovary syndrome in endocrinology, metabolism and inflammation.","volume":"18","author":"Su","year":"2025","journal-title":"Journal of Ovarian Research"},{"key":"2025110222444071000_R41","doi-asserted-by":"publisher","DOI":"10.1371\/journal.pone.0247486","article-title":"Impact of polycystic ovary syndrome on quality of life of women in correlation to age, basal metabolic index, education and marriage.","volume":"16","author":"Tabassum","year":"2021","journal-title":"PLoS ONE"},{"key":"2025110222444071000_R42","doi-asserted-by":"publisher","first-page":"5592","DOI":"10.1210\/jc.2004-0751","article-title":"Endothelial dysfunction in young women with polycystic ovary syndrome: relationship with insulin resistance and low-grade chronic inflammation.","volume":"89","author":"Tarkun","year":"2004","journal-title":"The Journal of Clinical Endocrinology & Metabolism"},{"key":"2025110222444071000_R43","doi-asserted-by":"publisher","first-page":"60","DOI":"10.1016\/j.ejogrb.2018.02.031","article-title":"Metabolic risk assessment of Indian women with polycystic ovarian syndrome in relation to four Rotterdam criteria based phenotypes.","volume":"224","author":"Tripathy","year":"2018","journal-title":"European Journal of Obstetrics & Gynecology and Reproductive Biology"},{"key":"2025110222444071000_R11","doi-asserted-by":"publisher","first-page":"e39205","DOI":"10.1016\/j.heliyon.2024.e39205","article-title":"SmartScanPCOS: a feature-driven approach to cutting-edge prediction of polycystic ovary syndrome using machine learning and explainable artificial intelligence.","volume":"10","author":"Umaa Mahesswari","year":"2024","journal-title":"Heliyon"},{"key":"2025110222444071000_R44","doi-asserted-by":"crossref","unstructured":"Vats S, Sengupta A, Chaurasia A, Narad P (2022) Combination of expression data and predictive modelling for polycystic ovary disease and assessing risk of infertility using machine learning techniques. In \u2018Innovations in computational intelligence and computer vision, advances in intelligent systems and computing\u2019. (Eds S Roy, D Sinwar, T Perumal, A Slowik, JMRS Tavares) pp. 547\u2013555. (Springer Nature: Singapore, Singapore) 10.1007\/978-981-19-0475-2_48","DOI":"10.1007\/978-981-19-0475-2_48"},{"key":"2025110222444071000_R45","doi-asserted-by":"publisher","first-page":"261","DOI":"10.1038\/s41592-019-0686-2","article-title":"SciPy 1.0: fundamental algorithms for scientific computing in Python.","volume":"17","author":"Virtanen","year":"2020","journal-title":"Nature Methods"},{"key":"2025110222444071000_R46","doi-asserted-by":"publisher","first-page":"357","DOI":"10.1111\/aogs.15047","article-title":"Association of hemoglobin levels with metabolic traits in women with PCOS.","volume":"104","author":"Virtanen","year":"2025","journal-title":"Acta Obstetricia et Gynecologica Scandinavica"},{"key":"2025110222444071000_R47","unstructured":"World Health Organization (WHO) (2025a) Polycystic ovary syndrome. WHO - Fact sheets - Polycystic ovary syndrome. Available at https:\/\/www.who.int\/news-room\/fact-sheets\/detail\/polycystic-ovary-syndrome [accessed 11 April 2025]"},{"key":"2025110222444071000_R48","unstructured":"World Health Organization (WHO) (2025b) Malnutrition in women. WHO. Available at https:\/\/www.who.int\/data\/nutrition\/nlis\/info\/malnutrition-in-women [accessed 11 April 2025]"},{"key":"2025110222444071000_R49","doi-asserted-by":"publisher","DOI":"10.3389\/fcvm.2022.822079","article-title":"Cardiovascular risk according to body mass index in women of reproductive age with polycystic ovary syndrome: a systematic review and meta-analysis.","volume":"9","author":"Zhuang","year":"2022","journal-title":"Frontiers in Cardiovascular Medicine"}],"container-title":["Reproduction, Fertility and Development"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/connectsci.au\/rd\/article-pdf\/doi\/10.1071\/RD25081\/1716500\/rd25081.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"syndication"},{"URL":"https:\/\/connectsci.au\/rd\/article-pdf\/doi\/10.1071\/RD25081\/1716500\/rd25081.pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,11,3]],"date-time":"2025-11-03T03:44:51Z","timestamp":1762141491000},"score":1,"resource":{"primary":{"URL":"https:\/\/connectsci.au\/rd\/article\/37\/16\/RD25081\/251828\/Data-driven-biomarker-discovery-and-risk-profiling"}},"subtitle":[],"editor":[{"given":"Jennifer","family":"Juengel","sequence":"additional","affiliation":[],"role":[{"role":"editor","vocabulary":"crossref"}]}],"short-title":[],"issued":{"date-parts":[[2025,10,7]]},"references-count":49,"journal-issue":{"issue":"16","published-print":{"date-parts":[[2025,10,23]]}},"URL":"https:\/\/doi.org\/10.1071\/rd25081","relation":{},"ISSN":["1031-3613","1448-5990"],"issn-type":[{"value":"1031-3613","type":"print"},{"value":"1448-5990","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,10,7]]},"article-number":"RD25081"}}