{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,17]],"date-time":"2026-07-17T12:27:03Z","timestamp":1784291223101,"version":"3.55.0"},"reference-count":49,"publisher":"Frontiers Media SA","license":[{"start":{"date-parts":[[2026,1,20]],"date-time":"2026-01-20T00:00:00Z","timestamp":1768867200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"content-domain":{"domain":["frontiersin.org"],"crossmark-restriction":true},"short-container-title":["Front. Artif. Intell."],"abstract":"<jats:sec>\n                    <jats:title>Background<\/jats:title>\n                    <jats:p>Despite national screening initiatives, coverage of breast cancer screening is low, and late-stage diagnosis remains a major contributor to mortality among Indian women. Accurate, precise, and actionable prediction of socioeconomic and structural inequities in screening uptake is critical for formulating equitable cancer control policies. This study aimed to apply machine learning to predict determinants of screening uptake, estimate inequalities in uptake and their concentration indices, and identify contributing factors to inequity using concentration index decomposition across economic, educational, and caste gradients.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Methods<\/jats:title>\n                    <jats:p>Cross-sectional National Family Health Survey (NFHS-5) 2019\u20132021 data, comprising 68,526 women aged 30\u201349\u202fyears, is used for the study. Levesque\u2019s framework of healthcare access directed variable selection across approachability, acceptability, affordability, availability, and appropriateness dimensions to decide on the set of explanatory covariates. We applied three single learners\u2014Logistic Regression (LR), Na\u00efve Bayes (NB), and Decision Tree (DT)\u2014and two ensemble learners\u2014Random Forest (RF) and XGBoost (XGB)\u2014to train on balanced weighted data. Given the risk of overfitting after the synthetic minority oversampling technique (SMOTE), predictive performance was validated using 10-fold cross-validation. Five evaluation metrics were compared to select the best learner predicting the screening uptake. Inequality was measured using conventional and algorithm-based concentration indices and decomposed using algorithm-based feature importance and feature-specific inequality scores to estimate contributions to three inequality-health gradients in screening access.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Findings<\/jats:title>\n                    <jats:p>\n                      In India, remarkably low (0.9%) screening uptake with clear economic, educational, and social disparities is evident. Although Random Forest and XGBoost performed with higher predictive accuracy (96%) and explainability (AUROC\u202f=\u202f0.99), Decision Tree brought stable generalizability (mean AUROC\u202f=\u202f0.995) after 10-fold validation. Feature importance results indicate that education, autonomy, interactions with community health workers, provincial and spatial features explain most of the variability. Proximity, transport availability, hesitancy in unaccompanied care seeking, and financial constraints were access barriers with limited contribution to the variation in screening uptake. Concentration index estimates reflect a pro-rich (0.1,\n                      <jats:italic>p<\/jats:italic>\n                      \u202f&amp;lt;\u202f0.001), pro-educated (0.182,\n                      <jats:italic>p<\/jats:italic>\n                      \u202f&amp;lt;\u202f0.001), and pro-marginalized social gradient (\u22120.011,\n                      <jats:italic>p<\/jats:italic>\n                      \u202f&amp;lt;\u202f0.05). Tree-based decomposition predicts higher affordability, and education deepens pro-rich and pro-educated inequalities but can be an effective policy instrument to mitigate social position-based disparities if contributions can be increased. Access-related barriers intensified inequality across all gradients. Nevertheless, factors that enable access flatten the gradients.\n                    <\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Conclusion<\/jats:title>\n                    <jats:p>Machine learning models can improve decision making, enhancing accuracy and precision in inequity prediction for breast cancer screening uptake and revealing crucial gradients and access barriers shaping breast cancer screening uptake in India. ML-based predictions that offer higher explainability suggest that financial protection, spatial accessibility to health centers, access to education, autonomy, higher contact with community health workers, and community-based awareness programs targeting poor, less educated, socially disadvantaged middle-aged women are likely to smooth the economic, educational disparities in screening coverage, claiming a requirement of deeper investigation with respect to social gradients.<\/jats:p>\n                  <\/jats:sec>","DOI":"10.3389\/frai.2025.1729796","type":"journal-article","created":{"date-parts":[[2026,1,20]],"date-time":"2026-01-20T06:29:23Z","timestamp":1768890563000},"update-policy":"https:\/\/doi.org\/10.3389\/crossmark-policy","source":"Crossref","is-referenced-by-count":3,"title":["Predicting and identifying correlates of inequalities in breast cancer screening uptake using national level data from India"],"prefix":"10.3389","volume":"8","author":[{"given":"Aleena","family":"Tanveer","sequence":"first","affiliation":[{"name":"Institute of International Health, Charit\u00e9\u2014Universit\u00e4tsmedizin Berlin","place":["Berlin, Germany"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Raja Hashim","family":"Ali","sequence":"additional","affiliation":[{"name":"Department of Business, University of Europe for Applied Sciences","place":["Potsdam, Germany"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jitendra","family":"Majhi","sequence":"additional","affiliation":[{"name":"All India Institute of Medical Sciences, Kalyani","place":["West Bengal, India"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Moumita","family":"Mukherjee","sequence":"additional","affiliation":[{"name":"Institute of International Health, Charit\u00e9\u2014Universit\u00e4tsmedizin Berlin","place":["Berlin, Germany"]}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"1965","published-online":{"date-parts":[[2026,1,20]]},"reference":[{"key":"ref1","doi-asserted-by":"publisher","first-page":"206","DOI":"10.1177\/27551938241230761","article-title":"An examination of inter-state variation in utilization of healthcare services, associated financial burden and inequality: evidence from nationally representative survey in India","volume":"54","author":"Aashima","year":"2024","journal-title":"Int. J. Soc. Determinants Health Health Serv."},{"key":"ref2","doi-asserted-by":"publisher","first-page":"3283","DOI":"10.3390\/jcm13113283","article-title":"A systematic review to evaluate the barriers to breast Cancer screening in women with disability","volume":"13","author":"Almohammed","year":"2024","journal-title":"J. Clin. Med."},{"key":"ref3","doi-asserted-by":"publisher","first-page":"197","DOI":"10.1186\/s12911-025-03039-y","article-title":"Cervical cancer screening uptake and its associated factor in sub-Sharan Africa: a machine learning approach","volume":"25","author":"Arage","year":"2025","journal-title":"BMC Med. Inform. Decis. Mak."},{"key":"ref4","doi-asserted-by":"publisher","first-page":"e71677","DOI":"10.2196\/71677","article-title":"Identifying predictors of cervical Cancer screening uptake in sub-Saharan Africa using machine learning: cross-sectional study","volume":"11","author":"Baykemagn","year":"2025","journal-title":"JMIR Public Health Surveill."},{"key":"ref5","doi-asserted-by":"publisher","first-page":"1082884","DOI":"10.3389\/fdgth.2022.1082884","article-title":"Expanding the horizon for breast cancer screening in India through artificial intelligent technologies -a mini-review [review]","volume":"4","author":"Bhattacharya","year":"2022","journal-title":"Front. Digit. Health"},{"key":"ref6","doi-asserted-by":"publisher","first-page":"100321","DOI":"10.1016\/j.sftr.2024.100321","article-title":"Accounting for socio-economic inequalities in health to inform SDG decision making: a proof-of-concept study","volume":"8","author":"Candio","year":"2024","journal-title":"Sustainable Futures"},{"key":"ref7","doi-asserted-by":"publisher","first-page":"195","DOI":"10.1186\/s13643-024-02620-2","article-title":"A systematic review of public health interventions to address breast cancer inequalities in low- and middle-income countries","volume":"13","author":"Chanakira","year":"2024","journal-title":"Syst. Rev."},{"key":"ref8","doi-asserted-by":"publisher","first-page":"e22523","DOI":"10.1200\/JCO.2025.43.16_suppl.e22523","article-title":"Predicting the uptake of free cancer screening services in rural India using machine learning tools","volume":"43","author":"Chandar","year":"2025","journal-title":"J. Clin. Oncol."},{"key":"ref9","doi-asserted-by":"publisher","first-page":"163","DOI":"10.1186\/s12939-016-0450-5","article-title":"Access to primary health care services for indigenous peoples: a framework synthesis","volume":"15","author":"Davy","year":"2016","journal-title":"Int. J. Equity Health"},{"key":"ref10","doi-asserted-by":"publisher","first-page":"191","DOI":"10.1186\/s12939-022-01804-3","article-title":"The economics of healthcare access: a scoping review on the economic impact of healthcare access for vulnerable urban populations in low- and middle-income countries","volume":"21","author":"de Siqueira Filha","year":"2022","journal-title":"Int. J. Equity Health"},{"key":"ref11","doi-asserted-by":"publisher","first-page":"e0000720","DOI":"10.1371\/journal.pgph.0000720","article-title":"Machine learning with routine electronic medical record data to identify people at high risk of disengagement from HIV care in Tanzania","volume":"2","author":"Fahey","year":"2022","journal-title":"PLOS Glob. Public Health"},{"key":"ref12","doi-asserted-by":"publisher","first-page":"105","DOI":"10.1186\/s12939-020-01216-1","article-title":"\u201cEverything is provided free, but they are still hesitant to access healthcare services\u201d: why does the indigenous community in Attapadi, Kerala continue to experience poor access to healthcare?","volume":"19","author":"George","year":"2020","journal-title":"Int. J. Equity Health"},{"key":"ref13","doi-asserted-by":"publisher","first-page":"7303","DOI":"10.4103\/jfmpc.jfmpc_1140_22","article-title":"Status of cancer screening in India: an alarm signal from the National Family Health Survey (NFHS-5)","volume":"11","author":"Gopika","year":"2022","journal-title":"J. Family Med. Prim. Care"},{"key":"ref14","doi-asserted-by":"publisher","first-page":"7301","DOI":"10.7314\/apjcp.2013.14.12.7301","article-title":"Determinants of participation in a breast cancer screening trial in Trivandrum district, India","volume":"14","author":"Grosse Frie","year":"2013","journal-title":"Asian Pac. J. Cancer Prev."},{"key":"ref50","doi-asserted-by":"publisher","first-page":"1409054","DOI":"10.3389\/fpubh.2024.1409054","article-title":"The prevalence and predictors of clinical breast cancer screening in Sub-Saharan African countries: a multilevel analysis of Demographic Health Survey","volume":"12","author":"Hailegebireal","year":"2024","journal-title":"Front Public Health,"},{"key":"ref15","doi-asserted-by":"publisher","first-page":"e59882","DOI":"10.2196\/59882","article-title":"Analyzing geospatial and socioeconomic disparities in breast Cancer screening among populations in the United States: machine learning approach","volume":"11","author":"Hashtarkhani","year":"2025","journal-title":"JMIR Cancer"},{"key":"ref16","doi-asserted-by":"publisher","first-page":"363","DOI":"10.1016\/j.pec.2008.07.036","article-title":"Latina patient perspectives about informed treatment decision making for breast cancer","volume":"73","author":"Hawley","year":"2008","journal-title":"Patient Educ. Couns."},{"key":"ref17","doi-asserted-by":"publisher","first-page":"e0004497","DOI":"10.1371\/journal.pgph.0004497","article-title":"Use of machine learning in predicting continuity of HIV treatment in selected Nigerian states","volume":"5","author":"Ijaiya","year":"2025","journal-title":"PLOS Glob. Public Health"},{"key":"ref18","year":"2022"},{"key":"ref19","doi-asserted-by":"publisher","first-page":"1278","DOI":"10.1186\/s12885-024-13035-6","article-title":"Estimation of burden of cancer incidence and mortality in India: based on global burden of disease study 1990\u20132021","volume":"24","author":"Jena","year":"2024","journal-title":"BMC Cancer"},{"key":"ref20","doi-asserted-by":"publisher","first-page":"690","DOI":"10.1111\/ajco.14126","article-title":"Clinical breast examination: a screening tool for lower- and middle-income countries","volume":"20","author":"Khanna","year":"2024","journal-title":"Asia Pac. J. Clin. Oncol."},{"key":"ref21","doi-asserted-by":"publisher","first-page":"1154","DOI":"10.1038\/s41591-025-03502-3","article-title":"Global patterns and trends in breast cancer incidence and mortality across 185 countries","volume":"31","author":"Kim","year":"2025","journal-title":"Nat. Med."},{"key":"ref22","doi-asserted-by":"publisher","first-page":"98","DOI":"10.1007\/s40944-025-01027-8","article-title":"Determinants of cervical cancer screening in early middle-aged women in India using weighted random forest","volume":"23","author":"Kolasseri","year":"2025","journal-title":"Indian J. Gynecol. Oncol."},{"key":"ref23","doi-asserted-by":"publisher","first-page":"e0002971","DOI":"10.1371\/journal.pgph.0002971","article-title":"Factors associated with uptake of breast and cervical cancer screening among Nepalese women: evidence from Nepal demographic and health survey 2022","volume":"4","author":"Lamichhane","year":"2024","journal-title":"PLOS Glob. Public Health"},{"key":"ref24","doi-asserted-by":"publisher","first-page":"18","DOI":"10.1186\/1475-9276-12-18","article-title":"Patient-centred access to health care: conceptualising access at the interface of health systems and populations","volume":"12","author":"Levesque","year":"2013","journal-title":"Int. J. Equity Health"},{"key":"ref25","doi-asserted-by":"publisher","first-page":"1081","DOI":"10.31557\/apjcp.2020.21.4.1081","article-title":"Barriers to cancer screening uptake in women: a qualitative study from Tamil Nadu, India","volume":"21","author":"Mahalakshmi","year":"2020","journal-title":"Asian Pac. J. Cancer Prev."},{"key":"ref26","doi-asserted-by":"publisher","first-page":"e56157","DOI":"10.7759\/cureus.56157","article-title":"Effectiveness of a health educational program in enhancing breast cancer knowledge among women in rural Karnataka, South India","volume":"16","author":"Mainaz","year":"2024","journal-title":"Cureus"},{"key":"ref27","year":"2023"},{"key":"ref28","doi-asserted-by":"publisher","first-page":"337","DOI":"10.1186\/s12905-023-02504-y","article-title":"Patterns in the prevalence and wealth-based inequality of cervical cancer screening in India","volume":"23","author":"Muthuramalingam","year":"2023","journal-title":"BMC Womens Health"},{"key":"ref29","doi-asserted-by":"publisher","first-page":"324","DOI":"10.1186\/s12905-021-01464-5","article-title":"Intersectional social-economic inequalities in breast cancer screening in India: analysis of the National Family Health Survey","volume":"21","author":"Negi","year":"2021","journal-title":"BMC Womens Health"},{"key":"ref30","doi-asserted-by":"publisher","first-page":"112","DOI":"10.1177\/1536867X1601600112","article-title":"Conindex: estimation of concentration indices","volume":"16","author":"O'Donnell","year":"2016","journal-title":"Stata J."},{"key":"ref31","volume-title":"Analyzing health equity using household survey data; a guide to techniques and their implementation","author":"O'Donnell","year":"2008"},{"key":"ref32","doi-asserted-by":"publisher","first-page":"1527","DOI":"10.1186\/s12889-025-22735-y","article-title":"Barriers and contributions of rural community health workers in enabling cancer early detection and subsequent care in India: a qualitative study","volume":"25","author":"Palaniraja","year":"2025","journal-title":"BMC Public Health"},{"key":"ref33","doi-asserted-by":"publisher","first-page":"7","DOI":"10.1186\/s12905-022-02147-5","article-title":"Does women's empowerment and their socioeconomic condition affect the uptake of breast cancer screening? Findings from NFHS-5, India","volume":"23","author":"Patil","year":"2023","journal-title":"BMC Womens Health"},{"key":"ref34","doi-asserted-by":"publisher","first-page":"161","DOI":"10.1196\/annals.1425.011","article-title":"Poverty and access to health care in developing countries","volume":"1136","author":"Peters","year":"2008","journal-title":"Ann. N. Y. Acad. Sci."},{"key":"ref35","year":"2024"},{"key":"ref36","doi-asserted-by":"publisher","first-page":"129","DOI":"10.2188\/jea.JE20240065","article-title":"Regional variations and inequalities in testing for early detection of breast and cervical cancer: evidence from a nationally representative survey in India","volume":"35","author":"Rahman","year":"2025","journal-title":"J. Epidemiol."},{"key":"ref37","doi-asserted-by":"publisher","first-page":"421","DOI":"10.4103\/jehp.jehp_746_22","article-title":"Maternal health literacy and pregnancy outcomes in Afghanistan","volume":"11","author":"Rostamzadeh","year":"2022","journal-title":"J. Educ. Health Promot."},{"key":"ref38","doi-asserted-by":"publisher","first-page":"e0002475","DOI":"10.1371\/journal.pgph.0002475","article-title":"Leveraging machine learning to evaluate factors influencing vitamin D insufficiency in SLE patients: a case study from southern Bangladesh","volume":"3","author":"Saha","year":"2023","journal-title":"PLOS Glob. Public Health"},{"key":"ref39","doi-asserted-by":"publisher","first-page":"598","DOI":"10.4103\/ijmr.ijmr_1821_22","article-title":"Cancer incidence estimates for 2022 & projection for 2025: result from National Cancer Registry Programme, India","volume":"156","author":"Sathishkumar","year":"2022","journal-title":"Indian J. Med. Res."},{"key":"ref51","doi-asserted-by":"publisher","first-page":"881","DOI":"10.1186\/s12885-023-11359-3","article-title":"Recognising socio-cultural barriers while seeking early detection services for breast cancer: a study from a Universal Health Coverage setting in India","volume":"23","author":"Sawhney","year":"2023","journal-title":"BMC Cancer,"},{"key":"ref40","doi-asserted-by":"publisher","first-page":"1279","DOI":"10.1186\/s12885-022-10387-9","article-title":"Socio-economic and regional variation in breast and cervical cancer screening among Indian women of reproductive age: a study from National Family Health Survey, 2019-21","volume":"22","author":"Sen","year":"2022","journal-title":"BMC Cancer"},{"key":"ref41","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1200\/jgo.19.00048","article-title":"History of the growing burden of cancer in India: from antiquity to the 21st century","volume":"5","author":"Smith","year":"2019","journal-title":"J. Global"},{"key":"ref42","doi-asserted-by":"publisher","first-page":"509","DOI":"10.1093\/heapol\/czac104","article-title":"Barriers to cervical cancer and breast cancer screening uptake in low- and middle-income countries: a systematic review","volume":"38","author":"Srinath","year":"2023","journal-title":"Health Policy Plan."},{"key":"ref43","doi-asserted-by":"publisher","first-page":"e0005187","DOI":"10.1371\/journal.pgph.0005187","article-title":"Machine learning based prediction of low birth weight and its associated risk factors: insights from the Bangladesh demographic and health survey 2022","volume":"5","author":"Sultana","year":"2025","journal-title":"PLOS Glob. Public Health"},{"key":"ref44","doi-asserted-by":"publisher","first-page":"976","DOI":"10.1007\/s10900-013-9681-1","article-title":"Traveling towards disease: transportation barriers to health care access","volume":"38","author":"Syed","year":"2013","journal-title":"J. Community Health"},{"key":"ref45","volume-title":"A short guide to cancer screening: Increase effectiveness, maximize benefits and minimize harm","year":"2022"},{"key":"ref46","doi-asserted-by":"publisher","first-page":"302","DOI":"10.1186\/s12889-025-21334-1","article-title":"Predicting home delivery and identifying its determinants among women aged 15\u201349 years in sub-Saharan African countries using a demographic and health surveys 2016\u20132023: a machine learning algorithm","volume":"25","author":"Zegeye","year":"2025","journal-title":"BMC Public Health"},{"key":"ref47","doi-asserted-by":"publisher","first-page":"9551","DOI":"10.2147\/JIR.S488676","article-title":"Integrating machine learning and the SHapley additive exPlanations (SHAP) framework to predict lymph node metastasis in gastric cancer patients based on inflammation indices and peripheral lymphocyte subpopulations","volume":"17","author":"Zhu","year":"2024","journal-title":"J. Inflamm. Res."}],"container-title":["Frontiers in Artificial Intelligence"],"original-title":[],"link":[{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/frai.2025.1729796\/full","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,1,27]],"date-time":"2026-01-27T09:32:29Z","timestamp":1769506349000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/frai.2025.1729796\/full"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,1,20]]},"references-count":49,"alternative-id":["10.3389\/frai.2025.1729796"],"URL":"https:\/\/doi.org\/10.3389\/frai.2025.1729796","relation":{},"ISSN":["2624-8212"],"issn-type":[{"value":"2624-8212","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,1,20]]},"article-number":"1729796"}}