{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,9,17]],"date-time":"2026-09-17T18:05:51Z","timestamp":1789668351433,"version":"4.0.1"},"reference-count":60,"publisher":"Public Library of Science (PLoS)","issue":"9","license":[{"start":{"date-parts":[[2026,9,17]],"date-time":"2026-09-17T00:00:00Z","timestamp":1789603200000},"content-version":"vor","delay-in-days":0,"URL":"http:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"content-domain":{"domain":["www.plosone.org"],"crossmark-restriction":false},"short-container-title":["PLoS One"],"abstract":"<jats:sec id=\"sec001\">\n                    <jats:title>Background<\/jats:title>\n                    <jats:p>Hypertension is a leading cause of cardiovascular morbidity and mortality in Bangladesh. This study examined its prevalence, risk factors, and predictive modeling using machine learning (ML) and deep learning (DL) approaches.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec id=\"sec002\">\n                    <jats:title>Method<\/jats:title>\n                    <jats:p>We analyzed cross-sectional data from the 2022 Bangladesh Demographic and Health Survey, which included 14,283 adults (\u226518 years). Prevalence was estimated, chi-square tests assessed associations, and four ML models (weighted logistic regression, random forest, extreme gradient boosting, light gradient boosting machine) and two DL models (TabNet, and multi-layer perceptron) were applied to predict hypertension risk. Model performance was evaluated using accuracy, precision, recall, specificity, F1 score, and area under the receiver operating characteristics curve and precision-recall curve.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec id=\"sec003\">\n                    <jats:title>Results<\/jats:title>\n                    <jats:p>Overall prevalence was 18.04% (95% CI: 17.2%\u201318.9%), higher among women (18.87%) than men (16.97%). The chi-square test suggests that hypertension was significantly associated with age, BMI, diabetes, wealth index, education, household size, and region (p\u2009&lt;\u20090.05). Among the machine learning and deep learning models, weighted logistic regression (WLR) achieved the highest accuracy (0.817), precision (0.444), specificity (0.981), AUC-ROC (0.751), and AUC-PR (0.357). However, WLR exhibited low recall (0.070). In contrast, the random forest (RF) model achieved the highest recall (0.687) and F1-score (0.460) on the test data, indicating greater sensitivity in identifying individuals with hypertension. Additionally, age, BMI, sex, family size, and educational level were identified as the most important predictors among the variables included in the study.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec id=\"sec004\">\n                    <jats:title>Conclusion<\/jats:title>\n                    <jats:p>Hypertension is common in Bangladesh, with higher prevalence in women and significant association with socio-demographic determinants. Although WLR demonstrated the highest accuracy, precision, specificity, and AUC-PR, its low recall limits its utility for identifying individuals with hypertension. RF may be more suitable for public health applications because of its higher recall and F1-score; however, further external validation and assessment of its clinical utility are required before implementation.<\/jats:p>\n                  <\/jats:sec>","DOI":"10.1371\/journal.pone.0358471","type":"journal-article","created":{"date-parts":[[2026,9,17]],"date-time":"2026-09-17T17:31:46Z","timestamp":1789666306000},"page":"e0358471","update-policy":"https:\/\/doi.org\/10.1371\/journal.pone.corrections_policy","source":"Crossref","is-referenced-by-count":0,"title":["Machine learning and deep learning\u2013based prediction of hypertension and analysis of its major risk factors in Bangladesh"],"prefix":"10.1371","volume":"21","author":[{"given":"Shawrab","family":"Chandra","sequence":"first","affiliation":[{"name":"University of Barishal","place":["Barishal, Bangladesh"],"department":["Department of Statistics and Data Science"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0000-9315-7338","authenticated-orcid":true,"given":"Md. Maeen","family":"Molla","sequence":"additional","affiliation":[{"name":"Pirojpur\u00a0Science and Technology University","place":["Pirojpur, Bangladesh"],"department":["Department of Statistics"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Samiul","family":"Islam","sequence":"additional","affiliation":[{"name":"University of Rajshahi","place":["Rajshahi, Bangladesh"],"department":["Department of Statistics and Data Science"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9799-9364","authenticated-orcid":true,"given":"Md. Matiur","family":"Rahaman","sequence":"additional","affiliation":[{"name":"Gopalganj Science and Technology University","place":["Gopalganj, Bangladesh"],"department":["Department of Statistics, Faculty of Science"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0279-1972","authenticated-orcid":true,"given":"Mohammad","family":"Ali","sequence":"additional","affiliation":[{"name":"Khulna University","place":["Khulna, Bangladesh"],"department":["Statistics Discipline"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5113-0054","authenticated-orcid":true,"given":"Md. Ayub","family":"Ali","sequence":"additional","affiliation":[{"name":"University of Barishal","place":["Barishal, Bangladesh"],"department":["Department of Statistics and Data Science"]}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"340","published-online":{"date-parts":[[2026,9,17]]},"reference":[{"issue":"33","key":"pone.0358471.ref001","doi-asserted-by":"crossref","first-page":"3021","DOI":"10.1093\/eurheartj\/ehy339","article-title":"2018 ESC\/ESH Guidelines for the management of arterial hypertension","volume":"39","author":"B Williams","year":"2018","journal-title":"Eur Heart J"},{"issue":"4","key":"pone.0358471.ref002","doi-asserted-by":"crossref","first-page":"223","DOI":"10.1038\/s41581-019-0244-2","article-title":"The global epidemiology of hypertension","volume":"16","author":"KT Mills","year":"2020","journal-title":"Nat Rev Nephrol"},{"issue":"9932","key":"pone.0358471.ref003","doi-asserted-by":"crossref","first-page":"1899","DOI":"10.1016\/S0140-6736(14)60685-1","article-title":"Blood pressure and incidence of twelve cardiovascular diseases: lifetime risks, healthy life-years lost, and age-specific associations in 1\u00b725 million people","volume":"383","author":"E Rapsomaniki","year":"2014","journal-title":"Lancet"},{"key":"pone.0358471.ref004","doi-asserted-by":"crossref","first-page":"285","DOI":"10.1161\/HYPERTENSIONAHA.119.14240","article-title":"High blood pressure and cardiovascular disease","author":"FD Fuchs","year":"2020","journal-title":"Hypertension"},{"issue":"7","key":"pone.0358471.ref005","doi-asserted-by":"crossref","first-page":"447","DOI":"10.1007\/s11906-014-0447-7","article-title":"Hypertension as a risk factor for heart failure","volume":"16","author":"A Kannan","year":"2014","journal-title":"Curr Hypertens Rep"},{"key":"pone.0358471.ref006","doi-asserted-by":"crossref","DOI":"10.1038\/sj.jhh.1001345","article-title":"Hypertension and coronary heart disease","author":"E Escobar","year":"2002","journal-title":"J Hum Hypertens"},{"issue":"7","key":"pone.0358471.ref007","doi-asserted-by":"crossref","first-page":"563","DOI":"10.1046\/j.1440-1681.1999.03081.x","article-title":"Hypertension mechanisms causing stroke","volume":"26","author":"BB Johansson","year":"1999","journal-title":"Clin Exp Pharmacol Physiol"},{"key":"pone.0358471.ref008","doi-asserted-by":"crossref","first-page":"207","DOI":"10.1016\/j.mcna.2016.08.001","article-title":"The kidney in hypertension","author":"H Sternlicht","year":"2017","journal-title":"Medical Clinics of North America. W.B. Saunders"},{"issue":"6","key":"pone.0358471.ref009","doi-asserted-by":"crossref","first-page":"930","DOI":"10.1161\/CIRCRESAHA.118.314487","article-title":"Type 2 diabetes and hypertension: a study on bidirectional causality","volume":"124","author":"D Sun","year":"2019","journal-title":"Circ Res"},{"key":"pone.0358471.ref010","author":"World Health Organization","year":"2023"},{"issue":"10","key":"pone.0358471.ref011","doi-asserted-by":"crossref","first-page":"1830","DOI":"10.1111\/jch.14363","article-title":"Prevalence, awareness, treatment, and control of hypertension in Bangladesh: Findings from National Demographic and Health Survey, 2017\u20132018","volume":"23","author":"MN Khan","year":"2021","journal-title":"J Clin Hypertens"},{"issue":"9455","key":"pone.0358471.ref012","doi-asserted-by":"crossref","first-page":"217","DOI":"10.1016\/S0140-6736(05)17741-1","article-title":"Global burden of hypertension: analysis of worldwide data","volume":"365","author":"PM Kearney","year":"2005","journal-title":"Lancet"},{"key":"pone.0358471.ref013","doi-asserted-by":"crossref","first-page":"10","DOI":"10.1186\/s40885-020-00143-1","article-title":"Hypertension prevalence and its trend in Bangladesh: evidence from a systematic review and meta-analysis","volume":"26","author":"MZI Chowdhury","year":"2020","journal-title":"Clin Hypertens"},{"key":"pone.0358471.ref014","article-title":"Heart Disease and Stroke Statistics-2022 Update: A Report from the American Heart Association","author":"CW Tsao","year":"2022","journal-title":"Circulation"},{"key":"pone.0358471.ref015","first-page":"1","volume-title":"Global report on hypertension 2025: High stakes - turning evidence into action","author":"WHO","year":"2025"},{"issue":"12","key":"pone.0358471.ref016","article-title":"The burden of diseases and risk factors in Bangladesh, 1990-2019: a systematic analysis for the Global Burden of Disease Study 2019","volume":"11","author":"GBD 2019 Bangladesh Burden of Disease Collaborators","year":"2023","journal-title":"Lancet Glob Health"},{"issue":"6","key":"pone.0358471.ref017","doi-asserted-by":"crossref","DOI":"10.1136\/bmjopen-2022-061467","article-title":"Cost of primary care approaches for hypertension management and risk-based cardiovascular disease prevention in Bangladesh: a HEARTS costing tool application","volume":"12","author":"MJ Husain","year":"2022","journal-title":"BMJ Open"},{"issue":"1","key":"pone.0358471.ref018","doi-asserted-by":"crossref","first-page":"1229","DOI":"10.1186\/s12889-021-11234-5","article-title":"Demographic, socioeconomic, and biological correlates of hypertension in an adult population: evidence from the Bangladesh demographic and health survey 2017-18","volume":"21","author":"A Iqbal","year":"2021","journal-title":"BMC Public Health"},{"issue":"12","key":"pone.0358471.ref019","article-title":"Changes in prevalence and risk factors of hypertension among adults in Bangladesh: an analysis of two waves of nationally representative surveys","volume":"16","author":"MAB Chowdhury","year":"2021","journal-title":"PLoS One"},{"issue":"5","key":"pone.0358471.ref020","doi-asserted-by":"crossref","first-page":"1199","DOI":"10.1161\/01.HYP.37.5.1199","article-title":"Gender differences in the regulation of blood pressure","volume":"37","author":"JF Reckelhoff","year":"2001","journal-title":"Hypertension"},{"key":"pone.0358471.ref021","doi-asserted-by":"crossref","first-page":"869","DOI":"10.1161\/01.HYP.26.6.869","article-title":"Diabetes mellitus and associated hypertension, vascular disease, and nephropathy. An update","volume":"26","author":"JR Sowers","year":"1995","journal-title":"Hypertension"},{"issue":"6","key":"pone.0358471.ref022","doi-asserted-by":"crossref","first-page":"816","DOI":"10.2105\/AJPH.82.6.816","article-title":"Socioeconomic status and health: how education, income, and occupation contribute to risk factors for cardiovascular disease","volume":"82","author":"MA Winkleby","year":"1992","journal-title":"Am J Public Health"},{"issue":"6","key":"pone.0358471.ref023","doi-asserted-by":"crossref","first-page":"1012","DOI":"10.1161\/HYPERTENSIONAHA.107.093336","article-title":"Hypertension in sub-saharan Africa: a systematic review","volume":"50","author":"J Addo","year":"2007","journal-title":"Hypertension"},{"issue":"9841","key":"pone.0358471.ref024","doi-asserted-by":"crossref","first-page":"611","DOI":"10.1016\/S0140-6736(12)60861-7","article-title":"Hypertension in developing countries","volume":"380","author":"MM Ibrahim","year":"2012","journal-title":"Lancet"},{"issue":"1","key":"pone.0358471.ref025","doi-asserted-by":"crossref","first-page":"131","DOI":"10.1016\/j.pcl.2013.09.011","article-title":"Hypertension in the teenager","volume":"61","author":"EI Anyaegbu","year":"2014","journal-title":"Pediatr Clin North Am"},{"key":"pone.0358471.ref026","doi-asserted-by":"crossref","first-page":"100912","DOI":"10.1016\/j.cegh.2021.100912","article-title":"Prevalence of and factors associated with prehypertension and hypertension among Bangladeshi young adults: An analysis of the Bangladesh Demographic and Health Survey 2017\u201318","volume":"12","author":"MA Rahman","year":"2021","journal-title":"Clin Epidemiol Glob Health"},{"issue":"7","key":"pone.0358471.ref027","article-title":"Association of overweight and obesity with hypertension, diabetes and comorbidity among adults in Bangladesh: evidence from nationwide Demographic and Health Survey 2017-2018 data","volume":"12","author":"S Das","year":"2022","journal-title":"BMJ Open"},{"issue":"5","key":"pone.0358471.ref028","doi-asserted-by":"crossref","DOI":"10.1371\/journal.pone.0267243","article-title":"Prevalence, trends and associated factors of hypertension and diabetes mellitus in Bangladesh: evidence from BHDS 2011 and 2017\u201318","volume":"17","author":"NJ Sathi","year":"2022","journal-title":"PLoS One"},{"key":"pone.0358471.ref029","doi-asserted-by":"crossref","first-page":"22","DOI":"10.1186\/s12872-016-0197-3","article-title":"Hypertension among adults in Bangladesh: evidence from a national cross-sectional survey","volume":"16","author":"MAB Chowdhury","year":"2016","journal-title":"BMC Cardiovasc Disord"},{"issue":"10","key":"pone.0358471.ref030","doi-asserted-by":"crossref","DOI":"10.1371\/journal.pone.0292989","article-title":"Prevalence and determinants of hypertension among older adults: a comparative analysis of the 6th and 8th national health surveys of Bangladesh","volume":"18","author":"PK Ghosh","year":"2023","journal-title":"PLoS One"},{"issue":"3","key":"pone.0358471.ref031","doi-asserted-by":"crossref","first-page":"877","DOI":"10.1016\/j.dsx.2021.03.035","article-title":"Machine learning algorithm for characterizing risks of hypertension, at an early stage in Bangladesh","volume":"15","author":"MM Islam","year":"2021","journal-title":"Diabetes Metab Syndr"},{"key":"pone.0358471.ref032","volume-title":"Bangladesh Demographic and Health Survey 2022: Key Indicators Report","author":"NIPORT NI of PR and T, ICF","year":"2022"},{"key":"pone.0358471.ref033","volume-title":"Definition and diagnosis of diabetes mellitus and intermediate hyperglycaemia: report of a WHO\/IDF consultation [Internet]","author":"WHO, IDF","year":"2006"},{"key":"pone.0358471.ref034","first-page":"1","article-title":"Imbalanced learning: Foundations, algorithms, and applications. Imbalanced Learning: Foundations, Algorithms, and Applications","author":"H He","year":"2013"},{"issue":"15","key":"pone.0358471.ref035","doi-asserted-by":"crossref","DOI":"10.1016\/j.heliyon.2024.e35040","article-title":"A comprehensive study of coefficient signs in weighted logistic regression","volume":"10","author":"G Zeng","year":"2024","journal-title":"Heliyon"},{"issue":"13","key":"pone.0358471.ref036","doi-asserted-by":"crossref","first-page":"3257","DOI":"10.1080\/02664763.2021.1939662","article-title":"Improving logistic regression on the imbalanced data by a novel penalized log-likelihood function","volume":"49","author":"L Zhang","year":"2021","journal-title":"J Appl Stat"},{"issue":"1","key":"pone.0358471.ref037","doi-asserted-by":"crossref","first-page":"5","DOI":"10.1023\/A:1010933404324","article-title":"Random forests","volume":"45","author":"L Breiman","year":"2001","journal-title":"Mach Learn"},{"key":"pone.0358471.ref038","article-title":"Lightgbm: a highly efficient gradient boosting decision tree","volume":"30","author":"G Ke","year":"2017","journal-title":"Adv Neural Inf Process Syst"},{"key":"pone.0358471.ref039","doi-asserted-by":"crossref","first-page":"785","DOI":"10.1145\/2939672.2939785","article-title":"Xgboost: A scalable tree boosting system.","volume-title":"Proceedings of the 22nd acm sigkdd international conference on knowledge discovery and data mining","author":"T Chen","year":"2016"},{"key":"pone.0358471.ref040","first-page":"6679","article-title":"Tabnet: Attentive interpretable tabular learning.","volume-title":"Proceedings of the AAAI conference on artificial intelligence","author":"S\u00d6 Arik","year":"2021"},{"key":"pone.0358471.ref041","volume-title":"Deep learning","author":"I Goodfellow","year":"2016"},{"key":"pone.0358471.ref042","article-title":"Evaluation: from precision, recall and F-measure to ROC, informedness, markedness and correlation","author":"DMW Powers","year":"2020","journal-title":"arXiv preprint arXiv:201016061"},{"issue":"8","key":"pone.0358471.ref043","doi-asserted-by":"crossref","first-page":"861","DOI":"10.1016\/j.patrec.2005.10.010","article-title":"An introduction to ROC analysis","volume":"27","author":"T Fawcett","year":"2006","journal-title":"Pattern Recogn Lett"},{"issue":"4","key":"pone.0358471.ref044","doi-asserted-by":"crossref","first-page":"427","DOI":"10.1016\/j.ipm.2009.03.002","article-title":"A systematic analysis of performance measures for classification tasks","volume":"45","author":"M Sokolova","year":"2009","journal-title":"Inf Process Manag"},{"issue":"7","key":"pone.0358471.ref045","doi-asserted-by":"crossref","first-page":"1145","DOI":"10.1016\/S0031-3203(96)00142-2","article-title":"The use of the area under the ROC curve in the evaluation of machine learning algorithms","volume":"30","author":"AP Bradley","year":"1997","journal-title":"Pattern Recognit"},{"key":"pone.0358471.ref046","doi-asserted-by":"crossref","first-page":"109","DOI":"10.1007\/978-3-030-89010-0_4","article-title":"Overfitting, model tuning, and evaluation of prediction performance","author":"OA Montesinos L\u00f3pez","year":"2022","journal-title":"Multivariate statistical machine learning methods for genomic prediction"},{"key":"pone.0358471.ref047","volume-title":"Bangladesh demographic and health survey 2011","author":"NIPORT NI of PR and T, ICF","year":"2013"},{"key":"pone.0358471.ref048","volume-title":"Bangladesh Demographic and Health Survey 2017-18","author":"NIPORT NI of PR and T, ICF","year":"2020"},{"key":"pone.0358471.ref049","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1109\/ICEE49691.2020.9249935","article-title":"Heart Disease prediction using MLP and LSTM models.","volume-title":"2020 international conference on electrical engineering (ICEE)","author":"M Djerioui","year":"2020"},{"key":"pone.0358471.ref050","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1109\/EICT48899.2019.9068755","article-title":"Prediction of heart disease using multi-layer perceptron neural network and support vector machine.","volume-title":"2019 4th International conference on electrical information and communication technology (EICT)","author":"M Nahiduzzaman","year":"2019"},{"key":"pone.0358471.ref051","first-page":"21","article-title":"Thyroid Disease Prediction Using a Novel Classification Enhancing MLP and Random Forest Algorithms","author":"D Akila","year":"2023","journal-title":"International Conference on Mathematical Modeling and Computational Science. Springer Nature Singapore"},{"issue":"2","key":"pone.0358471.ref052","doi-asserted-by":"crossref","first-page":"183","DOI":"10.1177\/1010539510392743","article-title":"Sociodemographic differentials of selected noncommunicable diseases risk factors among adults in Matlab, Bangladesh: findings from a WHO STEPS survey","volume":"23","author":"A Razzaque","year":"2011","journal-title":"Asia Pac J Public Health"},{"issue":"5","key":"pone.0358471.ref053","doi-asserted-by":"crossref","DOI":"10.1371\/journal.pone.0127954","article-title":"Are the rates of hypertension and diabetes higher in people from lower socioeconomic status in Bangladesh? Results from a nationally representative survey","volume":"10","author":"MI Tareque","year":"2015","journal-title":"PLoS One"},{"key":"pone.0358471.ref054","volume-title":"Household Income and Expenditure Survey (HIES) 2022","author":"(BBS) BB of S","year":"2023"},{"issue":"5","key":"pone.0358471.ref055","doi-asserted-by":"crossref","DOI":"10.1371\/journal.pone.0233754","article-title":"Prevalence and associated risk factors of general and abdominal obesity in rural and urban women in Bangladesh","volume":"15","author":"F Islam","year":"2020","journal-title":"PLoS One"},{"issue":"4","key":"pone.0358471.ref056","doi-asserted-by":"crossref","first-page":"2395","DOI":"10.3892\/etm.2016.3667","article-title":"Obesity and hypertension","volume":"12","author":"S-Z Jiang","year":"2016","journal-title":"Exp Ther Med"},{"key":"pone.0358471.ref057","doi-asserted-by":"crossref","first-page":"28","DOI":"10.1186\/s40885-019-0134-8","article-title":"Association between body mass index (BMI) and hypertension in south Asian population: evidence from nationally-representative surveys","volume":"25","author":"FB Hossain","year":"2019","journal-title":"Clin Hypertens"},{"issue":"3","key":"pone.0358471.ref058","doi-asserted-by":"crossref","first-page":"363","DOI":"10.1001\/jamainternmed.2017.8094","article-title":"Diabetes and hypertension in India: a nationally representative study of 1.3 million adults","volume":"178","author":"P Geldsetzer","year":"2018","journal-title":"JAMA Intern Med"},{"issue":"3","key":"pone.0358471.ref059","doi-asserted-by":"crossref","first-page":"381","DOI":"10.1016\/j.pec.2009.04.006","article-title":"Education, literacy, and health: Mediating effects on hypertension knowledge and control","volume":"75","author":"AU Pandit","year":"2009","journal-title":"Patient Educ Couns"},{"issue":"2","key":"pone.0358471.ref060","doi-asserted-by":"crossref","first-page":"165","DOI":"10.1016\/j.pec.2014.05.007","article-title":"Low literacy is associated with uncontrolled blood pressure in primary care patients with hypertension and heart disease","volume":"96","author":"CD McNaughton","year":"2014","journal-title":"Patient Educ Couns"}],"container-title":["PLOS One"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/dx.plos.org\/10.1371\/journal.pone.0358471","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,9,17]],"date-time":"2026-09-17T17:31:58Z","timestamp":1789666318000},"score":1,"resource":{"primary":{"URL":"https:\/\/dx.plos.org\/10.1371\/journal.pone.0358471"}},"subtitle":[],"editor":[{"given":"Andr\u00e9 Luis C","family":"Ramalho","sequence":"first","affiliation":[{"name":"University of Porto Faculty of Medicine: Universidade do Porto Faculdade de Medicina","place":["PORTUGAL"]}],"role":[{"vocabulary":"crossref","role":"editor"}]}],"short-title":[],"issued":{"date-parts":[[2026,9,17]]},"references-count":60,"journal-issue":{"issue":"9","published-online":{"date-parts":[[2026,9,17]]}},"URL":"https:\/\/doi.org\/10.1371\/journal.pone.0358471","relation":{},"ISSN":["1932-6203"],"issn-type":[{"value":"1932-6203","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,9,17]]}}}