{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,11,5]],"date-time":"2026-11-05T01:18:44Z","timestamp":1793841524828,"version":"4.6.1"},"reference-count":66,"publisher":"Frontiers Media SA","license":[{"start":{"date-parts":[[2026,7,23]],"date-time":"2026-07-23T00:00:00Z","timestamp":1784764800000},"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. Public Health"],"abstract":"<jats:sec>\n                    <jats:title>Background<\/jats:title>\n                    <jats:p>Asthma is one of the most prominent chronic diseases in children and one of the most challenging ailments to diagnose in infants and preschoolers in the United States. Predictive models can be instrumental in improving early diagnosis, personalized treatment strategies, and disease progression. By utilizing nationalized data, this study focuses on building and comparing high-performing analytical predictive models based on the relevant risk factors and identifying the most influential predictors.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Methods<\/jats:title>\n                    <jats:p>\n                      We analyzed cross-sectional BRFSS Asthma Call-Back Survey data (2011\u20132020;\n                      <jats:italic>N<\/jats:italic>\n                      \u202f=\u202f9,813) and randomly split participants into training and testing sets. An XGBoost model (hyperparameters tuned via grid search) was developed and compared with SVM, random forest, LASSO, and GBM using accuracy, AUC, precision, and recall. Calibration was evaluated with reliability plots and improved using Platt scaling and isotonic regression. Predictor contributions were examined using variable-importance (VIP) and Shapley Additive Explanations (SHAP) plot.\n                    <\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Results<\/jats:title>\n                    <jats:p>Of the five predictive models, the XGBoost was found to be the best performing model with AUC: 0.95, followed by random forest (AUC: 0.9345), GBM (AUC: 0.9341), SVM (AUC 0.9304), and LASSO (AUC 0.88); however, the random forest model was found to have the highest sensitivity (0.9786), and hence preferred for initial screening of asthma. On the independent test set, calibration (10-bin reliability curves; Brier\/ECE\/intercept\u2013slope) improved most with isotonic regression, specifically for Random Forest (ECE 0.0158 to 0.0086; intercept \u22120.174 to \u22120.010), whereas Platt scaling often worsened calibration, with AUC remaining largely stable across models (AUC\u202f\u2248\u202f0.92\u20130.95). The top two contributing predictors were overnight hospitalization visits and time since the last asthma medication, accounting for 24.62 and 20.92%, respectively, of the asthma status, from the VIP.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Conclusion<\/jats:title>\n                    <jats:p>The analytical methodology of model development was found to be instrumental in the discovery of behavioral health-risk knowledge and to visualize the significance of predictive modeling from a multidimensional behavioral health survey. These insights can be instrumental in predicting different types of chronic lung diseases affecting people of all ages and can be useful for clinicians to diagnose asthma at an early stage, allowing for early intervention and proactive management.<\/jats:p>\n                  <\/jats:sec>","DOI":"10.3389\/fpubh.2026.1823225","type":"journal-article","created":{"date-parts":[[2026,7,23]],"date-time":"2026-07-23T05:37:58Z","timestamp":1784785078000},"update-policy":"https:\/\/doi.org\/10.3389\/crossmark-policy","source":"Crossref","is-referenced-by-count":3,"title":["The crucial role of machine learning models in predicting current childhood asthma: model comparison, calibration, and SHAP-based interpretation"],"prefix":"10.3389","volume":"14","author":[{"given":"Aditya","family":"Chakraborty","sequence":"first","affiliation":[{"name":"Department of Epidemiology, Biostatistics and Environmental Health, Joint School of Public Health, Old Dominion University","place":["Norfolk, VA, United States"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"A. K. M. Raquibul","family":"Bashar","sequence":"additional","affiliation":[{"name":"Department of Mathematics and Computer Science, Augustana College","place":["Rock Island, United States"]}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"1965","published-online":{"date-parts":[[2026,7,23]]},"reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.1412.6830","article-title":"Learning activation functions to improve deep neural networks","author":"Agostinelli","year":"2014","journal-title":"arXiv preprint arXiv:14126830"},{"key":"ref2","doi-asserted-by":"publisher","first-page":"19426","DOI":"10.1038\/s41598-023-46633-8","article-title":"Using machine learning approach for screening metastatic biomarkers in colorectal cancer and predictive modeling with experimental validation","volume":"13","author":"Ahmadieh-Yazdi","year":"2023","journal-title":"Sci Rep"},{"key":"ref3","doi-asserted-by":"publisher","first-page":"776","DOI":"10.1016\/j.petrol.2018.11.067","article-title":"The linear random forest algorithm and its advantages in machine learning assisted logging regression modeling","volume":"174","author":"Ao","year":"2019","journal-title":"J Pet Sci Eng"},{"key":"ref4","doi-asserted-by":"publisher","first-page":"500","DOI":"10.1002\/ajim.20170","article-title":"Prevalence of asthma by industry in the us population: a study of 2001 nhis data","volume":"47","author":"Bang","year":"2005","journal-title":"Am J Ind Med"},{"key":"ref5","doi-asserted-by":"crossref","first-page":"140","DOI":"10.1080\/01621459.1972.10481216","article-title":"The isotonic regression problem and its dual","volume":"67","author":"Barlow","year":"1972","journal-title":"J Am Stat Assoc"},{"key":"ref6","doi-asserted-by":"publisher","first-page":"14","DOI":"10.1186\/s41512-024-00177-1","article-title":"Understanding overfitting in random forest for probability estimation: a visualization and simulation study","volume":"8","author":"Barren\u02dcada","year":"2024","journal-title":"Diagn Progn Res"},{"key":"ref7","doi-asserted-by":"publisher","first-page":"462","DOI":"10.4236\/jdaip.2024.123024","article-title":"A machine learning classification model for detecting prediabetes","volume":"12","author":"Bashar","year":"2024","journal-title":"J Data Anal Inf Process"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1123\/jpah.2026-0347","article-title":"Understanding Drivers of Physical Activity Through Explainable Machine Learning: The Role of Disability and Social Determinants","author":"Chakraborty","year":"2026","journal-title":"J Phys Act Health"},{"key":"ref9","doi-asserted-by":"publisher","first-page":"1","DOI":"10.4236\/oalib.1105828","article-title":"Statistical parametric analysis on democracy data","volume":"6","year":"2019","journal-title":"Open Access Libr J"},{"key":"ref10","doi-asserted-by":"publisher","first-page":"396","DOI":"10.4236\/jss.2024.129023","article-title":"Parametric and statistical analysis on corruption perception index (CPI) of countries of the world based on world governance index (WGI) data of transparency international (TI)","volume":"12","author":"Bashar","year":"2024","journal-title":"Open J Soc Sci"},{"key":"ref11","doi-asserted-by":"publisher","first-page":"875","DOI":"10.1080\/1206212X.2021.1974663","article-title":"Grid search in hyperparameter optimization of machine learning models for prediction of HIV\/AIDS test results","volume":"44","author":"Belete","year":"2022","journal-title":"Int J Comput Appl"},{"key":"ref12","first-page":"1","volume-title":"2024 International Conference on Communication, Computing and Internet of Things (IC3IoT)","author":"Belida","year":"2024"},{"key":"ref13","doi-asserted-by":"publisher","first-page":"642","DOI":"10.1001\/jamapsychiatry.2019.0174","article-title":"Prediction models for suicide attempts and deaths: a systematic review and simulation","volume":"76","author":"Belsher","year":"2019","journal-title":"JAMA Psychiatry"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.2103.03086","article-title":"A multi-modal respiratory disease exacerbation prediction technique based on a spatio-temporal machine learning architecture","author":"TanBhowmik","year":"2021","journal-title":"arXiv preprint arXiv:210303086"},{"key":"ref15","doi-asserted-by":"publisher","first-page":"197","DOI":"10.1007\/s11749-016-0481-7","article-title":"A random forest guided tour","volume":"25","author":"Biau","year":"2016","journal-title":"TEST"},{"key":"ref16","doi-asserted-by":"publisher","first-page":"e0295427","DOI":"10.1371\/journal.pone.0295427","article-title":"Predicting asthma using imbalanced data modeling techniques: evidence from 2019 Michigan brfss data","volume":"18","author":"Budhathoki","year":"2023","journal-title":"PLoS One"},{"key":"ref17","volume-title":"Synthesis Lectures on Artificial Intelligence and Machine Learning","author":"Campbell","year":"2011"},{"key":"ref18","doi-asserted-by":"publisher","first-page":"212","DOI":"10.1016\/j.jaci.2010.06.032","article-title":"The asthma predictive index: a very useful tool for predicting asthma in young children","volume":"126","author":"Castro-Rodriguez","year":"2010","journal-title":"J Allergy Clin Immunol"},{"key":"ref19","first-page":"1031","article-title":"A real data-driven clustering approach for countries based on happiness score","volume-title":"Amfiteatru Economic","author":"Chakraborty","year":"2021"},{"key":"ref20","first-page":"4725","article-title":"A modern approach of survival analysis of patients with pancreatic cancer","volume":"11","author":"Chakraborty","year":"2021","journal-title":"Am J Cancer Res"},{"key":"ref21","doi-asserted-by":"publisher","first-page":"45","DOI":"10.36347\/sjpms.2021.v08i03.001","article-title":"A real data-driven analytical model to predict happiness","volume":"3","author":"Chakraborty","year":"2021","journal-title":"Sch J Phys Math Stat"},{"key":"ref22","doi-asserted-by":"publisher","first-page":"29","DOI":"10.34257\/gjmrfvol21is3pg29","article-title":"Survival analysis for pancreatic cancer patients using cox-proportional hazard (CPH) model","volume":"21","author":"Chakraborty","year":"2021","journal-title":"Glob J Med Res"},{"key":"ref23","doi-asserted-by":"publisher","first-page":"262","DOI":"10.1007\/s44199-023-00063-7","article-title":"An ai-driven predictive model for pancreatic cancer patients using extreme gradient boosting","volume":"22","author":"Chakraborty","year":"2023","journal-title":"J Statistical Theory Applications"},{"key":"ref24","doi-asserted-by":"publisher","first-page":"126","DOI":"10.4236\/ojapps.2021.111009","article-title":"Parametric and non-parametric survival analysis of patients with acute myeloid leukemia (aml)","volume":"11","author":"Chakraborty","year":"2021","journal-title":"Open J Appl Sci"},{"key":"ref25","doi-asserted-by":"publisher","first-page":"895717","DOI":"10.3389\/fphar.2022.895717","article-title":"Adding Chinese herbal medicine to routine care is associated with a lower risk of rheumatoid arthritis among patients with asthma: a population-based retrospective cohort study","volume":"13","author":"Chang","year":"2022","journal-title":"Front Pharmacol"},{"key":"ref26","doi-asserted-by":"crossref","first-page":"305","DOI":"10.1016\/j.tics.2019.01.009","article-title":"Deep neural networks as scientific models","volume":"23","author":"Cichy","year":"2019","journal-title":"Trends Cogn Sci"},{"key":"ref27","doi-asserted-by":"publisher","first-page":"103","DOI":"10.3389\/fped.2017.00103","article-title":"Allergen avoidance in allergic asthma","volume":"5","author":"Cipriani","year":"2017","journal-title":"Front Pediatr"},{"key":"ref28","doi-asserted-by":"publisher","first-page":"193","DOI":"10.1146\/annurev-publhealth-031811-124532","article-title":"Community-based approaches to controlling childhood asthma","volume":"33","author":"Clark","year":"2012","journal-title":"Annu Rev Public Health"},{"key":"ref29","doi-asserted-by":"publisher","first-page":"410","DOI":"10.1111\/cea.13336","article-title":"Validation of childhood asthma predictive tools: a systematic review","volume":"49","author":"Colicino","year":"2019","journal-title":"Clin Exp Allergy"},{"key":"ref30","doi-asserted-by":"publisher","first-page":"19","DOI":"10.1038\/s41533-019-0132-z","article-title":"Systematic review of clinical prediction models to support the diagnosis of asthma in primary care","volume":"29","author":"Daines","year":"2019","journal-title":"NPJ Primary Care Respiratory Medicine"},{"key":"ref31","doi-asserted-by":"publisher","first-page":"246","DOI":"10.3389\/fped.2019.00246","article-title":"Epidemiology of asthma in children and adults","volume":"7","author":"Dharmage","year":"2019","journal-title":"Front Pediatr"},{"key":"ref32","doi-asserted-by":"publisher","first-page":"193","DOI":"10.1111\/j.1365-2222.2008.03157.x","article-title":"Acute exacerbations of asthma: epidemiology, biology and the exacerbation-prone phenotype","volume":"39","author":"Dougherty","year":"2009","journal-title":"Clin Exp Allergy"},{"key":"ref33","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1007\/s12553-023-00732-8","article-title":"Machine learning classification approach for asthma prediction models in children","volume":"13","author":"Ekpo","year":"2023","journal-title":"Health Technol"},{"key":"ref34","doi-asserted-by":"publisher","first-page":"3078025","DOI":"10.1155\/2022\/3078025","article-title":"Predictive analysis of diabetes-risk with class imbalance","author":"ElSeddawy","year":"2022","journal-title":"Comput Intell Neurosci"},{"key":"ref35","doi-asserted-by":"crossref","first-page":"579","DOI":"10.1109\/ICCSNT.2015.7490813","volume-title":"2015 4th International Conference on Computer Science and Network Technology (ICCSNT)","author":"Fan","year":"2015"},{"key":"ref36","doi-asserted-by":"publisher","first-page":"659","DOI":"10.1007\/s11222-016-9646-1","article-title":"Correlation and variable importance in random forests","volume":"27","author":"Gregorutti","year":"2017","journal-title":"Stat Comput"},{"key":"ref37","doi-asserted-by":"publisher","first-page":"5256","DOI":"10.3390\/su14095256","article-title":"Predicting determinants of lifelong learning intention using gradient boosting machine (gbm) with grid search","volume":"14","author":"Kim","year":"2022","journal-title":"Sustainability"},{"key":"ref38","doi-asserted-by":"publisher","first-page":"1237","DOI":"10.1080\/00140139.2023.2290983","article-title":"Prediction model of subacromial pain syndrome in assembly workers using shoulder range of motion and muscle strength based on support vector machine","volume":"67","author":"Kim","year":"2024","journal-title":"Ergonomics"},{"key":"ref39","doi-asserted-by":"publisher","first-page":"106993","DOI":"10.1016\/j.knosys.2021.106993","article-title":"Interpretable machine learning with an ensemble of gradient boosting machines","volume":"222","author":"Konstantinov","year":"2021","journal-title":"Knowl Based Syst"},{"key":"ref40","doi-asserted-by":"publisher","first-page":"1854","DOI":"10.1016\/j.jaci.2018.02.001","article-title":"Effectiveness of indoor allergen reduction in asthma management: a systematic review","volume":"141","author":"Leas","year":"2018","journal-title":"J Allergy Clin Immunol"},{"key":"ref41","doi-asserted-by":"publisher","first-page":"1619","DOI":"10.1007\/s00158-019-02270-2","article-title":"Review of statistical model calibration and validation\u2014from the perspective of uncertainty structures","volume":"60","author":"Lee","year":"2019","journal-title":"Struct Multidiscip Optim"},{"key":"ref42","doi-asserted-by":"publisher","first-page":"12507","DOI":"10.1038\/s41598-024-63437-6","article-title":"Lasso-derived model for the prediction of bleeding in aspirin users","volume":"14","author":"Liang","year":"2024","journal-title":"Sci Rep"},{"key":"ref43","doi-asserted-by":"publisher","first-page":"777","DOI":"10.1016\/j.cell.2010.03.004","article-title":"Asthma and allergic inflammation","volume":"140","author":"Locksley","year":"2010","journal-title":"Cell"},{"key":"ref44","doi-asserted-by":"publisher","first-page":"806","DOI":"10.1016\/j.procs.2023.03.107","article-title":"Shapley values for explaining the black box nature of machine learning model clustering","volume":"220","author":"Louhichi","year":"2023","journal-title":"Procedia Comput Sci"},{"key":"ref45","doi-asserted-by":"publisher","first-page":"1129380","DOI":"10.3389\/fonc.2023.1129380","article-title":"On the importance of interpretable machine learning predictions to inform clinical decision making in oncology","volume":"13","author":"Lu","year":"2023","journal-title":"Front Oncol"},{"key":"ref46","doi-asserted-by":"publisher","first-page":"303","DOI":"10.1177\/23998083241259069","article-title":"Exploring road safety through urban fabric characteristics and theory-driven prediction modeling with SEM-XGBoost","volume":"52","author":"McCarty","year":"2025","journal-title":"Environ Plan B Urban Anal City Sci"},{"key":"ref47","doi-asserted-by":"publisher","first-page":"1230","DOI":"10.3390\/s24041230","article-title":"Hyperparameter optimization with genetic algorithms and xgboost: a step forward in smart grid fraud detection","volume":"24","author":"Mehdary","year":"2024","journal-title":"Sensors"},{"key":"ref48","doi-asserted-by":"publisher","first-page":"727","DOI":"10.1001\/archpedi.153.7.727","article-title":"Rehospitalization of children with asthma","volume":"153","author":"Minkovitz","year":"1999","journal-title":"Arch Pediatr Adolesc Med"},{"key":"ref49","doi-asserted-by":"publisher","first-page":"21","DOI":"10.3389\/fnbot.2013.00021","article-title":"Gradient boosting machines, a tutorial","volume":"7","author":"Natekin","year":"2013","journal-title":"Front Neurorobot"},{"key":"ref50","doi-asserted-by":"publisher","first-page":"1565","DOI":"10.1038\/nbt1206-1565","article-title":"What is a support vector machine?","volume":"24","author":"Noble","year":"2006","journal-title":"Nat Biotechnol"},{"key":"ref51","doi-asserted-by":"publisher","first-page":"106584","DOI":"10.1016\/j.cmpb.2021.106584","article-title":"Explanation of machine learning models using shapley additive explanation and application for real data in hospital","volume":"214","author":"Nohara","year":"2022","journal-title":"Comput Methods Prog Biomed"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.1811.03378","article-title":"Activation functions: comparison of trends in practice and research for deep learning","author":"Nwankpa","year":"2018","journal-title":"arXiv preprint arXiv:181103378"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.2501.19047","article-title":"Understanding model calibration\u2013a gentle introduction and visual exploration of calibration and the expected calibration error (ECE)","author":"Pavlovic","year":"2025","journal-title":"arXiv preprint arXiv:250119047"},{"key":"ref54","first-page":"1","volume-title":"2018 International Conference on Current Trends towards Converging Technologies (ICCTCT)","author":"Rayavarapu","year":"2018"},{"key":"ref55","doi-asserted-by":"publisher","first-page":"234","DOI":"10.1002\/widm.1125","article-title":"Support vector machines in engineering: an overview","volume":"4","author":"Salcedo-Sanz","year":"2014","journal-title":"Wiley Interdiscip Rev Data Min Knowl Discov"},{"key":"ref56","doi-asserted-by":"publisher","first-page":"100353","DOI":"10.1016\/j.health.2024.100353","article-title":"A comparative study of machine learning models with lasso and shap feature selection for breast cancer prediction","volume":"6","author":"Shaon","year":"2024","journal-title":"Healthc Anal"},{"key":"ref57","doi-asserted-by":"publisher","first-page":"S574","DOI":"10.21037\/jtd.2019.01.25","article-title":"Developing prediction models for clinical use using logistic regression: an overview","volume":"11","author":"Shipe","year":"2019","journal-title":"J Thorac Dis"},{"key":"ref58","first-page":"5","volume-title":"Semin Immunopathol","author":"Stern","year":"2020"},{"key":"ref59","doi-asserted-by":"publisher","first-page":"e1379","DOI":"10.1002\/widm.1379","article-title":"Interpretability of machine learning-based prediction models in healthcare","volume":"10","author":"Stiglic","year":"2020","journal-title":"Wiley Interdiscip Rev Data Min Knowl Discov"},{"key":"ref60","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1287\/mnsc.2023.02025","article-title":"Measuring the driving forces of predictive performance: application to credit scoring","author":"Hu\u00e9","year":"2026","journal-title":"Management Science"},{"key":"ref61","doi-asserted-by":"crossref","first-page":"267","DOI":"10.1111\/j.2517-6161.1996.tb02080.x","article-title":"Regression shrinkage and selection via the lasso","volume":"58","author":"Tibshirani","year":"1996","journal-title":"J R Stat Soc B Stat Methodol"},{"key":"ref62","doi-asserted-by":"publisher","first-page":"062001","DOI":"10.1088\/1741-2552\/abbff2","article-title":"Supervised machine learning tools: a tutorial for clinicians","volume":"17","author":"Lo Vercio","year":"2020","journal-title":"J Neural Eng"},{"key":"ref63","doi-asserted-by":"publisher","first-page":"297","DOI":"10.1186\/s12911-023-02407-w","article-title":"Comparison of lasso and random forest models for predicting the risk of premature coronary artery disease","volume":"23","author":"Wang","year":"2023","journal-title":"BMC Med Inform Decis Mak"},{"key":"ref64","doi-asserted-by":"publisher","first-page":"581","DOI":"10.1515\/jom-2022-0063","article-title":"Asthma medications in schools: a cross-sectional analysis of the asthma call-back survey 2017-2018","volume":"122","author":"Wilkins","year":"2017","journal-title":"J Osteopath Med"},{"key":"ref65","doi-asserted-by":"publisher","first-page":"16","DOI":"10.3109\/02770903.2011.637594","article-title":"Asthma incidence among children and adults: findings from the behavioral risk factor surveillance system asthma call-back survey\u2014United States, 2006\u20132008","volume":"49","author":"Winer","year":"2006","journal-title":"J Asthma"},{"key":"ref66","doi-asserted-by":"publisher","first-page":"318","DOI":"10.3109\/02770903.2014.956894","article-title":"Assessing asthma control and associated risk factors among persons with current asthma\u2013findings from the child and adult asthma call-back survey","volume":"52","author":"Zahran","year":"2015","journal-title":"J Asthma"}],"container-title":["Frontiers in Public Health"],"original-title":[],"link":[{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/fpubh.2026.1823225\/full","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,7,23]],"date-time":"2026-07-23T05:38:01Z","timestamp":1784785081000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/fpubh.2026.1823225\/full"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,7,23]]},"references-count":66,"alternative-id":["10.3389\/fpubh.2026.1823225"],"URL":"https:\/\/doi.org\/10.3389\/fpubh.2026.1823225","relation":{},"ISSN":["2296-2565"],"issn-type":[{"value":"2296-2565","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,7,23]]},"article-number":"1823225"}}