{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,12,29]],"date-time":"2025-12-29T20:42:07Z","timestamp":1767040927976,"version":"3.48.0"},"reference-count":29,"publisher":"Springer Science and Business Media LLC","issue":"1","license":[{"start":{"date-parts":[[2025,12,22]],"date-time":"2025-12-22T00:00:00Z","timestamp":1766361600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"},{"start":{"date-parts":[[2025,12,29]],"date-time":"2025-12-29T00:00:00Z","timestamp":1766966400000},"content-version":"vor","delay-in-days":7,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["BMC Med Inform Decis Mak"],"abstract":"<jats:title>Abstract<\/jats:title>\n                  <jats:sec>\n                    <jats:title>Purpose<\/jats:title>\n                    <jats:p>Congenital hypothyroidism (CH) is a common cause of severe intellectual disability, affecting approximately 1 in 2,000 newborns globally. Treatable with early intervention, congenital hypothyroidism has long been a target of newborn screening programs. Current thyroid stimulating hormone (TSH) based programs suffer from low positive predictive value, resulting in unnecessary diagnostic investigations. Congenital hypothyroidism screening has proven challenging for machine learning previously due to massive class imbalance and having a single well known predictor, preventing acceptable screening sensitivity. This study represents the most comprehensive evaluation of machine learning for congenital hypothyroidism screening to date.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Methods<\/jats:title>\n                    <jats:p>Analyzing data from 616,910 infants screened by Newborn Screening Ontario between 2019 and 2024. 12 classification and 12 resampling algorithms were trained using 4 different optimization metrics, for a total of 576 distinct models evaluated using stratified 5-fold cross-validation to ensure robustness. Models were optimized for sensitivity and then positive predictive value using various metrics. Model explainability was assessed using SHAP values and feature importances.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Results<\/jats:title>\n                    <jats:p>We were able to create a model achieving 16.8% PPV while maintaining 100% sensitivity using a RUSBoost classifier and Gaussian Noise resampling. This represents a 60% improvement in positive predictive value over the current approach. TSH remained the dominant predictor as in current screening, but our model was able to include minor amounts of additional information from other features to improve performance.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Conclusion<\/jats:title>\n                    <jats:p>These machine learning algorithms show no missed cases of CH and are able to significantly improve performance across robust testing. The findings suggest that machine learning offers a promising avenue for refining TSH-based CH screening processes, reducing false positives, and alleviating unnecessary stress and costs associated with current methods used by the majority of newborn screening programs globally.<\/jats:p>\n                  <\/jats:sec>","DOI":"10.1186\/s12911-025-03312-0","type":"journal-article","created":{"date-parts":[[2025,12,22]],"date-time":"2025-12-22T16:54:47Z","timestamp":1766422487000},"update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Enhancing TSH-based congenital hypothyroidism screening using machine learning and resampling algorithms"],"prefix":"10.1186","volume":"25","author":[{"given":"Alexander","family":"De Furia","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Paula","family":"Branco","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Matthew","family":"Henderson","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2025,12,22]]},"reference":[{"issue":"5","key":"3312_CR1","doi-asserted-by":"publisher","first-page":"407","DOI":"10.1097\/MED.0000000000000181","volume":"22","author":"AJ Wassner","year":"2015","unstructured":"Wassner AJ, Brown RS. Congenital hypothyroidism: recent advances. Curr Opin In Endocrinol, Diabetes Obes. 2015, Oct;22(5):407. Available from: https:\/\/doi.org\/10.1097\/MED.0000000000000181.","journal-title":"Curr Opin In Endocrinol, Diabetes And Obes"},{"key":"3312_CR2","volume-title":"In: StatPearls. Treasure island (FL)","author":"SA Bowden","year":"2024","unstructured":"Bowden SA, Goldis M. Congenital hypothyroidism. In: StatPearls. Treasure island (FL). StatPearls Publishing; 2024. Available from: http:\/\/www.ncbi.nlm.nih.gov\/books\/NBK558913\/."},{"issue":"10","key":"3312_CR3","doi-asserted-by":"publisher","first-page":"3720","DOI":"10.1210\/jc.2018-00658","volume":"103","author":"RL Knowles","year":"2018","unstructured":"Knowles RL, Oerton J, Cheetham T, Butler G, Cavanagh C, Tetlow L, et al. Newborn screening for primary congenital hypothyroidism: estimating test performance at different TSH thresholds. The J Clin Endocrinol Metab. 2018;103(10):3720\u201328. https:\/\/doi.org\/10.1210\/jc.2018-00658.","journal-title":"The J Clin Endocrinol And Metab"},{"key":"3312_CR4","doi-asserted-by":"publisher","unstructured":"Mehran L, Khalili D, Yarahmadi S, Amouzegar A, Mojarrad M, Ajang N, et al. Worldwide recall rate in newborn screening programs for congenital hypothyroidism. Int J Endocrinol Metab. 2017, Jun;15(3):e55451. Available from: https:\/\/doi.org\/10.5812\/ijem.55451.","DOI":"10.5812\/ijem.55451"},{"issue":"4","key":"3312_CR5","doi-asserted-by":"publisher","first-page":"e230041","DOI":"10.1530\/ETJ-23-0041","volume":"12","author":"A Boelen","year":"2023","unstructured":"Boelen A, Zwaveling-Soonawala N, Heijboer AC, van Trotsenburg Asp. Neonatal screening for primary and central congenital hypothyroidism: is it time to go Dutch? Eur Thyroid J. 2023, Jul;12(4):e230041. Available from: https:\/\/doi.org\/10.1530\/ETJ-23-0041.","journal-title":"Eur Thyroid J"},{"issue":"4","key":"3312_CR6","doi-asserted-by":"publisher","first-page":"349","DOI":"10.21037\/tp.2017.09.07","volume":"6","author":"N Kanike","year":"2017","unstructured":"Kanike N, Davis A, Shekhawat PS. Transient hypothyroidism in the newborn: to treat or not to treat. Transl Pediatrics. 2017, Oct;6(4):349\u201358. Available from: https:\/\/doi.org\/10.21037\/tp.2017.09.07.","journal-title":"Transl Pediatrics"},{"key":"3312_CR7","unstructured":"Henderson M. NSO Ch screening process. 2024."},{"issue":"3","key":"3312_CR8","doi-asserted-by":"publisher","first-page":"250","DOI":"10.1002\/jmd2.12285","volume":"63","author":"E Zaunseder","year":"2022","unstructured":"Zaunseder E, Haupt S, M\u00fctze U, Garbade SF, K\u00f6lker S, Heuveline V. Opportunities and challenges in machine learning-based newborn screening\u2014A systematic literature review. JIMD Rep. 2022;63(3):250\u201361. Available from: https:\/\/doi.org\/10.1002\/jmd2.12285.","journal-title":"JIMD Rep"},{"issue":"5","key":"3312_CR9","doi-asserted-by":"publisher","first-page":"e98","DOI":"10.2196\/jmir.2495","volume":"15","author":"WH Chen","year":"2013","unstructured":"Chen WH, Hsieh SL, Hsu KP, Chen HP, Su XY, Tseng YJ, et al. Web-based newborn screening system for metabolic diseases: machine learning versus clinicians. J Med Internet Res. 2013, May;15(5):e98. Available from: https:\/\/doi.org\/10.2196\/jmir.2495.","journal-title":"J Med Internet Res"},{"key":"3312_CR10","doi-asserted-by":"publisher","unstructured":"Zhu Z, Gu J, Genchev GZ, Cai X, Wang Y, Guo J, et al. Improving the diagnosis of phenylketonuria by using a machine learning\u2013based screening Model of neonatal MRM data. Front Mol Biosci. 2020, Jul;7. Available from: https:\/\/doi.org\/10.3389\/fmolb.2020.00115.","DOI":"10.3389\/fmolb.2020.00115"},{"key":"3312_CR11","doi-asserted-by":"publisher","first-page":"100281","DOI":"10.1016\/j.imu.2019.100281","volume":"18","author":"SS Zarin Mousavi","year":"2020","unstructured":"Zarin Mousavi SS, Mohammadi Zanjireh M, Oghbaie M. Applying computational classification methods to diagnose congenital hypothyroidism: a comparative study. Inf In Med Unlocked. 2020, Jan;18:100281. Available from: https:\/\/doi.org\/10.1016\/j.imu.2019.100281.","journal-title":"Inf In Med Unlocked"},{"key":"3312_CR12","doi-asserted-by":"crossref","unstructured":"Raeder T, Forman G, Chawla NV. Learning from imbalanced data: evaluation matters. In: Data mining: foundations and intelligent paradigms. Intelligent systems reference library. Berlin, Heidelberg Berlin Heidelberg: Springer; 2012. p. 315\u201331.","DOI":"10.1007\/978-3-642-23166-7_12"},{"key":"3312_CR13","doi-asserted-by":"publisher","first-page":"7","DOI":"10.1016\/j.clinbiochem.2023.03.001","volume":"116","author":"K Stroek","year":"2023","unstructured":"Stroek K, Visser A, van der Ploeg CPB, Zwaveling-Soonawala N, Heijboer AC, Bosch AM, et al. Machine learning to improve false-positive results in the Dutch newborn screening for congenital hypothyroidism. Clin Biochem. 2023, Jun;116:7\u201310. Available from: https:\/\/doi.org\/10.1016\/j.clinbiochem.2023.03.001.","journal-title":"Clin Biochem"},{"issue":"6","key":"3312_CR14","doi-asserted-by":"publisher","first-page":"e230141","DOI":"10.1530\/ETJ-23-0141","volume":"12","author":"HI Jansen","year":"2023","unstructured":"Jansen HI, van Haeringen M, Bouva MJ, den Elzen WPJ, Bruinstroop E, van der Ploeg CPB, et al. Optimizing the Dutch newborn screening for congenital hypothyroidism by incorporating amino acids and acylcarnitines in a machine learning-based Model. Eur Thyroid J. 2023, Nov;12(6):e230141. Available from: https:\/\/doi.org\/10.1530\/ETJ-23-0141.","journal-title":"Eur Thyroid J"},{"key":"3312_CR15","first-page":"321","volume":"16","author":"NV Chawla","year":"2002","unstructured":"Chawla NV, Bowyer KW, Hall LO, Kegelmeyer WP. Smote: synthetic minority over-sampling technique. J Artif Intel Res. 2002;16:321\u201357.","journal-title":"J Artif Intel Res"},{"issue":"1","key":"3312_CR16","doi-asserted-by":"publisher","first-page":"5","DOI":"10.1023\/A:1010933404324","volume":"45","author":"L Breiman","year":"2001","unstructured":"Breiman L. Random forests. Mach Learn. 2001, Oct;45(1):5\u201332. Available from: https:\/\/doi.org\/10.1023\/A:1010933404324.","journal-title":"Mach Learn"},{"issue":"17","key":"3312_CR17","first-page":"1","volume":"18","author":"G Lema\u00eetre","year":"2017","unstructured":"Lema\u00eetre G, Nogueira F, Aridas CK. Imbalanced-Learn: a python toolbox to tackle the curse of Imbalanced datasets in machine learning. J Mach Learn Res. 2017;18(17):1\u20135.","journal-title":"J Mach Learn Res"},{"issue":"1","key":"3312_CR18","doi-asserted-by":"publisher","first-page":"24","DOI":"10.1186\/s12887-016-0559-0","volume":"16","author":"DS Saleh","year":"2016","unstructured":"Saleh DS, Lawrence S, Geraghty MT, Gallego PH, McAssey K, Wherrett DK, et al. Prediction of congenital hypothyroidism based on initial screening thyroid-stimulating-hormone. BMC Pediatrics. 2016, Feb;16(1):24. Available from: https:\/\/doi.org\/10.1186\/s12887-016-0559-0.","journal-title":"BMC Pediatrics"},{"key":"3312_CR19","doi-asserted-by":"publisher","first-page":"107043","DOI":"10.1016\/j.csda.2020.107043","volume":"152","author":"M Baak","year":"2020","unstructured":"Baak M, Koopman R, Snoek H, Klous S. A new correlation coefficient between categorical, ordinal and interval variables with Pearson characteristics. Comput Stat Data Anal. 2020, Dec;152:107043. Available from: https:\/\/doi.org\/10.1016\/j.csda.2020.107043.","journal-title":"Comput Stat Data Anal"},{"key":"3312_CR20","doi-asserted-by":"publisher","first-page":"110415","DOI":"10.1016\/j.asoc.2023.110415","volume":"143","author":"S Rezvani","year":"2023","unstructured":"Rezvani S, Wang X. A broad review on class imbalance learning techniques. Appl Soft Comput. 2023, Aug;143:110415. Available from: https:\/\/doi.org\/10.1016\/j.asoc.2023.110415.","journal-title":"Appl Soft Comput"},{"issue":"1","key":"3312_CR21","doi-asserted-by":"publisher","first-page":"281","DOI":"10.1186\/s12911-019-1004-8","volume":"19","author":"S Uddin","year":"2019","unstructured":"Uddin S, Khan A, Hossain ME, Moni MA. Comparing different supervised machine learning algorithms for disease prediction. BMC Med Inf Decis Mak. 2019, Dec;19(1):281. Available from: https:\/\/doi.org\/10.1186\/s12911-019-1004-8.","journal-title":"BMC Med Inf And Decis Mak"},{"key":"3312_CR22","doi-asserted-by":"publisher","DOI":"10.1002\/9781118646106","volume-title":"Imbalanced learning: foundations, algorithms, and applications","author":"H He","year":"2013","unstructured":"He H, Ma Y. Imbalanced learning: foundations, algorithms, and applications. Hoboken, New Jersey: John Wiley & Sons, Inc.; 2013."},{"key":"3312_CR23","first-page":"2825","volume":"12","author":"F Pedregosa","year":"2011","unstructured":"Pedregosa F, Varoquaux G, Gramfort A, Michel V, Thirion B, Grisel O, et al. Scikit-learn: machine learning in Python. J Mach Learn Res. 2011;12:2825\u201330.","journal-title":"J Mach Learn Res"},{"key":"3312_CR24","unstructured":"De Furia A, Branco P, Henderson MC-P. 2024. Available from: https:\/\/github.com\/nso-informatics\/CHML-Public."},{"issue":"2","key":"3312_CR25","doi-asserted-by":"publisher","first-page":"277","DOI":"10.1007\/s001800050018","volume":"14","author":"SS Lee","year":"1999","unstructured":"Lee SS. Regularization in skewed binary classification. Comput Stat. 1999;14(2):277\u201392. https:\/\/doi.org\/10.1007\/s001800050018.","journal-title":"Comput Stat"},{"issue":"1","key":"3312_CR26","doi-asserted-by":"publisher","first-page":"310","DOI":"10.1186\/s12911-020-01332-6","volume":"20","author":"J Amann","year":"2020","unstructured":"Amann J, Blasimme A, Vayena E, Frey D. Madai VI, the Precise4Q consortium. Explainability for artificial intelligence in healthcare: a multidisciplinary perspective. BMC Med Inf Decis Mak. 2020, Nov;20(1):310. Available from: https:\/\/doi.org\/10.1186\/s12911-020-01332-6.","journal-title":"BMC Med Inf And Decis Mak"},{"key":"3312_CR27","unstructured":"Lundberg S, Lee SI. A unified approach to interpreting Model predictions. arXiv; 2017. Available from: http:\/\/arxiv.org\/abs\/1705.07874."},{"key":"3312_CR28","doi-asserted-by":"publisher","unstructured":"Yang W, Wei Y, Wei H, Chen Y, Huang G, Li X, et al. Survey on explainable AI: from approaches, limitations and applications aspects. Hum-Centric Intell Syst. 2023, Sep;3(3):161\u201388. Available from: https:\/\/doi.org\/10.1007\/s44230-023-00038-y.","DOI":"10.1007\/s44230-023-00038-y"},{"issue":"11","key":"3312_CR29","doi-asserted-by":"publisher","first-page":"845","DOI":"10.1136\/adc.56.11.845","volume":"56","author":"DA Price","year":"1981","unstructured":"Price DA, Ehrlich RM, Walfish PG. Congenital hypothyroidism. Clinical and laboratory characteristics in infants detected by neonatal screening. Arch Dis Child. 1981;56(11):845\u201351.","journal-title":"Archiv Disease In Child"}],"container-title":["BMC Medical Informatics and Decision Making"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/article\/10.1186\/s12911-025-03312-0","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1186\/s12911-025-03312-0.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1186\/s12911-025-03312-0.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,12,29]],"date-time":"2025-12-29T20:37:17Z","timestamp":1767040637000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1186\/s12911-025-03312-0"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,12,22]]},"references-count":29,"journal-issue":{"issue":"1","published-online":{"date-parts":[[2025,12]]}},"alternative-id":["3312"],"URL":"https:\/\/doi.org\/10.1186\/s12911-025-03312-0","relation":{},"ISSN":["1472-6947"],"issn-type":[{"type":"electronic","value":"1472-6947"}],"subject":[],"published":{"date-parts":[[2025,12,22]]},"assertion":[{"value":"23 October 2024","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"1 December 2025","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"22 December 2025","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Declarations"}},{"value":"This study was approved, with the requirement to obtain consent waived, by the Children\u2019s Hospital of Eastern Ontario (CHEO) Research Ethics Board (REB). The CHEO REB criteria for waiving informed consent includes that the information used is essential to the research, is unlikely to adversely affect the welfare of the individuals to whom the information relates, and it is impossible or impracticable to seek consent from all individuals to whom the information relates. Permission for the secondary use of newborn screening data for the purposes of research was obtained from Newborn Screening Ontario.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Ethical approval"}},{"value":"Not applicable.","order":3,"name":"Ethics","group":{"name":"EthicsHeading","label":"Consent for publication"}},{"value":"The authors declare that they have no competing interests.","order":4,"name":"Ethics","group":{"name":"EthicsHeading","label":"Competing interests"}}],"article-number":"449"}}