{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,9,16]],"date-time":"2026-09-16T00:05:24Z","timestamp":1789517124115,"version":"build-2803163510"},"reference-count":27,"publisher":"The Endocrine Society","issue":"10","license":[{"start":{"date-parts":[[2026,6,26]],"date-time":"2026-06-26T00:00:00Z","timestamp":1782432000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by-nc-nd\/4.0\/"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2026,9,16]]},"abstract":"<jats:title>Abstract<\/jats:title>\n                  <jats:sec>\n                    <jats:title>Background<\/jats:title>\n                    <jats:p>Early and accurate etiological diagnosis of congenital disorders of adrenal steroidogenesis (CDAS) is critical as timely targeted management can prevent life-threatening complications and improve long-term outcomes.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Objective<\/jats:title>\n                    <jats:p>To develop and validate a machine learning-assisted decision tree model for classifying CDAS using plasma steroid hormone profiles quantified by liquid chromatography\u2013mass spectrometry (LC\u2013MS\/MS).<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Methods<\/jats:title>\n                    <jats:p>A development cohort of 1027 participants (325 genetically confirmed CDAS patients representing 8 subtypes\/702 controls) was used for model construction. The Light Gradient Boosting Machine algorithm identified key discriminatory steroid hormones, which were integrated into an optimized decision-tree classifier. Internal performance was assessed through 5-fold cross-validation. The performance of the model was further evaluated using a validation cohort comprising 507 independent LC\u2013MS\/MS steroid profiles. Additional analyses included Shapley additive explanations (SHAP), confusion matrix visualization, principal component analysis (PCA), and Uniform Manifold Approximation and Projection (UMAP).<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Results<\/jats:title>\n                    <jats:p>In the development cohort, the model achieved a mean overall accuracy of 97.1%, sensitivity of 99.5%, and specificity of 93.7%, with a macro-AUC (area under curve) of 0.97. Subtype-level accuracy exceeded 98% for most major CDAS subtypes. In the validation cohort, overall accuracy was 98.9%, sensitivity 93.6%, specificity 99.8%. Feature importance analysis and SHAP identified 11-deoxycortisol, 17-hydroxyprogesterone, 21-deoxycortisol, and corticosterone as the strongest discriminators. Principal component analysis and UMAP revealed distinct clustering of CDAS subtypes, confirming the biological coherence of model predictions.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Conclusion<\/jats:title>\n                    <jats:p>Machine learning\u2013assisted steroid profiling provides an accurate and highly interpretable diagnostic approach for CDAS, with potential for integration into pediatric endocrine diagnostics and decision-support systems.<\/jats:p>\n                  <\/jats:sec>","DOI":"10.1210\/clinem\/dgag237","type":"journal-article","created":{"date-parts":[[2026,6,25]],"date-time":"2026-06-25T11:47:04Z","timestamp":1782388024000},"page":"2737-2744","source":"Crossref","is-referenced-by-count":2,"title":["Machine learning algorithms to accelerate etiological diagnosis of congenital disorders of adrenal steroidogenesis"],"prefix":"10.1210","volume":"111","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-7588-9807","authenticated-orcid":false,"given":"Busra","family":"Gurpinar Tosun","sequence":"first","affiliation":[{"name":"Department of Pediatric Endocrinology and Diabetes, Faculty of Medicine, Marmara University , Istanbul 34854 ,","place":["Turkiye"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Atam Noyan","family":"Ercetin","sequence":"additional","affiliation":[{"name":"Department of Bioengineering, Faculty of Engineering, Marmara University , Istanbul 34854 ,","place":["Turkiye"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5172-5402","authenticated-orcid":false,"given":"Serap","family":"Turan","sequence":"additional","affiliation":[{"name":"Department of Pediatric Endocrinology and Diabetes, Faculty of Medicine, Marmara University , Istanbul 34854 ,","place":["Turkiye"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6584-9043","authenticated-orcid":false,"given":"Abdullah","family":"Bereket","sequence":"additional","affiliation":[{"name":"Department of Pediatric Endocrinology and Diabetes, Faculty of Medicine, Marmara University , Istanbul 34854 ,","place":["Turkiye"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6036-1348","authenticated-orcid":false,"given":"Kazim Yalcin","family":"Arga","sequence":"additional","affiliation":[{"name":"Department of Bioengineering, Faculty of Engineering, Marmara University , Istanbul 34854 ,","place":["Turkiye"]},{"name":"Genetic and Metabolic Diseases Research and Investigation Center, Marmara University , Istanbul 34854 ,","place":["Turkiye"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2658-6866","authenticated-orcid":false,"given":"Tulay","family":"Guran","sequence":"additional","affiliation":[{"name":"Department of Pediatric Endocrinology and Diabetes, Faculty of Medicine, Marmara University , Istanbul 34854 ,","place":["Turkiye"]}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"80","published-online":{"date-parts":[[2026,6,26]]},"reference":[{"issue":"5","key":"2026091519584394600_dgag237-B1","doi-asserted-by":"crossref","first-page":"292","DOI":"10.1159\/000488034","article-title":"Monogenic disorders of adrenal steroidogenesis","volume":"89","author":"Baranowski","year":"2018","journal-title":"Horm Res Paediatr"},{"issue":"2","key":"2026091519584394600_dgag237-B2","doi-asserted-by":"crossref","first-page":"275","DOI":"10.1016\/j.ecl.2015.02.002","article-title":"Adrenal steroidogenesis and congenital adrenal hyperplasia","volume":"44","author":"Turcu","year":"2015","journal-title":"Endocrinol Metab Clin North Am"},{"issue":"1","key":"2026091519584394600_dgag237-B3","doi-asserted-by":"crossref","first-page":"101593","DOI":"10.1016\/j.beem.2021.101593","article-title":"Rare forms of genetic steroidogenic defects affecting the gonads and adrenals","volume":"36","author":"Boettcher","year":"2022","journal-title":"Best Pract Res Clin Endocrinol Metab"},{"issue":"6","key":"2026091519584394600_dgag237-B4","doi-asserted-by":"crossref","first-page":"337","DOI":"10.1038\/s41574-022-00655-w","article-title":"Management challenges and therapeutic advances in congenital adrenal hyperplasia","volume":"18","author":"Mallappa","year":"2022","journal-title":"Nat Rev Endocrinol"},{"issue":"1","key":"2026091519584394600_dgag237-B5","doi-asserted-by":"crossref","first-page":"91","DOI":"10.1210\/endrev\/bnab016","article-title":"Congenital adrenal hyperplasia\u2014current insights in pathophysiology, diagnostics, and management","volume":"43","author":"Claahsen - van der Grinten","year":"2022","journal-title":"Endocr Rev"},{"issue":"Supplement_1","key":"2026091519584394600_dgag237-B6","doi-asserted-by":"crossref","first-page":"S25","DOI":"10.1210\/clinem\/dgae718","article-title":"Challenges in adolescent and adult males with classic congenital adrenal hyperplasia due to 21-hydroxylase deficiency","volume":"110","author":"Claahsen-van der Grinten","year":"2025","journal-title":"J Clin Endocrinol Metab"},{"key":"2026091519584394600_dgag237-B7","doi-asserted-by":"crossref","first-page":"1226284","DOI":"10.3389\/fendo.2023.1226284","article-title":"The use of liquid chromatography-tandem mass spectrometry in newborn screening for congenital adrenal hyperplasia: improvements and future perspectives","volume":"14","author":"de Hora","year":"2023","journal-title":"Front Endocrinol (Lausanne)"},{"issue":"7","key":"2026091519584394600_dgag237-B8","doi-asserted-by":"crossref","first-page":"1623","DOI":"10.1007\/s40618-025-02581-w","article-title":"Diagnostic cut-offs of 17-hydroxyprogesterone by LC-MS\/MS in children with non-classical congenital adrenal hyperplasia","volume":"48","author":"Bizzarri","year":"2025","journal-title":"J Endocrinol Invest"},{"key":"2026091519584394600_dgag237-B9","doi-asserted-by":"crossref","first-page":"1085","DOI":"10.1038\/s41390-025-04216-5","article-title":"Elevation of corticosterone and 17OH progesterone in extremely preterm infants and clinical implications","volume":"99","author":"Kessel","year":"2026","journal-title":"Pediatr Res"},{"key":"2026091519584394600_dgag237-B10","first-page":"488","article-title":"The first-year outcomes of the nationwide neonatal CAH screening in T\u00fcrkiye: high rate of false positives for 21-hydroxylase deficiency and a higher detection rate of non-classical cases","volume":"17","author":"G\u00fcran","year":"2025","journal-title":"J Clin Res Pediatr Endocrinol"},{"issue":"8","key":"2026091519584394600_dgag237-B11","doi-asserted-by":"crossref","first-page":"e3304","DOI":"10.1210\/clinem\/dgac271","article-title":"A multiclassifier system to identify and subtype congenital adrenal hyperplasia based on circulating steroid hormones","volume":"107","author":"Ye","year":"2022","journal-title":"J Clin Endocrinol Metab"},{"key":"2026091519584394600_dgag237-B12","doi-asserted-by":"crossref","first-page":"1353023","DOI":"10.3389\/fendo.2024.1353023","article-title":"Meta-analysis of machine learning models for the diagnosis of central precocious puberty based on clinical, hormonal (laboratory) and imaging data","volume":"15","author":"Chen","year":"2024","journal-title":"Front Endocrinol (Lausanne)"},{"key":"2026091519584394600_dgag237-B13","doi-asserted-by":"crossref","first-page":"1348","DOI":"10.1210\/clinem\/dgaf612","article-title":"Impact of growth-promoting therapies on puberty, growth, and final height in classical 21-hydroxylase deficiency","volume":"111","author":"Yavas Abali","year":"2026","journal-title":"J Clin Endocrinol Metab"},{"issue":"9","key":"2026091519584394600_dgag237-B14","doi-asserted-by":"crossref","first-page":"e3714","DOI":"10.1210\/clinem\/dgab225","article-title":"Clinical and hormonal profiles correlate with molecular characteristics in patients with 11\u03b2-hydroxylase deficiency","volume":"106","author":"Yildiz","year":"2021","journal-title":"J Clin Endocrinol Metab"},{"issue":"4","key":"2026091519584394600_dgag237-B15","doi-asserted-by":"crossref","first-page":"e1718","DOI":"10.1210\/clinem\/dgaa022","article-title":"Revisiting classical 3\u03b2-hydroxysteroid dehydrogenase 2 deficiency: lessons from 31 pediatric cases","volume":"105","author":"Guran","year":"2020","journal-title":"J Clin Endocrinol Metab"},{"issue":"9-10","key":"2026091519584394600_dgag237-B16","doi-asserted-by":"crossref","first-page":"558","DOI":"10.1159\/000515079","article-title":"Genotypic sex and severity of the disease determine the time of clinical presentation in steroid 17\u03b1-hydroxylase\/17,20-lyase deficiency","volume":"93","author":"Kurnaz","year":"2020","journal-title":"Horm Res Paediatr"},{"issue":"1","key":"2026091519584394600_dgag237-B17","doi-asserted-by":"crossref","first-page":"e106","DOI":"10.1210\/clinem\/dgab619","article-title":"Catch-up growth and discontinuation of fludrocortisone treatment in aldosterone synthase deficiency","volume":"107","author":"Gurpinar Tosun","year":"2022","journal-title":"J Clin Endocrinol Metab"},{"issue":"1","key":"2026091519584394600_dgag237-B18","doi-asserted-by":"crossref","first-page":"284","DOI":"10.1210\/jc.2015-3250","article-title":"Rare causes of primary adrenal insufficiency: genetic and clinical characterization of a large nationwide cohort","volume":"101","author":"Guran","year":"2016","journal-title":"J Clin Endocrinol Metab"},{"issue":"5","key":"2026091519584394600_dgag237-B19","doi-asserted-by":"crossref","first-page":"e1924","DOI":"10.1210\/clinem\/dgac016","article-title":"Steroid hormone profiles and molecular diagnostic tools in pediatric patients with non-CAH primary adrenal insufficiency","volume":"107","author":"Seven Menevse","year":"2022","journal-title":"J Clin Endocrinol Metab"},{"issue":"1","key":"2026091519584394600_dgag237-B20","doi-asserted-by":"crossref","first-page":"265","DOI":"10.1038\/s41390-021-01739-5","article-title":"Adrenal steroids reference ranges in infancy determined by LC-MS\/MS","volume":"92","author":"Enver","year":"2022","journal-title":"Pediatr Res"},{"issue":"2","key":"2026091519584394600_dgag237-B21","doi-asserted-by":"crossref","first-page":"108","DOI":"10.1111\/cen.15080","article-title":"Severe adrenal insufficiency in six neonates with normal newborn screening for CAH","volume":"101","author":"Kurt","year":"2024","journal-title":"Clin Endocrinol (Oxf)"},{"key":"2026091519584394600_dgag237-B22","doi-asserted-by":"crossref","first-page":"652801","DOI":"10.3389\/fenrg.2021.652801","article-title":"A review on data preprocessing techniques toward efficient and reliable knowledge discovery from building operational data","volume":"9","author":"Fan","year":"2021","journal-title":"Front Energy Res"},{"key":"2026091519584394600_dgag237-B23","unstructured":"Harrell \u00a0FE, Levy \u00a0DG. Regression modeling strategies. R package version 6.3-0. 2022."},{"key":"2026091519584394600_dgag237-B24","first-page":"3146","article-title":"Lightgbm: a highly efficient gradient boosting decision tree","volume":"30","author":"Ke","year":"2017","journal-title":"Adv Neural Inf Process Syst"},{"key":"2026091519584394600_dgag237-B25","doi-asserted-by":"crossref","unstructured":"Gurpinar Tosun B, Ercetin AN, Turan S, Bereket A, Arga KY, Guran T. \u00a0Supplementary materials for \u201cMachine Learning Algorithms to Accelerate Etiological Diagnosis of Congenital Disorders of Adrenal Steroidogenesis\u201d. Figshare. 2026. Deposited December 16, 2025. 10.6084\/m9.figshare.30893243","DOI":"10.1210\/clinem\/dgag237"},{"key":"2026091519584394600_dgag237-B26","first-page":"4765","article-title":"A unified approach to interpreting model predictions","volume":"30","author":"Lundberg","year":"2017","journal-title":"Adv Neural Inf Process Syst"},{"issue":"15","key":"2026091519584394600_dgag237-B27","doi-asserted-by":"crossref","first-page":"6638","DOI":"10.3390\/app14156638","article-title":"XAI-Based Clinical decision support systems: a systematic review","volume":"14","author":"Kim","year":"2024","journal-title":"Applied Sciences"}],"container-title":["The Journal of Clinical Endocrinology &amp; Metabolism"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/academic.oup.com\/jcem\/advance-article-pdf\/doi\/10.1210\/clinem\/dgag237\/68625646\/dgag237.pdf","content-type":"application\/pdf","content-version":"am","intended-application":"syndication"},{"URL":"https:\/\/academic.oup.com\/jcem\/article-pdf\/111\/10\/2737\/68625646\/dgag237.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"syndication"},{"URL":"https:\/\/academic.oup.com\/jcem\/article-pdf\/111\/10\/2737\/68625646\/dgag237.pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,9,15]],"date-time":"2026-09-15T23:58:53Z","timestamp":1789516733000},"score":1,"resource":{"primary":{"URL":"https:\/\/academic.oup.com\/jcem\/article\/111\/10\/2737\/8718840"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,6,26]]},"references-count":27,"journal-issue":{"issue":"10","published-online":{"date-parts":[[2026,6,26]]},"published-print":{"date-parts":[[2026,9,16]]}},"URL":"https:\/\/doi.org\/10.1210\/clinem\/dgag237","relation":{},"ISSN":["0021-972X","1945-7197"],"issn-type":[{"value":"0021-972X","type":"print"},{"value":"1945-7197","type":"electronic"}],"subject":[],"published-other":{"date-parts":[[2026,10]]},"published":{"date-parts":[[2026,6,26]]}}}