{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,9,30]],"date-time":"2026-09-30T05:19:19Z","timestamp":1790745559778,"version":"4.1.0"},"reference-count":40,"publisher":"Oxford University Press (OUP)","issue":"11","license":[{"start":{"date-parts":[[2018,11,1]],"date-time":"2018-11-01T00:00:00Z","timestamp":1541030400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/academic.oup.com\/journals\/pages\/open_access\/funder_policies\/chorus\/standard_publication_model"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2018,11,1]]},"abstract":"<jats:title>Abstract<\/jats:title>\n               <jats:sec>\n                  <jats:title>BACKGROUND<\/jats:title>\n                  <jats:p>Urine steroid profiles are used in clinical practice for the diagnosis and monitoring of disorders of steroidogenesis and adrenal pathologies. Machine learning (ML) algorithms are powerful computational tools used extensively for the recognition of patterns in large data sets. Here, we investigated the utility of various ML algorithms for the automated biochemical interpretation of urine steroid profiles to support current clinical practices.<\/jats:p>\n               <\/jats:sec>\n               <jats:sec>\n                  <jats:title>METHODS<\/jats:title>\n                  <jats:p>Data from 4619 urine steroid profiles processed between June 2012 and October 2016 were retrospectively collected. Of these, 1314 profiles were used to train and test various ML classifiers' abilities to differentiate between \u201cNo significant abnormality\u201d and \u201c?Abnormal\u201d profiles. Further classifiers were trained and tested for their ability to predict the specific biochemical interpretation of the profiles.<\/jats:p>\n               <\/jats:sec>\n               <jats:sec>\n                  <jats:title>RESULTS<\/jats:title>\n                  <jats:p>The best performing binary classifier could predict the interpretation of No significant abnormality and ?Abnormal profiles with a mean area under the ROC curve of 0.955 (95% CI, 0.949\u20130.961). In addition, the best performing multiclass classifier could predict the individual abnormal profile interpretation with a mean balanced accuracy of 0.873 (0.865\u20130.880).<\/jats:p>\n               <\/jats:sec>\n               <jats:sec>\n                  <jats:title>CONCLUSIONS<\/jats:title>\n                  <jats:p>Here we have described the application of ML algorithms to the automated interpretation of urine steroid profiles. This provides a proof-of-concept application of ML algorithms to complex clinical laboratory data that has the potential to improve laboratory efficiency in a setting of limited staff resources.<\/jats:p>\n               <\/jats:sec>","DOI":"10.1373\/clinchem.2018.292201","type":"journal-article","created":{"date-parts":[[2018,8,10]],"date-time":"2018-08-10T13:45:14Z","timestamp":1533908714000},"page":"1586-1595","source":"Crossref","is-referenced-by-count":59,"title":["Using Machine Learning to Aid the Interpretation of Urine Steroid Profiles"],"prefix":"10.1093","volume":"64","author":[{"given":"Edmund H","family":"Wilkes","sequence":"first","affiliation":[{"name":"Department of Clinical Biochemistry, University College London Hospitals, London, UK"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Gill","family":"Rumsby","sequence":"first","affiliation":[{"name":"Department of Clinical Biochemistry, University College London Hospitals, London, UK"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Gary M","family":"Woodward","sequence":"first","affiliation":[{"name":"Department of Clinical Biochemistry, University College London Hospitals, London, UK"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"286","published-online":{"date-parts":[[2018,11,1]]},"reference":[{"key":"2020022606050864900_B1","doi-asserted-by":"crossref","first-page":"474","DOI":"10.1258\/0004563042466721","article-title":"External quality assessment of urinary steroid profile analysis","volume":"41","author":"Phillips","year":"2004","journal-title":"Ann Clin Biochem"},{"key":"2020022606050864900_B2","doi-asserted-by":"crossref","first-page":"154","DOI":"10.1309\/AJCPIV2OG8TEGHHZ","article-title":"Building a laboratory workforce to meet the future: ASCP task force on the laboratory professionals workforce","volume":"141","author":"Bennett","year":"2014","journal-title":"Am J Clin Pathol"},{"key":"2020022606050864900_B3","doi-asserted-by":"crossref","first-page":"29","DOI":"10.7326\/0003-4819-157-1-201207030-00450","article-title":"Effect of clinical decision-support systems: a systematic review","volume":"157","author":"Bright","year":"2012","journal-title":"Ann Intern Med"},{"key":"2020022606050864900_B4","doi-asserted-by":"crossref","first-page":"309","DOI":"10.1016\/B978-0-12-398476-0.00011-7","article-title":"Generation of knowledge for clinical decision support. Statistical and machine learning techniques","volume-title":"Clinical decision support: the road to broad adoption","author":"Matheny","year":"2014","edition":"2nd Ed"},{"key":"2020022606050864900_B5","doi-asserted-by":"crossref","first-page":"406","DOI":"10.1309\/AJCPQIRIB3CT1EJV","article-title":"Detection of preanalytic laboratory testing errors using a statistically guided protocol","volume":"138","author":"Baron","year":"2012","journal-title":"Am J Clin Pathol"},{"key":"2020022606050864900_B6","doi-asserted-by":"crossref","first-page":"42","DOI":"10.1309\/AJCP05XBCQPHTLGQ","article-title":"Enhanced creatinine and estimated glomerular filtration rate reporting to facilitate detection of acute kidney injury","volume":"143","author":"Baron","year":"2015","journal-title":"Am J Clin Pathol"},{"key":"2020022606050864900_B7","doi-asserted-by":"crossref","first-page":"778","DOI":"10.1093\/ajcp\/aqw064","article-title":"Using machine learning to predict laboratory test results","volume":"145","author":"Luo","year":"2016","journal-title":"Am J Clin Pathol"},{"key":"2020022606050864900_B8","doi-asserted-by":"crossref","first-page":"1458","DOI":"10.1515\/CCLM.2008.284","article-title":"An expert system for the classification of serum protein electrophoresis patterns","volume":"46","author":"Altinier","year":"2008","journal-title":"Clin Chem Lab Med"},{"key":"2020022606050864900_B9","doi-asserted-by":"crossref","first-page":"3375","DOI":"10.1210\/jc.2011-1565","article-title":"Urine steroid metabolomics as a biomarker tool for detecting malignancy in adrenal tumors","volume":"96","author":"Arlt","year":"2011","journal-title":"J Clin Endocrinol Metab"},{"key":"2020022606050864900_B10","doi-asserted-by":"crossref","first-page":"41","DOI":"10.1016\/j.aca.2013.01.003","article-title":"Statistical discrimination of steroid profiles in doping control with support vector machines","volume":"768","author":"Van Renterghem","year":"2013","journal-title":"Anal Chim Acta"},{"key":"2020022606050864900_B11","doi-asserted-by":"crossref","first-page":"110","DOI":"10.3389\/fendo.2018.00110","article-title":"Serum steroid ratio profiles in prostate cancer: a new diagnostic tool toward personalized medicine approach","volume":"9","author":"Albini","year":"2018","journal-title":"Front Endocrinol"},{"key":"2020022606050864900_B12","doi-asserted-by":"crossref","first-page":"65","DOI":"10.1016\/0169-7439(88)80127-8","article-title":"Towards a steroid-profiling expert system","volume":"5","author":"Dybowski","year":"1988","journal-title":"Chemom Intell Lab Syst"},{"key":"2020022606050864900_B13","doi-asserted-by":"crossref","first-page":"321","DOI":"10.1038\/nrg3920","article-title":"Machine learning applications in genetics and genomics","volume":"16","author":"Libbrecht","year":"2015","journal-title":"Nat Rev Genet"},{"key":"2020022606050864900_B14","doi-asserted-by":"crossref","first-page":"184","DOI":"10.1007\/s005210170010","article-title":"Financial forecasting using support vector machines","volume":"10","author":"Cao","year":"2001","journal-title":"Neural Comput Appl"},{"key":"2020022606050864900_B15","doi-asserted-by":"publisher","article-title":"Estimating risk of severe neonatal morbidity in preterm births under 32 weeks of gestation","author":"Hamilton","DOI":"10.1080\/14767058.2018.1487395"},{"key":"2020022606050864900_B16","first-page":"18","article-title":"Classification and regression by randomForest","author":"Liaw","year":"2002","journal-title":"R News"},{"issue":"i05","key":"2020022606050864900_B17","article-title":"Building predictive models in R using the caret package","volume":"28","author":"Kuhn","year":"2008","journal-title":"J Stat Softw"},{"key":"2020022606050864900_B18","first-page":"785","article-title":"XGBoost: a scalable tree boosting system","author":"Chen"},{"key":"2020022606050864900_B19","doi-asserted-by":"crossref","first-page":"1","DOI":"10.18637\/jss.v077.i03","article-title":"WSRF: an R package for classification with scalable weighted subspace random forests","volume":"77","author":"Zhao","year":"2017","journal-title":"J Stat Softw"},{"key":"2020022606050864900_B20","doi-asserted-by":"crossref","first-page":"5","DOI":"10.1023\/A:1010933404324","article-title":"Random forests","volume":"45","author":"Breiman","year":"2001","journal-title":"Mach Learn"},{"key":"2020022606050864900_B21","first-page":"96","article-title":"An empirical evaluation of supervised learning in high dimensions","author":"Caruana"},{"key":"2020022606050864900_B22","doi-asserted-by":"crossref","first-page":"1636","DOI":"10.1093\/bioinformatics\/btg210","article-title":"Comparison of statistical methods for classification of ovarian cancer using mass spectrometry data","volume":"19","author":"Wu","year":"2003","journal-title":"Bioinformatics"},{"key":"2020022606050864900_B23","doi-asserted-by":"crossref","first-page":"319","DOI":"10.1186\/1471-2105-9-319","article-title":"A comprehensive comparison of random forests and support vector machines for microarray-based cancer classification","volume":"9","author":"Statnikov","year":"2008","journal-title":"BMC Bioinformatics"},{"key":"2020022606050864900_B24","doi-asserted-by":"crossref","first-page":"869","DOI":"10.1016\/j.csda.2004.03.017","article-title":"An extensive comparison of recent classification tools applied to microarray data","volume":"48","author":"Lee","year":"2005","journal-title":"Comput Stat Data Anal"},{"key":"2020022606050864900_B25","doi-asserted-by":"crossref","first-page":"299","DOI":"10.1186\/1756-0500-4-299","article-title":"Data mining methods in the prediction of dementia: a real-data comparison of the accuracy, sensitivity and specificity of linear discriminant analysis, logistic regression, neural networks, support vector machines, classification trees and random forests","volume":"4","author":"Maroco","year":"2011","journal-title":"BMC Res Notes"},{"key":"2020022606050864900_B26","first-page":"3121","article-title":"The balanced accuracy and its posterior distribution","author":"Brodersen"},{"key":"2020022606050864900_B27","doi-asserted-by":"crossref","first-page":"306","DOI":"10.1002\/gepi.20211","article-title":"A balanced accuracy function for epistasis modeling in imbalanced data sets using multifactor dimensionality reduction","volume":"31","author":"Velez","year":"2007","journal-title":"Genet Epidemiol"},{"key":"2020022606050864900_B28","doi-asserted-by":"crossref","first-page":"1","DOI":"10.18637\/jss.v036.i11","article-title":"Feature selection with the Boruta package","volume":"36","author":"Kursa","year":"2010","journal-title":"J Stat Softw"},{"key":"2020022606050864900_B29","doi-asserted-by":"crossref","first-page":"4","DOI":"10.1109\/34.824819","article-title":"Statistical pattern recognition: a review","volume":"22","author":"Jain","year":"2000","journal-title":"IEEE Trans Pattern Anal Mach Intel"},{"key":"2020022606050864900_B30","doi-asserted-by":"crossref","first-page":"1213","DOI":"10.1016\/j.clinbiochem.2016.07.013","article-title":"Clinical chemistry in higher dimensions: machine-learning and enhanced prediction from routine clinical chemistry data","volume":"49","author":"Richardson","year":"2016","journal-title":"Clin Biochem"},{"key":"2020022606050864900_B31","doi-asserted-by":"crossref","first-page":"2277","DOI":"10.1210\/jc.2018-00054","article-title":"Urine and serum sex steroid profile in testosterone-treated transgender and hypogonadal and healthy control men","volume":"103","author":"Savkovic","year":"2018","journal-title":"J Clin Endocrinol Metab"},{"key":"2020022606050864900_B32","doi-asserted-by":"crossref","first-page":"2985","DOI":"10.1093\/bioinformatics\/bth343","article-title":"Supervised machine learning techniques for the classification of metabolic disorders in newborns","volume":"20","author":"Baumgartner","year":"2004","journal-title":"Bioinformatics"},{"key":"2020022606050864900_B33","doi-asserted-by":"crossref","first-page":"2125","DOI":"10.1016\/S0140-6736(05)66736-0","article-title":"Congenital adrenal hyperplasia","volume":"365","author":"Merke","year":"2005","journal-title":"Lancet"},{"key":"2020022606050864900_B34","doi-asserted-by":"crossref","first-page":"776","DOI":"10.1056\/NEJMra021561","article-title":"Congenital adrenal hyperplasia","volume":"349","author":"Speiser","year":"2003","journal-title":"N Engl J Med"},{"key":"2020022606050864900_B35","doi-asserted-by":"crossref","first-page":"81","DOI":"10.1210\/er.2010-0013","article-title":"The molecular biology, biochemistry, and physiology of human steroidogenesis and its disorders","volume":"32","author":"Miller","year":"2011","journal-title":"Endocr Rev"},{"key":"2020022606050864900_B36","article-title":"An atlas of gas chromatographic profiles of neutral urinary steroids in health and disease","author":"Shackleton"},{"key":"2020022606050864900_B37","doi-asserted-by":"crossref","first-page":"433","DOI":"10.1111\/j.1365-2265.1982.tb02757.x","article-title":"Investigation of urinary steroid profiles as a diagnostic method in Cushing's syndrome","volume":"16","author":"Phillipou","year":"1982","journal-title":"Clin Endocrinol (Oxf)"},{"key":"2020022606050864900_B38","doi-asserted-by":"crossref","first-page":"574","DOI":"10.1016\/j.jsbmb.2010.03.031","article-title":"A new marker for early diagnosis of 21-hydroxylase deficiency: 3\u03b2,16\u03b1,17\u03b1-trihydroxy-5\u03b1-pregnane-7,20-dione","volume":"121","author":"Christakoudi","year":"2010","journal-title":"J Steroid Biochem Mol Biol"},{"key":"2020022606050864900_B39","doi-asserted-by":"crossref","first-page":"429","DOI":"10.3233\/IDA-2002-6504","article-title":"The class imbalance problem: a systematic study","volume":"6","author":"Japkowicz","year":"2002","journal-title":"Intel Data Anal"},{"key":"2020022606050864900_B40","doi-asserted-by":"crossref","first-page":"255","DOI":"10.1023\/B:MACH.0000015881.36452.6e","article-title":"Is combining classifiers with stacking better than selecting the best one?","volume":"54","author":"Dzeroski","year":"2004","journal-title":"Machine Learning"}],"container-title":["Clinical Chemistry"],"original-title":[],"language":"en","link":[{"URL":"http:\/\/academic.oup.com\/clinchem\/article-pdf\/64\/11\/1586\/32643120\/clinchem1586.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"syndication"},{"URL":"http:\/\/academic.oup.com\/clinchem\/article-pdf\/64\/11\/1586\/32643120\/clinchem1586.pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2020,2,26]],"date-time":"2020-02-26T11:13:49Z","timestamp":1582715629000},"score":1,"resource":{"primary":{"URL":"https:\/\/academic.oup.com\/clinchem\/article\/64\/11\/1586\/5608626"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2018,11,1]]},"references-count":40,"journal-issue":{"issue":"11","published-online":{"date-parts":[[2018,11,1]]},"published-print":{"date-parts":[[2018,11,1]]}},"URL":"https:\/\/doi.org\/10.1373\/clinchem.2018.292201","relation":{},"ISSN":["0009-9147","1530-8561"],"issn-type":[{"value":"0009-9147","type":"print"},{"value":"1530-8561","type":"electronic"}],"subject":[],"published-other":{"date-parts":[[2018,11,1]]},"published":{"date-parts":[[2018,11,1]]}}}