{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,9,18]],"date-time":"2026-09-18T04:28:12Z","timestamp":1789705692415,"version":"4.0.1"},"reference-count":36,"publisher":"Frontiers Media SA","license":[{"start":{"date-parts":[[2023,12,19]],"date-time":"2023-12-19T00:00:00Z","timestamp":1702944000000},"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. Vet. Sci."],"abstract":"<jats:sec><jats:title>Introduction<\/jats:title><jats:p>Hypothyroidism can be easily misdiagnosed in dogs, and prediction models can support clinical decision-making, avoiding unnecessary testing and treatment. The aim of this study is to develop and internally validate diagnostic prediction models for hypothyroidism in dogs by applying machine-learning algorithms.<\/jats:p><\/jats:sec><jats:sec><jats:title>Methods<\/jats:title><jats:p>A single-institutional cross-sectional study was designed searching the electronic database of a Veterinary Teaching Hospital for dogs tested for hypothyroidism. Hypothyroidism was diagnosed based on suggestive clinical signs and thyroid function tests. Dogs were excluded if medical records were incomplete or a definitive diagnosis was lacking. Predictors identified after data processing were dermatological signs, alopecia, lethargy, hematocrit, serum concentrations of cholesterol, creatinine, total thyroxine (tT4), and thyrotropin (cTSH). Four models were created by combining clinical signs and clinicopathological variables expressed as quantitative (models 1 and 2) and qualitative variables (models 3 and 4). Models 2 and 4 included tT4 and cTSH, models 1 and 3 did not. Six different algorithms were applied to each model. Internal validation was performed using a 10-fold cross-validation. Apparent performance was evaluated by calculating the area under the receiver operating characteristic curve (AUROC).<\/jats:p><\/jats:sec><jats:sec><jats:title>Results<\/jats:title><jats:p>Eighty-two hypothyroid and 233 euthyroid client-owned dogs were included. The best performing algorithms were naive Bayes in model 1 (AUROC\u2009=\u20090.85; 95% confidence interval [CI]\u2009=\u20090.83\u20130.86) and in model 2 (AUROC\u2009=\u20090.98; 95% CI\u2009=\u20090.97\u20130.99), logistic regression in model 3 (AUROC\u2009=\u20090.88; 95% CI\u2009=\u20090.86\u20130.89), and random forest in model 4 (AUROC\u2009=\u20090.99; 95% CI\u2009=\u20090.98\u20130.99). Positive predictive value was 0.76, 0.84, 0.93, and 0.97 in model 1, 2, 3, and 4, respectively. Negative predictive value was 0.89, 0.89, 0.99, and 0.99 in model 1, 2, 3, and 4, respectively.<\/jats:p><\/jats:sec><jats:sec><jats:title>Discussion<\/jats:title><jats:p>Machine learning-based prediction models were accurate in predicting and quantifying the likelihood of hypothyroidism in dogs based on internal validation performed in a single-institution, but external validation is required to support the clinical applicability of these models.<\/jats:p><\/jats:sec>","DOI":"10.3389\/fvets.2023.1292988","type":"journal-article","created":{"date-parts":[[2023,12,19]],"date-time":"2023-12-19T08:28:11Z","timestamp":1702974491000},"update-policy":"https:\/\/doi.org\/10.3389\/crossmark-policy","source":"Crossref","is-referenced-by-count":3,"title":["Development and internal validation of diagnostic prediction models using machine-learning algorithms in dogs with hypothyroidism"],"prefix":"10.3389","volume":"10","author":[{"given":"Andrea","family":"Corsini","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Francesco","family":"Lunetta","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Fabrizio","family":"Alboni","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Ignazio","family":"Drudi","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Eugenio","family":"Faroni","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Federico","family":"Fracassi","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"1965","published-online":{"date-parts":[[2023,12,19]]},"reference":[{"key":"ref1","doi-asserted-by":"publisher","first-page":"105","DOI":"10.1080\/00480169.2011.563729","article-title":"Canine hypothyroidism: a review of aetiology and diagnosis","volume":"59","author":"Mooney","year":"2011","journal-title":"N Z Vet J"},{"key":"ref2","doi-asserted-by":"publisher","first-page":"481","DOI":"10.1136\/vr.145.17.481","article-title":"Epidemiological, clinical, haematological and biochemical characteristics of canine hypothyroidism","volume":"145","author":"Dixon","year":"1999","journal-title":"Vet Rec"},{"key":"ref3","doi-asserted-by":"publisher","first-page":"89","DOI":"10.1111\/jsap.13212","article-title":"Symmetric dimethylarginine concentrations in dogs with hypothyroidism before and after treatement with levothyroxine","volume":"62","author":"di Paola","year":"2021","journal-title":"J Small Anim Pract"},{"key":"ref4","doi-asserted-by":"publisher","first-page":"257","DOI":"10.1111\/jsap.13290","article-title":"Recombinant human thyrotropin stimulation test in 114 dogs with suspected hypothyroidism: a cross-sectional study","volume":"62","author":"Corsini","year":"2021","journal-title":"J Small Anim Pract"},{"key":"ref5","doi-asserted-by":"publisher","first-page":"243","DOI":"10.1046\/j.1365-2885.2000.00278.x","article-title":"Changes in serum thyroxine and thyroid-stimulating hormone concentrations in epileptic dogs receiving phenobarbital for one year","volume":"23","author":"Gaskill","year":"2000","journal-title":"J Vet Pharmacol Ther"},{"key":"ref6","doi-asserted-by":"publisher","first-page":"765","DOI":"10.2460\/javma.2001.219.765","article-title":"Serum total thyroxine, total triiodothyronine, free thyroxine, and thyrotropin concentrations in dogs with nonthyroidal disease","volume":"219","author":"Kantrowitz","year":"2001","journal-title":"J Am Vet Med Assoc"},{"key":"ref7","doi-asserted-by":"publisher","first-page":"11","DOI":"10.1111\/j.1748-5827.2007.00418.x","article-title":"Thyroid hormone abnormalities and outcome in dogs with non-thyroidal illness","volume":"49","author":"Mooney","year":"2008","journal-title":"J Small Anim Pract"},{"key":"ref8","doi-asserted-by":"publisher","first-page":"377","DOI":"10.1111\/jvim.14882","article-title":"Effects of Toceranib phosphate on the hypothalamic-pituitary-thyroid Axis in tumor-bearing dogs","volume":"32","author":"Hume","year":"2018","journal-title":"J Vet Intern Med"},{"key":"ref9","doi-asserted-by":"publisher","first-page":"433","DOI":"10.1111\/vco.12538","article-title":"Investigation of thyroid function in dogs treated with the tyrosine kinase inhibitor toceranib","volume":"18","author":"Harper","year":"2020","journal-title":"Vet Comp Oncol"},{"key":"ref10","doi-asserted-by":"publisher","first-page":"1097","DOI":"10.1292\/jvms.19-0169","article-title":"Risk factors for low plasma thyroxine and high plasma thyroid-stimulating hormone concentrations in dogs with non-thyroidal diseases","volume":"81","author":"NISHII","year":"2019","journal-title":"J Vet Med Sci"},{"key":"ref11","doi-asserted-by":"publisher","first-page":"72","DOI":"10.1111\/j.1748-5827.1999.tb03040.x","article-title":"Evaluation of serum free thyroxine and thyrotropin concentrations in the diagnosis of canine hypothyroidism","volume":"40","author":"Dixon","year":"1999","journal-title":"J Small Anim Pract"},{"key":"ref12","doi-asserted-by":"publisher","first-page":"183","DOI":"10.1024\/0036-7281.146.4.183","article-title":"Endogenous TSH in the diagnosis of hypothyroidism in dogs","volume":"146","author":"Boretti","year":"2004","journal-title":"Schweiz Arch Tierheilkd"},{"key":"ref13","doi-asserted-by":"publisher","first-page":"616","DOI":"10.1136\/vr.161.18.616","article-title":"Thyroid hormone concentrations in young, healthy, pretraining greyhounds","volume":"161","author":"Shiel","year":"2007","journal-title":"Vet Rec"},{"key":"ref14","doi-asserted-by":"publisher","first-page":"429","DOI":"10.1111\/j.1751-0813.2008.00357.x","article-title":"Evaluation of the thyroid status of basenji dogs in Australia","volume":"86","author":"Seavers","year":"2008","journal-title":"Aust Vet J"},{"key":"ref15","doi-asserted-by":"publisher","first-page":"346","DOI":"10.1111\/vcp.12067","article-title":"Breed-specific biochemical reference intervals for the adult Dogue de Bordeaux","volume":"42","author":"Lavou\u00e9","year":"2013","journal-title":"Vet Clin Pathol"},{"key":"ref16","doi-asserted-by":"publisher","first-page":"452","DOI":"10.1111\/avj.12117","article-title":"Haematological and biochemical variations among eight sighthound breeds","volume":"91","author":"Uhr\u00edkov\u00e1","year":"2013","journal-title":"Aust Vet J"},{"key":"ref17","doi-asserted-by":"publisher","first-page":"2012","DOI":"10.2460\/ajvr.67.12.2012","article-title":"Evaluation of recombinant human thyroid-stimulating hormone to test thyroid function in dogs suspected of having hypothyroidism","volume":"67","author":"Boretti","year":"2006","journal-title":"Am J Vet Res"},{"key":"ref18","doi-asserted-by":"publisher","first-page":"25","DOI":"10.1892\/0891-6640(2007)21[25:AOTFID]2.0.CO;2","article-title":"Assessment of thyroid function in dogs with low plasma thyroxine concentration","volume":"21","author":"Diaz Espineira","year":"2007","journal-title":"J Vet Intern Med"},{"key":"ref19","doi-asserted-by":"publisher","first-page":"856","DOI":"10.1111\/j.1939-1676.2009.0336.x","article-title":"Comparison of 2 doses of recombinant human thyrotropin for thyroid function testing in healthy and suspected hypothyroid dogs","volume":"23","author":"Boretti","year":"2009","journal-title":"J Vet Intern Med"},{"key":"ref20","doi-asserted-by":"publisher","first-page":"278","DOI":"10.1111\/j.1748-5827.2011.01205.x","article-title":"Assessment of the value of quantitative thyroid scintigraphy for determination of thyroid function in dogs","volume":"53","author":"Shiel","year":"2012","journal-title":"J Small Anim Pract"},{"key":"ref21","doi-asserted-by":"publisher","first-page":"2306","DOI":"10.1111\/jvim.15851","article-title":"Development and internal validation of a prediction tool to aid the diagnosis of Cushing\u2019s syndrome in dogs attending primary-care practice","volume":"34","author":"Schofield","year":"2020","journal-title":"J Vet Intern Med"},{"key":"ref22","doi-asserted-by":"publisher","first-page":"106396","DOI":"10.1016\/j.domaniend.2019.106396","article-title":"Machine learning algorithm as a diagnostic tool for hypoadrenocorticism in dogs","volume":"72","author":"Reagan","year":"2020","journal-title":"Domest Anim Endocrinol"},{"key":"ref23","doi-asserted-by":"publisher","first-page":"275","DOI":"10.1080\/10408363.2020.1857681","article-title":"Potential value and impact of data mining and machine learning in clinical diagnostics","volume":"58","author":"Saberi-Karimian","year":"2021","journal-title":"Crit Rev Clin Lab Sci"},{"key":"ref24","doi-asserted-by":"crossref","first-page":"1572","DOI":"10.2460\/javma.1998.212.10.1572","article-title":"Effect of time of sample collection on serum thyroid-stimulating hormone concentrations in euthyroid and hypothyroid dogs","volume":"212","author":"Bruner","year":"1998","journal-title":"J Am Vet Med Assoc"},{"key":"ref25","doi-asserted-by":"publisher","first-page":"607","DOI":"10.1111\/jvim.15703","article-title":"Comparison of 2 assays for measuring serum total thyroxine concentration in dogs and cats","volume":"34","author":"Wolff","year":"2020","journal-title":"J Vet Intern Med"},{"key":"ref26","doi-asserted-by":"publisher","first-page":"19","DOI":"10.1016\/S0739-7240(99)00060-0","article-title":"Secretion pattern of thyroid-stimulating hormone in dogs during euthyroidism and hypothyroidism","volume":"18","author":"Kooistra","year":"2000","journal-title":"Domest Anim Endocrinol"},{"key":"ref27","doi-asserted-by":"publisher","first-page":"441","DOI":"10.1111\/vcp.12006","article-title":"ASVCP reference interval guidelines: determination of de novo reference intervals in veterinary species and other related topics","volume":"41","author":"Friedrichs","year":"2012","journal-title":"Vet Clin Pathol"},{"key":"ref28","doi-asserted-by":"publisher","first-page":"47112","DOI":"10.1109\/ACCESS.2021.3068614","article-title":"The benefits of the Matthews correlation coefficient (MCC) over the diagnostic odds ratio (DOR) in binary classification assessment","volume":"9","author":"Chicco","year":"2021","journal-title":"IEEE Access"},{"key":"ref29","doi-asserted-by":"publisher","first-page":"W1","DOI":"10.7326\/M14-0698","article-title":"Transparent reporting of a multivariable prediction model for individual prognosis or diagnosis (TRIPOD): explanation and elaboration","volume":"162","author":"Moons","year":"2015","journal-title":"Ann Intern Med"},{"key":"ref30","doi-asserted-by":"publisher","first-page":"g7594","DOI":"10.1136\/bmj.g7594","article-title":"Transparent reporting of a multivariable prediction model for individual prognosis or diagnosis (TRIPOD): the TRIPOD statement","volume":"350","author":"Collins","year":"2015","journal-title":"BMJ"},{"key":"ref31","doi-asserted-by":"publisher","first-page":"2644","DOI":"10.1111\/jvim.15623","article-title":"Predicting early risk of chronic kidney disease in cats using routine clinical laboratory tests and machine learning","volume":"33","author":"Bradley","year":"2019","journal-title":"J Vet Intern Med"},{"key":"ref32","doi-asserted-by":"publisher","first-page":"1140","DOI":"10.1177\/1098612X211001273","article-title":"Machine-learning algorithm as a prognostic tool in non-obstructive acute-on-chronic kidney disease in the cat","volume":"23","author":"Renard","year":"2021","journal-title":"J Feline Med Surg"},{"key":"ref33","doi-asserted-by":"publisher","first-page":"1","DOI":"10.3390\/s22093128","article-title":"Diagnostic classification of cases of canine Leishmaniasis using machine learning","volume":"22","author":"Ferreira","year":"2022","journal-title":"Sensors"},{"key":"ref34","doi-asserted-by":"crossref","first-page":"761","DOI":"10.2460\/javma.1994.204.05.761","article-title":"Hypothyroidism in dogs: 66 cases (1987-1992)","volume":"204","author":"Panciera","year":"1994","journal-title":"J Am Vet Med Assoc"},{"key":"ref35","doi-asserted-by":"publisher","first-page":"m441","DOI":"10.1136\/bmj.m441","article-title":"Calculating the sample size required for developing a clinical prediction model","volume":"368","author":"Riley","year":"2020","journal-title":"BMJ"},{"key":"ref36","doi-asserted-by":"publisher","first-page":"710","DOI":"10.1093\/aje\/kwk052","article-title":"Relaxing the rule of ten events per variable in logistic and cox regression","volume":"165","author":"Vittinghoff","year":"2007","journal-title":"Am J Epidemiol"}],"container-title":["Frontiers in Veterinary Science"],"original-title":[],"link":[{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/fvets.2023.1292988\/full","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,12,28]],"date-time":"2023-12-28T18:22:16Z","timestamp":1703787736000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/fvets.2023.1292988\/full"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,12,19]]},"references-count":36,"alternative-id":["10.3389\/fvets.2023.1292988"],"URL":"https:\/\/doi.org\/10.3389\/fvets.2023.1292988","relation":{},"ISSN":["2297-1769"],"issn-type":[{"value":"2297-1769","type":"electronic"}],"subject":[],"published":{"date-parts":[[2023,12,19]]},"article-number":"1292988"}}