{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,1,13]],"date-time":"2026-01-13T19:57:58Z","timestamp":1768334278936,"version":"3.49.0"},"reference-count":19,"publisher":"Medical Communications Sp. z.o.o.","issue":"103","license":[{"start":{"date-parts":[[2025,12,31]],"date-time":"2025-12-31T00:00:00Z","timestamp":1767139200000},"content-version":"unspecified","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by-nc-nd\/4.0\/"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["J Ultrason"],"abstract":"<jats:p>Aim: The aim of the study was to train, evaluate, and optimize machine learning models for classifying\nfocal lesions in the thyroid gland as benign or malignant based on their features. Material and methods: A dataset of 841 focal thyroid lesions described by 17 features (ultrasonographic and patient characteristics) was considered. Using the Python programming language, statistical and then exploratory data analyses were conducted using the libraries, including the generation of graphs and heat maps of correlations between the considered features. Binary classification models were selected to categorize the focal lesion on the basis of their characteristics into one of two classes (benign lesion, malignant lesion). The following models were used: logistic regression-based, support vector machine-based, k-nearest neighbor model, Random Forest model, and decision tree classifier. We applied formulas to select those focal lesion features that most contributed to the models\u2019 classification decisions. The final dataset consisted of 841 focal thyroid lesions described by seven ultrasonographic features and histopathological assessment of malignancy (benign or malignant). Classifiers were validated using 10-fold cross-validation. Model performance was evaluated using sensitivity, accuracy, measure-F, precision, area under the ROC curve, PPV, NPV, specificity. Results: The best-performing model (in term of sensitivity) was the classifier based on a support vector machine: sensitivity = 71.17%, accuracy = 83.24%, area under the ROC curve = 84.86%, measure f1 = 69.13%, precision = 68.85%, PPV = 68.49%, NPV = 89.06%. Conclusions: The study demonstrates the usefulness of data science methods in predicting the malignant nature of focal lesions in the thyroid gland. It proves that classification decisions made by the studied models are based on specific ultrasonographic features associated with increased or reduced risk of malignancy.<\/jats:p>","DOI":"10.15557\/jou.2025.0036","type":"journal-article","created":{"date-parts":[[2026,1,13]],"date-time":"2026-01-13T13:19:37Z","timestamp":1768310377000},"source":"Crossref","is-referenced-by-count":0,"title":["Application of data science methods, including machine learning, in the classification of focal lesions in the thyroid gland"],"prefix":"10.15557","volume":"25","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-6177-6783","authenticated-orcid":false,"given":"Pawe\u0142 Mariusz","family":"Gadzicki","sequence":"first","affiliation":[{"name":"Department of Nuclear Medicine, Medical University of Lodz, Poland"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4440-8302","authenticated-orcid":false,"given":"Ma\u0142gorzata","family":"Krzywicka","sequence":"additional","affiliation":[{"name":"Institute of Information Technology, Lodz University of Technology, Poland"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1470-4140","authenticated-orcid":false,"given":"Katarzyna","family":"Dobruch-Sobczak","sequence":"additional","affiliation":[{"name":"Radiology Department II, The Maria Sk\u0142odowska-Curie National Research Institute of Oncology, Poland"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8308-8121","authenticated-orcid":false,"given":"Bartosz","family":"Migda","sequence":"additional","affiliation":[{"name":"Diagnostic Ultrasound Lab, Department of Pediatric Radiology, Medical University of Warsaw, Poland"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3661-3274","authenticated-orcid":false,"given":"Ewelina","family":"Szczepanek-Parulska","sequence":"additional","affiliation":[{"name":"Department of Endocrinology, Metabolism and Internal Medicine, Poznan University of Medical Sciences, Poland"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6124-1236","authenticated-orcid":false,"given":"Agnieszka","family":"Wosiak","sequence":"additional","affiliation":[{"name":"Institute of Information Technology, Lodz University of Technology, Poland"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8713-6936","authenticated-orcid":false,"given":"Zbigniew","family":"Adamczewski","sequence":"additional","affiliation":[{"name":"Department of Nuclear Medicine, Medical University of Lodz, Poland"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"6250","published-online":{"date-parts":[[2025,12,31]]},"reference":[{"key":"ref0","doi-asserted-by":"crossref","unstructured":"1. Dobruch-Sobczak K, Adamczewski Z, Szczepanek-Parulska E, Migda B, Woli\u0144ski K, Krauze A et al.: Histopathological verification of the diagnostic performance of the EU-TIRADS classification of thyroid nodules-results of a multicenter study performed in a previously iodine-deficient region. J Clin Med 2019; 8: 1781. doi: 10.3390\/jcm8111781.","DOI":"10.3390\/jcm8111781"},{"key":"ref1","doi-asserted-by":"crossref","unstructured":"2. Russ G, Bonnema SJ, Erdogan MF, Durante C, Ngu R, Leenhardt L: European Thyroid Association Guidelines for Ultrasound Malignancy Risk Stratification of Thyroid Nodules in Adults: The EU-TIRADS. Eur Thyroid J 2017; 6: 225\u2013237. doi: 10.1159\/000478927.","DOI":"10.1159\/000478927"},{"key":"ref2","doi-asserted-by":"crossref","unstructured":"3. Jarz\u0105b B, Dedecjus M, Lewi\u0144ski A, Adamczewski Z, Baku\u0142a-Zalewska E, Ba\u0142dys-Walig\u00f3rska A et al.: Diagnosis and treatment of thyroid cancer in adult patients \u2013 recommendations of polish scientific societies and the National Oncological Strategy. 2022 Update [Diagnostyka i leczenie raka tarczycy u chorych doros\u0142ych \u2013 rekomendacje polskich towarzystw naukowych oraz Narodowej Strategii Onkologicznej. Aktualizacja na rok 2022]. Endokrynol Pol 2022; 73: 173\u2013300. doi: 10.5603\/EP.a2022.0028.","DOI":"10.5603\/EP.a2022.0028"},{"key":"ref3","doi-asserted-by":"crossref","unstructured":"4. Deng Y, Li H, Wang M, Li N, Tian T, Wu Y et al.: Global burden of thyroid cancer from 1990 to 2017. JAMA Netw Open 2020; 3: e208759. doi: 10.1001\/jamanetworkopen.2020.8759.","DOI":"10.1001\/jamanetworkopen.2020.8759"},{"key":"ref4","doi-asserted-by":"crossref","unstructured":"5. Liu H, Ma AL, Zhou YS, Yang DH, Ruan JL, Liu XD, Luo BM: Variability in the interpretation of grey-scale ultrasound features in assessing thyroid nodules: A systematic review and meta-analysis. Eur J Radiol 2020; 129: 109050. doi: 10.1016\/j.ejrad.2020.109050.","DOI":"10.1016\/j.ejrad.2020.109050"},{"key":"ref5","doi-asserted-by":"crossref","unstructured":"6. Habchi Y, Himeur Y, Kheddar H, Boukabou A, Atalla S, Chouchane A et al.: AI in thyroid cancer diagnosis: techniques, trends, and future directions. Systems 2023; 11: 519. doi: 10.3390\/systems11100519.","DOI":"10.3390\/systems11100519"},{"key":"ref6","doi-asserted-by":"crossref","unstructured":"7. Tessler FN, Thomas J: Artificial intelligence for evaluation of thyroid nodules: a primer. Thyroid 2023; 33: 150\u2013158. doi: 10.1089\/thy.2022.0560.","DOI":"10.1089\/thy.2022.0560"},{"key":"ref7","doi-asserted-by":"crossref","unstructured":"8. Hayashi C, Yajima K, Bock HH, Ohsumi N, Tanaka Y, Baba Y: Data Science, Classification, and Related Methods. Proceedings of the Fifth Conference of the International Federation of Classification Societies (IFCS-96), Kobe, Japan, March 27\u201330, 1996. Springer Japan, 1998.","DOI":"10.1007\/978-4-431-65950-1"},{"key":"ref8","doi-asserted-by":"crossref","unstructured":"9. Caruana R, Niculescu-Mizil A: An empirical comparison of supervised learning algorithms. In ACM Press; 2006; 161\u2013168. doi: 10.1145\/1143844.1143865.","DOI":"10.1145\/1143844.1143865"},{"key":"ref9","doi-asserted-by":"crossref","unstructured":"10. Rodriguez JD, Perez A, Lozano JA: Sensitivity analysis of k-fold cross validation in prediction error estimation. IEEE Trans Pattern Anal Mach Intell 2010; 32: 569\u2013575. doi: 10.1109\/TPAMI.2009.187.","DOI":"10.1109\/TPAMI.2009.187"},{"key":"ref10","doi-asserted-by":"crossref","unstructured":"11. Rodr\u00edguez JD, P\u00e9rez A, Lozano JA. Sensitivity analysis of kappa-fold cross validation in prediction error estimation. IEEE Trans Pattern Anal Mach Intell. 2010 Mar;32(3):569-75. doi: 10.1109\/TPAMI.2009.187. PMID: 20075479.","DOI":"10.1109\/TPAMI.2009.187"},{"key":"ref11","doi-asserted-by":"crossref","unstructured":"12. Topcuoglu OM, Uzunoglu B, Orhan T, Basaran EB, Gormez A, Sarica O. A realworld comparison of the diagnostic performances of six different TI-RADS guidelines, including ACR-\/Kwak-\/K-\/EU-\/ATA-\/C-TIRADS. Clin Imaging 2025; 117: 110366. doi: 10.1016\/j.clinimag.2024.110366.","DOI":"10.1016\/j.clinimag.2024.110366"},{"key":"ref12","doi-asserted-by":"crossref","unstructured":"13. Durante C, Heged\u00fcs L, Na DG, Papini E, Sipos JA, Baek JH et al.: International Expert Consensus on US Lexicon for Thyroid Nodules. Radiology 2023; 309: e231481. doi: 10.1148\/radiol.231481.","DOI":"10.1148\/radiol.231481"},{"key":"ref13","doi-asserted-by":"crossref","unstructured":"14. B\u00f6hland M, Tharun L, Scherr T, Mikut R, Hagenmeyer V, Thompson LDR et al. Machine learning methods for automated classification of tumors with papillary thyroid carcinoma-like nuclei: A quantitative analysis. PLoS One 2021; 16: e0257635. doi: 10.1371\/journal.pone.0257635.","DOI":"10.1371\/journal.pone.0257635"},{"key":"ref14","doi-asserted-by":"crossref","unstructured":"15. Hornik K, Meyer D, Karatzoglou A: Support vector machines in R. Journal of Statistical Software 2006; 15. doi: 10.18637\/jss.v015.i09.","DOI":"10.18637\/jss.v015.i09"},{"key":"ref15","unstructured":"16. Hsu CW, Chang CC, Lin CJ: A Practical Guide to Support Vector Classification. www.csie.ntu.edu.tw\/~cjlin 8.8. 2003."},{"key":"ref16","doi-asserted-by":"crossref","unstructured":"17. Bennett KP, Campbell C: Support Vector Machines: Hype or Hallelujah? ACM SIGKDD Explorations Newsletter 2000; 2: 1\u201313. doi: 10.1145\/380995.380999.","DOI":"10.1145\/380995.380999"},{"key":"ref17","doi-asserted-by":"crossref","unstructured":"18. Peng S, Liu Y, Lv W, Liu L, Zhou Q, Yang H et al.: Deep learning-based artificial intelligence model to assist thyroid nodule diagnosis and management: a multicentre diagnostic study. Lancet Digit Health 2021; 3: e250\u2013e259. doi: 10.1016\/S2589-7500(21)00041-8. Erratum in: Lancet Digit Health 2021; 3: e413.","DOI":"10.1016\/S2589-7500(21)00041-8"},{"key":"ref18","doi-asserted-by":"crossref","unstructured":"19. Xi NM, Wang L, Yang C: Improving the diagnosis of thyroid cancer by machine learning and clinical data. Sci Rep 2022; 12: 11143. doi: 10.1038\/s41598-022-15342-z. Erratum in: Sci Rep 2022; 12: 13252. doi: 10.1038\/s41598-022-17659-1.","DOI":"10.1038\/s41598-022-15342-z"}],"container-title":["Journal of Ultrasonography"],"original-title":[],"deposited":{"date-parts":[[2026,1,13]],"date-time":"2026-01-13T13:19:41Z","timestamp":1768310381000},"score":1,"resource":{"primary":{"URL":"https:\/\/jultrason.pl\/index.php\/wydawnictwa\/volume-25-no-103\/application-of-data-science-methods-including-machine-learning-in-the-classification-of-focal-lesions-in-the-thyroid-gland"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,12,31]]},"references-count":19,"journal-issue":{"issue":"103","published-online":{"date-parts":[[2025,12,31]]}},"URL":"https:\/\/doi.org\/10.15557\/jou.2025.0036","relation":{},"ISSN":["2084-8404","2451-070X"],"issn-type":[{"value":"2084-8404","type":"print"},{"value":"2451-070X","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,12,31]]}}}