{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,20]],"date-time":"2026-07-20T05:02:09Z","timestamp":1784523729263,"version":"3.55.0"},"reference-count":27,"publisher":"Frontiers Media SA","license":[{"start":{"date-parts":[[2026,7,20]],"date-time":"2026-07-20T00:00:00Z","timestamp":1784505600000},"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. Endocrinol."],"abstract":"<jats:sec>\n                    <jats:title>Background<\/jats:title>\n                    <jats:p>The preoperative differentiation between benign H\u00fcrthle cell adenoma (HCA) and malignant H\u00fcrthle cell carcinoma (HCC) remains clinically challenging. This study aimed to develop an interpretable machine learning framework to improve diagnostic accuracy and assist clinical decision-making.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Methods<\/jats:title>\n                    <jats:p>We retrospectively enrolled 554 patients (280 HCA, 274 HCC) from a single center. Fifteen clinical, serological, and ultrasonographic variables were incorporated. Following rigorous feature selection via LASSO and Random Forest algorithms, four advanced machine learning models and logistic regression (LR) were trained and evaluated using 10-fold cross-validation. The SHapley Additive exPlanations (SHAP) and Individual Conditional Expectation (ICE) trajectories were utilized to interpret the optimal model globally and locally.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Results<\/jats:title>\n                    <jats:p>The XGBoost model demonstrated superior discriminative performance, achieving an Area Under the Curve (AUC) of 0.911, significantly outperforming LR (AUC\u00a0=\u00a00.746). Decision curve analysis confirmed its higher clinical net benefit. SHAP analysis demystified the algorithmic \u201cblack box,\u201d identifying vascularity grade, absent halo sign, and elevated serum thyroglobulin as top malignant predictors. Furthermore, patient-specific ICE trajectories successfully simulated counterfactual clinical reasoning for misclassified cases.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Conclusion<\/jats:title>\n                    <jats:p>The SHAP-augmented XGBoost framework provides highly accurate, transparent, and personalized presurgical risk stratification for H\u00fcrthle cell neoplasms, potentially reducing unnecessary diagnostic thyroidectomies.<\/jats:p>\n                  <\/jats:sec>","DOI":"10.3389\/fendo.2026.1865321","type":"journal-article","created":{"date-parts":[[2026,7,20]],"date-time":"2026-07-20T04:21:18Z","timestamp":1784521278000},"update-policy":"https:\/\/doi.org\/10.3389\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["Interpretable machine learning for presurgical differentiation of H\u00fcrthle cell carcinoma and adenoma: a SHAP-augmented approach"],"prefix":"10.3389","volume":"17","author":[{"given":"Junyu","family":"Cao","sequence":"first","affiliation":[{"name":"Department of Breast and Thyroid Surgery, The First People\u2019s Hospital of Yunnan Province, Kunming University of Science and Technology Affiliated Hospital","place":["Kunming, Yunnan, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jing","family":"Li","sequence":"additional","affiliation":[{"name":"Department of Breast and Thyroid Surgery, The First People\u2019s Hospital of Yunnan Province, Kunming University of Science and Technology Affiliated Hospital","place":["Kunming, Yunnan, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Chuancheng","family":"Zhou","sequence":"additional","affiliation":[{"name":"Department of Breast and Thyroid Surgery, The First People\u2019s Hospital of Yunnan Province, Kunming University of Science and Technology Affiliated Hospital","place":["Kunming, Yunnan, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jie","family":"Zhou","sequence":"additional","affiliation":[{"name":"Department of Breast and Thyroid Surgery, The First People\u2019s Hospital of Yunnan Province, Kunming University of Science and Technology Affiliated Hospital","place":["Kunming, Yunnan, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Kunxian","family":"Yang","sequence":"additional","affiliation":[{"name":"Department of Breast and Thyroid Surgery, The First People\u2019s Hospital of Yunnan Province, Kunming University of Science and Technology Affiliated Hospital","place":["Kunming, Yunnan, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"1965","published-online":{"date-parts":[[2026,7,20]]},"reference":[{"key":"B1","doi-asserted-by":"publisher","DOI":"10.3390\/biomedicines10020468","article-title":"The autoantibodies against tumor-associated antigens as potential blood-based biomarkers in thyroid neoplasia: rationales, opportunities and challenges","volume":"10","author":"Belousov","year":"2022","journal-title":"Biomedicines"},{"key":"B2","doi-asserted-by":"publisher","DOI":"10.14366\/usg.21264","article-title":"Ultrasonographic characteristics of Hurthle cell neoplasms: prediction of Malignancy","volume":"41","author":"Kim","year":"2022","journal-title":"Ultrasonography"},{"key":"B3","doi-asserted-by":"publisher","DOI":"10.3390\/cancers13205184","article-title":"Molecular signature expands the landscape of driver negative thyroid cancers","volume":"13","author":"Bim","year":"2021","journal-title":"Cancers (Basel)"},{"key":"B4","doi-asserted-by":"publisher","first-page":"7","DOI":"10.1186\/s13044-021-00098-x","article-title":"Prevalence of thyroid carcinoma in nodules with thy 3 cytology: the role of preoperative ultrasonography and strain elastography","volume":"14","author":"Pikis","year":"2021","journal-title":"Thyroid Res"},{"key":"B5","doi-asserted-by":"publisher","first-page":"24216","DOI":"10.1038\/s41598-024-75677-7","article-title":"Diagnostic sensitivity of fine-needle aspiration cytology in thyroid cancer","volume":"14","author":"Lind","year":"2024","journal-title":"Sci Rep"},{"key":"B6","doi-asserted-by":"publisher","DOI":"10.1016\/j.eclinm.2025.103351","article-title":"Artificial intelligence-augmented ultrasound diagnosis of follicular-patterned thyroid neoplasms: a multicenter retrospective study","volume":"86","author":"Shen","year":"2025","journal-title":"EClinicalMedicine"},{"key":"B7","doi-asserted-by":"publisher","DOI":"10.7717\/peerj.19410","article-title":"Correlation between preoperative uric acid levels and lymph node metastases in patients with papillary thyroid cancer: a retrospective study","volume":"13","author":"Sun","year":"2025","journal-title":"PeerJ"},{"key":"B8","doi-asserted-by":"publisher","DOI":"10.1210\/js.2019-00111","article-title":"Inequitable long-term outcomes for an indigenous population after definitive treatment of patients with Graves disease","volume":"3","author":"Tamatea","year":"2019","journal-title":"J Endocr Soc"},{"key":"B9","doi-asserted-by":"publisher","DOI":"10.3389\/fendo.2025.1564752","article-title":"Lobectomy vs total thyroidectomy for unilateral papillary thyroid carcinoma with ipsilateral cervical lymph node metastasis","volume":"16","author":"Zhang","year":"2025","journal-title":"Front Endocrinol (Lausanne)"},{"key":"B10","doi-asserted-by":"publisher","DOI":"10.32007\/jfacmedbagdad.59386","article-title":"Pre-operative serum TSH level estimation for predicting Malignant nodular thyroid disease","volume":"59","author":"Hamdi","year":"2017","journal-title":"J Faculty Med Baghdad"},{"key":"B11","doi-asserted-by":"publisher","first-page":"79","DOI":"10.1111\/cen.15130","article-title":"Diagnostic nomogram model for ACR TI-RADS 4 nodules based on clinical, biochemical data and sonographic patterns","volume":"102","author":"Wang","year":"2025","journal-title":"Clin Endocrinol (Oxf)"},{"key":"B12","doi-asserted-by":"publisher","DOI":"10.3389\/fonc.2025.1549148","article-title":"Construction of a predictive model for cervical lymph node metastasis in papillary thyroid carcinoma","volume":"15","author":"Hao","year":"2025","journal-title":"Front Oncol"},{"key":"B13","doi-asserted-by":"publisher","DOI":"10.2174\/1570159x21666230808170123","article-title":"Machine learning and pharmacogenomics at the time of precision psychiatry","volume":"21","author":"Del Casale","year":"2023","journal-title":"Curr Neuropharmacol"},{"key":"B14","doi-asserted-by":"publisher","DOI":"10.2147\/rmhp.s328180","article-title":"Machine learning-based prediction for 4-year risk of metabolic syndrome in adults: a retrospective cohort study","volume":"14","author":"Zhang","year":"2021","journal-title":"Risk Manag Healthc Policy"},{"key":"B15","doi-asserted-by":"publisher","DOI":"10.3389\/fpubh.2025.1555697","article-title":"Machine learning algorithms to predict khat chewing practice and its predictors among men aged 15 to 59 in Ethiopia: further analysis of the 2011 and 2016 Ethiopian Demographic and Health Survey","volume":"13","author":"Melaku","year":"2025","journal-title":"Front Public Health"},{"key":"B16","doi-asserted-by":"publisher","DOI":"10.1016\/j.apjon.2025.100680","article-title":"Artificial intelligence-assisted machine learning models for predicting lung cancer survival","volume":"12","author":"Yuan","year":"2025","journal-title":"Asia Pac J Oncol Nurs"},{"key":"B17","doi-asserted-by":"publisher","first-page":"25240","DOI":"10.1038\/s41598-025-10906-1","article-title":"Prediction of gastrointestinal hemorrhage in cardiology inpatients using an interpretable XGBoost model","volume":"15","author":"Li","year":"2025","journal-title":"Sci Rep"},{"key":"B18","doi-asserted-by":"publisher","first-page":"32","DOI":"10.60084\/ijds.v1i1.91","article-title":"Ensemble machine learning approach for quantitative structure activity relationship based drug discovery: a review","volume":"1","author":"Noviandy","year":"2023","journal-title":"Infolitika J Data Sci"},{"key":"B19","doi-asserted-by":"publisher","DOI":"10.3390\/healthcare11071042","article-title":"A machine learning approach for predicting capsular contracture after postmastectomy radiotherapy in breast cancer patients","volume":"11","author":"Bavaro","year":"2023","journal-title":"Healthcare (Basel)"},{"key":"B20","doi-asserted-by":"publisher","DOI":"10.3390\/diagnostics16050752","article-title":"Transforming intracerebral hemorrhage care with artificial intelligence: opportunities, challenges, and future directions","volume":"16","author":"Gao","year":"2026","journal-title":"Diagnostics (Basel)"},{"key":"B21","doi-asserted-by":"publisher","first-page":"1082","DOI":"10.1186\/s12967-025-06965-7","article-title":"Deciphering tumor-intrinsic and immune characteristics in resectable non-small cell lung cancer treated with neoadjuvant pembrolizumab and chemotherapy","volume":"23","author":"Chen","year":"2025","journal-title":"J Transl Med"},{"key":"B22","doi-asserted-by":"publisher","DOI":"10.3390\/jimaging11030073","article-title":"Deepfake media forensics: status and future challenges","volume":"11","author":"Amerini","year":"2025","journal-title":"J Imaging"},{"key":"B23","doi-asserted-by":"publisher","DOI":"10.5376\/cmb.2024.14.0019","article-title":"Biostatistical challenges in high-dimensional data analysis: strategies and innovations","volume":"4","author":"Wang","year":"2024","journal-title":"Comput Mol Biol"},{"key":"B24","doi-asserted-by":"publisher","first-page":"315","DOI":"10.1186\/s12859-023-05446-2","article-title":"An adaptive multi-modal hybrid model for classifying thyroid nodules by combining ultrasound and infrared thermal images","volume":"24","author":"Zhang","year":"2023","journal-title":"BMC Bioinf"},{"key":"B25","doi-asserted-by":"publisher","DOI":"10.1111\/iwj.14098","article-title":"Construction and validation of the perioral moisture-related skin damage (PMASD) risk prediction model in patients with colorectal cancer","volume":"20","author":"Wang","year":"2023","journal-title":"Int Wound J"},{"key":"B26","doi-asserted-by":"publisher","DOI":"10.1200\/go.22.00150","article-title":"Regression derived staging model to predict overall and disease specific survival in patients with major salivary gland carcinomas with independent external validation","volume":"8","author":"Ramalingam","year":"2022","journal-title":"JCO Glob Oncol"},{"key":"B27","doi-asserted-by":"publisher","DOI":"10.3389\/fimmu.2025.1528046","article-title":"Interpretable machine learning algorithms reveal gut microbiome features associated with atopic dermatitis","volume":"16","author":"Ma","year":"2025","journal-title":"Front Immunol"}],"container-title":["Frontiers in Endocrinology"],"original-title":[],"link":[{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/fendo.2026.1865321\/full","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,7,20]],"date-time":"2026-07-20T04:21:19Z","timestamp":1784521279000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/fendo.2026.1865321\/full"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,7,20]]},"references-count":27,"alternative-id":["10.3389\/fendo.2026.1865321"],"URL":"https:\/\/doi.org\/10.3389\/fendo.2026.1865321","relation":{},"ISSN":["1664-2392"],"issn-type":[{"value":"1664-2392","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,7,20]]},"article-number":"1865321"}}