{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,1,19]],"date-time":"2026-01-19T22:57:48Z","timestamp":1768863468771,"version":"3.49.0"},"reference-count":27,"publisher":"MDPI AG","issue":"1","license":[{"start":{"date-parts":[[2026,1,19]],"date-time":"2026-01-19T00:00:00Z","timestamp":1768780800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"name":"MSU Program of Development","award":["23-SCH-04-34"],"award-info":[{"award-number":["23-SCH-04-34"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Life"],"abstract":"<jats:p>Background: The differentiation of pheochromocytoma (PCC) from other adrenal lesions, particularly in incidentalomas with non-benign radiological characteristics (size &gt; 4 cm or density &gt; 10 HU), remains a clinical challenge. The study aimed to develop and validate an interpretable machine learning (ML) model for pairwise differentiation of PCC from adrenocortical carcinomas (ACCs) and non-functioning adrenal adenomas (NAAs) and to identify the most important clinical features. Methods: We analyzed a dataset of 50 clinical, laboratory, and radiological parameters from 123 patients with histologically verified adrenal tumors (63 PCC, 30 ACC, 30 NAA). Four classifiers\u2014Logistic Regression (LR), Random Forest (RF), Linear Discriminant Analysis (LDA), and Extreme Gradient Boosting (XGBoost)\u2014were trained for binary classification tasks (PCC vs. ACC, PCC vs. NAA, ACC vs. NAA) using a robust nested stratified cross-validation pipeline to ensure generalizability and avoid overfitting. Results: All four models showed strong predictive performance, with discrimination (AUC) more than 0.8. Our analysis, based on the interpretable LR model, identified the key discriminators differentiated PCC from both ACC and NAA: maximum systolic blood pressure, grade 3 hypertension, headache, palpitation, tachycardia, male sex, and concomitant gastric and duodenal ulcers. In contrast, lower back pain and general weakness were strong signs of lower probability of PCC. The tumor density specifically differentiated PCC from NAA, whereas tumor size was an important marker for distinguishing PCC and ACC. Conclusions: We developed robust ML models capable of accurately differentiating PCC from other adrenal tumors in complex cases. The models provide a clinically actionable tool for pre-surgical decision support. Furthermore, the identification of key discriminative features enhances the clinical understanding of PCC and facilitates its differential diagnosis prior to histological verification.<\/jats:p>","DOI":"10.3390\/life16010164","type":"journal-article","created":{"date-parts":[[2026,1,19]],"date-time":"2026-01-19T09:57:02Z","timestamp":1768816622000},"page":"164","update-policy":"https:\/\/doi.org\/10.3390\/mdpi_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Machine Learning Approach for Differentiation of Pheochromocytoma from Adrenocortical Cancer and Non-Functioning Adrenal Adenomas"],"prefix":"10.3390","volume":"16","author":[{"ORCID":"https:\/\/orcid.org\/0009-0009-5702-3899","authenticated-orcid":false,"given":"Timur","family":"Nurkhabinov","sequence":"first","affiliation":[{"name":"Faculty of Mechanics and Mathematics, M.V. Lomonosov Moscow State University, 119991 Moscow, Russia"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3261-7366","authenticated-orcid":false,"given":"Irena","family":"Ilovayskaya","sequence":"additional","affiliation":[{"name":"Department of Neuroendocrine Diseases, M.F. Vladimirsky Moscow Regional Research Clinical Institute, 129110 Moscow, Russia"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5187-1602","authenticated-orcid":false,"given":"Anna","family":"Lugovskaya","sequence":"additional","affiliation":[{"name":"Department of Neuroendocrine Diseases, M.F. Vladimirsky Moscow Regional Research Clinical Institute, 129110 Moscow, Russia"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Victor","family":"Popov","sequence":"additional","affiliation":[{"name":"Faculty of Physics, M.V. Lomonosov Moscow State University, 119991 Moscow, Russia"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Lidia","family":"Nefedova","sequence":"additional","affiliation":[{"name":"Faculty of Biology, M.V. Lomonosov Moscow State University, 119991 Moscow, Russia"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"1968","published-online":{"date-parts":[[2026,1,19]]},"reference":[{"key":"ref_1","doi-asserted-by":"crossref","first-page":"G1","DOI":"10.1093\/ejendo\/lvad066","article-title":"European Society of Endocrinology Clinical Practice Guidelines on the Management of Adrenal Incidentalomas, in Collaboration with the European Network for the Study of Adrenal Tumors","volume":"189","author":"Fassnacht","year":"2023","journal-title":"Eur. J. Endocrinol."},{"key":"ref_2","doi-asserted-by":"crossref","first-page":"775","DOI":"10.1210\/endrev\/bnaa008","article-title":"Adrenal Incidentaloma","volume":"41","author":"Sherlock","year":"2020","journal-title":"Endocr. Rev."},{"key":"ref_3","doi-asserted-by":"crossref","unstructured":"Martin, C.S., Andrei, M., Voicu, B.A., Ri\u021b\u0103, M.A., Taralunga, A.A., S\u00eerbu, A.E., Cima, L.N., Stoian, I., Barbu, C.G., and Calu, V. (2024). The Spectrum of Adrenal Lesions in a Tertiary Referral Center. Biomedicines, 12.","DOI":"10.3390\/biomedicines12102214"},{"key":"ref_4","doi-asserted-by":"crossref","first-page":"894","DOI":"10.1016\/S2213-8587(20)30314-4","article-title":"Epidemiology of Adrenal Tumours in Olmsted County, Minnesota, USA: A Population-Based Cohort Study","volume":"8","author":"Ebbehoj","year":"2020","journal-title":"Lancet Diabetes Endocrinol."},{"key":"ref_5","doi-asserted-by":"crossref","first-page":"bvab180","DOI":"10.1210\/jendso\/bvab180","article-title":"Adrenal Incidentaloma: Prevalence and Referral Patterns From Routine Practice in a Large UK University Teaching Hospital","volume":"6","author":"Hanna","year":"2022","journal-title":"J. Endocr. Soc."},{"key":"ref_6","doi-asserted-by":"crossref","first-page":"376","DOI":"10.55730\/1300-0144.5802","article-title":"Clinical, Radiological, and Surgical Outcomes of 431 Patients with Adrenal Incidentalomas: Retrospective Study of a 10-Year Single-Center Experience","volume":"54","author":"Aslan","year":"2024","journal-title":"Turk. J. Med. Sci."},{"key":"ref_7","doi-asserted-by":"crossref","unstructured":"Cyranska-Chyrek, E., Szczepanek-Parulska, E., Olejarz, M., and Ruchala, M. (2019). Malignancy Risk and Hormonal Activity of Adrenal Incidentalomas in a Large Cohort of Patients from a Single Tertiary Reference Center. Int. J. Environ. Res. Public Health, 16.","DOI":"10.3390\/ijerph16101872"},{"key":"ref_8","doi-asserted-by":"crossref","first-page":"2813","DOI":"10.1007\/s40618-025-02639-9","article-title":"Global Epidemiology of Pheochromocytoma: A Systematic Review and Meta-Analysis of Observational Studies","volume":"48","author":"Vitturi","year":"2025","journal-title":"J. Endocrinol. Investig."},{"key":"ref_9","doi-asserted-by":"crossref","first-page":"90","DOI":"10.1007\/s12022-022-09704-6","article-title":"Overview of the 2022 WHO Classification of Paragangliomas and Pheochromocytomas","volume":"33","author":"Mete","year":"2022","journal-title":"Endocr. Pathol."},{"key":"ref_10","doi-asserted-by":"crossref","unstructured":"Fang, F., Ding, L., He, Q., and Liu, M. (2020). Preoperative Management of Pheochromocytoma and Paraganglioma. Front. Endocrinol., 11.","DOI":"10.3389\/fendo.2020.586795"},{"key":"ref_11","doi-asserted-by":"crossref","unstructured":"Xiao, D., Zhong, J., Peng, J., Fan, C., Wang, X., Wen, X., Liao, W., Wang, J., and Yin, X. (2023). Machine Learning for Differentiation of Lipid-Poor Adrenal Adenoma and Subclinical Pheochromocytoma Based on Multiphase CT Imaging Radiomics. BMC Med. Imaging, 23.","DOI":"10.1186\/s12880-023-01106-2"},{"key":"ref_12","doi-asserted-by":"crossref","unstructured":"Liu, H., Guan, X., Xu, B., Zeng, F., Chen, C., Yin, H.L., Yi, X., Peng, Y., and Chen, B.T. (2022). Computed Tomography-Based Machine Learning Differentiates Adrenal Pheochromocytoma From Lipid-Poor Adenoma. Front. Endocrinol., 13.","DOI":"10.3389\/fendo.2022.833413"},{"key":"ref_13","first-page":"234","article-title":"Machine Learning Analysis of Adrenal Lesions: Preliminary Study Evaluating Texture Analysis in the Differentiation of Adrenal Lesions","volume":"29","author":"Altay","year":"2023","journal-title":"Diagn. Interv. Radiol."},{"key":"ref_14","doi-asserted-by":"crossref","first-page":"e551","DOI":"10.1016\/S2589-7500(23)00094-8","article-title":"Prediction of Metastatic Pheochromocytoma and Paraganglioma: A Machine Learning Modelling Study Using Data from a Cross-Sectional Cohort","volume":"5","author":"Pamporaki","year":"2023","journal-title":"Lancet Digit. Health"},{"key":"ref_15","doi-asserted-by":"crossref","first-page":"2859","DOI":"10.1016\/j.acra.2024.01.008","article-title":"CT-Based Radiomics Analysis of Different Machine Learning Models for Discriminating the Risk Stratification of Pheochromocytoma and Paraganglioma: A Multicenter Study","volume":"31","author":"Zhou","year":"2024","journal-title":"Acad. Radiol."},{"key":"ref_16","doi-asserted-by":"crossref","first-page":"104749","DOI":"10.1016\/j.compbiomed.2021.104749","article-title":"An optimized two-stage cascaded deep neural network for adrenal segmentation on CT images","volume":"136","author":"Luo","year":"2021","journal-title":"Comput. Biol. Med."},{"key":"ref_17","doi-asserted-by":"crossref","unstructured":"Wang, S.C., Yin, S.N., Wang, Z.Y., Ding, N., Ji, Y.D., and Jin, L. (2025). Evaluation of a fusion model combining deep learning models based on enhanced CT images with radiological and clinical features in distinguishing lipid-poor adrenal adenoma from metastatic lesions. BMC Med. Imaging, 25.","DOI":"10.1186\/s12880-025-01798-8"},{"key":"ref_18","first-page":"2825","article-title":"Scikit-Learn: Machine Learning in Python","volume":"12","author":"Pedregosa","year":"2011","journal-title":"J. Mach. Learn. Res."},{"key":"ref_19","doi-asserted-by":"crossref","first-page":"11795468221133611","DOI":"10.1177\/11795468221133611","article-title":"XGBoost, A Novel Explainable AI Technique, in the Prediction of Myocardial Infarction: A UK Biobank Cohort Study","volume":"16","author":"Moore","year":"2022","journal-title":"Clin. Med. Insights Cardiol."},{"key":"ref_20","doi-asserted-by":"crossref","first-page":"427","DOI":"10.1016\/j.ipm.2009.03.002","article-title":"A Systematic Analysis of Performance Measures for Classification Tasks","volume":"45","author":"Sokolova","year":"2009","journal-title":"Inf. Process. Manag."},{"key":"ref_21","doi-asserted-by":"crossref","first-page":"636","DOI":"10.14740\/jocmr3503w","article-title":"The Characteristics and Trends in Adrenocortical Carcinoma: A United States Population Based Study","volume":"10","author":"Sharma","year":"2018","journal-title":"J. Clin. Med. Res."},{"key":"ref_22","doi-asserted-by":"crossref","first-page":"21","DOI":"10.1111\/cen.15235","article-title":"Approach to the Management of Gastrointestinal Manifestations in Patients With Phaeochromocytoma and Paraganglioma","volume":"103","author":"Majumder","year":"2025","journal-title":"Clin. Endocrinol."},{"key":"ref_23","doi-asserted-by":"crossref","first-page":"1115","DOI":"10.1507\/endocrj.EJ25-0132","article-title":"Development of a Prediction Model by Combining Tumor Diameter and Clinical Parameters of Adrenal Incidentaloma","volume":"72","author":"Iwamoto","year":"2025","journal-title":"Endocr. J."},{"key":"ref_24","doi-asserted-by":"crossref","first-page":"282","DOI":"10.1210\/er.2013-1029","article-title":"Adrenocortical Carcinoma","volume":"35","author":"Else","year":"2014","journal-title":"Endocr. Rev."},{"key":"ref_25","doi-asserted-by":"crossref","unstructured":"Yuan, H., Kang, B., Sun, K., Qin, S., Ji, C., and Wang, X. (2023). CT-Based Radiomics Nomogram for Differentiation of Adrenal Hyperplasia from Lipid-Poor Adenoma: An Exploratory Study. BMC Med. Imaging, 23.","DOI":"10.1186\/s12880-022-00951-x"},{"key":"ref_26","doi-asserted-by":"crossref","unstructured":"Rajput, D., Wang, W.-J., and Chen, C.-C. (2023). Evaluation of a Decided Sample Size in Machine Learning Applications. BMC Bioinform., 24.","DOI":"10.1186\/s12859-023-05156-9"},{"key":"ref_27","doi-asserted-by":"crossref","unstructured":"Vabalas, A., Gowen, E., Poliakoff, E., and Casson, A.J. (2019). Machine Learning Algorithm Validation With a Limited Sample Size. PLoS ONE, 14.","DOI":"10.1371\/journal.pone.0224365"}],"container-title":["Life"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.mdpi.com\/2075-1729\/16\/1\/164\/pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,1,19]],"date-time":"2026-01-19T10:12:36Z","timestamp":1768817556000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.mdpi.com\/2075-1729\/16\/1\/164"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,1,19]]},"references-count":27,"journal-issue":{"issue":"1","published-online":{"date-parts":[[2026,1]]}},"alternative-id":["life16010164"],"URL":"https:\/\/doi.org\/10.3390\/life16010164","relation":{},"ISSN":["2075-1729"],"issn-type":[{"value":"2075-1729","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,1,19]]}}}