{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,18]],"date-time":"2026-03-18T10:00:55Z","timestamp":1773828055932,"version":"3.50.1"},"reference-count":22,"publisher":"MDPI AG","issue":"3","license":[{"start":{"date-parts":[[2026,3,18]],"date-time":"2026-03-18T00:00:00Z","timestamp":1773792000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Information"],"abstract":"<jats:p>Accurate determination of human epidermal growth factor receptor 2 (HER2) status is a critical component of breast cancer prognosis and treatment planning. Conventional diagnostic techniques, such as immunohistochemistry (IHC) and fluorescence in situ hybridization (FISH), are clinically established but remain invasive, time-consuming, costly, and sensitive to pre-analytical and interpretative variability. Motivated by the need for scalable and data-driven decision-support tools, this study proposes a hybrid ensemble machine learning framework for non-invasive HER2 status prediction using routinely available clinical and immunohistochemical features. A retrospective dataset comprising 624 breast cancer patients from Mahdieh Clinic (Kermanshah, Iran) was analyzed using a structured preprocessing pipeline including normalization and class balancing. The proposed framework integrates multiple tree-based classifiers, Random Forest, XGBoost, and LightGBM, through ensemble strategies and enhances predictive robustness using membership-function feature engineering to capture gradual transitions in clinically relevant biomarkers. Decision threshold optimization was further applied to improve classification balance in borderline cases. The proposed ensemble framework achieved an accuracy of 0.816, an F1-score of 0.814, and an area under the receiver operating characteristic curve (AUC) of 0.862 on a held-out test set, demonstrating performance comparable to the best-performing individual classifier. These results indicate that ensemble learning combined with smooth membership-based feature representations can provide a reliable decision-support framework for HER2 status prediction, although further external validation is required before clinical use.<\/jats:p>","DOI":"10.3390\/info17030296","type":"journal-article","created":{"date-parts":[[2026,3,18]],"date-time":"2026-03-18T07:35:08Z","timestamp":1773819308000},"page":"296","update-policy":"https:\/\/doi.org\/10.3390\/mdpi_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["A Hybrid Ensemble Machine Learning Framework with Membership-Function Feature Engineering for Non-Invasive Prediction of HER2 Status in Breast Cancer"],"prefix":"10.3390","volume":"17","author":[{"ORCID":"https:\/\/orcid.org\/0009-0005-4287-7075","authenticated-orcid":false,"given":"Hassan","family":"Salarabadi","sequence":"first","affiliation":[{"name":"Department of Computer Engineering, Faculty of Engineering, University of Zanjan, Zanjan 45371-38791, Iran"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Dariush","family":"Salimi","sequence":"additional","affiliation":[{"name":"Department of Computer Engineering, Faculty of Engineering, University of Zanjan, Zanjan 45371-38791, Iran"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3803-6714","authenticated-orcid":false,"given":"Seyed Sahand","family":"Mohammadi Ziabari","sequence":"additional","affiliation":[{"name":"Informatics Institute, University of Amsterdam, 1098 XH Amsterdam, The Netherlands"},{"name":"Department of Computer Science and Technology, SUNY Empire State University, Saratoga Springs, NY 12866, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Mozaffar","family":"Aznab","sequence":"additional","affiliation":[{"name":"Medical Department, Kermanshah University of Medical Sciences and Health Services, Kermanshah 67158-47141, Iran"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"1968","published-online":{"date-parts":[[2026,3,18]]},"reference":[{"key":"ref_1","doi-asserted-by":"crossref","first-page":"100265","DOI":"10.1016\/j.imu.2019.100265","article-title":"Relationship among prognostic indices of breast cancer using classification techniques","volume":"18","author":"Tanha","year":"2020","journal-title":"Inform. Med. Unlocked"},{"key":"ref_2","doi-asserted-by":"crossref","first-page":"101171","DOI":"10.1016\/j.gim.2024.101171","article-title":"Cancer risks for other sites in addition to breast in CHEK2 c.1100delC families","volume":"26","author":"Schreurs","year":"2024","journal-title":"Genet. Med."},{"key":"ref_3","doi-asserted-by":"crossref","first-page":"104834","DOI":"10.1016\/j.critrevonc.2025.104834","article-title":"Bridging the gap: The role of MDM2 inhibition in overcoming treatment resistance in breast cancer","volume":"214","author":"Conti","year":"2025","journal-title":"Crit. Rev. Oncol."},{"key":"ref_4","doi-asserted-by":"crossref","first-page":"105324","DOI":"10.1016\/j.esmoop.2025.105324","article-title":"The impact of analysis methodology details on invasive breast cancer-free survival in randomized clinical trials","volume":"10","author":"Hlauschek","year":"2025","journal-title":"ESMO Open"},{"key":"ref_5","doi-asserted-by":"crossref","first-page":"104465","DOI":"10.1016\/j.breast.2025.104465","article-title":"Paclitaxel-related type I Kounis syndrome in a very young patient with HER2-positive breast cancer and the role of genomics to disentangle a complex therapeutic scenario: A case report and narrative review","volume":"81","author":"Nucera","year":"2025","journal-title":"Breast"},{"key":"ref_6","doi-asserted-by":"crossref","first-page":"102420","DOI":"10.1016\/j.tranon.2025.102420","article-title":"Downregulation of PIP4K2C inhibits the breast cancer cell proliferation, migration and invasion","volume":"57","author":"Jin","year":"2025","journal-title":"Transl. Oncol."},{"key":"ref_7","doi-asserted-by":"crossref","first-page":"971","DOI":"10.1016\/j.jfutfo.2025.07.002","article-title":"A comprehensive analysis of artificial intelligence, machine learning, deep learning and computer vision in food science","volume":"6","author":"Borugadda","year":"2025","journal-title":"J. Future Foods"},{"key":"ref_8","doi-asserted-by":"crossref","first-page":"3249929","DOI":"10.1155\/2024\/3249929","article-title":"Improved COVID-19 diagnosis using a hybrid transfer learning model with fuzzy edge detection on CT scan images","volume":"2024","author":"Salarabadi","year":"2024","journal-title":"Adv. Fuzzy Syst."},{"key":"ref_9","doi-asserted-by":"crossref","first-page":"e1152","DOI":"10.1016\/j.crad.2024.05.017","article-title":"Deep-learning features based on 18F-FDG PET\/CT to predict preoperative colorectal cancer lymph node metastasis","volume":"79","author":"Wang","year":"2024","journal-title":"Clin. Radiol."},{"key":"ref_10","doi-asserted-by":"crossref","first-page":"262","DOI":"10.1016\/j.aej.2025.04.045","article-title":"Enhancing aviation safety: Machine learning for real-time ADS-B injection detection through advanced data analysis","volume":"126","author":"Rahman","year":"2025","journal-title":"Alex. Eng. J."},{"key":"ref_11","doi-asserted-by":"crossref","first-page":"111362","DOI":"10.1016\/j.asoc.2024.111362","article-title":"Grid search with a weighted error function: Hyper-parameter optimization for financial time series forecasting","volume":"154","author":"Zhao","year":"2024","journal-title":"Appl. Soft Comput."},{"key":"ref_12","doi-asserted-by":"crossref","first-page":"e954","DOI":"10.1016\/j.clbc.2025.05.001","article-title":"Ultrasound radiomics-based machine learning and SHapley Additive exPlanations method predicting pathological prognostic stage in breast cancer: A bicentric and validation study","volume":"25","author":"Chen","year":"2025","journal-title":"Clin. Breast Cancer"},{"key":"ref_13","doi-asserted-by":"crossref","first-page":"e707","DOI":"10.1016\/j.clbc.2025.04.008","article-title":"A multi-omics-based prognostic model for elderly breast cancer by machine learning: Insights from hypoxia and immunity of tumor microenvironment","volume":"25","author":"Song","year":"2025","journal-title":"Clin. Breast Cancer"},{"key":"ref_14","doi-asserted-by":"crossref","first-page":"109204","DOI":"10.1016\/j.cmpb.2025.109204","article-title":"Explainable feature selection combining particle swarm optimisation with adaptive LASSO for MRI radiogenomics: Predicting HPV status in oropharyngeal cancer","volume":"275","author":"Ahmadian","year":"2026","journal-title":"Comput. Methods Programs Biomed."},{"key":"ref_15","doi-asserted-by":"crossref","first-page":"e622","DOI":"10.1016\/j.clbc.2025.03.002","article-title":"Development of machine learning models for predicting radiation dermatitis in breast cancer patients using clinical risk factors, patient-reported outcomes, and serum cytokine biomarkers","volume":"25","author":"Lin","year":"2025","journal-title":"Clin. Breast Cancer"},{"key":"ref_16","doi-asserted-by":"crossref","first-page":"104087","DOI":"10.1016\/j.esmoop.2024.104087","article-title":"Development of two machine learning models to predict conversion from primary HER2-0 breast cancer to HER2-low metastases: A proof-of-concept study","volume":"10","author":"Miglietta","year":"2025","journal-title":"ESMO Open"},{"key":"ref_17","doi-asserted-by":"crossref","first-page":"102349","DOI":"10.1016\/j.tranon.2025.102349","article-title":"A machine learning-based prognostic signature utilizing MSC proteomics for predicting bladder cancer prognosis and treatment response","volume":"54","author":"Zhang","year":"2025","journal-title":"Transl. Oncol."},{"key":"ref_18","doi-asserted-by":"crossref","first-page":"e37554","DOI":"10.1016\/j.heliyon.2024.e37554","article-title":"Machine learning-based cell death marker for predicting prognosis and identifying tumor immune microenvironment in prostate cancer","volume":"10","author":"Gao","year":"2024","journal-title":"Heliyon"},{"key":"ref_19","doi-asserted-by":"crossref","first-page":"e35157","DOI":"10.1016\/j.heliyon.2024.e35157","article-title":"Machine learning-driven mast cell gene signatures for prognostic and therapeutic prediction in prostate cancer","volume":"10","author":"Maimaitiyiming","year":"2024","journal-title":"Heliyon"},{"key":"ref_20","doi-asserted-by":"crossref","first-page":"108895","DOI":"10.1016\/j.cmpb.2025.108895","article-title":"Predicting clinical prognosis in gastric cancer using deep learning-based analysis of tissue pathomics images","volume":"269","author":"Liu","year":"2025","journal-title":"Comput. Methods Programs Biomed."},{"key":"ref_21","doi-asserted-by":"crossref","first-page":"102309","DOI":"10.1016\/j.omtn.2024.102309","article-title":"Molecular classification of geriatric breast cancer displays distinct senescent subgroups of prognostic significance","volume":"35","author":"Wu","year":"2024","journal-title":"Mol. Ther. Nucleic Acids"},{"key":"ref_22","doi-asserted-by":"crossref","first-page":"759","DOI":"10.1016\/j.procs.2024.10.302","article-title":"Comparative analysis of machine learning and survival analysis for breast cancer prediction","volume":"245","author":"Emily","year":"2024","journal-title":"Procedia Comput. Sci."}],"container-title":["Information"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.mdpi.com\/2078-2489\/17\/3\/296\/pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,3,18]],"date-time":"2026-03-18T07:49:17Z","timestamp":1773820157000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.mdpi.com\/2078-2489\/17\/3\/296"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,3,18]]},"references-count":22,"journal-issue":{"issue":"3","published-online":{"date-parts":[[2026,3]]}},"alternative-id":["info17030296"],"URL":"https:\/\/doi.org\/10.3390\/info17030296","relation":{},"ISSN":["2078-2489"],"issn-type":[{"value":"2078-2489","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,3,18]]}}}