Evolutionary Meta-Learning in Precision Oncology: Development and Validation of an Optimized Ensemble Architecture
Abstract
Background: Predictive oncology relies on algorithmic models to stratify patient risk; however, optimizing the critical precision-recall trade-off in heavily imbalanced clinical datasets remains a persistent challenge. This study establishes a genetically optimized, asymmetric ensemble pipeline designed to structurally resolve this diagnostic imbalance.
Methods: Leveraging a clinical cohort ( isolated test instances) balanced via sequential SMOTE-ENN and mapped through polynomial Principal Component Analysis (PCA), we engineered a multi-stage evolutionary architecture culminating in a heterogeneous asymmetric voting classifier.
Results: The proposed ensemble demonstrates a robust diagnostic equilibrium, achieving an F1-Score of , an accuracy of , and an ROC-AUC of . Direct benchmarking against a standard baseline, the Support Vector Machine (RBF kernel), reveals that the proposed architecture yields a substantial absolute increase in recall (; vs. ) and global accuracy (). Furthermore, genetic algorithm convergence isolated XGBoost dynamics within the first generations, identifying patient age and tumor size as the dominant predictive features defining the algorithmic decision boundary.
Conclusions: This asymmetric integration enhances predictive modeling in oncology, providing a framework that enables mathematically rigorous, high-sensitivity clinical screening protocols.
Keywords: Precision Oncology; Ensemble Learning; Feature Space Topology; Predictive Modeling; Clinical Decision Support.
References
Abdollahi J, Davari N, Panahi Y, Gardaneh M. Detection of metastatic breast cancer from whole-slide pathology images using an ensemble deep-learning method. https://doi.org/10.32768/abc.202293364-376
Abdollahi J, Keshandehghan A, Gardaneh M, Panahi Y, Gardaneh M. Accurate detection of breast cancer metastasis using a hybrid model of artificial intelligence algorithm. https://doi.org/10.32768/abc.20207122-28
Javadzadeh Barzaki MA, Negaresh M, Abdollahi J, Mohammadi M, Ghobadi H, Mohammadzadeh B, Amani F. USING DEEP LEARNING NETWORKS FOR CLASSIFICATION OF LUNG CANCER NODULES IN CT IMAGES. InIranian Congress of Radiology 2022 Jul 1 (Vol. 37, No. 2, pp. 34-34). Iranian Society of Radiology. doi: 10.22034/icrj.2022.173678
Agarwal S, Yadav AS, Dinesh V, Vatsav KS, Prakash KS, Jaiswal S. By artificial intelligence algorithms and machine learning models to diagnosis cancer. Materials Today: Proceedings. 2023 Jan 1;80:2969-75. https://doi.org/10.1016/j.matpr.2021.07.088.
Shirzad M, Shaban M, Mohammadzadeh V, Rahdar A, Fathi-karkan S, Hoseini ZS, Najafi M, Kharaba Z, Aboudzadeh MA. Artificial intelligence-assisted design of nanomedicines for breast cancer diagnosis and therapy: advances, challenges, and future directions. BioNanoScience. 2025 Sep;15(3):354. https://doi.org/10.1007/s12668-025-01980-w
Abele N, Tiemann K, Krech T, Wellmann A, Schaaf C, Länger F, Peters A, Donner A, Keil F, Daifalla K, Mackens M. Noninferiority of artificial intelligence–assisted analysis of Ki-67 and estrogen/progesterone receptor in breast cancer routine diagnostics. Modern Pathology. 2023 Mar 1;36(3):100033. https://doi.org/10.1016/j.modpat.2022.100033
Chia JL, He GS, Ngiam KY, Hartman M, Ng QX, Goh SS. Harnessing artificial intelligence to enhance global breast cancer care: a scoping review of applications, outcomes, and challenges. Cancers. 2025 Jan 9;17(2):197. https://doi.org/10.3390/cancers17020197
Koch HW, Larsen M, Bartsch H, Kurz KD, Hofvind S. Artificial intelligence in BreastScreen Norway: a retrospective analysis of a cancer-enriched sample including 1254 breast cancer cases. European radiology. 2023 May;33(5):3735-43. https://doi.org/10.1007/s00330-023-09461-y
Huang Z, Shao W, Han Z, Alkashash AM, De la Sancha C, Parwani AV, Nitta H, Hou Y, Wang T, Salama P, Rizkalla M. Artificial intelligence reveals features associated with breast cancer neoadjuvant chemotherapy responses from multi-stain histopathologic images. NPJ precision oncology. 2023 Jan 27;7(1):14.https://doi.org/10.1038/s41698-023-00352-5
Vargas-Palacios A, Sharma N, Sagoo GS. Cost-effectiveness requirements for implementing artificial intelligence technology in the Women’s UK Breast Cancer Screening service. Nature Communications. 2023 Sep 30;14(1):6110. https://doi.org/10.1038/s41467-023-41754-0
Jung M, Song SG, Cho SI, Shin S, Lee T, Jung W, Lee H, Park J, Song S, Park G, Song H. Augmented interpretation of HER2, ER, and PR in breast cancer by artificial intelligence analyzer: enhancing interobserver agreement through a reader study of 201 cases. Breast Cancer Research. 2024 Feb 23;26(1):31. https://doi.org/10.1186/s13058-024-01784-y
Kumar S, Das A. Peripheral blood mononuclear cell derived biomarker detection using eXplainable Artificial Intelligence (XAI) provides better diagnosis of breast cancer. Computational Biology and Chemistry. 2023 Jun 1;104:107867. https://doi.org/10.1016/j.compbiolchem.2023.107867.
Chang YW, Ryu JK, An JK, Choi N, Park YM, Ko KH, Han K. Artificial intelligence for breast cancer screening in mammography (AI-STREAM): preliminary analysis of a prospective multicenter cohort study. Nature Communications. 2025 Mar 6;16(1):2248. https://doi.org/10.1038/s41467-025-57469-3
Liu J, Lei J, Ou Y, Zhao Y, Tuo X, Zhang B, Shen M. Mammography diagnosis of breast cancer screening through machine learning: a systematic review and meta-analysis. Clinical and Experimental Medicine. 2023 Oct;23(6):2341-56. https://doi.org/10.1007/s10238-022-00895-0
Challa B, Tahir M, Hu Y, Kellough D, Lujan G, Sun S, Parwani AV, Li Z. Artificial intelligence–aided diagnosis of breast cancer lymph node metastasis on histologic slides in a digital workflow. Modern Pathology. 2023 Aug 1;36(8):100216. https://doi.org/10.1016/j.modpat.2023.100216
Akinlade, O., Abdollahi, J., Paul Etchie, M., Ajagbe, S., Alabi, O., & Ayo Adeyanju, B. (2026). Ensuring effective cervical cancer diseases diagnosis system using ensemble machine learning model. IAES International Journal of Artificial Intelligence (IJ-AI), 15(3), 2410-2422. doi:http://doi.org/10.11591/ijai.v15.i3.pp2410-2422
Van den Goorbergh R, Van Smeden M, Timmerman D, Van Calster B. The harm of class imbalance corrections for risk prediction models: illustration and simulation using logistic regression. Journal of the American Medical Informatics Association. 2022 Sep 1;29(9):1525-34. https://doi.org/10.1093/jamia/ocac093
Collins, G. S., Moons, K. G., Dhiman, P., Riley, R. D., Beam, A. L., Van Calster, B., ... & Logullo, P. (2024). TRIPOD+ AI statement: updated guidance for reporting clinical prediction models that use regression or machine learning methods. bmj, 385.
Authors
Copyright (c) 2026 jafar Abdollahi, Mahsa Yaghoobi , Tayebeh Ebrahimi , Mossa Gardaneh
This work is licensed under a Creative Commons Attribution-NonCommercial 4.0 International License.
Copyright©. This is an open-access article distributed under the terms of the Creative Commons Attribution-Non-Commercial 4.0 International License, which permits copy and redistribution of the material in any medium or format or adapt, remix, transform, and build upon the material for any purpose, except for commercial purposes.