Early Detection of Ovarian Cancer from Gene Expression Data Using an Optimized Multiple Indefinite Kernel-Based Twin Support Vector Machine with the Adaptive Lyrebird Optimization Algorithm
Received: 8 October 2025 | Revised: 5 December 2025 | Accepted: 19 February 2026 | Online: 6 June 2026
Corresponding author: S. Swetha
Abstract
Ovarian cancer, a frequent gynecological tumor, is usually symptom-free in its early phases; therefore, early diagnosis is important. Gene expression microarrays have great potential for diagnosing and treating ovarian cancer by allowing high-throughput gene examination. However, processing such data presents several challenges, including noise, redundancy, errors, increased complexity, small sample sizes with high dimensionality, and difficulties in interpretation. Recently, microarray datasets have been analyzed using Machine Learning (ML) approaches to classify ovarian cancer. While ML methods are promising in ovarian cancer classification, most models still face issues such as class imbalance, excessive computational expense, weak scalability, and limited interpretability, which limit their clinical utility. To address these constraints, in the present research, a new ML-based model named Optimized Multiple Indefinite kernel-based Twin Support Vector Machine (OMI-Twin SVM) is proposed for the classification of ovarian cancer based on gene expression datasets. The collected gene expression dataset is pre-processed, including data cleaning and normalization to ensure data quality. To select the most critical gene expression features for precise classification of ovarian cancer, the minimum Redundancy–Maximum Relevance (mRMR) approach is applied. Our suggested classification model employs the OMI-Twin SVM structure to predict whether gene expression samples belong to normal or cancerous categories. The proposed classifier is based on a Twin Support Vector Machine (TWSVM) system that incorporates multiple indefinite kernels instead of positive semi-definite kernels alone. To enhance classification performance, we propose an Adaptive Lyrebird Optimization (ALO) algorithm that alternately optimizes the kernel combination and coefficients of the OMI-Twin SVM.
Keywords:
gene expression data, ovarian cancer, multiple indefinite kernels, Twin Support Vector Machine (TWSVM), Adaptive Lyrebird Optimization (ALO) algorithm, Support Vector Machine (SVM)References
K. S. Prabhu, H. Q. Sadida, S. Kuttikrishnan, K. Junejo, A. A. Bhat, and S. Uddin, "Beyond genetics: Exploring the role of epigenetic alterations in breast cancer," Pathology - Research and Practice, vol. 254, Feb. 2024, Art. no. 155174.
A. Bajwa et al., "Challenges and opportunities in ovarian cancer care: A qualitative study of clinician perspectives from 24 low- and middle-income countries," Journal of Cancer Policy, vol. 44, June 2025, Art. no. 100582.
M.-K. Hong and D.-C. Ding, "Early Diagnosis of Ovarian Cancer: A Comprehensive Review of the Advances, Challenges, and Future Directions," Diagnostics, vol. 15, no. 4, Feb. 2025, Art. no. 406.
M. H. Sadeghi, S. Sina, H. Omidi, A. H. Farshchitabrizi, and M. Alavi, "Deep learning in ovarian cancer diagnosis: a comprehensive review of various imaging modalities," Polish Journal of Radiology, vol. 89, pp. 30–48, Jan. 2024.
J. A. Fadhil and A. M. Abdulazeez, "Classification of Cancer Microarray Data Based on Deep Learning: A Review," The Indonesian Journal of Computer Science, vol. 13, no. 1, pp. 55–77, Feb. 2024.
X. Wang, M. Yang, J. Zhu, Y. Zhou, and G. Li, "Role of exosomal non coding RNAs in ovarian cancer (Review)," International Journal of Molecular Medicine, vol. 54, no. 4, Oct. 2024, Art. no. 87.
S. A. Alanazi, N. Alshammari, M. Alruwaili, K. Junaid, M. R. Abid, and F. Ahmad, "Integrative analysis of RNA expression data unveils distinct cancer types through machine learning techniques," Saudi Journal of Biological Sciences, vol. 31, no. 3, Mar. 2024, Art. no. 103918.
K. Abdelnaeem, R. M. Dawood, B. E. Fotouh, A. Ismail, M. S. Abdalla, and S. S. Ramadan, "Expression profiling of KRAS and NOXA genes as prospective biomarkers in ovarian carcinoma," Scientific Reports, vol. 15, no. 1, Sept. 2025, Art. no. 32370.
M. Sokouti and B. Sokouti, "Cancer genetics and deep learning applications for diagnosis, prognosis, and categorization," Journal of Biological Methods, vol. 11, no. 3, Aug. 2024, Art. no. e99010017.
H. Ashayeri, N. Sobhi, P. Pławiak, S. Pedrammehr, R. Alizadehsani, and A. Jafarizadeh, "Transfer Learning in Cancer Genetics, Mutation Detection, Gene Expression Analysis, and Syndrome Recognition," Cancers, vol. 16, no. 11, June 2024, Art. no. 2138.
Y. Sekar, D. Ishwar, B. Tan, and K. Venkatakrishnan, "Nano biosensor unlocks tumor derived immune signals for the early detection of ovarian cancer," Biosensors and Bioelectronics, vol. 278, June 2025, Art. no. 117368.
A. Tokareva et al., "Machine Learning Framework for Ovarian Cancer Diagnostics Using Plasma Lipidomics and Metabolomics," International Journal of Molecular Sciences, vol. 26, no. 14, Jan. 2025, Art. no. 6630.
J. Cai, Z.-J. Lee, Z. Lin, C.-H. Hsu, and Y. Lin, "An Integrated Algorithm with Feature Selection, Data Augmentation, and XGBoost for Ovarian Cancer," Mathematics, vol. 12, no. 24, Dec. 2024, Art. no. 4041.
A. Kodipalli, V. S. Devi, S. Guruvare, and T. Ismail, "Explainable AI-based feature importance analysis for ovarian cancer classification with ensemble methods," Frontiers in Public Health, vol. 13, Mar. 2025, Art. no. 1479095.
J. Cai, Z.-J. Lee, Z. Lin, and M.-R. Yang, "A Novel SHAP-GAN Network for Interpretable Ovarian Cancer Diagnosis," Mathematics, vol. 13, no. 5, Jan. 2025, Art. no. 882.
E. I. A. El-Latif, M. El-dosuky, A. Darwish, and A. E. Hassanien, "A deep learning approach for ovarian cancer detection and classification based on fuzzy deep learning," Scientific Reports, vol. 14, no. 1, Nov. 2024, Art. no. 26463.
M. M. H. Aziz and S. A. Mahmood, "Utilizing Machine Learning Techniques for Cancer Prediction and Classification based on Gene Expression Data," UHD Journal of Science and Technology, vol. 9, no. 1, pp. 135–148, June 2025.
L. K. Hema et al., "Region-Based Segmentation and Classification for Ovarian Cancer Detection Using Convolution Neural Network," Contrast Media & Molecular Imaging, vol. 2022, no. 1, Nov. 2022, Art. no. 5968939.
Y. An and H. Xue, "Indefinite twin support vector machine with DC functions programming," Pattern Recognition, vol. 121, Jan. 2022, Art. no. 108195.
M. Dehghani, G. Bektemyssova, Z. Montazeri, G. Shaikemelev, O. P. Malik, and G. Dhiman, "Lyrebird Optimization Algorithm: A New Bio-Inspired Metaheuristic Algorithm for Solving Optimization Problems," Biomimetics, vol. 8, no. 6, Oct. 2023, Art. no. 507.
R. Edgar, M. Domrachev, and A. E. Lash, "Gene Expression Omnibus: NCBI gene expression and hybridization array data repository," Nucleic Acids Research, vol. 30, no. 1, pp. 207–210, Jan. 2002.
Downloads
How to Cite
License
Copyright (c) 2026 S. Swetha, G. N. Srinivasan, M. R. Anala
This work is licensed under a Creative Commons Attribution 4.0 International License.
Authors who publish with this journal agree to the following terms:
- Authors retain the copyright and grant the journal the right of first publication with the work simultaneously licensed under a Creative Commons Attribution License that allows others to share the work with an acknowledgement of the work's authorship and initial publication in this journal.
- Authors are able to enter into separate, additional contractual arrangements for the non-exclusive distribution of the journal's published version of the work (e.g., post it to an institutional repository or publish it in a book), with an acknowledgement of its initial publication in this journal.
- Authors are permitted and encouraged to post their work online (e.g., in institutional repositories or on their website) after its publication in ETASR with an acknowledgement of its initial publication in this journal.
