Citation :

Nishanov A. Kh, Khaydarov Sh I, Ollamberganov F.F, Mamatov M.J, Ruzibaev O.B, "A Measurement-Based Error-Minimisation Feature Selection Algorithm for Medical Diagnostic Systems," International Journal of Engineering Trends and Technology (IJETT), vol. 74, no. 6, pp. 440-452, 2026. Crossref, https://doi.org/10.14445/22315381/IJETT-V74I6P129

Abstract

Clinical decision-support models frequently depend on numerous heterogeneous diagnostic measurements, potentially elevating the risk of misclassification and complicating the interpretation of the resultant models. In this study, we present a measurement-oriented feature selection methodology that seeks a concise collection of informative measurements by directly minimising a cost-sensitive classification error. The objective function assigns asymmetric, class-dependent penalties to each feature to show how different types of errors affect clinical outcomes. The proposed method uses iterative probabilistic optimisation, keeping track of the inclusion probabilities for all measurements and updating them based on how much each measurement helps reduce the weighted error. This process gradually eliminates weak or unnecessary signals. The method was tested on a real breast cancer dataset comprising 743 patient records and 32 nominal diagnostic indicators, assembled with input from oncologists. When tested with k-Nearest Neighbour, Decision Tree, and Naive Bayes classifiers, the method cut the number of features down to 18 and improved classification accuracy by 8-17%. In general, the results show that the algorithm improves accuracy while remaining easy to understand and not too expensive to run. Its overall design makes it useful for other diagnostic tasks that require many measurements, not just breast cancer.

Keywords

Feature selection, Error minimization, Medical diagnostics, Breast cancer, Machine learning.

References

[1] Valeria Maeda-Gutiérrez et al., “Evaluating Feature Selection Methods for Accurate Diagnosis of Diabetic Kidney Disease,” Biomedicines, vol. 12, no. 12, pp. 1-26, 2024.
[CrossRef] [Google Scholar] [Publisher Link]

[2] Tomasz Klonecki, and Paweł Teisseyre, “Feature Selection Under Budget Constraint in Medical Applications: Analysis of Penalized Empirical Risk Minimization Methods,” Applied Intelligence, vol. 53, no. 24, pp. 29943-29973, 2023.
[CrossRef] [Google Scholar] [Publisher Link]

[3] Bjoern H. Menze et al., “The Multimodal Brain Tumor Image Segmentation Benchmark (BRATS),” IEEE Transactions on Medical Imaging, vol. 34, no. 10, pp. 1993-2024, 2015.
[CrossRef] [Google Scholar] [Publisher Link]

[4] Panagiotis Korfiatis et al., “MRI Texture Features as Biomarkers to Predict MGMT Methylation Status in Glioblastomas,” Medical Physics, vol. 43, no. 6, pp. 2835-2844, 2016.
[CrossRef] [Google Scholar] [Publisher Link]

[5] Stefan Bauer et al., “Segmentation of Brain Tumor Images based on Integrated Hierarchical Classification and Regularization,” MICCAI BraTS Workshop. Nice: Miccai Society, vol. 11, 2012.
[Google Scholar]

[6] Darko Zikic et al., “Decision Forests for Tissue-Specific Segmentation of High-Grade Gliomas in Multi-Channel MR,” Medical Image Computing and Computer-Assisted Intervention -- MICCAI 2012: 15^th International Conference, Nice, France, vol. 7512, pp. 369-376, 2012.
[CrossRef] [Google Scholar] [Publisher Link]

[7] Eletheria Panagiotaki et al., “Noninvasive Quantification of Solid Tumor Microstructure using VERDICT MRI,” Cancer Research, vol. 74, no. 7, pp. 1902-1912, 2014.
[CrossRef] [Google Scholar] [Publisher Link]

[8] Kenneth Clark et al., “The Cancer Imaging Archive (TCIA): Maintaining and Operating a Public Information Repository,” Journal of Digital Imaging, vol. 26, no. 6, pp. 1045-1057, 2013.
[CrossRef] [Google Scholar] [Publisher Link]

[9] Spyridon Bakas et al., “Advancing the Cancer Genome Atlas Glioma MRI Collections with Expert Segmentation Labels and Radiomic Features,” Scientific Data, vol. 4, no. 1, pp. 1-13, 2017.
[CrossRef] [Google Scholar] [Publisher Link]

[10] Nicholas J. Tustison et al., “N4ITK: Improved N3 Bias Correction,” IEEE Transactions on Medical Imaging, vol. 29, no. 6, pp. 1310-1320, 2010.
[CrossRef] [Google Scholar] [Publisher Link]

[11] Wei Shen et al., “Multi-Scale Convolutional Neural Networks for Lung Nodule Classification,” Information Processing in Medical Imaging: 24^th International Conference, IPMI 2015, Sabhal Mor Ostaig, Isle of Skye, UK, vol. 9123, pp. 588-599, 2015.
[CrossRef] [Google Scholar] [Publisher Link]

[12] Joost J.M. van Griethuysen et al., “Computational Radiomics System to Decode the Radiographic Phenotype,” Cancer Research, vol. 77, no. 21, pp. e104-e107, 2017.
[CrossRef] [Google Scholar] [Publisher Link]

[13] A.K. Nomozov et al., “Recent Developments in Polymer-based Composite Anticorrosion Coatings: Materials, Mechanisms and Applications,” International Journal of Corrosion and Scale Inhibition, vol. 14, no. 3, pp. 1362-1390, 2025.
[CrossRef] [Google Scholar]

[14] Abror Nomozov et al., “Antibacterial Evaluation and Prediction of the Ability of Salsola Oppositifolia Extract,” Journal of Chemical Letters, vol. 6, no. 3, pp. 203-211, 2025.
[Google Scholar] [Publisher Link]

[15] Z. Kh Misirov et al., “Synthesis and Application of Corrosion Inhibitor for Hydrogen Sulfide Corrosion of Steel,” Indian Journal of Chemical Technology, vol. 32, no. 3, pp. 407-417, 2023.
[CrossRef] [Google Scholar] [Publisher Link]

[16] S.G. Yuldashova et al., “Innovative Approaches for the Synthesis and Application of Anticorrosion Coatings for Pipeline Protection,” International Journal of Corrosion and Scale Inhibition, vol. 15, no. 1, pp. 31-57, 2026.
[CrossRef] [Google Scholar]

[17] A. Nomozov et al., “Inhibition Potential of Salsola Oppositifolia Extract as a Green Corrosion Inhibitor of Mild Steel in an Acidic Solution,” International Journal of Corrosion and Scale Inhibition, vol. 14, no. 3, pp. 1103-1115, 2025.
[CrossRef] [Google Scholar]

[18] M.B. Kholboyeva et al., “Determination of Fe(III) ion with a Novel Immobilized Nitrosa R-Salt in a Polymer Matrix,” Chemical Review and Letters, vol. 8, no. 3, pp. 448-459, 2025.
[CrossRef] [Google Scholar] [Publisher Link]

[19] Yusufjon E. Nazarov et al., “Synthesis, Crystal Structures, DFT Calculations, and Hirshfeld Surface Analysis of Tris (Quinolin-8-Olato-κ²N, O) Cobalt (III) Acetic Acid Monosolvate and Bis (μ-Quinolin-8-Olato-κ²N, O) Diaquabis(nitrato-κ²O, O′) Dinickel (II) Complexes,” Journal of Molecular Structure, vol. 1359, 2026.
[CrossRef] [Google Scholar] [Publisher Link]

[20] Botir Abdurakhmanov, and Otabek Ochildiev, “Estimation of Possible Volumes of Solar Panel Waste Generation in the Republic of Uzbekistan,” E3S Web of Conferences, vol. 563, 2024.
[CrossRef] [Google Scholar] [Publisher Link]

[21] M. Radkevich et al., “Possible Problems of Transport Electrification in Tashkent,” E3S Web of Conferences, vol. 401, 2023.
[CrossRef] [Google Scholar] [Publisher Link]

[22] Uchqun Umarov et al., “Selecting Wastewater Treatment Filters using Local Raw Materials,” E3S Web of Conferences, vol. 401, 2023.
[CrossRef] [Google Scholar] [Publisher Link]

[23] S.G. Yuldashova et al., “Nanocoatings and Anti-Corrosion Strategies: Anti-Corrosion Solutions in Medical Devices,” International Journal of Corrosion and Scale Inhibition, vol. 15, no. 3, pp. 58-88, 2026.
        [Google Scholar]