Decision-making in clinical diagnostic for brain tumor detection based on advanced machine learning algorithm

Aug 4, 2026

Upload by Levi

Brain tumors are benign or malignant abnormal growths that disrupt brain function and lead to symptoms such as headaches, seizures, and cognitive decline. Reliable predictive models are essential for diagnosis and prognosis. This study builds brain tumor prediction models using machine learning enhanced by an optimizer, Escaping Bird Search Optimization. Ada Boost, Gaussian Process, and Support Vector classifiers are evaluated, with the optimized enhanced SVC (SVEB) achieving the highest accuracy across models. Results highlight the value of optimization for accurate neuro-oncology prediction.

LanguageEnglish

CategoryHealthcare

FormatPDF

Pages17

Reading Time43 min

AccessFree to download

Introduction

Causes of brain tumors

Signs and symptoms

Diagnostic techniques

Treatment options

Int. J. Simul. Multidisci. Des. Optim. 16, 1 (2025)© T. Huang et al., Published by EDP Sciences, 2025 [https://doi.org/10.1051/smdo/2024021](https://doi.org/10.1051/smdo/2024021) Available online at: [https://www.ijsmdo.org](https://www.ijsmdo.org) | RESEARCH ARTICLE | | | --- | --- | Decision-making in clinical diagnostic for brain tumor detection based on advanced machine learning algorithm * Tangsen Huang, Xiangdong Yin , and Ensong Jiang School of Information Engineering, Hunan University of Science and Engineering, Yongzhou 425199, Hunan, China Received: 27 June 2024 / Accepted: 17 September 2024 Abstract. Brain tumors, abnormal growths in the brain or spinal canal, can be benign or malignant, causing symptoms like headaches, seizures, and cognitive decline by disrupting brain function. Therefore, developing reliable predictive models for diagnosis and prognosis is crucial. In this paper, the prediction of brain tumors is made using machine learning models enhanced by an optimizer, namely Escaping Bird Search Optimization. Optimized models incorporate Ada Boost Classiﬁer (ADEB), Gaussian Process Classiﬁer (GPEB), and Support Vector Classiﬁer (SVC) which, after being tested on a few databases, were named ADEB, SVEB, and GPEB, respectively, and their predictive power was assessed. The best single model performance overall on all databases is the SVC with an average accuracy of 0.981, while among enhanced models, the optimized model, called SVEB, using SVC, attained the highest accuracy for all models and reached as high as 0.990 . These ﬁndings underscore the role of optimization techniques and demonstrate the effectiveness of machine learning in predicting brain cancers. The improved performance of the enhanced SVC model, SVEB, suggests it could offer a reliable approach for accurate brain tumor prediction. Enhanced patient outcomes and early diagnosis could be an implication of this in the ﬁeld of neuro-oncology. Keywords: Brain tumor classiﬁcation / machine learning / Ada boost classiﬁer / Gaussian process classiﬁer / support vector classiﬁer 1 Introduction The human brain is a complex interconnection of neurons and synapses. It acts as the central nervous system to coordinate various physiological and cognitive tasks essential in life. Like other major organs, it can be subject to various degenerative diseases. One particularly serious problem pertains to that of tumors of the brain. Brain tumors are a heterogeneous group of neoplastic entities, diverging in their clinical relevance. They are characterized by the abnormal proliferation of cells inside the brain or central spinal canal. These tumors represent a heterogeneous group, including benign growths and malignant malignancies. They may arise from many types of neural cells or from the metastasis of cancerous cells that have developed in other areas of the body [1] . The diagnosis and management strategy for brain tumors appropriately requires the etiological factors, clinical symptoms, and therapeutic techniques involved task that calls for a complex interplay of neurological structures and functions. Such insight not only helps medical professionals make decisions about diagnosis and treatment but also has * e-mail: [yinxiangdong@huse.edu.cn](yinxiangdong@huse.edu.cn) signiﬁcant ramiﬁcations for improving patient outcomesand the quality of life when dealing with this powerful pathogenic entity [2] . 1.1 Causes of brain tumors There are some known risk factors for brain tumors, although the exact cause remains largely unknown. These include exposure to ionizing radiation, genetic predisposition, impairment of the immune system, and some genetic disorders like neuroﬁbromatosis and Li-Fraumeni syndrome. Furthermore, several reports indicate that exposure to electromagnetic ﬁelds and certain environmental chemicals may be associated with brain malignancies; however, further investigation is still required to verify the results [3,4

FAQs

Why is decision-making important for clinical brain tumor diagnosis?

Brain tumors can be benign or malignant and cause neurologic symptoms by disrupting brain function, so dependable diagnostic and prognostic prediction supports better clinical decisions and outcomes.

Which optimization method and classifiers are used in the study?

The models use Escaping Bird Search Optimization to enhance machine learning classifiers, including Ada Boost Classifier (ADEB), Gaussian Process Classifier (GPEB), and Support Vector Classifier (SVC), evaluated as ADEB, GPEB, and SVEB.

What model achieved the best predictive performance?

Across all databases, the best overall single-model performance is reported for SVC with an average accuracy around 0.981, while the optimized enhanced SVC model SVEB reaches up to about 0.990 accuracy.

Aug 4, 2026

Upload by Levi