Past Issues

Cancer remains one of the leading causes of mortality worldwide, necessitating advanced techniques for early detection and accurate diagnosis. Traditional diagnostic methods are often time-consuming and expensive. This study explores the application of data mining techniques in cancer prediction, utilizing machine learning algorithms such as decision trees, support vector machines (SVM), artificial neural networks (ANN), and clustering approaches. Through analysing large medical datasets, these techniques help in identifying high-risk individuals and improving diagnostic precision. The findings suggest that data mining significantly enhances early detection, treatment planning, and survival prediction. Despite challenges like data privacy and class imbalances, advancements in artificial intelligence continue to refine these predictive models, making them more reliable and accurate. .

Review of Machine Learning Applications in Medical Diagnosis, Treatment Optimization, Personalized Care, Clinical Decision Support

Ketankumar Chaturbhai Patel, Dr. Satish Narayan Gurjar

CrossRef DOI URL : https://doi.org/10.31426/ijesti.2023.3.12.3952

This study critically examines the integration of machine learning (ML) techniques in medical diagnosis and treatment, highlighting their transformative potential and the challenges that accompany their adoption. Through a comprehensive literature review of recent advancements—from deep neural networks in medical imaging to reinforcement learning in treatment optimization—we demonstrate how ML enhances diagnostic accuracy, accelerates drug discovery, and enables personalized therapeutic regimens. Case studies, such as three-dimensional neural networks for early lung cancer detection and AI-driven platforms for COVID-19 management, illustrate tangible improvements in clinical outcomes and operational efficiencies..

Clustering Techniques in Educational Data Mining for Student Career Guidance: A Systematic Review

Juveria, Dr. Saoud Sarwar

CrossRef DOI URL : https://doi.org/10.31426/ijesti.2023.3.12.3953

The rapid transformation of global labor markets, driven by technological advancement and digital innovation, has significantly increased the complexity of career decision-making among students. Traditional career guidance systems often rely on manual counseling methods and limited academic indicators, which may not adequately capture the multidimensional nature of student abilities, interests, and skills. In recent years, Educational Data Mining (EDM) and machine learning techniques have emerged as powerful tools for enhancing data-driven academic and career planning. Among these techniques, clustering algorithms play a critical role as unsupervised learning methods capable of identifying hidden patterns and grouping students based on similarity in performance, aptitude, behavioral attributes, and skill profiles..