A Systematic Review of Machine Learning-Based Disease Diagnosis in Modern Healthcare Systems

Abstract

Machine learning (ML) has emerged as a transformative approach in modern healthcare systems, significantly enhancing the accuracy and efficiency of disease diagnosis. This systematic review synthesizes recent advancements in ML-based diagnostic models, focusing on their applications across various diseases, including cancer, cardiovascular disorders, diabetes, and neurological conditions. The study evaluates different machine learning techniques such as supervised, unsupervised, and deep learning algorithms, along with their performance metrics, data sources, and clinical applicability. Furthermore, it examines the benefits of ML, including early disease detection, improved decision-making, and cost reduction, while also addressing critical challenges such as data privacy, model interpretability, and lack of standardized datasets. By identifying key research gaps and emerging trends, this review provides valuable insights into the future integration of ML technologies in healthcare, aiming to support researchers and practitioners in developing robust and reliable diagnostic systems.