Scholarlink

<p>This comprehensive review examines the transformative impact of artificial intelligence (AI) and machine learning (ML) on the diagnosis of human diseases. It highlights the advancements and implications of these techniques by analyzing diverse datasets and comparing machine learning and deep learning (DL) approaches. Emphasizing the superiority of DL in feature extraction and diagnostic accuracy, the review provides valuable insights for researchers and practitioners. Focusing on 22 prevalent diseases across various categories, including retinal disease; liver disease; lung diseases, e.g., pneumonia and tuberculosis; neurological conditions, e.g., encephalopathy, epilepsy, brain tumors, and Parkinson’s disease; heart disease; kidney disorders; diabetes; obstructive sleep apnea (OSA); osteoporosis; and cancers, e.g., breast, skin, melanoma, colorectal, cervical, prostate, and chronic myelogenous leukemia, this study consolidates the latest developments in AI-driven healthcare. It underscores the potential of AI to revolutionize medical practice and improve patient outcomes. Key topics include dataset characteristics, preprocessing techniques, dimensionality reduction, and AI methodologies. This review serves as a unified resource, facilitating comparative analysis and driving innovation in medical AI applications.</p>

错误：搜索内容不能为空，请输入英文关键词
错误：关键词超出字数限制，请精简
高级检索

The role of artificial intelligence and machine learning in human disease diagnosis: a comprehensive review

  • 期刊论文

  • 发表日期：

    2025年8月21日

查看全文
  • Fatemeh Imani,
  • Ali Bayani,
  • Masoud Kargar,
  • Alireza Assadzadeh

摘要

This comprehensive review examines the transformative impact of artificial intelligence (AI) and machine learning (ML) on the diagnosis of human diseases. It highlights the advancements and implications of these techniques by analyzing diverse datasets and comparing machine learning and deep learning (DL) approaches. Emphasizing the superiority of DL in feature extraction and diagnostic accuracy, the review provides valuable insights for researchers and practitioners. Focusing on 22 prevalent diseases across various categories, including retinal disease; liver disease; lung diseases, e.g., pneumonia and tuberculosis; neurological conditions, e.g., encephalopathy, epilepsy, brain tumors, and Parkinson’s disease; heart disease; kidney disorders; diabetes; obstructive sleep apnea (OSA); osteoporosis; and cancers, e.g., breast, skin, melanoma, colorectal, cervical, prostate, and chronic myelogenous leukemia, this study consolidates the latest developments in AI-driven healthcare. It underscores the potential of AI to revolutionize medical practice and improve patient outcomes. Key topics include dataset characteristics, preprocessing techniques, dimensionality reduction, and AI methodologies. This review serves as a unified resource, facilitating comparative analysis and driving innovation in medical AI applications.