Scholarlink

<p>The growth of artificial intelligence has been exponential, with remarkable advancements in various sectors like entertainment, finance, education, retail, automobile, agriculture, manufacturing, energy, and healthcare, to name a few. Healthcare is a very vast field that encompasses a variety of aspects like medical treatment, prevention, diagnosis, and overall well-being for humans. Machine learning, a subset of artificial intelligence, and deep learning, a subset of machine learning, play significant roles in the medical domain by providing reactive, proactive, and predictive healthcare services to the patients.&#xa0;The motivation behind the diagnosis of non-communicable diseases is driven by their rising global burden, long-term impact on health systems, and the need for early intervention to reduce mortality, disability, and healthcare costs. This paper provides a comprehensive survey based on machine learning and deep learning techniques used to diagnose various non-communicable chronic diseases such as cardiovascular diseases, cancers, diabetes, lung disease, mental health disorders, Alzimer’s disease, Parkinson’s disease, epileptic seizure, parkinson’s disease, and chronic kidney diseases. The review then summarizes the most recent trends and approaches in machine learning and deep learning-based disease diagnosis, considering the following elements: name of authors, name of the journal, year of publication, name of disease, modality, ML/DL algorithm used with performance parameter, dataset used, dataset instance, validation method used, interpretability, features/major biomarkers, code availability and overall quality of the literature. Finally, this paper highlights key results, and research challenges and provides insight into future scope and opportunities in the healthcare area using machine and deep learning techniques.</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

Harnessing Machine Learning and Deep Learning for Non-Communicable Disease Diagnosis: an In-Depth analysis

  • 期刊论文

  • 发表日期：

    2025年9月3日

查看全文
  • Dharmishtha Chaudhari,
  • Pariza Kamboj

摘要

The growth of artificial intelligence has been exponential, with remarkable advancements in various sectors like entertainment, finance, education, retail, automobile, agriculture, manufacturing, energy, and healthcare, to name a few. Healthcare is a very vast field that encompasses a variety of aspects like medical treatment, prevention, diagnosis, and overall well-being for humans. Machine learning, a subset of artificial intelligence, and deep learning, a subset of machine learning, play significant roles in the medical domain by providing reactive, proactive, and predictive healthcare services to the patients. The motivation behind the diagnosis of non-communicable diseases is driven by their rising global burden, long-term impact on health systems, and the need for early intervention to reduce mortality, disability, and healthcare costs. This paper provides a comprehensive survey based on machine learning and deep learning techniques used to diagnose various non-communicable chronic diseases such as cardiovascular diseases, cancers, diabetes, lung disease, mental health disorders, Alzimer’s disease, Parkinson’s disease, epileptic seizure, parkinson’s disease, and chronic kidney diseases. The review then summarizes the most recent trends and approaches in machine learning and deep learning-based disease diagnosis, considering the following elements: name of authors, name of the journal, year of publication, name of disease, modality, ML/DL algorithm used with performance parameter, dataset used, dataset instance, validation method used, interpretability, features/major biomarkers, code availability and overall quality of the literature. Finally, this paper highlights key results, and research challenges and provides insight into future scope and opportunities in the healthcare area using machine and deep learning techniques.