Scholarlink

<p>Artificial Intelligence (AI) is reshaping modern healthcare by improving diagnostic precision, optimizing treatment strategies, and enhancing patient care through advanced data analytics. While numerous studies have examined AI’s role in medicine, this work introduces a comprehensive, integrated Machine Learning (ML) framework designed to tackle practical challenges in healthcare data handling and implementation. The framework merges structured and unstructured data, incorporates hybrid supervised–unsupervised learning techniques, and evaluates models using clinically relevant performance indicators. Adopting a systematic mapping approach guided by PRISMA standards, we review 53 influential studies published between 2019 and 2025, ensuring both broad coverage and in-depth analysis. Key contributions include a specialized framework for deploying AI in rural healthcare, leveraging federated learning for privacy-preserving collaboration and explainable AI (XAI) for clinical transparency. This paper critically examines ethical concerns—such as data security, fairness in algorithms, and informed consent—and offers targeted mitigation approaches. Ultimately, the study consolidates the current state of AI in healthcare while presenting a strategic vision for inclusive, transparent, and scalable AI-driven healthcare systems.</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

Transforming Healthcare with Artificial Intelligence: Current Applications and Future Opportunities

  • 期刊论文

  • 发表日期：

    2026年5月27日

查看全文
  • Kanta Prasad Sharma,
  • Rashmi Agrawal,
  • Firas Mahmood Mustafa,
  • M. G. M. Johar,
  • Jasgurpreet Singh Chohan,
  • Ahmed Alkhayyat,
  • Devendra Singh

摘要

Artificial Intelligence (AI) is reshaping modern healthcare by improving diagnostic precision, optimizing treatment strategies, and enhancing patient care through advanced data analytics. While numerous studies have examined AI’s role in medicine, this work introduces a comprehensive, integrated Machine Learning (ML) framework designed to tackle practical challenges in healthcare data handling and implementation. The framework merges structured and unstructured data, incorporates hybrid supervised–unsupervised learning techniques, and evaluates models using clinically relevant performance indicators. Adopting a systematic mapping approach guided by PRISMA standards, we review 53 influential studies published between 2019 and 2025, ensuring both broad coverage and in-depth analysis. Key contributions include a specialized framework for deploying AI in rural healthcare, leveraging federated learning for privacy-preserving collaboration and explainable AI (XAI) for clinical transparency. This paper critically examines ethical concerns—such as data security, fairness in algorithms, and informed consent—and offers targeted mitigation approaches. Ultimately, the study consolidates the current state of AI in healthcare while presenting a strategic vision for inclusive, transparent, and scalable AI-driven healthcare systems.