Extending artificial intelligence research in the clinical domain: a theoretical perspective

Area of Science:

• * Medical Informatics
• * Artificial Intelligence in Healthcare

Background:

• * Rapid advancements in artificial intelligence (AI) and machine learning (ML) have transformed various sectors, yet their integration into daily clinical practice remains underexplored.
• * A significant gap exists in understanding the current landscape and potential of AI/ML for improving patient care and disease management.

Purpose of the Study:

• * To systematically review and map the applications of AI and ML in clinical care.
• * To identify strategies, algorithms, and outcomes associated with AI implementation in healthcare settings.
• * To provide insights into future research directions and the influence of AI on disease management.

Main Methods:

• * A systematic literature review employing a smart approach.
• * Latent Dirichlet Allocation (LDA) topic modeling used to analyze and categorize 305 unique articles, with 115 selected for inclusion.
• * Focus on strategies, algorithms, applications, results, qualities, and implications of AI in the clinical domain.

Main Results:

• * Identified key application areas of AI and ML in clinical care and disease management.
• * Provided a structured overview of current AI strategies, algorithms, and their reported outcomes.
• * Highlighted the potential of AI to influence future healthcare practices and patient care.

Conclusions:

• * AI technologies offer significant potential to enhance patient care and disease management within clinical settings.
• * Further research is needed to fully realize the capabilities and implications of AI in healthcare.
• * The study outlines future research directions, limitations, and administrative ramifications of AI in clinical practice.