From bedside queries to complex care: AI for decision-making in infectious diseases

Area of Science:

• Infectious Diseases
• Artificial Intelligence
• Clinical Decision-Making

Background:

• Infectious diseases necessitate rapid decisions using complex clinical data.
• A growing shortage of infectious disease specialists impacts expert availability.
• Artificial intelligence (AI) shows promise for supporting clinical decisions in infectious diseases.

Purpose of the Study:

• Review current and emerging AI applications in infectious disease decision-making.
• Examine the clinical relevance, limitations, and implementation challenges of AI tools.
• Assess AI's potential role in addressing specialist shortages and improving care.

Main Methods:

• Comprehensive literature search across major scientific databases (PubMed/MEDLINE, Scopus, Web of Science, Google Scholar).
• Manual screening of references from relevant articles on AI in infectious diseases.
• Synthesis of findings on AI applications, clinical relevance, and implementation barriers.

Main Results:

• AI applications include large language models for knowledge retrieval and diagnostic support.
• Machine learning models are used for risk stratification, predicting patient deterioration and antimicrobial resistance.
• AI-driven therapeutic tools assist with antibiotic selection, stewardship, and dose optimization.

Conclusions:

• AI functions as a decision-support layer, extending specialist expertise and enhancing care consistency.
• Successful clinical adoption hinges on external validation, seamless workflow integration, and ongoing clinician supervision.
• AI integration must address practical challenges to realize its full potential in infectious disease management.