Machine learning, antimicrobial stewardship, and solid organ transplantation: Is this the future?

Area of Science:

• Infectious Diseases
• Medical Informatics
• Transplantation Medicine

Background:

• Machine learning (ML) applications in infectious diseases are rapidly increasing.
• Solid organ transplantation (SOT) recipients are at high risk for infectious complications.

Purpose of the Study:

• To review the literature on ML for clinical decision support in antimicrobial stewardship specifically for SOT.
• To identify current applications, challenges, and future directions of ML in this field.

Main Methods:

• A comprehensive literature search was conducted using MEDLINE/PubMed and Google Scholar up to July 2022.
• References were identified and reviewed to synthesize existing knowledge.

Main Results:

• ML can enhance prediction of infectious complications, diagnosis, and treatment in SOT patients.
• A key application is predicting antimicrobial resistance to inform empiric therapy and optimize dosing considering drug interactions.
• Challenges include the need for large, high-quality, accessible clinical databases for ML model development.
• ML-driven clinical decision support systems (CDSSs) are currently experimental, requiring clinician education.

Conclusions:

• ML holds potential to significantly improve antimicrobial stewardship in SOT.
• The current literature on this specific topic is limited.
• Further research is essential to develop and validate ML-CDSS for SOT recipients in clinical practice.