Advancing lung transplantation through machine learning and artificial intelligence.

Area of Science:

• Medical Informatics
• Computational Biology
• Transplantation Science

Background:

• Lung transplantation is a complex procedure with significant challenges in patient management and outcome prediction.
• The adoption of artificial intelligence (AI) and machine learning (ML) offers novel approaches to address these challenges.

Purpose of the Study:

• To review current applications of AI and ML in lung transplantation.
• To explore AI/ML's role in outcome prediction and drug dosing.
• To discuss future potential uses and risks of these technologies in the field.

Main Methods:

• Review of existing literature on AI and ML applications in lung transplantation.
• Analysis of models developed for predicting short-term and long-term transplant outcomes.
• Examination of AI/ML approaches for optimizing drug dosing, such as Tacrolimus.

Main Results:

• AI/ML models have been developed to predict primary graft dysfunction, extubation time, patient survival, and chronic lung allograft dysfunction.
• Proof-of-concept models demonstrate AI/ML's utility in time-series drug dosing, exemplified by Tacrolimus.
• Early integration of ML models shows promise for improving clinical decision-making.

Conclusions:

• AI and ML integration in lung transplantation can enhance post-transplant survival and optimize donor lung utilization.
• Advancements in data acquisition, including real-time monitoring, will drive more sophisticated ML models.
• The field is poised for significant evolution, with AI/ML playing an increasingly vital role in lung transplant care.