Machine learning methods, applications and economic analysis to predict heart failure hospitalisation risk: a scoping...

Area of Science:

• Cardiology
• Medical Informatics
• Artificial Intelligence

Background:

• Heart failure (HF) is a global chronic condition affecting over 64 million individuals.
• Machine learning (ML) offers powerful pattern recognition and predictive capabilities.
• Accurate risk assessment for HF hospitalisation is crucial for patient management.

Purpose of the Study:

• To conduct a scoping review of ML methods, applications, and economic analyses for predicting HF hospitalisation risk.
• To synthesize current evidence on the use of ML in HF risk prediction.
• To identify gaps and future directions in ML for HF management.

Main Methods:

• Utilizing the Arksey and O'Malley scoping review framework.
• Adhering to PRISMA Protocol and PRISMA extension for scoping reviews.
• Systematic literature search across PubMed, Scopus, and Web of Science databases.

Main Results:

• Data extraction and synthesis of studies on ML models for adult HF hospitalisation risk prediction.
• Identification of various ML algorithms and their reported performance.
• Analysis of economic implications associated with ML-driven HF risk prediction.

Conclusions:

• Machine learning demonstrates significant potential in predicting heart failure hospitalisation risk.
• Further research is needed to refine ML models and assess their real-world economic impact.
• This review provides a comprehensive overview of ML applications in HF risk stratification.