Applications of artificial intelligence and machine learning in heart failure

Abstract

Machine learning (ML) is a sub-field of artificial intelligence that uses computer algorithms to extract patterns from raw data, acquire knowledge without human input, and apply this knowledge for various tasks. Traditional statistical methods that classify or regress data have limited capacity to handle large datasets that have a low signal-to-noise ratio. In contrast to traditional models, ML relies on fewer assumptions, can handle larger and more complex datasets, and does not require predictors or interactions to be pre-specified, allowing for novel relationships to be detected. In this review, we discuss the rationale for the use and applications of ML in heart failure, including disease classification, early diagnosis, early detection of decompensation, risk stratification, optimal titration of medical therapy, effective patient selection for devices, and clinical trial recruitment. We discuss how ML can be used to expedite implementation and close healthcare gaps in learning healthcare systems. We review the limitations of ML, including opaque logic and unreliable model performance in the setting of data errors or data shift. Whilst ML has great potential to improve clinical care and research in HF, the applications must be externally validated in prospective studies for broad uptake to occur.

Keywords: Artificial intelligence; Heart failure; Machine learning.

Graphical abstract

Figure 1

Comparison of the accuracy and interpretability of statistical vs. machine learning models. Traditional regression models demonstrate poor accuracy but are easier to interpret. Machine learning models with non-linear relationships offer superior accuracy but are harder to interpret. Adapted from Stewart 2020.

Figure 2

Limitations of machine learning models. Machine learning models face several limitations including lack of external validation, limited generalizability, opaque decision-making, logistical challenges in implementation due to reliance on digital infrastructure, error propagation between iterations, and dataset shift. The effectiveness of machine learning models in improving outcomes at the point of care needs to be tested prospectively in randomized controlled trials.