Explainable AI in Healthcare

Abstract

The traditional cardiology prediction model includes factors like age, total cholesterol, HDL cholesterol, smoking, blood pressure, and diabetes. But the machine algorithms turned up a wider array of factors in their models, including: COPD, severe mental illness, prescription of oral corticosteroids, triglyceride levels, atrial fibrillations, chronic kidney disease, and rheumatoid arthritis. Allowing machines to learn risk factors in a huge number of patients makes for better predictions of heart attacks. Machine-learning significantly improves accuracy of cardiovascular risk prediction, increasing the number of patients identified who could benefit from preventive treatment, while avoiding unnecessary treatment of others. However, the use of machine learning algorithms has been limited due to the lack of interpretability of more complex models, reducing the trust of users in the model. The solution to the limitation of the ‘black-box’ nature of machine-learning algorithms, in particular neural networks, which are difficult to interpret, the inherent complexity in how the risk factor variables are interacting and their independent effects on the outcome is achieved through explainable AI.