April 24, 2023Scientific ReportsOpen Access

Classification models for assessing coronary artery disease instances using clinical and biometric data: an explainable man-in-the-loop approach

View Full Paper

Ask AI

Bookmark

Why the study?

The authors sought to develop computer-aided machine learning classification models using clinical data and an expert man-in-the-loop approach to identify coronary artery disease with high accuracy.

Does incorporating expert opinion into machine learning models improve the diagnostic accuracy of coronary artery disease in patients with clinical and biometric data?

Structured PICO

Does incorporating expert opinion into machine learning models improve the diagnostic accuracy of coronary artery disease in patients with clinical and biometric data?

Population

571 patients with biometric and clinical data (21 total features, 43% ICA-confirmed CAD instances)

Intervention

Machine learning classification models incorporating expert's diagnostic yield ('man-in-the-loop' approach)

Comparator

Machine learning classification models without expert's diagnosis as input

Outcome

Accuracy, sensitivity, and specificity of CAD identificationsurrogate

Incorporating expert diagnostic opinion into machine learning models for CAD detection significantly improves diagnostic accuracy and sensitivity compared to models relying solely on clinical and biometric data.

Implication

Expert input may augment ML accuracy for CAD diagnosis; leaves open prospective validation before clinical adoption.

Abstract

The main goal driving this work is to develop computer-aided classification models relying on clinical data to identify coronary artery disease (CAD) instances with high accuracy while incorporating the expert's opinion as input, making it a "man-in-the-loop" approach. CAD is traditionally diagnosed in a definite manner by Invasive Coronary Angiography (ICA). A dataset was created using biometric and clinical data from 571 patients (21 total features, 43% ICA-confirmed CAD instances) along with the expert's diagnostic yield. Five machine learning classification algorithms were applied to the dataset. For the selection of the best feature set for each algorithm, three different parameter selection algorithms were used. Each ML model's performance was evaluated using common metrics, and the best resulting feature set for each is presented. A stratified ten-fold validation was used for the performance evaluation. This procedure was run both using the assessments of experts/doctors as input and without them. The significance of this paper lies in its innovative approach of incorporating the expert's opinion as input in the classification process, making it a "man-in-the-loop" approach. This approach not only increases the accuracy of the models but also provides an added layer of explainability and transparency, allowing for greater trust and confidence in the results. Maximum achievable accuracy, sensitivity, and specificity are 83.02%, 90.32%, and 85.49% when using the expert's diagnosis as input, compared to 78.29%, 76.61%, and 86.07% without the expert's diagnosis. The results of this study demonstrate the potential for this approach to improve the diagnosis of CAD and highlight the importance of considering the role of human expertise in the development of computer-aided classification models.