(C47) Machine Learning-based Risk Prediction for Canine Myxomatous Mitral Valve Disease Using Electronic Health Record Data

Abstract:

Background: Myxomatous mitral valve disease (MMVD) is the most common cause of heart failure (HF) in dogs, and its risk assessment of HF is often challenging. Machine learning applied to electronic health records (EHRs) is an effective tool for predicting prognosis in the medical field.

Objectives: This study aimed to develop machine learning-based HF risk prediction models for dogs with MMVD using a dataset of EHRs.

Animals: A total of 143 dogs with MMVD between May 2018 and May 2022.

Methods: Complete medical records were reviewed for all patients. Demographic data, radiographic measurements, echocardiographic values, and laboratory results were obtained from the clinical database. Four machine learning algorithms (Random Forest, K-Nearest Neighbors, Naïve Bayes, Support Vector Machine) were used to develop the risk prediction models. Model performance was represented by plotting the receiver operating characteristic (ROC) curve and calculating the area under the curve (AUC). The best-performing model was chosen for the feature ranking process.

Results: Random forest showed superior performance to the other models (AUC = 0.88), while the performance of the K-nearest neighbors showed the lowest performance (AUC = 0.69). The top three models showed excellent performance (AUC ≥ 0.8). According to the random forest algorithm feature ranking, echocardiographic and radiographic variables had the highest predictive values for HF, followed by PCV and respiratory rates. Among the electrolyte variables, chloride had the highest predictive value for HF.

Conclusions and clinical importance: These machine-learning models will support clinical decision-making in estimating the prognosis of patients with MMVD.