MIEO: encoding clinical data to enhance cardiovascular event prediction
This work addresses cardiovascular event prediction for patients with ischaemic heart disease, offering an incremental improvement in handling data challenges.
The paper tackled the problem of predicting cardiovascular death from clinical data with low labeled data availability and heterogeneity by using self-supervised auto-encoders to embed patient data into a latent space, resulting in improved balanced accuracy compared to raw data classification.
As clinical data are becoming increasingly available, machine learning methods have been employed to extract knowledge from them and predict clinical events. While promising, approaches suffer from at least two main issues: low availability of labelled data and data heterogeneity leading to missing values. This work proposes the use of self-supervised auto-encoders to efficiently address these challenges. We apply our methodology to a clinical dataset from patients with ischaemic heart disease. Patient data is embedded in a latent space, built using unlabelled data, which is then used to train a neural network classifier to predict cardiovascular death. Results show improved balanced accuracy compared to applying the classifier directly to the raw data, demonstrating that this solution is promising, especially in conditions where availability of unlabelled data could increase.