MIEO: encoding clinical data to enhance cardiovascular event prediction

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Borghini, Davide, Marchi, Davide, Nardone, Angelo, Scerra, Giordano, Galfrè, Silvia Giulia, Pingitore, Alessandro, Prencipe, Giuseppe, Priami, Corrado, Sîrbu, Alina
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866909841524523008
author Borghini, Davide
Marchi, Davide
Nardone, Angelo
Scerra, Giordano
Galfrè, Silvia Giulia
Pingitore, Alessandro
Prencipe, Giuseppe
Priami, Corrado
Sîrbu, Alina
author_facet Borghini, Davide
Marchi, Davide
Nardone, Angelo
Scerra, Giordano
Galfrè, Silvia Giulia
Pingitore, Alessandro
Prencipe, Giuseppe
Priami, Corrado
Sîrbu, Alina
contents 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.
format Preprint
id arxiv_https___arxiv_org_abs_2510_11257
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle MIEO: encoding clinical data to enhance cardiovascular event prediction
Borghini, Davide
Marchi, Davide
Nardone, Angelo
Scerra, Giordano
Galfrè, Silvia Giulia
Pingitore, Alessandro
Prencipe, Giuseppe
Priami, Corrado
Sîrbu, Alina
Machine Learning
Quantitative Methods
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.
title MIEO: encoding clinical data to enhance cardiovascular event prediction
topic Machine Learning
Quantitative Methods
url https://arxiv.org/abs/2510.11257