Machine Learning-Driven Diagnostic Screening of Cardiovascular Disease via Gut Microbiome Profiling

DOI

10.2991/978-94-6463-716-8_25How to use a DOI?

Keywords

Cardiovascular Disease (CVD); Gut Microbiome; Boosting Algorithms; Non-Invasive Diagnosis

Abstract

Cardiovascular disease remains one of the top causes of morbidity and mortality around the globe, with a growing requirement for innovative non-invasive diagnostic tools. Most established methods of diagnosis suffer from the drawbacks of invasiveness, costliness, and limited access to different settings, particularly resource-restricted ones. Current literature on the gut microbiota has shown promising aspects on being a gold mine source of biomarkers for almost all dis eases, including CVD. This study explores a machine learning-based diagnostic approach that uses gut microbiota data to predict the presence of CVD with high accuracy and interpretability.

We used the advanced ensemble model LightGBM, given its strength in dealing with high-dimensional data and superior prediction. This model was trained and validated on a very well-crafted dataset comprising gut microbiome profiles with normalization and feature scaling applied for preprocessing to ensure that data are consistent. Model performance is further optimized using hyperparameter tuning, applied via grid search and cross-validation.

To improve interpretability, SHAP (SHapley Additive exPlanations) analysis was incorporated, providing detailed insights into feature importance and identifying key microbial taxa, such as Faecalibacterium prausnitzii, as significant predictors of CVD. The model’s performance was evaluated using metrics such as accuracy, precision, recall, F1-score, and ROC-AUC, demonstrating robust diagnostic capabilities.

This work represents a significant leap in precision medicine: it presents a scalable, non-invasive diagnostic approach to CVD based on gut microbiome data. It com bines the state-of-the-art predictive modeling with interpretability to bridge the gap between computational advancements and clinical applicability, thus opening up further avenues for innovations in microbiome-based diagnostics.

Copyright

© 2025 The Author(s)

Open Access

Open Access This chapter is licensed under the terms of the Creative Commons Attribution-NonCommercial 4.0 International License (http://creativecommons.org/licenses/by-nc/4.0/), which permits any noncommercial use, sharing, adaptation, distribution and reproduction in any medium or format, as long as you give appropriate credit to the original author(s) and the source, provide a link to the Creative Commons license and indicate if changes were made.

Download article (PDF)

TY  - CONF
AU  - Gagandeep Marken
AU  - Prasad Naik
PY  - 2025
DA  - 2025/05/26
TI  - Machine Learning-Driven Diagnostic Screening of Cardiovascular Disease via Gut Microbiome Profiling
BT  - Proceedings of the International Conference on Recent Advancements and Modernisations in Sustainable Intelligent Technologies and Applications (RAMSITA 2025)
PB  - Atlantis Press
SP  - 305
EP  - 322
SN  - 1951-6851
UR  - https://doi.org/10.2991/978-94-6463-716-8_25
DO  - 10.2991/978-94-6463-716-8_25
ID  - Marken2025
ER  -