首页|Insights into Heart Failure Metabolite Markersthrough Explainable Machine Learning
Insights into Heart Failure Metabolite Markersthrough Explainable Machine Learning
扫码查看
点击上方二维码区域，可以放大扫码查看
原文链接
NETL
NSTL
By a News Reporter-Staff News Editor at Robotics & Machine Learning Daily News Daily News – According to news reporting based on a preprint abstract, our journalists obtained the following quote sourced from bi orxiv.org: “Understanding molecular traits through metabolomics offers an avenue to tailor cardiovascular prevention, diagnosis and treatment strategies more effectively. “This study focuses on the application of machine learning (ML) and explainable artificial intelligence (XAI) algorithms to detect discriminant molecular signat ures in heart failure (HF). “In this study, we aim to uncover metabolites with significant predictive value by analyzing targeted metabolomics data through ML models and XAI methodologies. After robust quality control procedures, we analyzed 55 metabolites from 124 pl asma samples, including 53 HF patients and 71 controls, comparing Logistic Regre ssion (Logit) models with Support Vector Machine (SVM) and eXtreme Gradient Boos ting (XGB), all achieving high accuracy in predicting group labels: 84.20% (sigma=5.46), 85.73% (sigma=6.25), and 84.80% (sigma =7.84), respectively. Permutation-based variable importance and Local Interpreta ble Model-agnostic Explanations (LIME) were used for group-level and individual- level explainability, respectively, complemented by H-Friedman statistics for va riable interactions, yielding reliable, explainable insights of the ML models. M etabolites well-known for their association with heart failure, such as glucose and cholesterol, but also more recently described association such C18:1 carniti ne, were reaffirmed in our analysis. The novel discovery of lignoceric acid (C24 :0) as a critical discriminator, was confirmed in a replication cohort, undersco ring its potential as a metabolite marker.
NETL
NSTL
