Explainable machine learning for neoplasms diagnosis via electrocardiograms: an externally validated study

2024-12-10

Cardio-Oncology

AI Summary

Early tumor diagnosis remains hampered by invasiveness, high cost, and limited accessibility in resource-constrained settings. Method: We propose a non-invasive machine learning screening framework leveraging routine 12-lead electrocardiograms (ECG), integrating multi-scale temporal ECG feature engineering with ensemble tree models (XGBoost/LightGBM) and, for the first time, applying SHAP analysis to interpret ECG signals and identify novel cardiovascular–oncological interaction biomarkers. Contribution/Results: The method achieves AUC >0.92 in both internal and independent external validation cohorts. Key biomarkers were confirmed by blinded clinical expert review for interpretability and biological plausibility. This work establishes a low-cost, robust, and deployable technical pathway for early tumor screening in resource-limited environments and provides preliminary mechanistic insights into cardio-neoplasm crosstalk.

Technology Category

• Machine Learning: Ensemble Methods
• Humans and AI: Human-in-the-loop Machine Learning
• Computer Vision: Multi-modal Vision

Application Category

• Economics, Online Markets and Human Computation: Data quality aspects of human-annotated datasets
• User Modeling, Personalization and Recommendation: Explainable and interpretable methods for personalization
• Web Mining and Content Analysis: Machine learning and data science for the Web

Abstract

Neoplasms are a major cause of mortality globally, where early diagnosis is essential for improving outcomes. Current diagnostic methods are often invasive, expensive, and inaccessible in resource-limited settings. This study explores the potential of electrocardiogram (ECG) data, a widely available and non-invasive tool for diagnosing neoplasms through cardiovascular changes linked to neoplastic presence. A diagnostic pipeline combining tree-based machine learning models with Shapley value analysis for explainability was developed. The model was trained and internally validated on a large dataset and externally validated on an independent cohort to ensure robustness and generalizability. Key ECG features contributing to predictions were identified and analyzed. The model achieved high diagnostic accuracy in both internal testing and external validation cohorts. Shapley value analysis highlighted significant ECG features, including novel predictors. The approach is cost-effective, scalable, and suitable for resource-limited settings, offering insights into cardiovascular changes associated with neoplasms and their therapies. This study demonstrates the feasibility of using ECG signals and machine learning for non-invasive neoplasm diagnosis. By providing interpretable insights into cardio-neoplasm interactions, this method addresses gaps in diagnostics and supports integration into broader diagnostic and therapeutic frameworks.

Problem

• Diagnosing neoplasms non-invasively using ECG data
• Identifying cardiovascular changes linked to neoplastic presence
• Providing cost-effective diagnostics for resource-limited settings

Innovation

• Using ECG signals for non-invasive neoplasm diagnosis
• Combining tree-based models with Shapley value analysis
• Identifying significant ECG features for interpretable predictions