Related Experiment Video
Updated: Jul 9, 2025
Multimodal Study of Murine Cardiovascular Remodeling: Four-Dimensional Ultrasound and Mass Spectrometry Imaging
Published on: January 10, 2025
Cardiac murmur grading and risk analysis of cardiac diseases based on adaptable heterogeneous-modality multi-task
Chenyang Xu1, Xin Li2, Xinyue Zhang1
1Department of Computer Science, Tianjin University of Technology, Tianjin, China.
Insights
This study introduces an AI method for cardiac murmur grading and risk analysis using multi-task learning. The approach improves early cardiovascular disease detection by analyzing cardiac sounds and patient data, offering better clinical insights.
Area of Science:
- Cardiology
- Artificial Intelligence
- Medical Diagnostics
Background:
- Cardiovascular diseases (CVDs) are a leading cause of mortality, necessitating improved early detection methods.
- Current AI for cardiac sound analysis is limited to classification, not grading, and often neglects demographic data, hindering clinical application.
- Deep learning models for cardiac diagnostics often lack interpretability, posing challenges for clinical adoption.
Purpose of the Study:
- To develop an AI-assisted method for accurate cardiac murmur grading and cardiovascular disease risk analysis.
- To address limitations in existing AI by integrating multi-task learning for murmur grading and incorporating heterogeneous data modalities.
- To enhance the interpretability of AI models for clinical decision support in cardiology.
Main Methods:
- Proposed a Hierarchical Multi-Task learning (HMT) method to prevent negative interference between cardiac murmur detection and grading tasks.
- Developed a Heterogeneous Multi-modal feature impact Adaptation (HMA) method to balance unstructured cardiac sound and structured demographic data for risk prediction.
- Implemented a multi-task interpretability module using SHAP graphs and nomograms for visualizing critical sound segments and decoupling risk factors.
Main Results:
- The proposed AI method achieved state-of-the-art performance in cardiac murmur detection, grading, and risk analysis on the CirCor DigiScope PCG dataset.
- The HMT and HMA methods effectively handled multi-task learning and heterogeneous data, outperforming existing approaches.
- The interpretability module provided clinical insights into cardiac disease risk by visualizing key murmur features and risk factors.
Conclusions:
- The developed AI framework offers a robust solution for AI-assisted cardiac murmur grading and risk analysis.
- Integrating multi-task learning and heterogeneous data adaptation significantly improves diagnostic accuracy and clinical utility.
- Enhanced model interpretability provides valuable evidence for clinical decision-making in cardiovascular disease diagnosis.
Abstract:
Cardiovascular disease (CVDs) has become one of the leading causes of death, posing a significant threat to human life. The development of reliable Artificial Intelligence (AI) assisted diagnosis algorithms for cardiac sounds is of great significance for early detection and treatment of CVDs. However, there is scarce research in this field. Existing research mainly faces three major challenges: (1) They mainly limited to murmur classification and cannot achieve murmur grading, but attempting both classification and grading may lead to negative effects between different multi-tasks. (2) They mostly pay attention to unstructured cardiac sound modality and do not consider the structured demographic modality, as it is difficult to balance the influence of heterogeneous modalities. (3) Deep learning methods lack interpretability, which makes it challenging to apply them clinically. To tackle these challenges, we propose a method for cardiac murmur grading and cardiac risk analysis based on heterogeneous modality adaptive multi-task learning. Specifically, a Hierarchical Multi-Task learning-based cardiac murmur detection and grading method (HMT) is proposed to prevent negative interference between different tasks. In addition, a cardiac risk analysis method based on Heterogeneous Multi-modal feature impact Adaptation (HMA) is also proposed, which transforms unstructured modality into structured modality representation, and utilizes an adaptive mode weight learning mechanism to balance the impact between unstructured modality and structured modality, thus enhancing the performance of cardiac risk prediction. Finally, we propose a multi-task interpretability learning module that incorporates an important evaluation using random masks. This module utilizes SHAP graphs to visualize crucial murmur segments in cardiac sound and employs a multi-factor risk decoupling model based on nomograms. And then we gain insights into the cardiac disease risk in both pre-decoupled multi-modality and post-decoupled single-modality scenarios, thus providing a solid foundation for AI assisted cardiac murmur grading and risk analysis. Experimental results on a large real-world CirCor DigiScope PCG dataset demonstrate that the proposed method outperforms the state-of-the-art (SOTA) method in murmur detection, grading, and cardiac risk analysis, while also providing valuable diagnostic evidence.
