Research Projects

Prediction of Cancer Therapy-Related Cardiac Dysfunction Using ECG

Machine Learning / Deep Learning Recognition

Prediction of Cancer Therapy-Related Cardiac Dysfunction Using ECG

Research Overview

Construction of early risk assessment systems using machine learning

Administration of anticancer drugs in cancer treatment can cause side effects on the heart. In this research, we are developing systems that predict the risk of cancer therapy-related cardiac dysfunction (CTRCD) early from ECG data. Research approach: - Detection of subtle change patterns in 12-lead ECG - Risk prediction models using time-series deep learning - Visualization of prediction rationale using explainable AI We are advancing verification using real clinical data through joint research with the National Cancer Center.

Keywords

EcgCardiotoxicityPredictive Medicine

Related Publications

View All →
2026Int'l Conf.

Graph neural networks enhance CTRCD detection from 12-lead ECG by modeling inter-lead relationships: a preliminary study

Yifan Liang, Natsu Suyama, Yuki Ishizuka et al.

2026 IEEE/SICE international symposium on system integration (SII)

ECGDeep Learning+2
2025Int'l Conf.

Multi-scale feature learning with CNN-RNN-attention framework for ECG-based cancer therapy-related cardiac dysfunction detection

Natsu Suyama, Akira Furui, Takio Kurita et al.

Proceedings of the 47th annual international conference of the IEEE engineering in medicine and biology society (EMBC)

ECGDeep Learning+2
PDFDOI