Combining High-Fidelity hiPSC-Derived Cardiomyocytes with AI-Enhanced Modeling for Improved Assessment of Proarrhythmic Risks
-
By
-
Su-Bin Kim
-
Jaehun Lee
-
Jieun An
-
Ara Cho
-
Kun Hee Lee
-
Hwan Choi
-
Choongseong Han
-
Muhammad Adnan Pramudito
-
Ki Moo Lim
-
Dong-Hun Woo
-
April 28, 2026
-
Clinical Scorecard: Combining High-Fidelity hiPSC-Derived Cardiomyocytes with AI-Enhanced Modeling for Improved Assessment of Proarrhythmic Risks
At a Glance
| Category | Detail |
|---|
| Condition | Drug-induced cardiotoxicity |
| Key Mechanisms | Integration of high-purity hiPSC-CMs and AI-driven modeling to assess proarrhythmic risks. |
| Target Population | Patients undergoing treatment with drugs that may induce cardiotoxicity. |
| Care Setting | Pharmaceutical industry and preclinical research. |
Key Highlights
- hiPSC-CMs provide a comprehensive electrophysiological environment mimicking human cardiac tissue.
- AI models enhance predictive power of in vitro assays for proarrhythmic risk.
- Integration of multiple biomarkers improves detection of cardiotoxicity.
- Long-term monitoring is essential to identify time-dependent cardiotoxic effects.
- The platform successfully differentiates between cytotoxicity and functional irregularities.
Guideline-Based Recommendations
Diagnosis
- Utilize hiPSC-CMs for assessing drug-induced cardiotoxicity.
Management
- Implement AI-enhanced modeling to evaluate proarrhythmic risks in drug development.
Monitoring & Follow-up
- Conduct long-term monitoring (e.g., 120 hours) to detect functional cardiotoxicity.
Risks
- Consider the limitations of traditional assays in predicting cardiotoxicity.
Patient & Prescribing Data
Patients receiving anticancer agents and other drugs with potential cardiotoxic effects.
AI-hiPSC-CM platform can identify hidden proarrhythmic risks that conventional assays may overlook.
Clinical Best Practices
- Adopt the CiPA initiative framework for comprehensive cardiac safety assessments.
- Ensure high-purity, ventricular-like hiPSC-CMs are used for consistent results.
- Leverage AI to analyze complex electrophysiological data for improved risk prediction.
References
