Multimodal Fusion Artificial Intelligence Model to Predict Risk for MACE and Myocarditis in Cancer Patients Receiving Immune Checkpoint Inhibitor Therapy
Authors' conclusion
A multimodal fusion AI model to predict myocarditis and adverse cardiovascular events in cancer patients starting ICI therapy had good prognostic performance.
Study context
- Population
- Cancer patients treated with immune checkpoint inhibitor (ICI) who had troponin measurement, tertiary institution, 2011–2022
- Participants
- 2,258 patients
- Exposure
- Multimodal joint fusion artificial intelligence (AI) model vs individual electrocardiogram (ECG) and baseline EMR/laboratory value models
- Outcome
- Composite of:
- ICI-related myocarditis
- MACE (TIA/stroke, new HF diagnosis, MI, cardiac death)
Methodological detailssingle tertiary institution
- Single tertiary institution
Main finding
As reported in the abstract
Prediction of composite:
- ICI-related myocarditis
- MACE
| Group | AUC | True positive rate | NPV |
|---|---|---|---|
| Joint fusion model | 0.72 | 0.64 | 0.98 |
Joint fusion model
AUC0.72
True positive rate0.64
NPV0.98
Observational data: associations, not effects.
Further findings
Composite of CV clinical adverse events (ICI-related myocarditis and MACE)
- Patients with composite event
- 264 (11.7%)
- Events overall
- 428
- ICI-related myocarditis events
- 59 [3%]
- Cardiac deaths
- 59 [3%]
- Mean age 68.5 ± 11.5 years, 59.7% male
Parts of this Brief are withheld: the automatic checks could not confirm them against the abstract.
Original publication
Multimodal Fusion Artificial Intelligence Model to Predict Risk for MACE and Myocarditis in Cancer Patients Receiving Immune Checkpoint Inhibitor Therapy. JACC Adv. Published 13 December 2024. doi:10.
Composed by AI from the published abstract and checked against it. How Briefs are made →