Development of an Electronic Medical Record–Based Score for Heart Failure Prediction in Cancer Survivors
Authors' conclusion
The integration of the CHERISH score into EMR systems may provide large-scale, automated HF risk assessment in cancer survivors, using routinely collected clinical data.
Study context
- Population
- Cancer survivors (UK Biobank derivation; Ontario population-based external validation)derivation
- Participants
- 16,191 survivors
- Comparison
- CHERISH risk score vs ARIC-HF score
- Outcome
- Prediction of HF incidence (AUC)
- Follow-up
- 10 years
Methodological detailsUK Biobank derivation cohort, population-based external validation cohort (Ontario)
- UK Biobank derivation cohort
- Population-based external validation cohort (Ontario)
Performance
As reported in the abstract
Prediction of 10-year HF incidence
| Test or model | AUC, internal validation | AUC, external validation |
|---|---|---|
| CHERISH | 0.829 | 0.721 |
| ARIC-HF | 0.697 | 0.751 |
AUC, internal validation
CHERISH0.829
ARIC-HF0.697
AUC, external validation
CHERISH0.721
ARIC-HF0.751
- CHERISH vs ARIC-HF: P < 0.001 — internal validation: 0.829 vs 0.697
- CHERISH vs ARIC-HF: P < 0.001 — external validation: 0.721 vs 0.751
Original publication
Development of an Electronic Medical Record–Based Score for Heart Failure Prediction in Cancer Survivors. JACC Adv. Published 11 September 2025. doi:10.
Summarised from the published abstract; every number is checked against it