# Development of an Electronic Medical Record–Based Score for Heart Failure Prediction in Cancer Survivors

## TL;DR

This study developed a new risk score to predict heart failure in cancer survivors using electronic medical records, which outperformed existing scores in internal validation.

## Contribution

A cancer-specific heart failure risk score (CHERISH) tailored for electronic medical records was developed and validated.

## Key findings

- CHERISH demonstrated strong 10-year heart failure prediction with an AUC of 0.829 in internal validation.
- CHERISH outperformed the ARIC-HF score in internal validation (AUC: 0.829 vs. 0.697).
- In external validation, CHERISH had an AUC of 0.721 for predicting heart failure.

## Abstract

Awareness of heart failure (HF) as a long-term complication of cancer has led to an interest in HF surveillance among survivors. However, existing HF risk scores are not tailored for survivors and not designed for the use in electronic medical records (EMRs) or administrative data sets where clinical data such as blood pressure and pathology results are often unavailable.

The objective of the study is to develop a cancer-specific incident HF risk score suitable for screening in EMR or administrative data sets.

The cancer-specific HF prediction from EMRs in survivor health care (CHERISH) risk score was developed from risk variables identified in 16,191 cancer survivors (mean 61 years; 59.5% female) derived from the UK Biobank. External validation was conducted in a population-based Ontario cohort (n = 446,096; mean 67 years; 53.9% female). HF risk classification with CHERISH was compared against the ARIC (Atherosclerotic Risk In Community)-HF score using area under the curve (AUC).

The CHERISH score incorporates 11 clinical variables—age, years since cancer diagnosis, coronary heart disease, arrhythmia, myocardial infarct, diabetes, hypertension, leukemia, non-Hodgkin lymphoma, lung cancer, and breast cancer. CHERISH demonstrated strong prediction of 10-year HF incidence during internal validation (AUC: 0.829), exceeding ARIC-HF (AUC: 0.697; P < 0.001). In external validation, CHERISH showed an AUC of 0.721 in predicting 10-year HF incidence, compared to an AUC of 0.751 (P < 0.001) with ARIC-HF.

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.