Artificial intelligence electrocardiogram as a novel screening tool to detect a newly abnormal left ventricular ejection fraction after anthracycline-based cancer therapy.

AIMS: Cardiotoxicity is a serious side effect of anthracycline treatment, most commonly manifesting as a reduction in left ventricular ejection fraction (EF). Early recognition and treatment have been advocated, but robust, convenient, and cost-effective alternatives to cardiac imaging are missing. Recent developments in artificial intelligence (AI) techniques applied to electrocardiograms (ECGs) may fill this gap, but no study so far has demonstrated its merit for the detection of an abnormal EF after anthracycline therapy. METHODS AND RESULTS: Single centre consecutive cohort study of all breast cancer patients with ECG and transthoracic echocardiography (TTE) evaluation before and after (neo)adjuvant anthracycline chemotherapy. Patients with HER2-directed therapy, metastatic disease, second primary malignancy, or pre-existing cardiovascular disease were excluded from the analyses as were patients with EF decline for reasons other than anthracycline-induced cardiotoxicity. Primary readout was the diagnostic performance of AI-ECG by area under the curve (AUC) for EFs < 50%. Of 989 consecutive female breast cancer patients, 22 developed a decline in EF attributed to anthracycline therapy over a follow-up time of 9.8 ± 4.2 years. After exclusion of patients who did not have ECGs within 90 days of a TTE, 20 cases and 683 controls remained. The AI-ECG model detected an EF < 50% and ≤ 35% after anthracycline therapy with an AUC of 0.93 and 0.94, respectively. CONCLUSION: These data support the use of AI-ECG for cardiotoxicity screening after anthracycline-based chemotherapy. This technology could serve as a gatekeeper to more costly cardiac imaging and could enable patients to monitor themselves over long periods of time.

Artificial intelligence electrocardiogram can be used to screen for an abnormal heart function after anthracycline chemotherapy, opening the door to new ways of cost-effective screening of cancer survivors at risk of cardiotoxicity over long periods of time.

Mortality and Major Adverse Cardiac Events in Patients With Breast Cancer Receiving Radiotherapy: The First Decade.

Background Treatment for breast cancer (BC) frequently involves radiotherapy. Guidelines recommend screening for cardiac adverse events starting 10 years after radiotherapy. The rationale for this interval is unclear. Methods and Results We aimed to study cardiovascular event rates in the first decade following curative radiotherapy for BC. We compared mortality and cardiovascular event rates with an age- and risk factor-matched control population. We included 1095 patients with BC (mean age 56±12 years). Two hundred and eighteen (19.9%) women died. Cancer and cardiovascular mortality caused 107 (49.1%) and 22 (10.1%) deaths, respectively. A total of 904 cases were matched to female FLEMENGHO (Flemish Study on Environment, Genes and Health Outcomes) participants. Coronary artery disease incidence was similar (risk ratio [RR], 0.75 [95% CI, 0.48-1.18]), yet heart failure (RR, 1.97 [95% CI, 1.19-3.25]) and atrial fibrillation/flutter (RR, 1.82 [95% CI, 1.07-3.08]) occurred more often in patients with BC. Age (hazard ratio [HR], 1.033 [95% CI, 1.006-1.061], P=0.016), tumor grade (HR, 1.739 [95% CI, 1.166-2.591], P=0.007), and neoadjuvant treatment setting (HR, 2.782 [95% CI, 1.304-5.936], P=0.008) were risk factors for mortality. Risk factors for major adverse cardiac events were age (HR, 1.053 [95% CI, 1.013-1.093]; P=0.008), mean heart dose (HR, 1.093 [95% CI, 1.025-1.167]; P=0.007), history of cardiovascular disease (HR, 2.386 [95% CI, 1.096-6.197]; P=0.029) and Mayo Clinic Cardiotoxicity Risk Score (HR, 2.664 [95% CI, 1.625-4.367]; P<0.001). Conclusions Ten-year mortality following curative treatment for unilateral BC was mainly cancer related, but heart failure and atrial fibrillation/flutter were already common in the first decade following irradiation. Mean heart dose, pre-existing cardiovascular diseases, and Mayo Clinic Cardiotoxicity Risk Score were risk factors for cardiac adverse events. These results suggest a need for early dedicated cardio-oncological follow-up after radiotherapy.

Predictability of cardiotoxicity: Experience of a Belgian cardio-oncology clinic.

BACKGROUND: New oncological treatments improved survival but also increased awareness of cardiovascular side-effects during and after cancer therapy. METHODS: We report the experience of the cardio-oncology clinic at a large Belgian tertiary care center and investigated the predictability of cardiotoxicity based on referring department, cardiovascular risk factors, cancer treatment and existing risk scores of the American Society of Clinical Oncologists (ASCO) and Mayo Clinic. Cardiotoxicity was defined as a 10% reduction in Left Ventricular Ejection Fraction (LVEF) compared to the baseline transthoracic echocardiography (TTE) in asymptomatic patients or 5% in symptomatic patients. RESULTS: Of the 324 patients included, 14.5% died during follow-up. Most deaths were oncological, yet 19% of deaths were attributable to cardiovascular diseases. Models based on cardiovascular risk factors alone and cardiovascular risk factors combined with cardiotoxic medication poorly predicted cardiotoxicity. Existing risk scores from ASCO and Mayo Clinic also poorly predicted cardiotoxicity. A weighed model based on the Mayo Clinic cardiotoxicity risk score was the best risk assessment tool with still a limited predictive value with an Area Under the Receiver Operating Characteristic curve of 0.654 (CI 95%: 0.601-0.715). CONCLUSION: Cardiovascular morbidity and mortality are common in cancer patients and survivors and stress the unmet need of adequate risk prediction tools for systematic screening and rigorous cardiovascular follow-up. In our outpatient cohort, cardiotoxicity risk could not be adequately predicted by cancer type, using classic cardiovascular risk factors, nor by the combination of cardiovascular risk factors and the proposed cancer treatment. Furthermore, we showed that existing cardiotoxicity risk scores are suboptimal and should thus be interpreted with caution.