RESUMEN
Aims: There are no comprehensive machine learning (ML) tools used by oncologists to assist with risk identification and referrals to cardio-oncology. This study applies ML algorithms to identify oncology patients at risk for cardiovascular disease for referrals to cardio-oncology and to generate risk scores to support quality of care. Methods and results: De-identified patient data were obtained from Vanderbilt University Medical Center. Patients with breast, kidney, and B-cell lymphoma cancers were targeted. Additionally, the study included patients who received immunotherapy drugs for treatment of melanoma, lung cancer, or kidney cancer. Random forest (RF) and artificial neural network (ANN) ML models were applied to analyse each cohort: A total of 20 023 records were analysed (breast cancer, 6299; B-cell lymphoma, 9227; kidney cancer, 2047; and immunotherapy for three covered cancers, 2450). Data were divided randomly into training (80%) and test (20%) data sets. Random forest and ANN performed over 90% for accuracy and area under the curve (AUC). All ANN models performed better than RF models and produced accurate referrals. Conclusion: Predictive models are ready for translation into oncology practice to identify and care for patients who are at risk of cardiovascular disease. The models are being integrated with electronic health record application as a report of patients who should be referred to cardio-oncology for monitoring and/or tailored treatments. Models operationally support cardio-oncology practice. Limited validation identified 86% of the lymphoma and 58% of the kidney cancer patients with major risk for cardiotoxicity who were not referred to cardio-oncology.
RESUMEN
A 28-year-old G2P0010 woman with a history of COVID infection during her current pregnancy treated with monoclonal antibodies and benign gestational thrombocytopenia presented for routine prenatal care at 33 weeks' gestation. The patient was asymptomatic, but incidental tachycardia was noted on the physical exam with an irregular rhythm. An electrocardiogram (ECG) was performed and was consistent with multifocal atrial tachycardia at a rate of 144 beats per minute. The patient was started on labetalol 50 mg daily and was referred to cardiology for consultation. An echocardiogram was performed and showed dilated left ventricular cavity with a moderately reduced ejection fraction of 40%. No previous echocardiogram was available for comparison; the patient had no history of cardiac disease. The dose of labetalol was increased to 50 mg twice daily and she was admitted for digoxin loading and titration. Though fetal tolerance was excellent, her heart rate was not controlled. Digoxin was switched to flecainide and labetalol was switched to metoprolol which improved her heart rate and repeat echocardiogram showed an ejection fraction of 50%. The patient was admitted for induction of labor at 39 weeks of gestation and continued intrapartum flecainide. Metoprolol was continued intra and postpartum. Flecainide was resumed at three days postpartum due to the recurrence of atrial tachycardia and has been maintained. A repeat echocardiogram is scheduled six weeks postpartum to evaluate left ventricular function and wean off antiarrhythmics.
