News
Article
Author(s):
Consumer-wearable devices can monitor treatment response and provide continuous health data for patients with heart disease and atrial fibrillation.
Consumer wearable devices, which monitor heart rate and physical activity (PA) via a wristband connected smartphone, can provide clinically valuable data for comparing the efficacy of digoxin (Digox; Concordia Pharmaceuticals) versus beta-blockers in patients with atrial fibrillation (AF) and heart failure (HF), according to a study published in Nature Medicine. The findings support the potential of utilizing wearable technology and artificial intelligence (AI) to continuously monitor treatment responses, measure disease severity, and provide timely clinical information for patients with cardiovascular disease (CVD).
CVD is the leading cause of death in the US, accounting for approximately 928,741 deaths in 2020, and encompasses various other related conditions affecting the heart and blood vessels, such as HF and AF. HF occurs when the heart is not pumping well enough to meet the body’s needs for blood and oxygen, leading to the buildup of fluid in the lungs. This may lead to symptoms like shortness of breath, persistent coughing, or rapid or irregular heartbeat. HF has strong associations with AF, the most common type of heart arrythmia characterized by the heart beating too fast, slow, or irregularly. The conditions are considered bidirectional, meaning one can contribute to the development or worsening of the other.1-4
Treatment for patients with HF and AF often includes medications to help improve the function of the heart, control blood pressure, or reduce cholesterol; however, surgery to repair the heart or implant a device to support the heart’s function may be recommended for patients with greater disease severity. Patients may struggle to adhere to their treatment plans due to the time-consuming clinical visits and the high costs associated with the treatment. Additionally, clinicians can receive limited functional data demonstrating a patient’s health status at individual appointments. Utilizing consumer-wearable devices gives providers the ability to continuously monitor patients’ health metrics, allowing them to provide more personalized treatment plans and respond more promptly to shifts in disease severity.3,5
In the study, the researchers hypothesized that wearable devices can (1) identify whether digoxin is inferior to beta-blockers for long-term heart rate control in patients with AF at rest and on exertion, (2) improve ability to adjust for differences in PA, and (3) explore whether data collected from wearable devices are comparable with conventional methods for predicting treatment progress. They performed statistical analyses to compare heart rates between participants receiving digoxin and participants receiving beta-blockers based on reported results from the RATE-AF trial (NCT02391337). Using a convolutional neural network, they analyzed the wearable device data and predicted New York Heart Association (NYHA) functional class.5,6
The study involved 53 older, multimorbid patients (mean age 75.6 years [s.d. 8.4], 40% women) with permanent AF and HF who were randomized to receive either digoxin or beta-blockers. The researchers successfully collected over 140 million data points for heart rate and PA intervals and found there was no significant difference in heart rate between participants receiving digoxin compared with those treated with beta-blockers. Additionally, data collected from wearable devices were comparable to standard clinical measures of electrocardiographic heart rate and 6-minute walk test (F1 score 0.56 [95% CI 0.41 to 0.70] versus (0.55 [95% CI 0.41 to 0.68]) and can predict NYHA functional class.5
The findings highlight the potential of consumer-wearable devices as an alternative, dynamic method for monitoring patients with HR and AF, potentially replacing or supplementing in-person clinical assessments and enhancing the timeliness and quality of care for patients.
“Heart conditions such as [AF] and HF are expected to double in prevalence over the next few decades, leading to a large burden on patients as well as substantial healthcare cost,” said Professor Dipak Kotecha, MBChB, PCAP, MSc, FRCP, FESC, FHEA, professor of cardiology at the Institute of Cardiovascular Sciences at the University of Birmingham, and lead study author, in a press release. “This study is an exciting showcase for how artificial intelligence can support new ways to help treat patients better.”7
REFERENCES