Rationale and design of a digital trial using smartphones to detect subclinical atrial fibrillation in a population at risk: The eHealth-based bavarian alternative detection of Atrial Fibrillation (eBRAVE-AF) trial

A Novel Mobile App to Identify Patients With Multimorbidity in the Emergency Setting: Development of an App and Feasibility Trial

BACKGROUND

Multimorbidity is associated with an increased risk of poor surgical outcomes among older adults; however, identifying multimorbidity in the clinical setting can be a challenge.

OBJECTIVE

We created the Multimorbid Patient Identifier App (MMApp) to easily identify patients with multimorbidity identified by the presence of a Qualifying Comorbidity Set and tested its feasibility for use in future clinical research, validation, and eventually to guide clinical decision-making.

METHODS

We adapted the Qualifying Comorbidity Sets' claims-based definition of multimorbidity for clinical use through a modified Delphi approach and developed MMApp. A total of 10 residents input 5 hypothetical emergency general surgery patient scenarios, common among older adults, into the MMApp and examined MMApp test characteristics for a total of 50 trials. For MMApp, comorbidities selected for each scenario were recorded, along with the number of comorbidities correctly chosen, incorrectly chosen, and missed for each scenario. The sensitivity and specificity of identifying a patient as multimorbid using MMApp were calculated using composite data from all scenarios. To assess model feasibility, we compared the mean task completion by scenario to that of the American College of Surgeons National Surgical Quality Improvement Program Surgical Risk Calculator (ACS-NSQIP-SRC) using paired t tests. Usability and satisfaction with MMApp were assessed using an 18-item questionnaire administered immediately after completing all 5 scenarios.

RESULTS

There was no significant difference in the task completion time between the MMApp and the ACS-NSQIP-SRC for scenarios A (86.3 seconds vs 74.3 seconds, P=.85) or C (58.4 seconds vs 68.9 seconds,P=.064), MMapp took less time for scenarios B (76.1 seconds vs 87.4 seconds, P=.03) and E (20.7 seconds vs 73 seconds, P<.001), and more time for scenario D (78.8 seconds vs 58.5 seconds, P=.02). The MMApp identified multimorbidity with 96.7% (29/30) sensitivity and 95% (19/20) specificity. User feedback was positive regarding MMApp's usability, efficiency, and usefulness.

CONCLUSIONS

The MMApp identified multimorbidity with high sensitivity and specificity and did not require significantly more time to complete than a commonly used web-based risk-stratification tool for most scenarios. Mean user times were well under 2 minutes. Feedback was overall positive from residents regarding the usability and usefulness of this app, even in the emergency general surgery setting. It would be feasible to use MMApp to identify patients with multimorbidity in the emergency general surgery setting for validation, research, and eventual clinical use. This type of mobile app could serve as a template for other research teams to create a tool to easily screen participants for potential enrollment.

Smartphone-based screening for atrial fibrillation: a pragmatic randomized clinical trial

Digital smart devices have the capability of detecting atrial fibrillation (AF), but the efficacy of this type of digital screening has not been directly compared to usual care for detection of treatment-relevant AF. In the eBRAVE-AF trial ( NCT04250220 ), we randomly assigned 5,551 policyholders of a German health insurance company who were free of AF at baseline (age 65 years (median; interquartile range (11) years, 31% females)) to digital screening (n = 2,860) or usual care (n = 2,691). In this siteless trial, for digital screening, participants used a certified app on their own smartphones to screen for irregularities in their pulse waves. Abnormal findings were evaluated by 14-day external electrocardiogram (ECG) loop recorders. The primary endpoint was newly diagnosed AF within 6 months treated with oral anti-coagulation by an independent physician not involved in the study. After 6 months, participants were invited to cross-over for a second study phase with reverse assignment for secondary analyses. The primary endpoint of the trial was met, as digital screening more than doubled the detection rate of treatment-relevant AF in both phases of the trial, with odds ratios of 2.12 (95% confidence interval (CI), 1.19-3.76; P = 0.010) and 2.75 (95% CI, 1.42-5.34; P = 0.003) in the first and second phases, respectively. This digital screening technology provides substantial benefits in detecting AF compared to usual care and has the potential for broad applicability due to its wide availability on ordinary smartphones. Future studies are needed to test whether digital screening for AF leads to better treatment outcomes.

A Powerful Paradigm for Cardiovascular Risk Stratification Using Multiclass, Multi-Label, and Ensemble-Based Machine Learning Paradigms: A Narrative Review

Background and Motivation: Cardiovascular disease (CVD) causes the highest mortality globally. With escalating healthcare costs, early non-invasive CVD risk assessment is vital. Conventional methods have shown poor performance compared to more recent and fast-evolving Artificial Intelligence (AI) methods. The proposed study reviews the three most recent paradigms for CVD risk assessment, namely multiclass, multi-label, and ensemble-based methods in (i) office-based and (ii) stress-test laboratories. Methods: A total of 265 CVD-based studies were selected using the preferred reporting items for systematic reviews and meta-analyses (PRISMA) model. Due to its popularity and recent development, the study analyzed the above three paradigms using machine learning (ML) frameworks. We review comprehensively these three methods using attributes, such as architecture, applications, pro-and-cons, scientific validation, clinical evaluation, and AI risk-of-bias (RoB) in the CVD framework. These ML techniques were then extended under mobile and cloud-based infrastructure. Findings: Most popular biomarkers used were office-based, laboratory-based, image-based phenotypes, and medication usage. Surrogate carotid scanning for coronary artery risk prediction had shown promising results. Ground truth (GT) selection for AI-based training along with scientific and clinical validation is very important for CVD stratification to avoid RoB. It was observed that the most popular classification paradigm is multiclass followed by the ensemble, and multi-label. The use of deep learning techniques in CVD risk stratification is in a very early stage of development. Mobile and cloud-based AI technologies are more likely to be the future. Conclusions: AI-based methods for CVD risk assessment are most promising and successful. Choice of GT is most vital in AI-based models to prevent the RoB. The amalgamation of image-based strategies with conventional risk factors provides the highest stability when using the three CVD paradigms in non-cloud and cloud-based frameworks.

Current Advancement in Diagnosing Atrial Fibrillation by Utilizing Wearable Devices and Artificial Intelligence: A Review Study

Atrial fibrillation (AF) is a common arrhythmia affecting 8–10% of the population older than 80 years old. The importance of early diagnosis of atrial fibrillation has been broadly recognized since arrhythmias significantly increase the risk of stroke, heart failure and tachycardia-induced cardiomyopathy with reduced cardiac function. However, the prevalence of atrial fibrillation is often underestimated due to the high frequency of clinically silent atrial fibrillation as well as paroxysmal atrial fibrillation, both of which are hard to catch by routine physical examination or 12-lead electrocardiogram (ECG). The development of wearable devices has provided a reliable way for healthcare providers to uncover undiagnosed atrial fibrillation in the population, especially those most at risk. Furthermore, with the advancement of artificial intelligence and machine learning, the technology is now able to utilize the database in assisting detection of arrhythmias from the data collected by the devices. In this review study, we compare the different wearable devices available on the market and review the current advancement in artificial intelligence in diagnosing atrial fibrillation. We believe that with the aid of the progressive development of technologies, the diagnosis of atrial fibrillation shall be made more effectively and accurately in the near future.