Background and objectives: The Korean National Health Insurance Service (NHIS) database has been widely used for cardiovascular research. We validated the primary diagnostic codes of major clinical outcomes, including acute myocardial infarction (AMI), gastrointestinal bleeding (GIB), stroke, and intracranial hemorrhage (ICH) used for Korea NHIS claims. Subjects and methods: From 2016 to 2017, 800 patients with primary diagnostic codes of AMI, GIB, stroke, or ICH at discharge were randomly selected from a single tertiary medical center in Korea (200 patients per each diagnosis). The positive predictive value (PPV), sensitivity, and specificity of the primary diagnostic codes were calculated using hospital medical record review as the gold standard. Further improvement in the diagnostic validity of the codes was assessed by combining clinical information such as duration of hospitalization, blood transfusion, brain imaging studies, or prescription records of antithrombotic agents. Results: Among 200 patients with AMI as the primary discharge diagnosis, 184 patients were clinically confirmed (PPV of 92.0%). For GIB, 184 (92.0%) patients with the primary discharge diagnosis were verified to have true GIB events, showing PPV of 92%. For stroke, 181 (90.5%) patients were clinically confirmed with true stroke events. For ICH, 143 (71.5%) patients were verified to be true ICH events. In stroke and ICH, the PPV and specificity improved after combining with the hospitalization duration, imaging studies, and prescription of antithrombotic agents. Conclusions: For major clinical outcomes in the NHIS database, the primary diagnostic codes showed favorable reliability. For stroke and ICH, considerations of relevant clinical information could improve the accuracy of diagnosis.

Background: Wearable devices have evolved as screening tools for atrial fibrillation (AF). A photoplethysmographic (PPG) AF detection algorithm was developed and applied to a convenient smartphone-based device with good accuracy. However, patients with paroxysmal AF frequently exhibit premature atrial complexes (PACs), which result in poor unmanned AF detection, mainly because of rule-based or handcrafted machine learning techniques that are limited in terms of diagnostic accuracy and reliability. Objective: This study aimed to develop deep learning (DL) classifiers using PPG data to detect AF from the sinus rhythm (SR) in the presence of PACs after successful cardioversion. Methods: We examined 75 patients with AF who underwent successful elective direct-current cardioversion (DCC). Electrocardiogram and pulse oximetry data over a 15-min period were obtained before and after DCC and labeled as AF or SR. A 1-dimensional convolutional neural network (1D-CNN) and recurrent neural network (RNN) were chosen as the 2 DL architectures. The PAC indicator estimated the burden of PACs on the PPG dataset. We defined a metric called the confidence level (CL) of AF or SR diagnosis and compared the CLs of true and false diagnoses. We also compared the diagnostic performance of 1D-CNN and RNN with previously developed AF detectors (support vector machine with root-mean-square of successive difference of RR intervals and Shannon entropy, autocorrelation, and ensemble by combining 2 previous methods) using 10 5-fold cross-validation processes. Results: Among the 14,298 training samples containing PPG data, 7157 samples were obtained during the post-DCC period. The PAC indicator estimated 29.79% (2132/7157) of post-DCC samples had PACs. The diagnostic accuracy of AF versus SR was 99.32% (70,925/71,410) versus 95.85% (68,602/71,570) in 1D-CNN and 98.27% (70,176/71,410) versus 96.04% (68,736/71,570) in RNN methods. The area under receiver operating characteristic curves of the 2 DL classifiers was 0.998 (95% CI 0.995-1.000) for 1D-CNN and 0.996 (95% CI 0.993-0.998) for RNN, which were significantly higher than other AF detectors (P<.001). If we assumed that the dataset could emulate a sufficient number of patients in training, both DL classifiers improved their diagnostic performances even further especially for the samples with a high burden of PACs. The average CLs for true versus false classification were 98.56% versus 78.75% for 1D-CNN and 98.37% versus 82.57% for RNN (P<.001 for all cases). Conclusions: New DL classifiers could detect AF using PPG monitoring signals with high diagnostic accuracy even with frequent PACs and could outperform previously developed AF detectors. Although diagnostic performance decreased as the burden of PACs increased, performance improved when samples from more patients were trained. Moreover, the reliability of the diagnosis could be indicated by the CL. Wearable devices sensing PPG signals with DL classifiers should be validated as tools to screen for AF.

Background: Continuous photoplethysmography (PPG) monitoring with a wearable device may aid the early detection of atrial fibrillation (AF). Objective: We aimed to evaluate the diagnostic performance of a ring-type wearable device (CardioTracker, CART), which can detect AF using deep learning analysis of PPG signals. Methods: Patients with persistent AF who underwent cardioversion were recruited prospectively. We recorded PPG signals at the finger with CART and a conventional pulse oximeter before and after cardioversion over a period of 15 min (each instrument). Cardiologists validated the PPG rhythms with simultaneous single-lead electrocardiography. The PPG data were transmitted to a smartphone wirelessly and analyzed with a deep learning algorithm. We also validated the deep learning algorithm in 20 healthy subjects with sinus rhythm (SR). Results: In 100 study participants, CART generated a total of 13,038 30-s PPG samples (5850 for SR and 7188 for AF). Using the deep learning algorithm, the diagnostic accuracy, sensitivity, specificity, positive-predictive value, and negative-predictive value were 96.9%, 99.0%, 94.3%, 95.6%, and 98.7%, respectively. Although the diagnostic accuracy decreased with shorter sample lengths, the accuracy was maintained at 94.7% with 10-s measurements. For SR, the specificity decreased with higher variability of peak-to-peak intervals. However, for AF, CART maintained consistent sensitivity regardless of variability. Pulse rates had a lower impact on sensitivity than on specificity. The performance of CART was comparable to that of the conventional device when using a proper threshold. External validation showed that 94.99% (16,529/17,400) of the PPG samples from the control group were correctly identified with SR. Conclusions: A ring-type wearable device with deep learning analysis of PPG signals could accurately diagnose AF without relying on electrocardiography. With this device, continuous monitoring for AF may be promising in high-risk populations. Trial Registration: ClinicalTrials.gov NCT04023188; https://clinicaltrials.gov/ct2/show/NCT04023188

Background: There is a paucity of information about cardiovascular outcomes related to exercise habit change after a new diagnosis of atrial fibrillation (AF). We investigated the association between exercise habits after a new AF diagnosis and ischemic stroke, heart failure (HF), and all-cause death.Methods and findings: This is a nationwide population-based cohort study using data from the Korea National Health Insurance Service. A retrospective analysis was performed for 66,692 patients with newly diagnosed AF between 2010 and 2016 who underwent 2 serial health examinations within 2 years before and after their AF diagnosis. Individuals were divided into 4 categories according to performance of regular exercise, which was investigated by a self-reported questionnaire in each health examination, before and after their AF diagnosis: persistent non-exercisers (30.5%), new exercisers (17.8%), exercise dropouts (17.4%), and exercise maintainers (34.2%). The primary outcomes were incidence of ischemic stroke, HF, and all-cause death. Differences in baseline characteristics among groups were balanced considering demographics, comorbidities, medications, lifestyle behaviors, and income status. The risks of the outcomes were computed by weighted Cox proportional hazards models with inverse probability of treatment weighting (IPTW) during a mean follow-up of 3.4 ± 2.0 years. The new exerciser and exercise maintainer groups were associated with a lower risk of HF compared to the persistent non-exerciser group: the hazard ratios (HRs) (95% CIs) were 0.95 (0.90–0.99) and 0.92 (0.88–0.96), respectively (p <0.001). Also, performing exercise any time before or after AF diagnosis was associated with a lower risk of mortality compared to persistent non-exercising: the HR (95% CI) was 0.82 (0.73–0.91) for new exercisers, 0.83 (0.74–0.93) for exercise dropouts, and 0.61 (0.55–0.67) for exercise maintainers (p <0.001). For ischemic stroke, the estimates of HRs were 10%–14% lower in patients of the exercise groups, yet differences were statistically insignificant (p =0.057). Energy expenditure of 1,000–1,499 MET-min/wk (regular moderate exercise 170–240 min/wk) was consistently associated with a lower risk of each outcome based on a subgroup analysis of the new exerciser group. Study limitations include recall bias introduced due to the nature of the self-reported questionnaire and restricted external generalizability to other ethnic groups.Conclusions: Initiating or continuing regular exercise after AF diagnosis was associated with lower risks of HF and mortality. The promotion of exercise might reduce the future risk of adverse outcomes in patients with AF.

Background and Objective Alcohol consumption is one of the important modifiable risk factors for stroke in young adults. The association between the cumulative burden of alcohol consumption and its impact on incident stroke in young adults is unknown. We aimed to investigate the association between cumulative alcohol burden and the risk for stroke among young adults. Methods Using data from the Korean National Health Insurance Service database, patients age between 20 and 39 years, who underwent 4 consecutive annual health examinations between 2009 and 2012, were included. The cumulative alcohol burden score of moderate-to-heavy drinking was evaluated by assigning a score of 1 for alcohol consumption ≥105 g/wk at the health examination each year and calculating the sum of 4 years (0–4). The main outcome was incident stroke and its subtypes, ischemic stroke, and hemorrhagic stroke during the follow-up period. Results Of 1 536 668 patients (mean age of 29.5 years, 71.5% male, and median follow-up of 6-year), 3 153 experienced an incident stroke (incidence rate, 0.37 per 1,000 person-years). After multivariable adjustment, patients with alcohol burden scores of 2, 3, and 4, who consumed more than 105 g/wk of alcohol for 2, 3, and 4 years, demonstrated significantly higher risks for stroke (hazard ratio [HR] 1.19, 95% CI 1.05–1.34 for 2; HR 1.22, 95% CI 1.09–1.38 for 3; HR 1.23, 95% CI 1.10–1.38 for 4) compared with those with a burden score of 0. This positive dose-response relationship was primarily driven by hemorrhagic rather than ischemic stroke. High alcohol burden scores (i.e., 2, 3, and 4) were significantly associated with higher risks for hemorrhagic stroke (HR 1.30, 95% CI 1.10–1.54 for 2; HR 1.42, 95% CI 1.21–1.67 for 3; HR 1.36, 95% CI 1.16–1.59 for 4) compared with a burden score of 0. Discussion Young adults who engaged in moderate-to-heavy drinking demonstrated a higher risk for incident stroke, especially hemorrhagic stroke. Reducing alcohol consumption should be emphasized in young adults with heavy drinking habits as part of any stroke prevention strategy.

Background: There is insufficient evidence for the use of single-lead electrocardiogram (ECG) monitoring with an adhesive patch-type device (APD) over an extended period compared to that of the 24-hour Holter test for atrial fibrillation (AF) detection. Objective: In this paper, we aimed to compare AF detection by the 24-hour Holter test and 72-hour single-lead ECG monitoring using an APD among patients with AF. Methods: This was a prospective, single-center cohort study. A total of 210 patients with AF with clinical indications for the Holter test at cardiology outpatient clinics were enrolled in the study. The study participants were equipped with both the Holter device and APD for the first 24 hours. Subsequently, only the APD continued ECG monitoring for an additional 48 hours. AF detection during the first 24 hours was compared between the two devices. The diagnostic benefits of extended monitoring using the APD were evaluated. Results: A total of 200 patients (mean age 60 years; n=141, 70.5% male; and n=59, 29.5% female) completed 72-hour ECG monitoring with the APD. During the first 24 hours, both monitoring methods detected AF in the same 40/200 (20%) patients (including 20 patients each with paroxysmal and persistent AF). Compared to the 24-hour Holter test, the APD increased the AF detection rate by 1.5-fold (58/200; 29%) and 1.6-fold (64/200; 32%) with 48- and 72-hour monitoring, respectively. With the APD, the number of newly discovered patients with paroxysmal AF was 20/44 (45.5%), 18/44 (40.9%), and 6/44 (13.6%) at 24-, 48-, and 72-hour monitoring, respectively. Compared with 24-hour Holter monitoring, 72-hour monitoring with the APD increased the detection rate of paroxysmal AF by 2.2-fold (44/20). Conclusions: Compared to the 24-hour Holter test, AF detection could be improved with 72-hour single-lead ECG monitoring with the APD.