Diagnostic assessment of a deep learning system for detecting atrial fibrillation in pulse waveforms.

OBJECTIVE: To evaluate the diagnostic performance of a deep learning system for automated detection of atrial fibrillation (AF) in photoplethysmographic (PPG) pulse waveforms. METHODS: We trained a deep convolutional neural network (DCNN) to detect AF in 17 s PPG waveforms using a training data set of 149 048 PPG waveforms constructed from several publicly available PPG databases. The DCNN was validated using an independent test data set of 3039 smartphone-acquired PPG waveforms from adults at high risk of AF at a general outpatient clinic against ECG tracings reviewed by two cardiologists. Six established AF detectors based on handcrafted features were evaluated on the same test data set for performance comparison. RESULTS: In the validation data set (3039 PPG waveforms) consisting of three sequential PPG waveforms from 1013 participants (mean (SD) age, 68.4 (12.2) years; 46.8% men), the prevalence of AF was 2.8%. The area under the receiver operating characteristic curve (AUC) of the DCNN for AF detection was 0.997 (95% CI 0.996 to 0.999) and was significantly higher than all the other AF detectors (AUC range: 0.924-0.985). The sensitivity of the DCNN was 95.2% (95% CI 88.3% to 98.7%), specificity was 99.0% (95% CI 98.6% to 99.3%), positive predictive value (PPV) was 72.7% (95% CI 65.1% to 79.3%) and negative predictive value (NPV) was 99.9% (95% CI 99.7% to 100%) using a single 17 s PPG waveform. Using the three sequential PPG waveforms in combination (<1 min in total), the sensitivity was 100.0% (95% CI 87.7% to 100%), specificity was 99.6% (95% CI 99.0% to 99.9%), PPV was 87.5% (95% CI 72.5% to 94.9%) and NPV was 100% (95% CI 99.4% to 100%). CONCLUSIONS: In this evaluation of PPG waveforms from adults screened for AF in a real-world primary care setting, the DCNN had high sensitivity, specificity, PPV and NPV for detecting AF, outperforming other state-of-the-art methods based on handcrafted features.

Diagnostic performance of an automatic blood pressure measurement device, Microlife WatchBP Home A, for atrial fibrillation screening in a real-world primary care setting.

OBJECTIVE: To evaluate the diagnostic performance of a UK National Institute for Health and Care Excellence-recommended automatic oscillometric blood pressure (BP) measurement device incorporated with an atrial fibrillation (AF) detection algorithm (Microlife WatchBP Home A) for real-world AF screening in a primary healthcare setting. SETTING: Primary healthcare setting in Hong Kong. INTERVENTIONS: This was a prospective AF screening study carried out between 1 September 2014 and 14 January 2015. The Microlife device was evaluated for AF detection and compared with a reference standard of lead-I ECG. PRIMARY OUTCOME MEASURES: Diagnostic performance of Microlife for AF detection. RESULTS: 5969 patients (mean age: 67.2±11.0 years; 53.9% female) were recruited. The mean CHA2DS2-VASc ( C : congestive heart failure [1 point]; H : hypertension [1 point]; A2 : age 65-74 years [1 point] and age ≥75 years [2 points]; D : diabetes mellitus [1 point]; S : prior stroke or transient ischemic attack [2 points]; VA : vascular disease [1 point]; and Sc : sex category [female] [1 point])score was 2.8±1.3. AF was diagnosed in 72 patients (1.21%) and confirmed by a 12-lead ECG. The Microlife device correctly identified AF in 58 patients and produced 79 false-positives. The corresponding sensitivity and specificity for AF detection were 80.6% (95% CI 69.5 to 88.9) and 98.7% (95% CI 98.3 to 98.9), respectively. Among patients with a false-positive by the Microlife device, 30.4% had sinus rhythm, 35.4% had sinus arrhythmia and 29.1% exhibited premature atrial complexes. With the low prevalence of AF in this population, the positive and negative predictive values of Microlife device for AF detection were 42.4% (95% CI 34.0 to 51.2) and 99.8% (95% CI 99.6 to 99.9), respectively. The overall diagnostic performance of Microlife device to detect AF as determined by area under the curves was 0.90 (95% CI 0.89 to 0.90). CONCLUSIONS: In the primary care setting, Microlife WatchBP Home was an effective means to screen for AF, with a reasonable sensitivity of 80.6% and a high negative predictive value of 99.8%, in addition to its routine function of BP measurement. In a younger patient population aged <65 years with a lower prevalence of AF, Microlife WatchBP Home A demonstrated a similar diagnostic accuracy.

Diagnostic Performance of a Smartphone-Based Photoplethysmographic Application for Atrial Fibrillation Screening in a Primary Care Setting.

BACKGROUND: Diagnosing atrial fibrillation (AF) before ischemic stroke occurs is a priority for stroke prevention in AF. Smartphone camera-based photoplethysmographic (PPG) pulse waveform measurement discriminates between different heart rhythms, but its ability to diagnose AF in real-world situations has not been adequately investigated. We sought to assess the diagnostic performance of a standalone smartphone PPG application, Cardiio Rhythm, for AF screening in primary care setting. METHODS AND RESULTS: Patients with hypertension, with diabetes mellitus, and/or aged ≥65 years were recruited. A single-lead ECG was recorded by using the AliveCor heart monitor with tracings reviewed subsequently by 2 cardiologists to provide the reference standard. PPG measurements were performed by using the Cardiio Rhythm smartphone application. AF was diagnosed in 28 (2.76%) of 1013 participants. The diagnostic sensitivity of the Cardiio Rhythm for AF detection was 92.9% (95% CI] 77-99%) and was higher than that of the AliveCor automated algorithm (71.4% [95% CI 51-87%]). The specificities of Cardiio Rhythm and the AliveCor automated algorithm were comparable (97.7% [95% CI: 97-99%] versus 99.4% [95% CI 99-100%]). The positive predictive value of the Cardiio Rhythm was lower than that of the AliveCor automated algorithm (53.1% [95% CI 38-67%] versus 76.9% [95% CI 56-91%]); both had a very high negative predictive value (99.8% [95% CI 99-100%] versus 99.2% [95% CI 98-100%]). CONCLUSIONS: The Cardiio Rhythm smartphone PPG application provides an accurate and reliable means to detect AF in patients at risk of developing AF and has the potential to enable population-based screening for AF.

Long-term booster schedules with AS03A-adjuvanted heterologous H5N1 vaccines induces rapid and broad immune responses in Asian adults.

BACKGROUND: The pandemic potential of avian influenza A/H5N1 should not be overlooked, and the continued development of vaccines against these highly pathogenic viruses is a public health priority. METHODS: This open-label extension booster study followed a Phase III study of 1206 adults who had received two 3.75 µg doses of primary AS03A-adjuvanted or non-adjuvanted H5N1 split-virus vaccine (A/Vietnam/1194/2004; clade 1) (NCT00449670). The aim of the extension study was to evaluate different timings for heterologous AS03A-adjuvanted booster vaccination (A/Indonesia/5/2005; clade 2.1) given at Month 6, 12, or 36 post-primary vaccination. Immunogenicity was assessed 21 days after each booster vaccination and the persistence of immune responses against the primary vaccine strain (A/Vietnam) and the booster strain (A/Indonesia) was evaluated up to Month 48 post-primary vaccination. Reactogenicity and safety were also assessed. RESULTS: After booster vaccination given at Month 6, HI antibody responses to primary vaccine, and booster vaccine strains were markedly higher with one dose of AS03A-H5N1 booster vaccine in the AS03A-adjuvanted primary vaccine group compared with two doses of booster vaccine in the non-adjuvanted primary vaccine group. HI antibody responses were robust against the primary and booster vaccine strains 21 days after boosting at Month 12 or 36. At Month 48, in subjects boosted at Month 6, 12, or 36, HI antibody titers of ≥1:40 against the booster strain persisted in 39.2%, 61.2%, and 95.6% of subjects, respectively. Neutralizing antibody responses and cell-mediated immune responses also showed that AS03A-H5N1 heterologous booster vaccination elicited robust immune responses within 21 days of boosting at Month 6, 12, or 36 post-primary vaccination. The booster vaccine was well tolerated, and no safety concerns were raised. CONCLUSIONS: In Asian adults primed with two doses of AS03A-adjuvanted H5N1 pandemic influenza vaccine, strong cross-clade anamnestic antibody responses were observed after one dose of AS03A-H5N1 heterologous booster vaccine given at Month 6, 12, or 36 after priming, suggesting that AS03A-adjuvanted H5N1 vaccines may provide highly flexible prime-boost schedules. Although immunogenicity decreased with time, vaccinated populations could potentially be protected for up to three years after vaccination, which is likely to far exceed the peak of the a pandemic.

Screening for diabetic retinopathy with or without a copayment in a randomized controlled trial: influence of the inverse care law.

OBJECTIVE: To examine whether the inverse care law operates in a screening program for diabetic retinopathy (DR) based on fee for service in Hong Kong. DESIGN: Randomized controlled trial. PARTICIPANTS: All those with type 1 or 2 diabetes from 2 clinics were recruited. INTERVENTION: Diabetic retinopathy screening with a small copayment versus free access in a publicly funded family medicine service. MAIN OUTCOME MEASURES: Uptake of screening and severity of DR detected. Association between these outcome variables and independent variables were determined using multivariate logistic regression models and reported as odds ratios (ORs). RESULTS: After randomization, 1387 subjects in the free group and 1379 subjects in the pay group were eligible for screening, and 94.9% (1316/1387) and 92.6% (1277/1379), respectively, agreed to participate in the study. The offer of screening was accepted by 94.8% (1247/1316) in the free group and 91.2% (1164/1277) in the pay group, and the final uptake ratios were 88.5% (1165/1316) and 82.4% (1052/1277), respectively (Pearson chi = 19.74, P<0.001). Being in the pay group was associated with a lower uptake of screening than being in the free group (OR, 0.59; confidence interval [CI], 0.47-0.74) and a lower detection rate of DR (OR, 0.73; CI, 0.60-0.90) after adjustment for potential confounding factors. Subjects with higher socioeconomic status were more likely to attend screening and had a lower prevalence of DR detected. CONCLUSIONS: The inverse care law seems to operate in a preventive intervention when a relatively small copayment is applied. There is a case for making effective preventive services free of charge. FINANCIAL DISCLOSURE(S): The author(s) have no proprietary or commercial interest in any materials discussed in this article.

Long-acting neuraminidase inhibitor laninamivir octanoate versus oseltamivir for treatment of influenza: A double-blind, randomized, noninferiority clinical trial.

BACKGROUND: A single administration of laninamivir octanoate, a long-acting neuraminidase inhibitor, against influenza infection has been proven effective in nonclinical studies. This study evaluated the clinical efficacy of laninamivir octanoate for the treatment of adult influenza patients. METHODS: A double-blind, randomized controlled trial examined whether laninamivir octanoate was noninferior to oseltamivir. A total of 1003 patients aged ≥ 20 years with febrile influenza symptoms for no more than 36 h were randomized to receive either 40 mg of laninamivir octanoate, 20 mg of laninamivir octanoate, or oseltamivir. Laninamivir octanoate was inhaled once on day 1, and oseltamivir (75 mg) was administered orally twice daily for 5 days. The primary end point was the time to illness alleviation. RESULTS: A total of 996 patients were included in the primary analysis (40-mg laninamivir octanoate, n = 334; 20-mg laninamivir octanoate, n = 326; and oseltamivir, n = 336). The median time to illness alleviation in the 40-mg laninamivir octanoate, 20-mg laninamivir octanoate, and oseltamivir groups was 73.0, 85.8, and 73.6 h, respectively. The difference between laninamivir octanoate and oseltamivir was -0.6 h (95% confidence interval, -9.9 to 6.9 h) for the 40-mg group and 12.2 h (95% confidence interval, -1.5 to 17.2 h) for the 20-mg group. The upper limits of the 95% confidence intervals were less than the prespecified noninferiority margin (18 h). The proportion of patients shedding virus at day 3 was significantly lower in the 40-mg laninamivir octanoate group than in the oseltamivir group (P = .006). CONCLUSIONS: A single inhalation of laninamivir octanoate is effective for the treatment of seasonal influenza, including that caused by oseltamivir-resistant virus, in adults. CLINICAL TRIALS REGISTRATION: NCT00803595.

Immunogenicity and tolerability of an AS03(A)-adjuvanted prepandemic influenza vaccine: a phase III study in a large population of Asian adults.

The immunogenicity and lot-to-lot consistency of an AS03-adjuvanted H5N1 vaccine were evaluated in 1206 Asian adults, randomised to receive two doses of adjuvanted (3.75 microg haemagglutinin) or diluent-mixed vaccines, 21 days apart. Post-Dose 2, 96.0% of vaccinees in the H5N1-AS03 group demonstrated a four-fold increase in neutralising antibody titres against the vaccine strain A/Vietnam/1194/2004 and 91.4% against strain A/Indonesia/05/2005. Haemagglutination-inhibiting antibodies (titre > or = 1:40) against A/Vietnam/1194/2004 and A/Indonesia/05/2005 strains were observed in 94.3% and 50.2% of subjects, respectively. Lot-to-lot consistency of the AS03-adjuvanted vaccine combinations was demonstrated. The AS03-adjuvanted vaccine was well tolerated, induced a high frequency of immune responses to the vaccine strain, allowed antigen sparing and promoted cross-clade immunity. These characteristics make it suitable for presumptive use if an H5N1 pandemic were considered to be imminent.