DeepBreath-automated detection of respiratory pathology from lung auscultation in 572 pediatric outpatients across 5 countries.

The interpretation of lung auscultation is highly subjective and relies on non-specific nomenclature. Computer-aided analysis has the potential to better standardize and automate evaluation. We used 35.9 hours of auscultation audio from 572 pediatric outpatients to develop DeepBreath : a deep learning model identifying the audible signatures of acute respiratory illness in children. It comprises a convolutional neural network followed by a logistic regression classifier, aggregating estimates on recordings from eight thoracic sites into a single prediction at the patient-level. Patients were either healthy controls (29%) or had one of three acute respiratory illnesses (71%) including pneumonia, wheezing disorders (bronchitis/asthma), and bronchiolitis). To ensure objective estimates on model generalisability, DeepBreath is trained on patients from two countries (Switzerland, Brazil), and results are reported on an internal 5-fold cross-validation as well as externally validated (extval) on three other countries (Senegal, Cameroon, Morocco). DeepBreath differentiated healthy and pathological breathing with an Area Under the Receiver-Operator Characteristic (AUROC) of 0.93 (standard deviation [SD] ± 0.01 on internal validation). Similarly promising results were obtained for pneumonia (AUROC 0.75 ± 0.10), wheezing disorders (AUROC 0.91 ± 0.03), and bronchiolitis (AUROC 0.94 ± 0.02). Extval AUROCs were 0.89, 0.74, 0.74 and 0.87 respectively. All either matched or were significant improvements on a clinical baseline model using age and respiratory rate. Temporal attention showed clear alignment between model prediction and independently annotated respiratory cycles, providing evidence that DeepBreath extracts physiologically meaningful representations. DeepBreath provides a framework for interpretable deep learning to identify the objective audio signatures of respiratory pathology.

Factors associated with nonadherence to the American Academy of Pediatrics 2014 bronchiolitis guidelines: A retrospective study.

The latest guideline from the American Academy of Pediatrics for the management of bronchiolitis has helped reduce unnecessary interventions and costs. However, data on patients still receiving interventions are missing. In patients with acute bronchiolitis whose management was assessed and compared with current achievable benchmarks of care, we aimed to identify factors associated with nonadherence to guideline recommendations. In this single-centre retrospective study the management of bronchiolitis pre-guideline (Period 1: 2010 to 2012) was compared with two periods post-guideline (Period 2: 2015 to 2016, early post-guideline; and Period 3: 2017 to 2018, late post-guideline) in otherwise healthy infants aged less than 1 year presenting at the Children's University Hospitals of Geneva (Switzerland). Post-guideline, bronchodilators were more frequently administered to older (>6 months; OR 25.8, 95%CI 12.6-52.6), and atopic (OR 3.5, 95%CI 1.5-7.5) children with wheezing (OR 5.4, 95%CI 3.3-8.7). Oral corticosteroids were prescribed more frequently to older (>6 months; OR 5.2, 95%CI 1.4-18.7) infants with wheezing (OR 4.9, 95% CI 1.3-17.8). Antibiotics and chest X-ray were more frequently prescribed to children admitted to the intensive care unit (antibiotics: OR 4.2, 95%CI 1.3-13.5; chest X-ray: OR 19.4, 95%CI 7.4-50.6). Latest prescription rates were all below the achievable benchmarks of care. In summary, following the latest American Academy of Pediatrics guideline, older, atopic children with wheezing and infants admitted to the intensive care unit were more likely to receive nonevidence-based interventions during an episode of bronchiolitis. These patient profiles are generally excluded from bronchiolitis trials, and therefore not specifically covered by the current guideline. Further research should focus on the benefit of bronchiolitis interventions in these particular populations.

Impact of blended learning on manual defibrillator's use: A simulation-based randomized trial.

BACKGROUND: Blended learning, defined as the combination of traditional face-to-face instructor-led learning and e-learning course, has never been validated as a teaching method for the effective use of manual defibrillators in cardiopulmonary resuscitation. AIM: To evaluate whether paediatric emergency and critical care providers exposed to a blended learning session performed better and recalled more defibrillator skills than those exposed to face-to-face learning only. STUDY DESIGN: A two-period prospective, stratified, single-centre, simulation-based, randomized, controlled trial. METHODS: Registered nurses and postgraduate residents from either a paediatric emergency department or an intensive care unit were randomly assigned to a blended learning or face-to-face learning sessions on the recommended use of a manual defibrillator. Participants' adherence to recommendations was assessed by testing defibrillator skills in three consecutive paediatric cardiopulmonary scenarios performed on the day of the training and once again 2 months later. The primary endpoint was the number of errors observed during defibrillation, cardioversion, and transcutaneous pacing at the time of the initial intervention. RESULTS: Fifty participants were randomized to receive the intervention and 51 to the control group. When pooling all three procedures, the median total errors per participant was lower (2 [IQR: 1-4]) in providers exposed to blended learning than in those exposed to face-to-face learning only (3 [IQR: 2-5]; P = .06). The median of total errors per procedure was also lower. However, both training methods appeared insufficient to maintain appropriate skill retention over time as a repetition of procedures 2 months later without any refresher learning session yielded more errors in both groups. CONCLUSIONS: Learners exposed to blended learning showed a reduced number in the total amount of errors compared with those exposed to face-to-face learning alone, with waning of skills over time. RELEVANCE TO CLINICAL PRACTICE: Proficiently teaching the use of a manual defibrillator can be performed through blended learning.

Diagnostic Accuracy of SARS-CoV-2 Rapid Antigen Detection Testing in Symptomatic and Asymptomatic Children in the Clinical Setting.

Antigen-based rapid diagnostic tests (RDTs) are used in children despite the lack of data. We evaluated the diagnostic performance of the Panbio-COVID-19 Ag Rapid Test Device (P-RDT) in children. Symptomatic and asymptomatic participants 0 to 16 years old had two nasopharyngeal swabs (NPS) for both reverse transcription-PCR (RT-PCR) and P-RDT. A total of 822 participants completed the study, of which 533 (64.9%) were symptomatic. Among the 119 (14.5%) RT-PCR-positive patients, the P-RDT sensitivity was 0.66 (95% confidence interval [CI] 0.57 to 0.74). Mean viral load (VL) was higher among P-RDT-positive patients than negative ones (P < 0.001). Sensitivity was 0.91 in specimens with VL of >1.0E6 IU/ml (95% CI 0.83 to 0.99) and decreased to 0.75 (95% CI 0.66 to 0.83) for specimens >1.0E3 IU/ml. Among symptomatic participants, the P-RDT displayed a sensitivity of 0.73 (95% CI 0.64 to 0.82), which peaked at 1.00 at 2 days post-onset of symptoms (DPOS) (95% CI 1.00 to 1.00), then decreased to 0.56 (95% CI 0.23 to 0.88) at 5 DPOS. There was a trend toward lower P-RDT sensitivity in symptomatic children <12 years (0.62 [95% CI 0.45 to 0.78]) versus ≥12 years (0.80 [95% CI 0.69 to 0.91]; P = 0.09). In asymptomatic participants, the P-RDT displayed a sensitivity of 0.43 (95% CI 0.26 to 0.61). Specificity was 1.00 in symptomatic and asymptomatic children (95% CI 0.99 to 1.00). The overall 73% and 43% sensitivities of P-RDT in symptomatic and asymptomatic children, respectively, was below the 80% cutoff recommended by the World Health Organization. We observed a correlation between VL and P-RDT sensitivity, as well as variation of sensitivity according to DPOS, a major determinant of VL. These data highlight the limitations of RDTs in children, with the potential exception in early symptomatic children ≥12yrs.

Deep learning diagnostic and risk-stratification pattern detection for COVID-19 in digital lung auscultations: clinical protocol for a case-control and prospective cohort study.

BACKGROUND: Lung auscultation is fundamental to the clinical diagnosis of respiratory disease. However, auscultation is a subjective practice and interpretations vary widely between users. The digitization of auscultation acquisition and interpretation is a particularly promising strategy for diagnosing and monitoring infectious diseases such as Coronavirus-19 disease (COVID-19) where automated analyses could help decentralise care and better inform decision-making in telemedicine. This protocol describes the standardised collection of lung auscultations in COVID-19 triage sites and a deep learning approach to diagnostic and prognostic modelling for future incorporation into an intelligent autonomous stethoscope benchmarked against human expert interpretation. METHODS: A total of 1000 consecutive, patients aged ≥ 16 years and meeting COVID-19 testing criteria will be recruited at screening sites and amongst inpatients of the internal medicine department at the Geneva University Hospitals, starting from October 2020. COVID-19 is diagnosed by RT-PCR on a nasopharyngeal swab and COVID-positive patients are followed up until outcome (i.e., discharge, hospitalisation, intubation and/or death). At inclusion, demographic and clinical data are collected, such as age, sex, medical history, and signs and symptoms of the current episode. Additionally, lung auscultation will be recorded with a digital stethoscope at 6 thoracic sites in each patient. A deep learning algorithm (DeepBreath) using a Convolutional Neural Network (CNN) and Support Vector Machine classifier will be trained on these audio recordings to derive an automated prediction of diagnostic (COVID positive vs negative) and risk stratification categories (mild to severe). The performance of this model will be compared to a human prediction baseline on a random subset of lung sounds, where blinded physicians are asked to classify the audios into the same categories. DISCUSSION: This approach has broad potential to standardise the evaluation of lung auscultation in COVID-19 at various levels of healthcare, especially in the context of decentralised triage and monitoring. TRIAL REGISTRATION: PB_2016-00500, SwissEthics. Registered on 6 April 2020.

Frequency, Timing, Risk Factors, and Outcomes of Desaturation in Infants With Acute Bronchiolitis and Initially Normal Oxygen Saturation.

Importance: Little is known about the natural course of oxygen desaturation in acute bronchiolitis. Information on risk factors associated with desaturation as well as the time to desaturation in infants with bronchiolitis could help physicians better treat these infants before deciding whether to hospitalize them. Objective: To prospectively determine the frequency of desaturation in infants with bronchiolitis, along with the time to desaturation and risk factors associated with desaturation, and to compare infants who were hospitalized with those discharged home and evaluate risk factors for rehospitalization. Design, Setting, and Participants: This cohort study was conducted during the 2017 to 2018 and 2018 to 2019 respiratory syncytial virus seasons in a tertiary care pediatric emergency department in Switzerland. Included individuals were 239 otherwise-healthy infants aged younger than 1 year, diagnosed with acute bronchiolitis and oxygen saturation of 90% or more on arrival. Data were analyzed from July 2019 to October 2020. Exposures: After receiving triage care, study participants admitted to the emergency department were equipped with a pulse oximeter to continuously record oxygen saturation (Spo2 levels), regardless of subsequent hospitalization or discharge home. Main Outcomes and Measures: The primary outcome was desaturation (ie, Spo2 < 90%) during the first 36 hours. Results: Of 239 infants enrolled, with a median (interquartile range [IQR]) age of 3.9 (1.5-6.5) months, 116 (48.5%) were boys and desaturation occurred in 165 infants (69.0%). Median (IQR) time to desaturation was 3.6 (1.8-9.4) hours. The rate of desaturation was similar between infants hospitalized and those discharged home (137 of 200 infants [68.5%] vs 28 of 39 infants [71.8%]; difference, -3.3%; 95% CI, -18.8% to 12.2%; P = .85). A more severe initial clinical presentation with moderate or severe retractions was the only independent risk factor associated with desaturation (odds ratio, 2.73; 95% CI, 1.49 to 5.02; P = .001). Of 39 infants discharged home, 22 infants (56.4%) experienced major desaturations. However, infants with desaturations, including those with major desaturations, had rates of rehospitalization similar to those of infants without desaturations (8 of 28 infants [28.5%] vs 3 of 11 infants [27.3%]; difference, 1.2%; 95% CI, -29.9% to 32.5; P > .99). Conclusions and Relevance: These findings suggest that rates of desaturation in infants with acute bronchiolitis were high and similar between infants who were hospitalized and those discharged home. A more severe initial clinical presentation was the only risk factor associated with desaturation. However, for infants discharged home, desaturation was not a risk factor associated with rehospitalization.