A study protocol for community use of digital auscultation to improve diagnosis of paediatric pneumonia in Bangladesh

The World Health Organisation Integrated Management of Childhood Illnesses (IMCI) algorithm relies on counting respiratory rate and observing respiratory distress to diagnose childhood pneumonia. IMCI performs with high sensitivity but low specificity, leading to over-diagnosis of child pneumonia and unnecessary antibiotic use. Including lung auscultation in IMCI could improve pneumonia diagnosis. Our objectives are: (i) assess lung sound recording quality by primary health care workers (HCWs) from under-five children with the Feelix Smart Stethoscope; and (ii) determine the reliability and performance of recorded lung sound interpretations by an automated algorithm compared to reference paediatrician interpretations. In a cross-sectional design, Community HCWs will record lung sounds of 1,003 under-five-year-old children with suspected pneumonia at first-level facilities in Zakiganj sub-district, Sylhet, Bangladesh. Enrolled children will be evaluated for pneumonia, including oxygen saturation, and have their lung sounds recorded by the Feelix Smart stethoscope at four sequential chest locations: two back and two front positions. A novel sound-filtering algorithm will be applied to recordings to address ambient noise and optimize recording quality. Recorded sounds will be assessed against a pre-defined quality threshold. A trained paediatric listening panel will classify recordings into one of the following categories: normal, crackle, wheeze, crackle and wheeze, or uninterpretable. All sound files will be classified into the same categories by the automated algorithm and compared with panel classifications. Lung auscultation and reliable interpretation of lung sounds of children are usually not feasible in first-level facilities in Bangladesh and other low- and middle-income countries (LMICs). Incorporating automated lung sound classification within the current IMCI pneumonia diagnostic algorithm may improve childhood pneumonia diagnostic accuracy at LMIC first-level facilities.

The Utility of Real-Time Remote Auscultation Using an Internet-Connected Electronic Stethoscope: An Open-Label Randomized Controlled Pilot Trial

Objective: This study aimed to assess the utility of real-time remote auscultation using the cardiopulmonary simulators.Methods: In this open-label, randomized controlled trial, the researchers randomly assigned general internal medicine doctors to the real-time remote auscultation group (intervention group) or the classical auscultation group (control group). In the training session, participants listened to five different lung sounds and five cardiac sounds in a previously determined order with the correct classification. In the test session, participants had to classify the five lung sounds and five cardiac sounds in random order. For both sessions, the intervention group auscultated at a distance of 220 m, with an Internet-connected electronic stethoscope while watching the auscultation places on the computer screen. The control group performed direct auscultation using a classical stethoscope. The primary outcome was the total test score.Results: Twenty participants were included in the study. The total test scores of lung auscultation in the intervention (86%) and control (90%) groups were not significantly different (P = .54). The total test score of cardiac auscultation in the control group (94%) was superior to that in the intervention group (72%, P < .05). Valvular diseases were not misclassified as normal sounds in real-time remote cardiac auscultation. Discussion and Conclusions: The utility of real-time remote lung auscultation using an Internet-connected electronic stethoscope was comparable to that of classical lung auscultation. Classical cardiac auscultation was superior to real-time remote cardiac auscultation. However, real-time remote cardiac auscultation is useful for classifying valvular diseases and normal sounds. Trial Registration: UMIN-CTR UMIN000043153; https://upload.umin.ac.jp/cgi-open-bin/ctr/ctr_view.cgi?recptno=R000049259 The date of first registration:28/01/2021

Pulmonary edema in a pediatric patient undergoing ureteroscopy: a case report

Background This report demonstrates a case of pediatric pulmonary edema, detected due to the overuse of irrigation fluids during ureteroscopy. Case presentation A 7-year-old girl was hospitalized due to the large number of opaque stones in the right kidney. After extubation, the patient’s oxygen saturation dropped down to 85%, and respiratory distress was observed. It was determined that the surgical team used 5 Lt 0.9% NaCl solution as irrigation fluid. Positive pressure ventilation with mask continued, and intravenous bolus injection of furosemide was administered to the patient with a preliminary diagnosis of pulmonary edema. Conclusions In prolonged operations, patients should be checked for the presence of pulmonary edema with lung auscultation, and noninvasive mechanical ventilation and diuretic treatment should be instituted if necessary.

From bed-side to web-side, Advanced-Telemedicine platform for Spinal Muscular Atrophy

We aimed to assess feasibility, accuracy, satisfaction of an advanced-telemedicine (A-TM) platform designed for remote physical evaluation, especially focused on lung auscultation, in spinal muscular atrophy (SMA) patients. Children affected by type 1 and 2 SMA, typically present generalized weakness, scoliosis, chest deformities the leading cause of progressive respiratory insufficiency and recurrent hospitalization. Covid-19 stimulated efforts to adopt innovative digital health solutions especially when caring for people living with disabilities. Because of chest asymmetry and scoliosis, SMA patients are not always the ideal candidates for telemedicine tools that have proved to be useful in the general population. 23 children affected by SMA (15 type 1 and 8 type 2) with different degree of scoliosis and chest asymmetry. Prospective study: We localized optimal thoracic auscultatory landmarks with traditional stethoscope and lung ultrasound for each child. Carers were trained to record complete lung auscultation independently and share data with our physicians via A-TM platform. After the first remote exam, carers videorecorded their experience (satisfaction). Our physicians blindly rated the audio files shared via A-TM which were compared to traditional auscultation findings for each child. to assess. Overall feasibility and accuracy of carers-performed remote physical evaluation. Our study showed that remotely performed lung auscultation was possible in all type 1 and 2 SMA children but adaptations to find optimal landmarks were needed in cases with asymmetrical or rotated chest and trunk. A-TM tools may simplify access to care, reduce logistic/economic burden for families, improve communication, safety and disease management while limiting infection exposure.

Detection of Respiratory Phases in a Breath Sound and Their Subsequent Utilization in a Diagnosis

Detection of lung sounds and their propagation is a powerful tool for analysing the behaviour of the respiratory system. A common approach to detect the respiratory sounds is lung auscultation, however, this method has significant limitations including low sensitivity of human ear or ambient background noise. This article targets the major limitations of lung auscultation and presents a new approach to analyse the respiratory sounds and visualise them together with the respiratory phases. The respiratory sounds from 41 patients were recorded and filtered to eliminate the ambient noise and noise artefacts. The filtered signal is processed to identify the respiratory phases. The article also contains an approach for removing the noise that is very difficult to filter but the removal is crucial for identifying the respiratory phases. Finally, the respiratory phases are overlaid with the frequency spectrum which simplifies the orientation in the recording and additionally offers the information on the inter-individual ratio of the inhalation and exhalation phases. Such interpretation provides a powerful tool for further analysis of lung sounds, simplifythe diagnosis of various types of respiratory tract dysfunctions, and returns data which are comparable among the patients.

Efficiently Classifying Lung Sounds through Depthwise Separable CNN Models with Fused STFT and MFCC Features

Lung sounds remain vital in clinical diagnosis as they reveal associations with pulmonary pathologies. With COVID-19 spreading across the world, it has become more pressing for medical professionals to better leverage artificial intelligence for faster and more accurate lung auscultation. This research aims to propose a feature engineering process that extracts the dedicated features for the depthwise separable convolution neural network (DS-CNN) to classify lung sounds accurately and efficiently. We extracted a total of three features for the shrunk DS-CNN model: the short-time Fourier-transformed (STFT) feature, the Mel-frequency cepstrum coefficient (MFCC) feature, and the fused features of these two. We observed that while DS-CNN models trained on either the STFT or the MFCC feature achieved an accuracy of 82.27% and 73.02%, respectively, fusing both features led to a higher accuracy of 85.74%. In addition, our method achieved 16 times higher inference speed on an edge device and only 0.45% less accuracy than RespireNet. This finding indicates that the fusion of the STFT and MFCC features and DS-CNN would be a model design for lightweight edge devices to achieve accurate AI-aided detection of lung diseases.

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.

The Effect of Hydroxychloroquine on Mortality and Pneumonia Development in SARS-Cov-2 Positive Mildly Symptomatic Outpatients without Findings of Pneumonia

Although a period longer than 10 months has passed since the detection of the first cases in and more than 40 million people have been diagnosed with COVID-19 worldwide, there is still no well-accepted and proven treatment choice for the novel coronavirus disease. This study aimed to retrospectively investigate cases in whom treatment had started due to detected as positive during screening and also having shown signs including fever, cough, shortness of breath, excessive malaise, fatigue or loss of smell-taste, without any findings of pneumonia between March 11, 2020, when the first cases were detected in Turkey, and the beginning of May, 2020. A total of 19.276 SARS-CoV-2 PCR positive outpatients, within the first 48 hours of detection and had no findings in lung auscultation or radiology, were detected from the data of Health Information System. 9559 patients were males (49.6%) and 9717 were females (50.4%). An underlying disease considered in the risk group for COVID-19 was found in 1789 of the patients (8.8%). An underlying disease was present in 9.4% using hydroxychloroquine and in 9% not using hydroxychloroquine. 43 deaths (0.2%) were detected among all cases. Mortality in cases using and not using hydroxychloroquine was respectively 5 (in 12.293 cases) and 38 (in 6.983 cases). It was confirmed that pneumonia developed in 2.080 of the patients (10.8%). This number was found as 1286 (10.5%) in cases using HQ and as 794 (11.4%) in cases not using HQ. In conclusion, since this study confirmed that hydroxychloroquine used in outpatients presenting in the early period without any symptoms of pneumonia can ensure survival and prevent pneumonia development particularly in young adults, we may speculate that the early use of hydroxychloroquine in mildly symptomatic patients results in a cost-effective and potent treatment.