Laurence Lacroix

A critical factor contributing to the burden of childhood asthma is the lack of effective self-management in homecare settings. Artificial intelligence (AI) and lung sound monitoring could help address this gap. Yet, existing AI-driven auscultation tools focus on wheeze detection and often rely on subjective human labels. To improve the early detection of asthma worsening in children in homecare setting, we trained and evaluated a Deep Learning model based on spirometry-labelled lung sounds recordings to detect asthma exacerbation. A single-center prospective observational study was conducted between November 2020 and September 2022 at a tertiary pediatric pulmonology department. Electronic stethoscopes were used to record lung sounds before and after bronchodilator administration in outpatients. In the same session, children also underwent spirometry, which served as the reference standard for labelling the lung sound data. Model performance was assessed on an internal validation set using receiver operating characteristic (ROC) curves. A total of 16.8 h of lung sound recordings from 151 asthmatic pediatric outpatients were collected. The model showed promising discrimination performance, achieving an AUROC of 0.763 in the training set, but performance in the validation set was limited (AUROC = 0.398). This negative result demonstrates that acoustic features alone may not provide sufficient diagnostic information for the early detection of asthma attacks, especially in mostly asymptomatic outpatients typical of homecare settings. It also underlines the challenges introduced by differences in how digital stethoscopes process sounds and highlights the need to define the severity threshold at which acoustic monitoring becomes informative, and clinically relevant for home management.

Background: The interpretation of lung sounds plays a crucial role in the appropriate diagnosis and management of pediatric asthma. Applying artificial intelligence (AI) to this task has the potential to better standardize assessment and may even improve its predictive potential. Objective: This study aims to objectively review the literature on AI-assisted lung auscultation for pediatric asthma and provide a balanced assessment of its strengths, weaknesses, opportunities, and threats. Methods: A scoping review on AI-assisted lung sound analysis in children with asthma was conducted across 4 major scientific databases (PubMed, MEDLINE Ovid, Embase, and Web of Science), supplemented by a gray literature search on Google Scholar, to identify relevant studies published from January 1, 2000, until May 23, 2023. The search strategy incorporated a combination of keywords related to AI, pulmonary auscultation, children, and asthma. The quality of eligible studies was assessed using the ChAMAI (Checklist for the Assessment of Medical Artificial Intelligence). Results: The search identified 7 relevant studies out of 82 (9%) to be included through an academic literature search, while 11 of 250 (4.4%) studies from the gray literature search were considered but not included in the subsequent review and quality assessment. All had poor to medium ChAMAI scores, mostly due to the absence of external validation. Identified strengths were improved predictive accuracy of AI to allow for prompt and early diagnosis, personalized management strategies, and remote monitoring capabilities. Weaknesses were the heterogeneity between studies and the lack of standardization in data collection and interpretation. Opportunities were the potential of coordinated surveillance, growing data sets, and new ways of collaboratively learning from distributed data. Threats were both generic for the field of medical AI (loss of interpretability) but also specific to the use case, as clinicians might lose the skill of auscultation. Conclusions: To achieve the opportunities of automated lung auscultation, there is a need to address weaknesses and threats with large-scale coordinated data collection in globally representative populations and leveraging new approaches to collaborative learning.

Background: Improved tools are required to detect bacterial infection in children with fever without source (FWS), especially when younger than 3 years old. The aim of the present study was to investigate the diagnostic accuracy of a host signature combining for the first time two viral-induced biomarkers, tumor necrosis factor-related apoptosis-inducing ligand (TRAIL) and interferon γ-induced protein-10 (IP-10), with a bacterial-induced one, C-reactive protein (CRP), to reliably predict bacterial infection in children with fever without source (FWS) and to compare its performance to routine individual biomarkers (CRP, procalcitonin (PCT), white blood cell and absolute neutrophil counts, TRAIL, and IP-10) and to the Labscore. Methods: This was a prospective diagnostic accuracy study conducted in a single tertiary center in children aged less than 3 years old presenting with FWS. Reference standard etiology (bacterial or viral) was assigned by a panel of three independent experts. Diagnostic accuracy (AUC, sensitivity, specificity) of host individual biomarkers and combinatorial scores was evaluated in comparison to reference standard outcomes (expert panel adjudication and microbiological diagnosis). Results: 241 patients were included. 68 of them (28%) were diagnosed with a bacterial infection and 5 (2%) with invasive bacterial infection (IBI). Labscore, ImmunoXpert, and CRP attained the highest AUC values for the detection of bacterial infection, respectively 0.854 (0.804–0.905), 0.827 (0.764–0.890), and 0.807 (0.744–0.869). Labscore and ImmunoXpert outperformed the other single biomarkers with higher sensitivity and/or specificity and showed comparable performance to one another although slightly reduced sensitivity in children < 90 days of age. Conclusion: Labscore and ImmunoXpert demonstrate high diagnostic accuracy for safely discriminating bacterial infection in children with FWS aged under and over 90 days, supporting their adoption in the assessment of febrile patients.

BACKGROUND The interpretation of lung sounds plays a crucial role in the appropriate diagnosis and management of pediatric asthma. Applying artificial intelligence (AI) to this task has the potential to better standardize assessment and may even improve its predictive potential. OBJECTIVE This study aims to objectively review the literature on AI-assisted lung auscultation for pediatric asthma and provide a balanced assessment of its strengths, weaknesses, opportunities, and threats. METHODS A scoping review on AI-assisted lung sound analysis in children with asthma was conducted across 4 major scientific databases (PubMed, MEDLINE Ovid, Embase, and Web of Science), supplemented by a gray literature search on Google Scholar, to identify relevant studies published from January 1, 2000, until May 23, 2023. The search strategy incorporated a combination of keywords related to AI, pulmonary auscultation, children, and asthma. The quality of eligible studies was assessed using the ChAMAI (Checklist for the Assessment of Medical Artificial Intelligence). RESULTS The search identified 7 relevant studies out of 82 (9%) to be included through an academic literature search, while 11 of 250 (4.4%) studies from the gray literature search were considered but not included in the subsequent review and quality assessment. All had poor to medium ChAMAI scores, mostly due to the absence of external validation. Identified strengths were improved predictive accuracy of AI to allow for prompt and early diagnosis, personalized management strategies, and remote monitoring capabilities. Weaknesses were the heterogeneity between studies and the lack of standardization in data collection and interpretation. Opportunities were the potential of coordinated surveillance, growing data sets, and new ways of collaboratively learning from distributed data. Threats were both generic for the field of medical AI (loss of interpretability) but also specific to the use case, as clinicians might lose the skill of auscultation. CONCLUSIONS To achieve the opportunities of automated lung auscultation, there is a need to address weaknesses and threats with large-scale coordinated data collection in globally representative populations and leveraging new approaches to collaborative learning.

Background: Effective team communication, coordination, and situational awareness (SA) by team members are critical components to deliver optimal cardiopulmonary resuscitation (CPR). Complexity of care during CPR, involvement of numerous providers, miscommunication, and other exogenous factors can all contribute to negatively influencing patient care, thus jeopardizing survival. We aim to investigate whether an mHealth supportive tool (the Interconnected and Focused Mobile Apps on patient Care Environment [InterFACE]) developed as a collaborative platform to support CPR providers in real-time and share patient-centered information would increase SA during pediatric CPR.Methods: We will conduct a prospective, cluster randomized controlled trial by groups of 6 participants in a tertiary pediatric emergency department (33,000 consultations/year) with pediatric physicians and nurses. We will compare the impact of the InterFACE tool with conventional communication methods on SA and effective team communication during a standardized pediatric in-hospital cardiac arrest and a polytrauma high-fidelity simulations. Forty-eight participants will be randomized (1:1) to consecutively perform two 20-min video-recorded scenarios using either the mHealth tool or conventional methods. The primary endpoint is the SA score, measured with the Situation Awareness Global Assessment Technique (SAGAT) instrument. Enrollment will start in late 2020 and data analysis in early 2021. We anticipate that the intervention will be completed by early 2021 and study results will be submitted in mid 2021 for publication.Discussion: This clinical trial will assess the impact of a collaborative mHealth tool on increasing situational awareness and effective team communication during in-hospital pediatric resuscitation. As research in this area is scarce, the results generated by this study may become of paramount importance in improving the care of children receiving in-hospital CPR, in the era of increasing communication technology.Trial registration: ClinicalTrials.govNCT04464603. Registered on 9 July 2020.

Background: Evidence-based best practices are the cornerstone to guide optimal cardiopulmonary arrest resuscitation care. Adherence to the American Heart Association (AHA) guidelines for cardiopulmonary resuscitation (CPR) optimizes the management of critically ill patients and increases their chances of survival after cardiac arrest. Despite advances in resuscitation science and survival improvement over the last decades, only approximately 38% of children survive to hospital discharge after in-hospital cardiac arrest and only 6%-20% after out-of-hospital cardiac arrest. Objective: We investigated whether a mobile app developed as a guide to support and drive CPR providers in real time through interactive pediatric advanced life support (PALS) algorithms would increase adherence to AHA guidelines and reduce the time to initiation of critical life-saving maneuvers compared to the use of PALS pocket reference cards. Methods: This study was a randomized controlled trial conducted during a simulation-based pediatric cardiac arrest scenario caused by pulseless ventricular tachycardia (pVT). A total of 26 pediatric residents were randomized into two groups. The primary outcome was the elapsed time in seconds in each allocation group from the onset of pVT to the first defibrillation attempt. Secondary outcomes were time elapsed to (1) initiation of chest compression, (2) subsequent defibrillation attempts, and (3) administration of drugs, including the time intervals between defibrillation attempts and drug doses, shock doses, and the number of shocks. All outcomes were assessed for deviation from AHA guidelines. Results: Mean time to the first defibrillation attempt (121.4 sec, 95% CI 105.3-137.5) was significantly reduced among residents using the app compared to those using PALS pocket cards (211.5 sec, 95% CI 162.5-260.6, P<.001). With the app, 11 out of 13 (85%) residents initiated chest compressions within 60 seconds from the onset of pVT and 12 out of 13 (92%) successfully defibrillated within 180 seconds. Time to all other defibrillation attempts was reduced with the app. Adherence to the 2018 AHA pVT algorithm improved by approximately 70% (P=.001) when using the app following all CPR sequences of action in a stepwise fashion until return of spontaneous circulation. The pVT rhythm was recognized correctly in 51 out of 52 (98%) opportunities among residents using the app compared to only 19 out of 52 (37%) among those using PALS cards (P<.001). Time to epinephrine injection was similar. Among a total of 78 opportunities, incorrect shock or drug doses occurred in 14% (11/78) of cases among those using the cards. These errors were reduced to 1% (1/78, P=.005) when using the app. Conclusions: Use of the mobile app was associated with a shorter time to first and subsequent defibrillation attempts, fewer medication and defibrillation dose errors, and improved adherence to AHA recommendations compared with the use of PALS pocket cards.

BACKGROUND Evidence-based best practices are the cornerstone to guide optimal cardiopulmonary arrest resuscitation care. Adherence to the American Heart Association (AHA) guidelines for cardiopulmonary resuscitation (CPR) optimizes the management of critically ill patients and increases their chances of survival after cardiac arrest. Despite advances in resuscitation science and survival improvement over the last decades, only approximately 38% of children survive to hospital discharge after in-hospital cardiac arrest and only 6%-20% after out-of-hospital cardiac arrest. OBJECTIVE We investigated whether a mobile app developed as a guide to support and drive CPR providers in real time through interactive pediatric advanced life support (PALS) algorithms would increase adherence to AHA guidelines and reduce the time to initiation of critical life-saving maneuvers compared to the use of PALS pocket reference cards. METHODS This study was a randomized controlled trial conducted during a simulation-based pediatric cardiac arrest scenario caused by pulseless ventricular tachycardia (pVT). A total of 26 pediatric residents were randomized into two groups. The primary outcome was the elapsed time in seconds in each allocation group from the onset of pVT to the first defibrillation attempt. Secondary outcomes were time elapsed to (1) initiation of chest compression, (2) subsequent defibrillation attempts, and (3) administration of drugs, including the time intervals between defibrillation attempts and drug doses, shock doses, and the number of shocks. All outcomes were assessed for deviation from AHA guidelines. RESULTS Mean time to the first defibrillation attempt (121.4 sec, 95% CI 105.3-137.5) was significantly reduced among residents using the app compared to those using PALS pocket cards (211.5 sec, 95% CI 162.5-260.6, P<.001). With the app, 11 out of 13 (85%) residents initiated chest compressions within 60 seconds from the onset of pVT and 12 out of 13 (92%) successfully defibrillated within 180 seconds. Time to all other defibrillation attempts was reduced with the app. Adherence to the 2018 AHA pVT algorithm improved by approximately 70% (P=.001) when using the app following all CPR sequences of action in a stepwise fashion until return of spontaneous circulation. The pVT rhythm was recognized correctly in 51 out of 52 (98%) opportunities among residents using the app compared to only 19 out of 52 (37%) among those using PALS cards (P<.001). Time to epinephrine injection was similar. Among a total of 78 opportunities, incorrect shock or drug doses occurred in 14% (11/78) of cases among those using the cards. These errors were reduced to 1% (1/78, P=.005) when using the app. CONCLUSIONS Use of the mobile app was associated with a shorter time to first and subsequent defibrillation attempts, fewer medication and defibrillation dose errors, and improved adherence to AHA recommendations compared with the use of PALS pocket cards. CLINICALTRIAL According to ICMJE recommendations, a trial registration number was not required as the purpose of the study was to examine the effect of the intervention on healthcare providers.

Background: Accurate diagnosis and appropriate treatment of group A streptococcal (GAS) pharyngitis are important to prevent complications. Most available rapid antigen detection tests (RADTs) have shown excellent specificity but often lack sensitivity. Our objective was to compare the diagnostic performances of a new fluorescence-based immunoassay and a classic immunochromatographic RADT using standard throat culture or polymerase chain reaction as references. Methods: Prospective observational study in 2 pediatric emergency departments in children 3-15 years of age presenting with pharyngitis and a McIsaac score 2. Three throat swabs were obtained simultaneously: one for culture and one for each of both RADTs. Polymerase chain reaction assay of the DNaseB sequence was performed in case of discordant results (culture negative and either RADTs positive). Results: A total of 1002 patients were analyzed, with an overall 37.1% prevalence of GAS pharyngitis. Sensitivity, specificity, positive and negative predictive values were, respectively, 84.9%*, 96.8%, 94.0% and 91.6% for the new fluorescence-based immunoassay, and 75.3%*, 98.1%, 95.9% and 87.0% for the immunochromatographic test (*P < 0.05). Conclusions: The immunofluorescence-based assay demonstrated improved diagnostic performances over the standard immunochromatographic RADT. Similarly specific for GAS detection, it demonstrates significantly higher sensitivity in children with McIsaac scores 2 or more. A negative result rules out a risk of GAS pharyngitis in 91.6% of children, making it an appropriate tool in pediatric emergency settings. Combined to the low incidence of rheumatic strains, critical appraisal of current practice to routinely perform a backup throat culture from children with pharyngitis and with negative GAS RADT could be reconsidered.

Journal of Medical Internet Research - International Scientific Journal for Medical Research, Information and Communication on the Internet