Point-of-care ultrasound: An emerging technology in Canadian paediatrics

Classification of Lung Disease in Children by Using Lung Ultrasound Images and Deep Convolutional Neural Network

Bronchiolitis is the most common cause of hospitalization of children in the first year of life and pneumonia is the leading cause of infant mortality worldwide. Lung ultrasound technology (LUS) is a novel imaging diagnostic tool for the early detection of respiratory distress and offers several advantages due to its low-cost, relative safety, portability, and easy repeatability. More precise and efficient diagnostic and therapeutic strategies are needed. Deep-learning-based computer-aided diagnosis (CADx) systems, using chest X-ray images, have recently demonstrated their potential as a screening tool for pulmonary disease (such as COVID-19 pneumonia). We present the first computer-aided diagnostic scheme for LUS images of pulmonary diseases in children. In this study, we trained from scratch four state-of-the-art deep-learning models (VGG19, Xception, Inception-v3 and Inception-ResNet-v2) for detecting children with bronchiolitis and pneumonia. In our experiments we used a data set consisting of 5,907 images from 33 healthy infants, 3,286 images from 22 infants with bronchiolitis, and 4,769 images from 7 children suffering from bacterial pneumonia. Using four-fold cross-validation, we implemented one binary classification (healthy vs. bronchiolitis) and one three-class classification (healthy vs. bronchiolitis vs. bacterial pneumonia) out of three classes. Affine transformations were applied for data augmentation. Hyperparameters were optimized for the learning rate, dropout regularization, batch size, and epoch iteration. The Inception-ResNet-v2 model provides the highest classification performance, when compared with the other models used on test sets: for healthy vs. bronchiolitis, it provides 97.75% accuracy, 97.75% sensitivity, and 97% specificity whereas for healthy vs. bronchiolitis vs. bacterial pneumonia, the Inception-v3 model provides the best results with 91.5% accuracy, 91.5% sensitivity, and 95.86% specificity. We performed a gradient-weighted class activation mapping (Grad-CAM) visualization and the results were qualitatively evaluated by a pediatrician expert in LUS imaging: heatmaps highlight areas containing diagnostic-relevant LUS imaging-artifacts, e.g., A-, B-, pleural-lines, and consolidations. These complex patterns are automatically learnt from the data, thus avoiding hand-crafted features usage. By using LUS imaging, the proposed framework might aid in the development of an accessible and rapid decision support-method for diagnosing pulmonary diseases in children using LUS imaging.

Focus on PoCUS or hocus pocus? Integrating point-of-care ultrasound into residency and clinical practice

Point-of care ultrasound (PoCUS) is a new clinical diagnostic paradigm that plays an instrumental role in the ongoing anesthesiologist’s evolving role towards a perioperative physician. Currently, there are few approved curricula that incorporate a PoCUS program into anesthesia residency. This article examines relevant PoCUS applications for anesthesiologists, presents an overview of existing international guidelines for education and training, and reflects on the need for specialty-wide standards. We present a possible framework, that could offer a first move towards a structured PoCUS pathway for Belgian anesthesia residents and facilitate its incorporation into national anesthesia practice.

Accuracy of point-of-care ultrasound by pediatric emergency physicians for testicular torsion

INTRODUCTION

Acute scrotum is a common presentation to the pediatric emergency department, and ultrasound is frequently used to narrow the differential diagnosis. Point-of-care ultrasound (POCUS) is increasingly used by urologists and emergency physicians and could potentially be used to detect pediatric testicular torsion.

OBJECTIVES

This study aimed to determine the accuracy of POCUS by pediatric emergency physicians in diagnosing testicular torsion and the agreement between point-of-care ultrasound and final diagnosis for other causes of acute scrotum.

STUDY DESIGN

A chart review of patients presenting to the study emergency department who received POCUS by a pediatric emergency physician, as well as radiology department ultrasound and/or surgery, was performed. Charts were reviewed for POCUS diagnoses, final diagnoses, and imaging time metrics.

RESULTS

A total of 120 patients met study criteria, with 12 cases of testicular torsion. The diagnostic accuracy of POCUS for testicular torsion is described in the summary table. For all causes of acute scrotum, point-of-care ultrasound agreed with final diagnosis in 70% (95% confidence interval [CI] 62-78%) of cases, and more experienced point-of-care ultrasound users displayed higher agreement with final diagnosis. Point-of-care ultrasound results were generated a median of 73 min (Q1 = 51, Q3 = 112) before radiology department ultrasound results.

DISCUSSION

Scrotal POCUS performed by pediatric emergency physicians appears to be an accurate tool to detect testicular torsion in children with acute scrotum and saves time compared with radiology ultrasound. The study results may not be generalizable to hospitals without a multidisciplinary POCUS system for quality assurance and image sharing. Future work on POCUS for acute scrotum should investigate its impact on patient outcomes, cost-effectiveness, and family satisfaction.

CONCLUSION

Point-of-care ultrasound by pediatric emergency physicians is accurate for detecting testicular torsion in children with acute scrotum and could expedite diagnosis of this time-sensitive condition.

Point of care ultrasound (POCUS) in Canadian neonatal intensive care units (NICUs): where are we?

OBJECTIVES

Despite increased evidence that point-of-care ultrasound (POCUS) has the potential to improve patient care in many clinical areas, the extent of use and training in POCUS in Canadian neonatal intensive care units (NICUs) has not been described in the literature. In this study, we aimed to explore the extent to which POCUS is being used and the need for a formal curriculum with defined POCUS competencies in the field of Neonatal-Perinatal Medicine (NPM).

METHODS

We sent a cross-sectional electronic survey to all NPM program directors and fellows in Canada. All 13 Canadian NPM programs were invited to participate. Data were analyzed using descriptive statistics and qualitative content analysis.

RESULTS

The response rate was 69% (n = 9) from program directors (PDs) and 29% (n = 25) from NPM fellows. Most respondents indicated regular use of POCUS in clinical practice and ready access to a portable ultrasound machine. The most common use for POCUS was targeted assessment of patent ductus arteriosus (PDA) and persistent pulmonary hypertension (PPHN). Only six PDs reported that POCUS skills are taught to trainees in their centers and only two PDs reported that a structured program existed. Barriers to POCUS structured training include a lack of trained personnel as well as insufficient time in the busy NPM curriculum.

CONCLUSION

POCUS is widely used in Canadian NICUs. However, a formal curriculum and assessment of competencies in this area of neonatal clinical care are lacking.

Point-of-care lung ultrasound in infants with bronchiolitis in the pediatric emergency department: a prospective study

Bronchiolitis is the most common cause of hospitalization of children in the first year of life. The lung ultrasound is a new diagnostic tool which is inexpensive, non-invasive, rapid, and easily repeatable. Our prospective study was conducted in the emergency department and all patients underwent a routine clinical evaluation and lung ultrasound by the pediatricians who defined the clinical and the ultrasound score. We enrolled 76 infants (median age 90 days [IQR 62-183], 53.9% males). In nasopharyngeal aspirates, the respiratory syncytial virus was isolated in 33 patients. Considering the clinical score, children with higher score had a higher probability of requiring respiratory support (p 0.001). At the ultrasound evaluation, there was a significant difference on ultrasound score between those who will need respiratory support or not (p 0.003). Infants who needed ventilation with helmet continuous positive airway pressure had a more severe ultrasound score (p 0.028) and clinical score (p 0.004), if compared with those who did not need it.Conclusion: Our study shows that lung ultrasound in the bronchiolitis may be a useful method to be integrated with the clinical evaluation to better define the prognosis of the individual patient. Multicenter studies on larger populations are necessary to confirm our data. What is Known: • Bronchiolitis is the main cause of lower respiratory tract infection in children younger than 24 months. • Ultrasound can evaluate the lung parenchyma without ionizing radiations. What is New: • Lung ultrasound may be a useful diagnostic tool to define the prognosis of the infants affected by bronchiolitis if performed at the first assessment in the emergency department. • The score obtained at the ultrasound evaluation is higher in those who will need oxygen therapy during admission for more time and in those who will need respiratory support with helmet continuous positive airway pressure.

Point of care diaphragm ultrasound in infants with bronchiolitis: A prospective study

BACKGROUND

Bronchiolitis is the most common reason for hospitalization of children worldwide. Many scoring systems have been developed to quantify respiratory distress and predict outcome, but none of them have been validated. We hypothesized that the ultrasound evaluation of the diaphragm could quantify respiratory distress and therefore we correlated the ultrasound diaphragm parameters with outcome.

METHODS

Prospective study of infants with bronchiolitis (1-12 months) evaluated in a pediatric emergency department. Ultrasonography examinations of the diaphragm was performed (diaphragm excursion [DE], inspiratory excursion [IS], inspiratory/expiratory relationship [I/E], and thickness at end-expiration [TEE] and at end-inspiration [TEI]; thickening fraction [TF]).

RESULTS

We evaluated 61 infants, 50.8 % males. Mean TF was 47% (IQR 28.6-64.7), mean I/E 0.47 (± 0.15), mean DE 10.39 ± 4 mm. There was a linear correlation between TF and oxygen saturation at first evaluation (P = 0.006, r = 0.392). All children with lower values of TF required HFNC and one of them required CPAP. A higher IS was associated with the future need of respiratory support during admission (P = 0.007). IS correlated with the hours of oxygen delivery needed (P = 0.032, r = 0.422). TEI (t = 3.701, P = 0.002) was found to be main predictor of hours of oxygen delivery needed.

CONCLUSION

This study described ultrasound diaphragmatic values of previously healthy infants with bronchiolitis. DE, IS, and TEI correlated with outcome. If confirmed in larger studies, bedside ultrasound semiology of the diaphragm can be a new objective tool for the evaluation and outcome prediction of infants with bronchiolitis.

Precision Medicine With Point-of-Care Ultrasound: The Future of Personalized Pediatric Emergency Care

The Precision Medicine Initiative spearheaded by the National Institute of Health has pioneered a new model of health care focused on health care delivery that is tailored to an individual. Medical advances have already provided clinicians with the tools to better predict treatment outcomes based on the individual needs of each patient's disease process. Three-dimensional printing allows medical devices and implants to be custom made-to-order. Technological advances in preoperative imaging have augmented the ability for surgeons to plan a specific surgical approach for each patient. In a similar vein, point-of-care ultrasound offers the emergency care provider an opportunity to move beyond protocols and provide precise medical care tailored to the acute needs of each ill or injured emergent patient. In this article, we explore several cutting-edge applications of point-of-care ultrasound that can help providers develop a personalized approach to resuscitation and emergent procedures in pediatrics.

Emergency point-of-care ultrasound in Canadian pediatric emergency fellowship programs: current integration and future directions

BACKGROUND

Adult and pediatric emergency physicians have been using point-of-care ultrasound (POCUS) for many years. It is a fast, usually painless, noninvasive diagnostic tool that does not expose the patient to radiation. Information about its current implementation in pediatric emergency medicine (PEM) fellowship programs in Canada is lacking.

OBJECTIVE

The main goal of our study was to investigate current integration and future direction of POCUS training in Canadian PEM programs.

METHODS

The study consisted of two surveys designed for fellows and program directors of all Canadian PEM fellowship programs. The major aspects of the survey were 1) to describe current training in POCUS in fellowship programs, 2) to compare the kind of training that programs offer with what fellows actually receive, and 3) a needs assessment by fellows and program directors for future POCUS training programs. Surveys were sent to program directors and passed on to their fellows.

RESULTS

Ninety percent of fellowship program directors as well as 70% (42/60) of fellows responded to the survey. A formal POCUS curriculum exists in five of the nine PEM programs included in this study. Three programs offer specific pediatric POCUS training. The main application is the FAST (focused assessment with sonography for trauma) exam.

CONCLUSION

There is a wide variation in POCUS content and delivery across PEM fellowship programs, as well as differences in perceptions of current training and of needs by fellows and program directors. However, given that both groups feel POCUS is very important and essential for PEM training, the opportunity exists to develop a standardized curriculum across Canada.