Aspiration pneumonia in children with neurological disorders: a new indication for lung ultrasound? A case series

A new scoring system and clinical algorithm for the management of suspected foreign body aspiration in children: a retrospective cohort study

BACKGROUND

Cases of foreign body aspiration in children may be encountered in emergency departments. A suggestive history is important in diagnosing aspirated foreign body owing to the difficulty in making a diagnosis on the basis of an abnormal physical examination or chest radiography alone. The aim of this study was to examine the sensitivity and specificity of the presenting symptoms, physical examination, and radiologic findings as predictors of foreign body aspiration in children. In addition, a feasible simple algorithm with a scoring system was generated to indicate bronchoscopic investigation.

METHODS

In a retrospective cohort, medical records of patients aged less than 16 years with suspected foreign body aspiration who underwent flexible or rigid bronchoscopy were included. Data including age, sex, symptoms, physical examination findings, radiological features, nature and location of the foreign body, and outcome of the bronchoscopy were collected, and multivariable binary logistic regression analysis was employed for prediction of foreign body aspiration.

RESULTS

A total of 203 children were included, and the model showed excellent discrimination power for positive foreign body aspiration (area under the curve = 0.911) with an accuracy, sensitivity, and specificity of 86.2, 90.6, and 76.6%, respectively. The total weighted risk score at a cut-off > 2 showed a significant good power of discrimination (area under the curve = 0.879), with a sensitivity of 79.9% and specificity of 84.4%. Accordingly, a clinical algorithm was recommended.

CONCLUSIONS

The proposed scoring system and clinical algorithm might help in decision making with regard to the need and type of bronchoscopy in children presenting with potential foreign body aspiration. However, further prospective multicenter studies should be conducted to validate this scoring system.

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.

Role of lung ultrasound for the etiological diagnosis of acute lower respiratory tract infection (ALRTI) in children: a prospective study

Objective and design

Our prospective study assesses the role of detailed lung ultrasound (LUS) features to discriminate the etiological diagnosis of acute lower respiratory tract infection (ALRTI) in children.

Methodology

We analyzed patients aged from 1 month to 17 years admitted between March 2018 and April 2020 who were hospitalized for ALRTI. For all patients, history, clinical parameters, microbiological data, and lung ultrasound data were collected. Patients were stratified into three main groups (“bacterial”, “viral”, “atypical”) according to the presumed microbial etiology and LUS findings evaluated according to the etiological group. Nasopharyngeal swabs were obtained from all patients. A qualitative diagnostic test developed by Nurex S.r.l. was used for identification of bacterial and fungal DNA in respiratory samples. The Seegene Allplex™ Respiratory assays were used for the molecular diagnosis of viral respiratory pathogens. In addition, bacterial culture of blood and respiratory samples were performed, when indicated.

Results

A total of 186 children with suspected ALRTI (44% female) with an average age of 6 were enrolled in the study. We found that some ultrasound findings as size, number and distribution of consolidations, the position and motion of air bronchograms, pleural effusions and distribution of vertical artifacts significantly differ (p < 0.05) in children with bacterial, viral and atypical ALRTI.

Conclusion

Our study provides a detailed analysis of LUS features able to predict the ALRTI ethology in children. These findings may help the physicians to better manage a child with ALRTI and to offer personalized approach, from diagnosis to treatment and follow-up.

Point-of-care lung and diaphragm ultrasound in a patient with spinal muscular atrophy with respiratory distress type 1

Spinal muscular atrophy with respiratory distress type 1 (SMARD1, OMIM #604,320), is a rare autosomal recessive disease resulting from degeneration of motor neurons in the anterior horns, which leads irreversible diaphragmatic palsy and progressive distal symmetrical muscular weakness. Respiratory distress is the main symptom and is severe, rapidly progressive, and frequently requiring invasive ventilation. Despite diaphragm being one of the target organ of the disease, no specific study has been done using ultrasound.We report diaphragm and lung ultrasound findings of a 13-month-old girl affected by SMARD1 (homozygosis c.1540G > A mutation in IGHMPB2 gene) with respiratory failure requiring permanent mechanical ventilation since birth and we discuss the role of diaphragmatic and lung ultrasound in this category of patients and its clinical implications.

Impact of scan quality on AI assessment of hip dysplasia ultrasound

AIMS

Early diagnosis of developmental dysplasia of the hip (DDH) using ultrasound (US) is safe, effective and inexpensive, but requires high-quality scans. The effect of scan quality on diagnostic accuracy is not well understood, especially as artificial intelligence (AI) begins to automate such diagnosis. In this paper, we developed a 10-point scoring system for reporting DDH US scan quality, evaluated its inter-rater agreement and examined its effect on automated assessment by an AI system-MEDO-Hip.

METHODS

Scoring was based on iliac wing straightness and angulation; visibility of labrum, os ischium and femoral head; motion; and other artifacts. Four readers from novice to expert separately scored the quality of 107 scans with this 10-point scale and with holistic grading on a scale of 1-5. MEDO-Hip interpreted the same scans, providing a diagnostic category or identifying the scan as uninterpretable.

RESULTS

Inter-rater agreement for the 10-point scale was significantly higher than holistic scoring ICC 0.68 vs 0.93, p < 0.05. Inter-rater agreement on the categorisation of individual features, by Cohen's kappa, was highest for os ischium (0.67 ± 0.06), femoral head (0.65 ± 0.07) and iliac wing (0.49 ± 0.12) indices, and lower for the presence of labrum (0.21 ± 0.19). MEDO-Hip interpreted all images of a quality > 7 and flagged 13/107 as uninterpretable. These were low-quality images (3 ± 1.2 vs. 7 ± 1.8 in others, p < 0.05), with poor visualization of the os ischium and noticeable motion. AI accuracy in cases with quality scores <  = 7 was 57% vs. 89% on other cases, p < 0.01.

CONCLUSION

This study validates that our scoring system reliably characterises scan quality, and identifies cases likely to be misinterpreted by AI. This could lead to more accurate use of AI in DDH diagnosis by flagging low-quality scans likely to provide poor diagnosis up front.