Interobserver agreement in interpretation of chest radiographs for pediatric community acquired pneumonia: Findings of the pedCAPNETZ-cohort

Investigation of Childhood Pneumonia With Thoracic Ultrasound: A Comparison Between X-ray and Ultrasound

ABSTRACT

Childhood pneumonia is a common entity, and chest x-rays are widely used as an initial diagnostic step. To avoid radiation exposure in the pediatric age group, we assessed whether the diagnostic accuracy of ultrasound (US) imaging is sufficient in the diagnosis. One hundred thirty-three children with pneumonia (72 girls/61 boys) were participated to study between 2019 and 2021. All participants had a chest x-ray. Radiologists who perform the US scans and interpret the x-rays were blinded to each other. A comparative analysis was also done to assess US findings on pneumonia for different age groups. We compare the diagnostic accuracy of US and x-rays by McNemar test and receiver operating characteristic curves. Intraclass correlation coefficient values were calculated for the assessment of interobserver agreement of x-ray evaluation. The participants' ages ranged from 1 month to 17 years and 8 months with a median age of 24 months (Q 1 : 8 and Q 3 : 66 months). Hospital stay lengths were longer, consolidation depths were greater, and presence of air bronchogram or pleural effusion was more frequent in school-age children. The proportion of consolidation seen on chest x-ray and transthoracic US scan was significantly different ( P < 0.001). The area under the curve was greater in the US than in the chest x-ray (area under the curve, 0.94 and 0.76 respectively). There was a good agreement between the 2 interpreters on chest x-ray assessment ( κ = 0.661). The thoracic US can be used as a safe and efficient imaging tool in the diagnosis of pediatric pneumonia.

Point-of-care lung ultrasound score for predicting escalated care in children with respiratory distress

PURPOSE

Respiratory distress due to lower respiratory illnesses is a leading cause of death in children. Early recognition of high-risk populations is critical for the allocation of adequate resources. Our goal was to assess whether the lung ultrasound (US) score obtained at admission in children with respiratory distress predicts the need for escalated care.

METHODS

This prospective study included 0-18-year-old patients with respiratory distress admitted to three emergency departments in the state of Sao Paulo, Brazil, between July 2019 and September 2021. The enrolled patients underwent lung US performed by a pediatric emergency physician within two hours of arrival. Lung ultrasound scores ranging from 0 to 36 were computed. The primary outcome was the need for high-flow nasal cannula (HFNC), noninvasive ventilation (NIV), or mechanical ventilation within 24 h.

RESULTS

A total of 103 patients were included. The diagnoses included wheezing (33%), bronchiolitis (27%), pneumonia (16%), asthma (9%), and miscellaneous (16%). Thirty-five patients (34%) required escalated care and had a higher lung ultrasound score: median 13 (0-34) vs 2 (0-21), p < 0.0001; area under the curve (AUC): 0.81 (95% confidence interval [CI]: 0.71-0.90). The best cut-off score derived from Youden's index was seven (sensitivity: 71.4%; specificity: 79.4%; odds ratio (OR): 9.6 [95% CI: 3.8-24.7]). A lung US score above 12 was highly specific and had a positive likelihood ratio of 8.74 (95% CI:3.21-23.86).

CONCLUSION

An elevated lung US score measured in the first assessment of children with any type of respiratory distress was predictive of severity as defined by the need for escalated care with HFNC, NIV, or mechanical ventilation.

Pathogen spectra in hospitalised and nonhospitalised children with community-acquired pneumonia

Background

Paediatric community-acquired pneumonia (CAP) is a leading cause of paediatric morbidity. However, particularly for outpatients with paediatric CAP, data on aetiology and management are scarce.

Methods

The prospective pedCAPNETZ study multicentrically enrols children and adolescents with outpatient-treated or hospitalised paediatric CAP in Germany. Blood and respiratory specimens were collected systematically, and comprehensive analyses of pathogen spectra were conducted. Follow-up evaluations were performed until day 90 after enrolment.

Results

Between December 2014 and August 2020, we enrolled 486 children with paediatric CAP at eight study sites, 437 (89.9%) of whom had radiographic evidence of paediatric CAP. Median (interquartile range) age was 4.5 (1.6-6.6) years, and 345 (78.9%) children were hospitalised. The most prevalent symptoms at enrolment were cough (91.8%), fever (89.2%) and tachypnoea (62.0%). Outpatients were significantly older, displayed significantly lower C-reactive protein levels and were significantly more likely to be symptom-free at follow-up days 14 and 90. Pathogens were detected in 90.3% of all patients (one or more viral pathogens in 68.1%; one or more bacterial strains in 18.7%; combined bacterial/viral pathogens in 4.1%). Parainfluenza virus and Mycoplasma pneumoniae were significantly more frequent in outpatients. The proportion of patients with antibiotic therapy was comparably high in both groups (92.4% of outpatients versus 86.2% of hospitalised patients).

Conclusion

We present first data on paediatric CAP with comprehensive analyses in outpatients and hospitalised cases and demonstrate high detection rates of viral pathogens in both groups. Particularly in young paediatric CAP patients with outpatient care, antibiotic therapy needs to be critically debated.

A machine learning approach on chest X-rays for pediatric pneumonia detection

Background

According to the World Health Organization (WHO), pneumonia is the leading infectious cause of death in children below 5 years old. Hence, the early detection of pediatric pneumonia is crucial to reduce its morbidity and mortality rates. Even though chest radiography is the most commonly employed modality for pneumonia detection, recent studies highlight the existence of poor interobserver agreement in the chest X-ray interpretation of healthcare practitioners when it comes to diagnosing pediatric pneumonia. Thus, there is a significant need for automating the detection process to minimize the potential human error. Since Artificial Intelligence tools such as Deep Learning (DL) and Machine Learning (ML) have the potential to automate disease detection, many researchers explored how such tools can be implemented to detect pneumonia in chest X-rays. Notably, the majority of efforts tackled this problem from a DL point of view. However, ML has shown a higher potential for medical interpretability while being less computationally demanding than DL.

Objective

The aim of this paper is to automate the early detection process of pediatric pneumonia using ML as it is less computationally demanding than DL.

Methods

The proposed approach entails performing data augmentation to balance the classes of the utilized dataset, optimizing the feature extraction scheme, and evaluating the performance of several ML models. Moreover, the performance of this approach is compared to a TL benchmark to evaluate its candidacy.

Results

Using the proposed approach, the Quadratic SVM model yielded an accuracy of 97.58%, surpassing the accuracies reported in the current ML literature. In addition, this model classification time was significantly smaller than that of the TL benchmark.

Conclusion

The results strongly support the candidacy of the proposed approach in reliably detecting pediatric pneumonia.