Digital image analysis of ultrasound images using machine learning to diagnose pediatric nonalcoholic fatty liver disease.

PURPOSE: Prevalence of nonalcoholic fatty liver disease (NAFLD) in children is rising with the epidemic of childhood obesity. Our objective was to perform digital image analysis (DIA) of ultrasound (US) images of the liver to develop a machine learning (ML) based classification model capable of differentiating NAFLD from healthy liver tissue and compare its performance with pixel intensity-based indices. METHODS: De-identified hepatic US images obtained as part of a cross-sectional study examining pediatric NAFLD prevalence were used to build an image database. Texture features were extracted from a representative region of interest (ROI) selected from US images of subjects with normal liver and subjects with confirmed NAFLD using ImageJ and MAZDA image analysis software. Multiple ML classification algorithms were evaluated. RESULTS: Four-hundred eighty-four ROIs from images in 93 normal subjects and 260 ROIs from images in 39 subjects with NAFLD with 28 texture features extracted from each ROI were used to develop, train, and internally validate the model. An ensembled ML model comprising Support Vector Machine, Neural Net, and Extreme Gradient Boost algorithms was accurate in differentiating NAFLD from normal when tested in an external validation cohort of 211 ROIs from images in 42 children. The texture-based ML model was also superior in predictive accuracy to ML models developed using the intensity-based indices (hepatic-renal index and the hepatic echo-intensity attenuation index). CONCLUSION: ML-based predictive models can accurately classify NAFLD US images from normal liver images with high accuracy using texture analysis features.

Pediatric Cervical Spine Clearance and Immobilization Practice Among Prehospital Emergency Medical Providers: A Statewide Survey.

OBJECTIVES: Pediatric cervical spine injuries are rare but potentially life threatening. Although published guidelines for assessment of such injuries exist, there is less uniformity in its implementation in out-of-hospital settings. Our purpose was to assess the knowledge and practice patterns for pediatric cervical spine immobilization among prehospital emergency medical services (EMS) providers in Arizona. METHODS: A cross-sectional web-based survey was conducted (October-December 2018), using an electronic mailing list of certified EMS providers (ground and air) in Arizona. A 20-question structured web-based survey was developed and deployed. RESULTS: One hundred eight EMS stations were contacted with the survey. Sixty-eight providers responded; majority were emergency medical paramedics (73.1%). Most of the stations surveyed did not have a pediatric trauma center (66.2%). When treating children younger than 3 years, half of the respondents stated they did not know of a specific cervical spine clearance criterion; 59.3% felt that cervical spine immobilization was required "sometimes," and 40.0% were unaware of the state's EMS pediatric cervical spine clearance algorithm; 93.9% of EMS providers felt that an age-based algorithm for cervical spine clearance in children would be useful. CONCLUSIONS: In this statewide survey involving prehospital EMS providers, we found that pediatric cervical spine clearance and immobilization practices, even within a specific geographic location, remain inconsistent.

Superior Mesenteric Vein Thrombosis in a Pediatric Patient: Case Report and Review of the Literature.

ABSTRACT: Patients with inflammatory bowel disease are at increased risk of thromboembolism. There are various sites for thromboembolism including the cerebral, limbs, abdominal vessels, retina, and lungs. Here, we report a case of a 17-year-old patient with a history of Crohn disease presenting with abdominal pain. Upon further evaluation, the patient was found to have mesenteric vein thrombosis, which was discovered on computed tomographic scan. Potential causes, contributing factors, diagnosis, and treatment are discussed here.

Age-Based Characteristics of Pediatric Burn Injuries From Outdoor Recreational Fires.

Accidental burns from outdoor recreational activities, such as campfires, bonfires, ceremonial fires, and firepits, are not uncommon; however, few studies describe the nature of such injuries in children. The objective of this study was to examine the age-based pattern of pediatric burn injuries from outdoor fires. Children and adolescents 0 to 18 years, admitted to the Burn Center between 2008 and 2018 with acute burn injuries from outdoor fires, were included in the current study. Demographic and clinical data were obtained from the burn injury database. Patients were categorized into three age groups: 0 to 5 years, 5 to 10 years, and 10 to 18 years. One hundred and sixty-seven children were included in the data analysis, the mean age of the cohort was 6.4 (SD ± 4.9) years, and the majority (66.5%) were males. More than half (52.1%) were less than 5 years of age, they commonly sustained hand burns and frequently required inpatient burn management. Burn severity varied between age groups, and the mean total burn surface area (TBSA) was significantly higher in adolescents (10.9%). Almost half the injuries (49.7%) resulted from a fall onto a campfire, bonfire, or a firepit. In this study, we found age-specific variation in the mechanism and pattern of burn injuries. Children at least 5 years and adolescents were least common victims of burns due to outdoor fires but suffered from more serious injuries with significantly higher TBSA involvement, longer intensive care unit, and ventilator days. Raising awareness among parents, caregivers, and children about outdoor fire safety is important for the prevention of such injuries.