Multiview child motor development dataset for AI-driven assessment of child development.

BACKGROUND: Children's motor development is a crucial tool for assessing developmental levels, identifying developmental disorders early, and taking appropriate action. Although the Korean Developmental Screening Test for Infants and Children (K-DST) can accurately assess childhood development, its dependence on parental surveys rather than reliable, professional observation limits it. This study constructed a dataset based on a skeleton of recordings of K-DST behaviors in children aged between 20 and 71 months, with and without developmental disorders. The dataset was validated using a child behavior artificial intelligence (AI) learning model to highlight its possibilities. RESULTS: The 339 participating children were divided into 3 groups by age. We collected videos of 4 behaviors by age group from 3 different angles and extracted skeletons from them. The raw data were used to annotate labels for each image, denoting whether each child performed the behavior properly. Behaviors were selected from the K-DST's gross motor section. The number of images collected differed by age group. The original dataset underwent additional processing to improve its quality. Finally, we confirmed that our dataset can be used in the AI model with 93.94%, 87.50%, and 96.31% test accuracy for the 3 age groups in an action recognition model. Additionally, the models trained with data including multiple views showed the best performance. CONCLUSION: Ours is the first publicly available dataset that constitutes skeleton-based action recognition in young children according to the standardized criteria (K-DST). This dataset will enable the development of various models for developmental tests and screenings.

Initial base deficit as predictors for mortality and transfusion requirement in the severe pediatric trauma except brain injury.

OBJECTIVE: The initial base deficit (BD) is an important indicator of shock in adult trauma patients, but its value is unclear in pediatric trauma patients. This study assessed the ability of the initial BD to predict mortality and blood transfusion requirements in children except severe brain injury patients. METHODS: This study was a retrospective review of pediatric patients with severe trauma arriving at the emergency department of a university hospital from January 1998 to June 2005. Blood pressure, the initial BD, and the Injury Severity Score were assessed as independent predictors of mortality and the blood transfusion requirement using multiple regression analysis. RESULTS: The study group constituted 102 patients. According to the multiple regression analysis results, the initial systolic blood pressure, Injury Severity Score, and blood transfusion requirement were not independent predictors of mortality (P = 0.104, 0.959, 0.386, respectively). By contrast, the initial BD was an independent predictor, with an odds ratio of 13.6 for BD of -8 mEq/L or less (confidence interval [CI], 3.51-35.23, P = 0.037), and systolic blood pressure and BD were independent predictors of blood transfusion requirement; the odds ratio for hypotension was 3.2 (CI, 0.51-8.32, P = 0.044), and the odds ratio was 15.3 for BD values of -8 or less (CI, 2.24-51.43, P = 0.003). CONCLUSION: The initial BD in pediatric trauma patients except severe brain injury was an independent predictor of mortality and blood transfusion requirement within 24 hours. Mortality and blood transfusion requirement were significantly high when initial BD was less than -8 mEq/L.

A case of hemoperfusion and L-carnitine management in valproic acid overdose.

Valproic acid (VPA) is used to manage a variety of conditions, including simple and complex absence seizure disorder, bipolar disorder, and migraine prophylaxis. The clinical manifestations of VPA overdose range in severity from mild confusion and lethargy to severe coma and death. The treatment of VPA toxicity is mainly supportive. There is no specific antidote or guidelines for managing VPA intoxication. Anecdotal reports describe the efficacy of naloxone and L-carnitine, but the data are insufficient to make strong conclusions. Various extracorporeal techniques for managing VPA toxicity have been described, but none has prevailed as standard therapy. We report a patient with VPA overdose who was treated successfully with hemoperfusion with activated charcoal and L-carnitine. The VPA level of the patient exceeded 1000 microg/mL and was normalized after 3 rounds of hemoperfusion. The patient was injected with L-carnitine at a maximum of 600 mg/kg per day for 5 days without complications.