Bmc Med
-
Multicenter Study
A deep learning model for differentiating paediatric intracranial germ cell tumour subtypes and predicting survival with MRI: a multicentre prospective study.
The pretherapeutic differentiation of subtypes of primary intracranial germ cell tumours (iGCTs), including germinomas (GEs) and nongerminomatous germ cell tumours (NGGCTs), is essential for clinical practice because of distinct treatment strategies and prognostic profiles of these diseases. This study aimed to develop a deep learning model, iGNet, to assist in the differentiation and prognostication of iGCT subtypes by employing pretherapeutic MR T2-weighted imaging. ⋯ By leveraging pretherapeutic MR imaging data, iGNet accurately differentiates iGCT subtypes, facilitating prognostic evaluation and increasing the potential for tailored treatment.
-
Multicenter Study Observational Study
Development and validation of machine-learning models of diet management for hyperphenylalaninemia: a multicenter retrospective study.
Assessing dietary phenylalanine (Phe) tolerance is crucial for managing hyperphenylalaninemia (HPA) in children. However, traditionally, adjusting the diet requires significant time from clinicians and parents. This study aims to investigate the development of a machine-learning model that predicts a range of dietary Phe intake tolerance for children with HPA over 10 years following diagnosis. ⋯ Our model integrates metabolic and genetic information to accurately predict age-specific Phe tolerance, aiding in the precision management of patients with HPA. This study provides a potential framework that could be applied to other inborn errors of metabolism.
-
Uncertainty remains about the long-term effects of air pollutants (AP) on multiple diseases, especially subtypes of cardiovascular disease (CVD). We aimed to assess the individual and joint associations of fine particulate matter (PM2.5), along with its chemical components, nitrogen dioxide (NO2) and ozone (O3), with risks of 32 health conditions. ⋯ Long-term exposure to increased levels of multiple air pollutants was associated with risks of multiple health conditions. OM accounted for substantial weight for these increased risks, suggesting it may play an important role in these associations.
-
Ongoing conflict between multiple armed groups, including pastoralist herders in the Central African Republic (CAR) causes frequent population displacements, food insecurity and scarcity of healthcare services. The inaccessibility and insecurity of many areas of CAR limit data collection and assessments from national nutritional surveys. Community health workers (CHWs) trained by an international non-governmental organisation, The MENTOR Initiative, deliver basic healthcare to children under 5 years old living in hard-to-reach and conflict-affected areas in eight subprefectures of north-west CAR. Their nutritional status and its associations with geography, malaria, season and conflict are unknown. ⋯ This analysis shows geographical differences in levels of malnutrition in north-west CAR and demonstrates clear associations between malnutrition, season and malaria. It provides evidence that levels of GAM may be underestimated in north-west CAR in areas experiencing conflict. These findings highlight the need for targeted nutritional support to reach children most at risk of malnutrition. CHWs are a proven effective means of delivering essential primary healthcare services in hard-to-reach, conflict-affected areas.
-
Helicobacter pylori colonizes the human stomach and may affect the inflammatory response, hormone production related to energy regulation, and gastrointestinal microbiota composition. Previous studies have explored a potential association between H. pylori infection and pediatric obesity with varying results. Considering the immunomodulatory effects of early-life infection with H. pylori that can confer beneficial effects, we hypothesized that we would find an inverse relationship between H. pylori seropositivity and obesity among Danish children and adolescents. ⋯ While we did not find an association between H. pylori seropositivity and BMI SDS, we observed a significant association with higher fasting plasma glucose levels and increased prevalence of hyperglycemia, suggesting that H. pylori infection may contribute to impaired glucose regulation in Danish children and adolescents.