Characteristic or classic phenotype of Cornelia de Lange syndrome (CdLS) is associated with a recognisable facial pattern. However, the heterogeneity in causal genes and the presence of overlapping syndromes have made it increasingly difficult to diagnose only by clinical features. DeepGestalt technology, and its app Face2Gene, is having a growing impact on the diagnosis and management of genetic diseases by analysing the features of affected individuals. Here, we performed a phenotypic study on a cohort of 49 individuals harbouring causative variants in known CdLS genes in order to evaluate Face2Gene utility and sensitivity in the clinical diagnosis of CdLS. Based on the profile images of patients, a diagnosis of CdLS was within the top five predicted syndromes for 97.9% of our cases and even listed as first prediction for 83.7%. The age of patients did not seem to affect the prediction accuracy, whereas our results indicate a correlation between the clinical score and affected genes. Furthermore, each gene presents a different pattern recognition that may be used to develop new neural networks with the goal of separating different genetic subtypes in CdLS. Overall, we conclude that computer-assisted image analysis based on deep learning could support the clinical diagnosis of CdLS.

Oxidative stress could help explain the relationship between childhood obesity and a metabolically unhealthy (MU) status. Moreover, puberty could also influence this relationship, since it entails physiological cardiometabolic changes. We aimed to evaluate plasma antioxidants and oxidative stress biomarkers in MU and metabolically healthy (MH) prepubertal and pubertal children and their associations with pro-inflammatory and endothelial damage biomarkers, taking puberty into account. A total of 1444 Spanish children aged 3–17 years (48.9% males, 66% prepubertal, 47.1% with obesity) were recruited. Blood pressure, anthropometric and biochemical parameters were measured, and children were categorized as having a MU or MH status according to risk factors. Retinol, carotenes, tocopherols, total antioxidant capacity (TAC), oxidized low-density lipoprotein and selected pro-inflammatory and endothelial damage biomarkers were analyzed. General linear models adjusted for age, sex, recruitment center and body mass index, partial correlations and stepwise linear regressions were performed. Lower carotenes and tocopherols levels were found in MU than in MH children. Plasma TAC was lower in prepubertal and higher in pubertal children with obesity compared to normal-weight children. Antioxidants and oxidative stress biomarkers showed novel associations with several pro-inflammatory and endothelial damage biomarkers, with pubertal differences, supporting the importance of considering both the antioxidant and oxidative stress status and puberty in the prevention of metabolic diseases in childhood.

Sedentary habits during childhood are associated with adverse health outcomes. The aim of this work was to cluster lifestyle behaviors and metabolic biomarkers to establish different patterns in children. Their physical and sedentary activities were evaluated by accelerometry, and questionnaires that included lifestyle behaviors, such as adherence to a Mediterranean diet, anthropometry and blood biochemical markers. Cluster analysis was performed to establish different groups based on physical activity levels. A total of 489 children were finally selected. Cluster 1 included children with a mostly sedentary state, whereas Cluster 3 included the most active children and Cluster 2 included children that did not fit into either the sedentary or the highly active groups. In Cluster 3, 56% of children were in a sports club, and a lower percentage used electronic devices in their rooms compared to the other groups. Cluster 1 children exhibited higher insulin, HOMA-IR and triacylglycerides with respect to the other groups. No differences were found regarding adherence to a Mediterranean diet. The choice to practice an extracurricular sport could be an influencing factor to increase exercise and ensure an active lifestyle in children. Reducing or limiting screen time mainly in children’s rooms could contribute to an active lifestyle.

There are three human enzymes with HMG-CoA lyase activity that are able to synthesize ketone bodies in different subcellular compartments. The mitochondrial HMG-CoA lyase was the first to be described, and catalyzes the cleavage of 3-hydroxy-3-methylglutaryl CoA to acetoacetate and acetyl-CoA, the common final step in ketogenesis and leucine catabolism. This protein is mainly expressed in the liver and its function is metabolic, since it produces ketone bodies as energetic fuels when glucose levels are low. Another isoform is encoded by the same gene for the mitochondrial HMG-CoA lyase (HMGCL), but it is located in peroxisomes. The last HMG-CoA lyase to be described is encoded by a different gene, HMGCLL1, and is located in the cytosolic side of the endoplasmic reticulum membrane. Some activity assays and tissue distribution of this enzyme have shown the brain and lung as key tissues for studying its function. Although the roles of the peroxisomal and cytosolic HMG-CoA lyases remain unknown, recent studies highlight the role of ketone bodies in metabolic remodeling, homeostasis, and signaling, providing new insights into the molecular and cellular function of these enzymes.

Pediatric obesity can drastically heighten the risk of cardiometabolic alterations later in life, with insulin resistance standing as the cornerstone linking adiposity to the increased cardiovascular risk. Puberty has been pointed out as a critical stage after which obesity-associated insulin resistance is more difficult to revert. Timely prediction of insulin resistance in pediatric obesity is therefore vital for mitigating the risk of its associated comorbidities. The construction of effective and robust predictive systems for a complex health outcome like insulin resistance during the early stages of life demands the adoption of longitudinal designs for more causal inferences, and the integration of factors of varying nature involved in its onset. In this work, we propose an eXplainable Artificial Intelligence-based decision support pipeline for early diagnosis of insulin resistance in a longitudinal cohort of 90 children. For that, we leverage multi-omics (genomics and epigenomics) and clinical data from the pre-pubertal stage. Different data layers combinations, pre-processing techniques (missing values, feature selection, class imbalance, etc.), algorithms, training procedures were considered following good practices for Machine Learning. SHapley Additive exPlanations were provided for specialists to understand both the decision-making mechanisms of the system and the impact of the features on each automatic decision, an essential issue in high-risk areas such as this one where system decisions may affect people's lives. The system showed a relevant predictive ability (AUC and G-mean of 0.92). A deep exploration, both at the global and the local level, revealed promising biomarkers of insulin resistance in our population, highlighting classical markers, such as Body Mass Index z-score or leptin/adiponectin ratio, and novel ones such as methylation patterns of relevant genes, such as HDAC4, PTPRN2, MATN2, RASGRF1 and EBF1. Our findings highlight the importance of integrating multi-omics data and following eXplainable Artificial Intelligence trends when building decision support systems.

Obesity and cardiometabolic risk have been associated with vitamin D levels even in children. The objective of the present study was to evaluate the association between insulin resistance (IR), cardiometabolic risk factors, and vitamin D in children from prepubertal to pubertal stages. A total of 76 children from the PUBMEP study, aged 4–12 years at baseline, were included. Children were evaluated in prepubertal and pubertal stages. Anthropometric measurements and selected cardiometabolic risk biomarkers, such as plasma glucose, blood lipids, insulin, adiponectin, leptin, and blood pressure, and serum 25-hydroxyvitamin D (25(OH)D) were determined. Children were categorized by obesity degree and IR status combined before and after puberty. Paired t-test and multivariate linear regression analyses were conducted. During puberty, the increase in triacylglycerols, insulin, and HOMA-IR and the decrease in QUICKI were significantly associated with the reduction in 25(OH)D (B = −0.274, p = 0.032; B = −0.219, p = 0.019; B = −0.250, p = 0.013; B = 1.574, p = 0.013, respectively) after adjustment by BMI-z, sex, and pubertal stage. Otherwise, prepubertal non-IR children with overweight/obesity that became IR during puberty showed a significant decrease in 25(OH)D and HDL-c, and an increase in waist circumference and triacylglycerol concentrations (p < 0.05 for all) over time. These results suggest that changes in IR seem to be associated with an effect on 25(OH)D levels during puberty, especially in children with overweight.