Predicting age at onset of type 1 diabetes in children using regression, artificial neural network and Random Forest: A case study in Saudi Arabia.

The rising incidence of type 1 diabetes (T1D) among children is an increasing concern globally. A reliable estimate of the age at onset of T1D in children would facilitate intervention plans for medical practitioners to reduce the problems with delayed diagnosis of T1D. This paper has utilised Multiple Linear Regression (MLR), Artificial Neural Network (ANN) and Random Forest (RF) to model and predict the age at onset of T1D in children in Saudi Arabia (S.A.) which is ranked as the 7th for the highest number of T1D and 5th in the world for the incidence rate of T1D. De-identified data between (2010-2020) from three cities in S.A. were used to model and predict the age at onset of T1D. The best subset model selection criteria, coefficient of determination, and diagnostic tests were deployed to select the most significant variables. The efficacy of models for predicting the age at onset was assessed using multi-prediction accuracy measures. The average age at onset of T1D is 6.2 years and the most common age group for onset is (5-9) years. Most of the children in the sample (68%) are from urban areas of S.A., 75% were delivered after a full term pregnancy length and 31% were delivered through a cesarean section. The models of best fit were the MLR and RF models with R2 = (0.85 and 0.95), the root mean square error = (0.25 and 0.15) and mean absolute error = (0.19 and 0.11) respectively for logarithm of age at onset. This study for the first time has utilised MLR, ANN and RF models to predict the age at onset of T1D in children in S.A. These models can effectively aid health care providers to monitor and create intervention strategies to reduce the impact of T1D in children in S.A.

Adipsic Diabetes Insipidus in Children: A Case Report and Practical Guide.

BACKGROUND Diabetes insipidus (DI) is a clinical syndrome characterized by polyuria and polydipsia that result from a deficiency of antidiuretic hormone (ADH), central DI, or resistance to ADH, nephrogenic DI. In otherwise healthy patients with DI, normal thirst mechanism, and free access to water, the thirst system can maintain plasma osmolality in the near-normal range. However, in cases where DI presents with adipsia, cognitive impairment, or restricted access to water, true hypernatremia may occur, leading to severe morbidity and mortality. CASE REPORT We report a case of a 2-year-old boy who had global developmental delay and post-brain debulking surgery involving the hypothalamic region, which resulted in central DI and thirst center dysfunction. We describe the clinical presentation, the current understanding of adipsic DI, and a new practical approach for management. The main guidelines of treatment include (1) fixed desmopressin dosing that allows minimal urinary breakthroughs in-between the doses; (2) timely diaper weight-based replacement of water; (3) bodyweight-based fluid correction 2 times a day, and (4) providing the nutritional and water requirements in a way similar to any healthy child but at fixed time intervals. CONCLUSIONS This plan of management showed good effectiveness in controlling plasma sodium level and volume status of a child with adipsic DI without interfering with his average growth. This home treatment method is practical and readily available, provided that the family remains very adherent.

Mean glycosylated hemoglobin in children with type 1 diabetes at King Fahad Medical City, Riyadh, Saudi Arabia.

BACKGROUND: Type 1 diabetes is the third most common chronic disease among teenagers. In Saudi Arabia, there is a gap of knowledge regarding hemoglobin A1C (HbA1c) concentration levels, and adherence to regular follow-up visits by patients. The aim of this study was to determine the mean glycosylated hemoglobin (HbA1c) levels in diabetic children who have been diagnosed with type 1 diabetes and were being followed up at a tertiary care center in Saudi Arabia. MATERIALS AND METHODS: This cross-sectional study was conducted among all diabetic children treated at King Fahad Medical City (KFMC) in Riyadh, Saudi Arabia. Data were retrieved and analysed during the period from September to December 2018. Diabetic patients of <18 years and who were being followed up at KFMC were included in the study. Data on age, sex, duration of illness, associated comorbidities, antidiabetic regimen, and HbA1c levels were obtained. Student t-test was used to compare quantitative parameters between two groups, and Chi-square employed to test for associations between categorical variables at 5% significance level. RESULTS: A total of 510 patients of were included in the study; about 53% were females. The mean HbA1c level was 10.6% and females showed higher HbA1c levels. Data showed a strong correlation between age and HbA1c levels (P < 0.001), with older patients showing higher HbA1c levels. The HbA1c levels also increased as the duration of disease increased. The median number of patient visits to KFMC was two per year. No statistically significant differences were observeed for type of treatment for diabetes. Celiac disease, the most frequent comorbidity, was seen in 50% of patients. CONCLUSION: Diabetic children who were followed up at KFMC had high HbA1C level (10.6%), and lower than recommended follow-up visits per year. The treating physicians should educate patients and their legal guardians on the importance of follow-up visits and their role in controlling HbA1C levels, and following healthier lifestyle.