Search

Introduction Treatment in the intensive care unit (ICU) generates complex data where machine learning (ML) modelling could be beneficial. Using routine hospital data, we evaluated the ability of multiple ML models to predict inpatient mortality in a paediatric population in a low/middle-income country.Method We retrospectively analysed hospital record data from 0-59 months old children admitted to the ICU of Dhaka hospital of International Centre for Diarrhoeal Disease Research, Bangladesh. Five commonly used ML models- logistic regression, least absolute shrinkage and selection operator, elastic net, gradient boosting trees (GBT) and random forest (RF), were evaluated using the area under the receiver operating characteristic curve (AUROC). Top predictors were selected using RF mean decrease Gini scores as the feature importance values.Results Data from 5669 children was used and was reduced to 3505 patients (10% death, 90% survived) following missing data removal. The mean patient age was 10.8 months (SD=10.5). The top performing models based on the validation performance measured by mean 10-fold cross-validation AUROC on the training data set were RF and GBT. Hyperparameters were selected using cross-validation and then tested in an unseen test set. The models developed used demographic, anthropometric, clinical, biochemistry and haematological data for mortality prediction. We found RF consistently outperformed GBT and predicted the mortality with AUROC of ≥0.87 in the test set when three or more laboratory measurements were included. However, after the inclusion of a fourth laboratory measurement, very minor predictive gains (AUROC 0.87 vs 0.88) resulted. The best predictors were the biochemistry and haematological measurements, with the top predictors being total CO2, potassium, creatinine and total calcium.Conclusions Mortality in children admitted to ICU can be predicted with high accuracy using RF ML models in a real-life data set using multiple laboratory measurements with the most important features primarily coming from patient biochemistry and haematology.

Objectives This study evaluated the prevalence and correlates of guideline non-adherence for common childhood illnesses in low-resource settings.Design and setting We used secondary cross-sectional data from eight healthcare facilities in six Asian and African countries.Participants A total of 2796 children aged 2–23 months hospitalised between November 2016 and January 2019 with pneumonia, diarrhoea or severe malnutrition (SM) and without HIV infection were included in this study.Primary outcome measures We identified children treated with full, partial or non-adherent initial inpatient care according to site-specific standard-of-care guidelines for pneumonia, diarrhoea and SM within the first 24 hours of admission. Correlates of guideline non-adherence were identified using generalised estimating equations.Results Fully adherent care was delivered to 32% of children admitted with diarrhoea, 34% of children with pneumonia and 28% of children with SM when a strict definition of adherence was applied. Non-adherence to recommendations was most common for oxygen and antibiotics for pneumonia; fluid, zinc and antibiotics for diarrhoea; and vitamin A and zinc for SM. Non-adherence varied by site. Pneumonia guideline non-adherence was more likely among patients with severe disease (OR 1.82; 95% CI 1.38, 2.34) compared with non-severe disease. Diarrhoea guideline non-adherence was more likely among lower asset quintile groups (OR 1.16; 95% CI 1.01, 1.35), older children (OR 1.10; 95% CI 1.06, 1.13) and children presenting with wasting (OR 6.44; 95% CI 4.33, 9.57) compared with those with higher assets, younger age and not wasted.Conclusions Non-adherence to paediatric guidelines was common and associated with older age, disease severity, and comorbidities, and lower household economic status. These findings highlight opportunities to improve guidelines by adding clarity to specific recommendations.

Rationale Since the first documentation of skin changes in malnutrition in the early 18th century, various hair and skin changes have been reported in severely malnourished children globally. We aimed to describe the frequency and types of skin conditions in children admitted with acute illness to Queen Elizabeth Central Hospital, Blantyre, Malawi across a spectrum of nutritional status and validate an existing skin assessment tool.Methods Children between 1 week and 23 months of age with acute illness were enrolled and stratified by anthropometry. Standardised photographs were taken, and three dermatologists assessed skin changes and scored each child according to the SCORDoK tool.Results Among 103 children, median age of 12 months, 31 (30%) had severe wasting, 11 (11%) kwashiorkor (nutritional oedema), 20 (19%) had moderate wasting, 41 (40%) had no nutritional wasting and 18 (17%) a positive HIV antibody test. Six (5.8%) of the included patients died. 51 (50%) of children presented with at least one skin change. Pigmentary changes were the most common, observed in 35 (34%), with hair loss and bullae, erosions and desquamation the second most prevalent skin condition. Common diagnoses were congenital dermal melanocytosis, diaper dermatitis, eczema and postinflammatory hyperpigmentation. Severe skin changes like flaky paint dermatosis were rarely identified. Inter-rater variability calculations showed only fair agreement (overall Fleiss’ kappa 0.25) while intrarater variability had a fair-moderate agreement (Cohen’s kappa score of 0.47–0.58).Discussion Skin changes in hospitalised children with an acute illness and stratified according to nutritional status were not as prevalent as historically reported. Dermatological assessment by means of the SKORDoK tool using photographs is less reliable than expected.