NOMIS researcher Luregn Schlapbach and colleagues have developed a machine learning model to predict poor school outcomes in children surviving the intensive care unit (ICU). Their findings were published in Intensive Care Medicine.
Progress in the field of paediatric intensive care over the past decades has led to a reduction of in-hospital mortality to as little as 2.5% even for complex conditions such as congenital heart disease or cancer. However, critical illness during childhood occurs at a vulnerable period of brain development, and neurological injury may result from disease, complications or treatment-related mechanisms, for example inadequate cerebral oxygen supply during shock or drug-related toxicity. Families of critically ill children, clinicians, and researchers consider survival with good long-term neurodevelopment as a priority for care, benchmarking, and research. The ability of a child to meet minimum requirements in primary or secondary school represents a desirable outcome from the family, healthcare provider and societal perspectives and translates into a high chance to ultimately learn a profession, earn an income and lead an independent life in adulthood. Yet, most paediatric intensive care unit (PICU) survivors are not offered follow-up beyond hospital discharge due to lack of long-term follow-up resources. Currently, there are no models available enabling the prediction of long-term neurodevelopmental outcomes which permit risk stratification to target post-discharge rehabilitation measures for children most likely to benefit. Machine learning approaches to make unbiased use of large datasets carry great promise to improve prediction of complex outcomes in heterogeneous populations.
Abstract
Purpose: Whilst survival in paediatric critical care has improved, clinicians lack tools capable of predicting long-term outcomes. We developed a machine learning model to predict poor school outcomes in children surviving intensive care unit (ICU).
Methods: Population-based study of children < 16 years requiring ICU admission in Queensland, Australia, between 1997 and 2019. Failure to meet the National Minimum Standard (NMS) in the National Assessment Program-Literacy and Numeracy (NAPLAN) assessment during primary and secondary school was the primary outcome. Routine ICU information was used to train machine learning classifiers. Models were trained, validated and tested using stratified nested cross-validation.
Results: 13,957 childhood ICU survivors with 37,200 corresponding NAPLAN tests after a median follow-up duration of 6 years were included. 14.7%, 17%, 15.6% and 16.6% failed to meet NMS in school grades 3, 5, 7 and 9. The model demonstrated an Area Under the Receiver Operating Characteristic curve (AUROC) of 0.8 (standard deviation SD, 0.01), with 51% specificity to reach 85% sensitivity [relative Area Under the Precision Recall Curve (rel-AUPRC) 3.42, SD 0.06]. Socio-economic status, illness severity, and neurological, congenital, and genetic disorders contributed most to the predictions. In children with no comorbidities admitted between 2009 and 2019, the model achieved a AUROC of 0.77 (SD 0.03) and a rel-AUPRC of 3.31 (SD 0.42).
Conclusions: A machine learning model using data available at time of ICU discharge predicted failure to meet minimum educational requirements at school age. Implementation of this prediction tool could assist in prioritizing patients for follow-up and targeting of rehabilitative measures.
Read the Intensive Care Medicine publication: Machine learning to predict poor school performance in paediatric survivors of intensive care: a population-based cohort study
