Machine learning to predict poor school performance in paediatric survivors of intensive care: a population-based cohort study

• Published in: Intensive care medicine Vol. 49; no. 7; pp. 785 - 795
• Main Authors: Gilholm, Patricia, Gibbons, Kristen, Brüningk, Sarah, Klatt, Juliane, Vaithianathan, Rhema, Long, Debbie, Millar, Johnny, Tomaszewski, Wojtek, Schlapbach, Luregn J.
• Format: Journal Article
• Language: English
• Published: Berlin/Heidelberg Springer Berlin Heidelberg 01.07.2023; Springer; Springer Nature B.V
• Subjects: Academic failure; Analysis; Anesthesiology; Child; Children; Cohort analysis; Cohort Studies; Comorbidity; Critical Care; Critical Care Medicine; Emergency Medicine; Genetic disorders; High schools; Hospital patients; Hospitalization; Humans; Intensive; Intensive care; Intensive Care Units; Learning algorithms; Literacy programs; Machine Learning; Medicine; Medicine & Public Health; Neurological diseases; Neurological disorders; Numeracy; Original; Pain Medicine; Pediatric intensive care; Pediatrics; Pneumology/Respiratory System; Population studies; Population-based studies; Prognosis; Retrospective Studies; Risk factors; Socioeconomics; Survival; Survivor; Australia; Neurodevelopment; Intensive care; School; Child; Machine learning
• ISSN: 0342-4642; 1432-1238; 1432-1238
• DOI: 10.1007/s00134-023-07137-1

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.