Background: The rapid development in big data analytics and the data-rich environment of intensive care units\ntogether provide unprecedented opportunities for medical breakthroughs in the field of critical care. We developed\nand validated a machine learning-based model, the Pediatric Risk of Mortality Prediction Tool (PROMPT), for realtime\nprediction of all-cause mortality in pediatric intensive care units.\nMethods: Utilizing two separate retrospective observational cohorts, we conducted model development and\nvalidation using a machine learning algorithm with a convolutional neural network. The development cohort\ncomprised 1445 pediatric patients with 1977 medical encounters admitted to intensive care units from January\n2011 to December 2017 at Severance Hospital (Seoul, Korea). The validation cohort included 278 patients with 364\nmedical encounters admitted to the pediatric intensive care unit from January 2016 to November 2017 at Samsung\nMedical Center.\nResults: Using seven vital signs, along with patient age and body weight on intensive care unit admission, PROMPT\nachieved an area under the receiver operating characteristic curve in the range of 0.89-0.97 for mortality prediction\n6 to 60 h prior to death. Our results demonstrated that PROMPT provided high sensitivity with specificity and\noutperformed the conventional severity scoring system, the Pediatric Index of Mortality, in predictive ability. Model\nperformance was indistinguishable between the development and validation cohorts.\nConclusions: PROMPT is a deep model-based, data-driven early warning score tool that can predict mortality in\ncritically ill children and may be useful for the timely identification of deteriorating patients.
Loading....