Quantitative EEG parameters can improve the predictive value of the non-traumatic neurological ICU patient prognosis through the machine learning method

Abstract

BackgroundBetter outcome prediction could assist in reliable classification of the illnesses in neurological intensive care unit (ICU) severity to support clinical decision-making. We developed a multifactorial model including quantitative electroencephalography (QEEG) parameters for outcome prediction of patients in neurological ICU.MethodsWe retrospectively analyzed neurological ICU patients from November 2018 to November 2021. We used 3-month mortality as the outcome. Prediction models were created using a linear discriminant analysis (LDA) based on QEEG parameters, APACHEII score, and clinically relevant features. Additionally, we compared our best models with APACHEII score and Glasgow Coma Scale (GCS). The DeLong test was carried out to compare the ROC curves in different models.ResultsA total of 110 patients were included and divided into a training set (n=80) and a validation set (n = 30). The best performing model had an AUC of 0.85 in the training set and an AUC of 0.82 in the validation set, which were better than that of GCS (training set 0.64, validation set 0.61). Models in which we selected only the 4 best QEEG parameters had an AUC of 0.77 in the training set and an AUC of 0.71 in the validation set, which were similar to that of APACHEII (training set 0.75, validation set 0.73). The models also identified the relative importance of each feature.ConclusionMultifactorial machine learning models using QEEG parameters, clinical data, and APACHEII score have a better potential to predict 3-month mortality in non-traumatic patients in neurological ICU.

Neuromonitoring of Pediatric and Adult Extracorporeal Membrane Oxygenation Patients: The Importance of Continuous Bedside Tools in Driving Neuroprotective Clinical Care

“…These tools may readily be integrated with EEG including quantitative EEG with automated detection, to improve the capability for dynamic assessment of the neurovascular unit and for real-time detection of critical neurologic events as this will provide opportunities for interventions to prevent permanent neurologic injury. 95,99…”

“…These tools may readily be integrated with EEG including quantitative EEG with automated detection, to improve the capability for dynamic assessment of the neurovascular unit and for real-time detection of critical neurologic events as this will provide opportunities for interventions to prevent permanent neurologic injury. 95,99 Additional research is needed to study the development and integration of continuous neurologic monitoring methods with the goal of assisting clinicians in stratifying patients into risk categories for brain injury, determining response to neuroprotective interventions, and providing accurate prognostication of long-term outcomes. 96…”