Intelligent systems for the prediction of Brain Death Index

Abstract

New techniques to enable the prediction of a reliable brain death index (BDI) measures are needed to improve patient care in the intensive care unit (ICU). The utilization of robust indicators combined with improved methods of data analysis and modeling is likely to deliver this facility. Like many forms of indicators, a combination of different measurement types can always improve the assessment accuracy. Doctors can manage by a combination of local indicators and signal of heart rhythm to decide the BDI of neurosurgical and traumatized patients. New techniques for the prediction are needed as statistical analysis has a poor accuracy and is not applicable to the individual. artificial intelligence (AI) may provide these suitable methods. Artificial neural networks (ANN), the best-studied form of AI, has been used successfully, and can be used to model the patient BDI based on multi-input measurements from the patient. A multi-layer perception (MLP) and ensembled neural networks are chosen to be the network type of BDI model. This model can provide medical staffs a reference index to evaluate the status of IAC and brain death patients.