Cushing response-based warning system for intensive care of brain-injured patients.

Objective: Cushing response (CR) is categorized. Wavelet transform (WT) and decision tree (DT) are utilized to analyze physiological signals from neurocritical patients. A warning model is built for recognition of CR, real-time evaluation of intracranial condition and prediction of neurological outcome.

Methods: Physiological signals of neurocritical patients are preprocessed by WT and compressed by linear regression. An algorithm labels each segment as pathological, physiological, negative or uncertain CR. The DT identifies CR. Continuous data input to the established DT predicts condition at that moment and following outcome.

Results: From 33 neurocritical patients, 422,524 sets of physiological signals were collected. The cross-validation scores of DT ranged from 0.562 to 0.579 with averaged accuracy rate 60.6% (3.5-98.1%). The model correctly predicted the outcome of the training group, 87.9% in accuracy. The ratios of pathological CR were 9.3 ± 16.6%, 74.2 ± 29.7% and 99.7 ± 0.3% in patients of good, coma and death groups, respectively. The prediction accuracy for a test set of 103 patients reached 81.6%.

Conclusions: Cushing response categorization helps in identifying critical conditions and predicting outcome.

Significance: A novel concept of four categories of Cushing response is proposed to represent broader ranges of intracranial change.