Assessing the performance and clinical impact of a computerized prognostic system in severe head injury

Abstract

The ability to predict outcome in the early stages of severe head injury would have several uses. A computerized system which has been developed in Glasgow to assist clinicians in this task, based on information from over 2500 severely head-injured patients, is described, with particular attention to the testing of the statistical properties of the system, and, more importantly, the assessment of its clinical impact.

Early Glasgow Outcome Scale Scores Predict Long-Term Functional Outcome in Patients with Severe Traumatic Brain Injury

“…The authors used logistic regression to examine the association between 6-month GOS outcomes and 3-month GOS and patient characteristics, and they were unable to document any statistically significant independent predictive value of patient characteristics (age, intracranial diagnosis, GCS score, hematoma location, papillary response) on 6-month GOS outcomes. The Glasgow Head Injury Outcomes Prediction Program was developed to predict long-term TBI outcomes based on early clinical data (Murray et al, 1986). The program used a Bayesian algorithm to predict outcomes using numerous variables, including age, GCS, papillary response, CT findings, clinical course, and exam findings.…”

Severe head injury and the risk of early death

“…The fact that patients in our study were in a coma for the first 6 h and it was possible to carry out a computed tomography scan in that time defines a minimum and a maximum level of severity, thus making the group that we studied well defined and relatively homogeneous. 12 Another reason to choose the interval of 6 h was that many of the trials carried out for SHI to date have generally used a therapeutic window of at least 8 h after trauma. 1 The patients included in clinical trials for SHI are heterogeneous.…”

Analysis of Clinico-Radiological Factors and Their Effectiveness in Prognostication of Traumatic Brain Injury- A Prospective Study Conducted at a Tertiary Care Hospital

“…Prediction of an uncertain outcome may also be useful in preventing an overconfident clinical decision. [18]…”