Clinical signs and early prognosis in vegetative state: A decisional tree, data-mining study

Abstract

Re-appearance with proper timing of spontaneous motility, eye tracking and oculo-cephalic reflex and disappearance of oral automatisms proved highly correlated to outcome and allowed early and reliable prognosis. These findings are consistent with the brain functional organization thought to sustain consciousness and warrant systematic investigation. Classification and regression trees and data-mining procedures proved applicable in neurology to sort out significant clinical signs also in clinical conditions characterized by paucity of signs such as the vegetative state. Extended application in clinical medicine is conceivable based on the approach peculiarities.

From unresponsive wakefulness to minimally conscious PLUS and functional locked-in syndromes: recent advances in our understanding of disorders of consciousness

“…Since its formal definition nearly 10 years ago [9], a number of authors have questioned the usefulness of differentiating vegetative/unresponsive from minimally responsive patients considering both patient groups as hopelessly brain damaged [24]. Recent studies have demonstrated that it is important to disentangle both clinical entities as functional neuroimaging have shown differences in residual cerebral processing and hence, conscious perception (e.g., [20,[25][26][27]), as well as differences in outcome (e.g., [28,29]). …”

Data Mining in Neurology

“…Aim of studies was to identify the clinical signs observed by the medical staff at the admission and after 50, 100, and 180 days to be used as markers of good or poor outcome. A model (Figure 1) based on CART algorithm proved reliable in predicting the outcome after identifying a limited set of significant clinical signs and the timing of observation (Dolce et al, 2008a). Performance as evaluated through cross-validation techniques ranged from 74% to 83% depending on the follow-up time point.…”

“…It was concluded that these Data Mining approaches are comparable, without any indication as to clinical usefulness being given. Early prognosis is necessary for subjects in a vegetative state (a condition of severe impairment of consciousness requiring continuous care); the issue was approached via Decision Tree (Dolce et al, 2008a) and Artificial Neural Networks ) in studies analyzing the appearance/disappearance of twenty-two relevant clinical signs with respect to outcome in three hundred and thirty-three subjects in a vegetative state, whose outcome was rated according to the Glasgow Outcome Scale. Aim of studies was to identify the clinical signs observed by the medical staff at the admission and after 50, 100, and 180 days to be used as markers of good or poor outcome.…”

Mechanisms that Regulate Recovery of Consciousness in Patients in Vegetative State/Unresponsive Wakefulness Syndrome: A New Model

“…class 2 and the other half in class 1 (death). [9,10]. These are the reasons that prompted us into thinking that spontaneous motility is the fourth major system that regulates that particular functional state of the brain that enables wakefulness.…”