PubMed Health⌕ Search
Home/Archive/PubMed

PubMed · 10724973

Modelling oculomotor data with decision tree induction.

K Viikki·E Isotalo·M Juhola·I Pyykkö
View original source ↗Export metadata ↓

Abstract

We studied relationships between oculomotor test results and the site of lesion in the data set containing patient cases with operated cerebello-pontine angle tumour, operated hemangioblastoma, infarction of cerebello-brainstem or Meniere's disease and control subjects. Several classification models were generated by decision tree induction to find parameter combinations which are efficient in classification. The studied data were characterised by missing values and scarcity of example cases. This study suggested that decision tree induction can be a useful method even in problematic real world classification tasks. Models generated by decision tree induction and evaluated by an expert physician may give information that is beneficial for research.

Explore related subjects

Brain Stem InfarctionsCerebellar NeoplasmsComputer SimulationDecision TreesDiagnosis, Computer-AssistedDiagnosis, DifferentialHemangioblastomaHumansMeniere DiseaseOcular Motility DisordersJournal Article

Keep this discovery

Explore connections, maps & timelines

BibTeXRIS

K Viikki, E Isotalo, M Juhola, I Pyykkö. 1999. Modelling oculomotor data with decision tree induction.. https://pubmed.ncbi.nlm.nih.gov/10724973/

Cite the original work for its findings. Save a collection to share your selection of sources.

KEEP EXPLORING

Related citations

PubMed2002

[A case of the persistent vegetative state following symmetrical peduncular infarction].

A 64-year-old woman presented with sudden onset of disequilibrium and dysarthria. Two days later she became lethargic and tetraparetic. An emergency MRI disclosed multiple infarctions in the medulla oblongata and pons. An angiogram revealed severe stenosis of the rostral basilar artery. The patient underwent a rapidly progressive course with impaired consciousness and flaccid tetraplegia. MR images 7 days after the onset disclosed a symmetrical midbrain infarction that was localized mainly in the cerebral peduncles, suggesting a distal basilar artery occlusion as the cause of this pathology. Since 4 weeks after the onset the patient was in the persistent vegetative state, which was essentially unchanged during the 1-year follow-up period. Persistent vegetative state is known to be caused by diffuse supratentorial or bilateral thalamic lesions, but in our case the lesions were restricted to the infratentorial area. We speculate a mechanism to cause the persistent vegetative state by partial impairment of the connection to the thalamic ascending system or extrathalamic ascending system, which leads to the dissociation of arousal(preserved in this case) and awareness(impaired in this case) after the ventral midbrain infarction.

Brain Stem Infarctions↗
PubMed2001

Time course of lesion development in patients with acute brain stem infarction and correlation with NIHSS score.

BACKGROUND AND PURPOSE: diffusion weighted magnetic resonance imaging (MRI) is highly sensitive in detecting acute supratentorial cerebral ischemia and Diffusion Weighted Imaging (DWI) lesion size has been shown to correlate strongly with the neurologic deficit in middle cerebral artery territory stroke. However, data concerning infratentorial strokes are rare. We examined the size and evolution of acute brain stem ischemic lesions and their relationship to neurological outcome. METHODS: brain stem infarctions of 11 patients were analyzed. We performed DWI in all patients and in 7/11 patients within 24 h, T2W sequences within the first 2 weeks (10/11 patients) and follow-up MRI (MR2) within 3-9 months (median 4.8 months) later (12/12 patients). Lesion volumes were compared with early and follow-up neurologic deficit as determined by National Institutes of Health Stroke Scale (NIHSS) score. RESULTS: the relative infarct volumes--with MR2 lesion size set to 100%--decreased over the time (P<0.02) with a mean shrinking factor of 3.3 between DWI (MR0) and the follow-up MRT (P<0.02), and 1.6 between early T2W (MR1) and MR2 (P<0.04). The mean DWI volume size (MR0) was larger than the early T2W (P<0.02). Although neurological outcome was good in all patients (mean NIHSS score of 1.3 at follow-up), early NIHSS and follow-up NIHSS scores were strongly correlated (r=0.9, P<0.00). NIHSS score at follow-up was highly correlated with lesion size of DWI (MR0; r=0.71, P<0.04) and T2W of MR1 (r=0.86, P<0.001). CONCLUSIONS: in this study, we saw a shrinking of the brain stem infarct volume according to clinical improvement of patients. Great extension of restricted diffusion in the acute stage does not necessarily implicate a large resulting infarction or a bad clinical outcome.

Brain Stem Infarctions↗