Applying instance-based techniques to prediction of final outcome in acute stroke

OBJECTIVE Acute cerebral stroke is a frequent cause of death and the major cause of adult neurological disability in the western world. Thrombolysis is the only established treatment of ischemic stroke; however, its use carries a substantial risk of symptomatic intracerebral hemorrhage. A clinical tool to guide the use of thrombolysis would be very valuable. One of the major goals of such a tool would be the identification of potentially salvageable tissue. This requires an accurate prediction of the extent of infarction if untreated. In this study, we investigate the applicability of highly flexible instance-based (IB) methods for such predictions. METHODS AND MATERIALS Based on information obtained from magnetic resonance imaging of 14 patients with acute stroke, we explored three different implementations of the IB method: k-NN, Gaussian weighted, and constant radius search classification. Receiver operating characteristics analysis, in particular area under the curve (AUC), was used as performance measure. RESULTS We found no significant difference (P = 0.48) in performance for the optimal k-NN (k = 164, AUC = 0.814 +/- 0.001) and Gaussian weight (sigma = 0.17, AUC = 0.813 +/- 0.001) implementations, while they were both significantly better (P < 1 x 10(-6) for both) than the constant radius implementation (R = 0.28, AUC = 0.809 +/- 0.001). Qualitative analyses of the distribution of instances in the feature space indicated that non-infarcted instances tends to cluster together while infarcted instances are more dispersed, and that there may not exist a stringent boundary separating infarcted from non-infarcted instances. CONCLUSIONS This study shows that IB methods can be used, and may be advantageous, for predicting final infarct in patients with acute stroke, but further work must be done to make them clinically applicable.

[1]  F. Buonanno,et al.  Predicting Tissue Outcome in Acute Human Cerebral Ischemia Using Combined Diffusion- and Perfusion-Weighted MR Imaging , 2001, Stroke.

[2]  J. Mazziotta,et al.  Rapid Automated Algorithm for Aligning and Reslicing PET Images , 1992, Journal of computer assisted tomography.

[3]  Vladimir Cherkassky,et al.  Learning from Data: Concepts, Theory, and Methods , 1998 .

[4]  W. Powers.  Cerebral hemodynamics in ischemic cerebrovascular disease , 1991, Annals of neurology.

[5]  J. Hanley,et al.  A method of comparing the areas under receiver operating characteristic curves derived from the same cases. , 1983, Radiology.

[6]  J. Kurhanewicz,et al.  Diffusion-weighted MR imaging of acute stroke: correlation with T2-weighted and magnetic susceptibility-enhanced MR imaging in cats. , 1990, AJNR. American journal of neuroradiology.

[7]  Wei Li,et al.  Fast magnetic resonance diffusion‐weighted imaging of acute human stroke , 1992, Neurology.

[8]  Ian H. Witten,et al.  Data mining: practical machine learning tools and techniques with Java implementations , 2002, SGMD.

[9]  J. Hanley,et al.  The meaning and use of the area under a receiver operating characteristic (ROC) curve. , 1982, Radiology.

[10]  David J. Spiegelhalter,et al.  Machine Learning, Neural and Statistical Classification , 2009 .

[11]  Robert A. Lordo,et al.  Learning from Data: Concepts, Theory, and Methods , 2001, Technometrics.

[12]  Ian H. Witten,et al.  Data mining: practical machine learning tools and techniques, 3rd Edition , 1999 .

[13]  Joseph P. Broderick,et al.  Tissue plasminogen activator for acute ischemic stroke. The National Institute of Neurological Disorders and Stroke rt-PA Stroke Study Group. , 1995 .

[14]  Scott T. Grafton,et al.  Automated image registration: I. General methods and intrasubject, intramodality validation. , 1998, Journal of computer assisted tomography.

[15]  Charu C. Aggarwal,et al.  On the Surprising Behavior of Distance Metrics in High Dimensional Spaces , 2001, ICDT.

[16]  Tony R. Martinez,et al.  Reduction Techniques for Instance-Based Learning Algorithms , 2000, Machine Learning.

[17]  M. O’Sullivan,et al.  MRI based diffusion and perfusion predictive model to estimate stroke evolution. , 2001, Magnetic resonance imaging.

[18]  L. Hedlund,et al.  Mechanism of Detection of Acute Cerebral Ischemia in Rats by Diffusion‐Weighted Magnetic Resonance Microscopy , 1992, Stroke.

[19]  Andrew P. Bradley,et al.  The use of the area under the ROC curve in the evaluation of machine learning algorithms , 1997, Pattern Recognit..

[20]  M E Moseley,et al.  Echo-planar perfusion-sensitive MR imaging of acute cerebral ischemia. , 1993, Radiology.

[21]  Ricardo A. Baeza-Yates,et al.  Searching in metric spaces , 2001, CSUR.

[22]  N. Lassen,et al.  The luxury-perfusion syndrome and its possible relation to acute metabolic acidosis localised within the brain. , 1966, Lancet.

[23]  Charu C. Aggarwal,et al.  Re-designing distance functions and distance-based applications for high dimensional data , 2001, SGMD.

[24]  Rafael C. González,et al.  Local Determination of a Moving Contrast Edge , 1985, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[25]  R. Bernstein,et al.  Stroke: A Practical Guide to Management , 2001 .

[26]  I D Wilkinson,et al.  The imaging of ischaemic stroke. , 2001, Clinical radiology.

[27]  Stephen M. Smith,et al.  Segmentation of brain MR images through a hidden Markov random field model and the expectation-maximization algorithm , 2001, IEEE Transactions on Medical Imaging.