Research Article

Stroke Subtype Clustering by Multifractal Bayesian Denoising with Fuzzy Means and -Means Algorithms

Table 3

Stroke dataset description.

AttributesStatusNumber of patients/values (%)Descriptions

HTNYes1593 (72%)Hypertension
HyperlipYes1197 (54%)High levels of lipid (fat) in blood

DMYes602 (27%) Diabetes
H/O stroke/TIAYes546 (25%)History of stroke/TIA
AttrialFibYes541 (25%)Abnormal heart rhythm
CADYes513 (23%)Coronary artery disease
CHFYes229 (10%)Congestive heart failure
PAD/carotid DiseaseYes318 (14%)Peripheral artery disease

TobaccoYes520 (23%)Cigarette addict
ETOHYes308 (1.7%)Alcohol addict

StatinYes1000 (45%)Medications given to the patient are grouped into five broad categories
AntiHTNYes1332 (60%)
AntidiabeticYes454 (20%)
AntiplateletYes1031 (47%)
AnticoagulationYes242 (10%)

CT perfusionYes137 (0.06%)Procedures used for treatment
NeurointerventionYes271 (12%)
mRS 90 daysLow2007Dichotomized into low (0–2), high (3–6)
High197

Hemorrhagic con.Yes204 (0.09%)Whether the ischemic stroke turned to hemorrhagic

NIHSS admission9.3 +/− 8.3 Measures the severity of stroke

TPAYes413 (19%)TPA (tissue plasminogen activator) is used to break down blood clots