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

Table 2

Stroke dataset.

Number of stroke subtypes/TOAST	Main heading of attributes	Data size
No stroke/TIA (167); Large vessel (481); Small vessel (228); Cardioembolic (689); Cryptogenic (528); Dissection (59); Other (52)	Demographic information; (Age, gender); Medical history; (HTN, hyperlip, DM,; H/O stroke/TIA, AtrialFib, CAD, CHF, PAD/carotid; disease, tobacco, ETOH); Results of laboratory test; (mRS 90 days, hemorrhagic conversion,; NIHSS admission, TPA); Treatment and medication data; (Statin, antiHTN, antidiabetic,; antiplatelet, anticoagulation, CT perfusion,; neurointervention)

TOAST: type/etiology of stroke; TIA: ischemic attack; HTN: hypertension; DM: diabetes mellitus; CAD: coronary artery disease; AtrialFib: atrial fibrillation stroke; CAD: coronary artery disease; CHF: congestive heart failure; PAD/carotid disease: peripheral artery disease; NIHSS 90 days: National Institutes of Health Stroke Scale 90-day mortality; CT perfusion: computer tomography perfusion, ETOH: alcohol; antiHTN: antihypertensive drugs after acute ischemic stroke; NIHSS discharge: National Institutes of Health Stroke Scale; H/O stroke/TIA: history of transient ischemic attack.