Crimson Publishers Publish With Us Reprints e-Books Video articles

Abstract

Techniques in Neurosurgery & Neurology

Clinical Predictors of the Evolving Ischemic Stroke According to the Tree-Structured Model

  • Open or CloseIrina Gontschar1* and Igor Prudyvus2

    1Student, Health Information Management and Insurance Billing Program by the EVANS Community Adult School, USA

    2Chief Application Support Analysts, EPAM Systems, Belarus, Europe

    *Corresponding author: Irina Gontschar, Health Information Management and Insurance Billing Program by the EVANS Community Adult School, Los Angeles, California, USA

Submission: July 25, 2019 Published: September 18, 2019

DOI: 10.31031/TNN.2019.02.000550

ISSN 2637-7748
Volume2 Issue5

Abstract

Introduction: The purpose of the study is to identify the independent clinical predictors of the evolving ischemic stroke (EIS) according to the tree-structured model.

Methods and Materials: The objects of the study were 1421 patients with ischemic stroke (IS), hospitalized within 48 hours from the development of the initial symptoms. Patients with IS were admitted to the 5th Minsk City Clinical Hospital and the Minsk Emergency Hospital (Belarus) in 2002-2014 years. Evolving clinical course of the stroke is defined as an increase in the severity of neurological deficit by 2 or more points on the NIHSS scale or the death of the patient during the first seven days of hospitalization. The research is characterized due to the prospective-data-collection, and the retrospective evaluation design. The statistical method of decision trees and an algorithm of the conditional inference trees were used to create the prognostic model of EIS. Statistical data analysis was carried out applying the software packages of R V.3.2.5 and IBM SPSS Statistics 26.0.

Results: The rate of EIS reached 30%. The patients with EIS were 72.6±10.2 years old, patients without EIS-68.1±11.3 years; p = 0.005. Previously, 22 clinical, demographic, laboratory variables accommodated in the computer database were included in the conditional inference trees statistical algorithm. The prognostic statistical model of EIS has been constructed. The following independent predictors of evolving IS were identified: the stroke subtype according to the Oxford Community Stroke Project classification, the serum urea level, and red blood cell number in the total blood count. The accuracy of the statistical model reaches 0.77 (95% CI: 0.75; 0.80), the sensitivity is 0.52, the specificity-0.88, PPV-0.66, and NPV- 0.81; p < 0.001.

Conclusion: The tree-structural model allowed us to identify the independent clinical predictors of EIS.

Keywords: Cerebral infarction; Clinical characteristics; Clinical course; Conditional inference trees algorithm; Decision tree; Evolving ischemic stroke; Model; Predictor; Prognosis; Stroke deterioration

Abbreviations

AF: Atrial Fibrillation; AH: Arterial Hypertension; BMI: Body Mass Index; BUN/Cr: Blood Urea Nitrogen to Creatinine Ratio; BUN: Blood Urea Nitrogen; CART: Classification and Regression Trees; CI: Confidence Interval; CT: Computer Tomography; DBP: Diastolic Blood Pressure; ECG: Electrocardiogram; EIS: Evolving Ischemic Stroke; END: Early Neurological Deterioration; IQR: Interquartile Range; IS: Ischemic Stroke; LACS: Lacunar Syndrome; LMWH: Low-Molecular-Weight Heparins; MRI: Magnetic Resonance Imaging; mRS: Modified Rankin Scale; NIHSS: National Institutes of Health Stroke Scale; No EIS: Non-Evolving Ischemic Stroke; NPV: Predictive Value of the Negative Test Result; OCSP: Oxfordshire Community Stroke Project; OR: Odds Ratio; PACS: Partial Anterior Circulation Syndrome; PBP: Pulse Blood Pressure; POCS: Posterior Circulation Syndrome; PPV: Predictive Value of the Positive Test Result; Q1: Lower Quartile; Q3: Upper Quartile; RBC: Red Blood Cells; RSPCNN: The Republican Scientific and Practical Center for Neurology and Neurosurgery of the Ministry of Health of the Republic of Belarus; rtPA: Recombinant Tissue Plasminogen Activator; SBP: Systolic Blood Pressure; SD: Standard Deviation; SSS: Scandinavian Stroke Scale; TACS: Total Anterior Circulation Syndrome; TIA: Transient Ischemic Attack; TOAST: Trial of ORG 10172 in Acute Stroke Treatment; UFN: Unfractionated Heparin; WBC: White Blood Cells; WHO: World Health Organization

Get access to the full text of this article