Article

A score to predict early risk of recurrence after ischemic stroke

Stroke Service, Department of Neurology, Massachusetts General Hospital, Harvard Medical School, Boston, MA, USA.
Neurology (Impact Factor: 8.29). 12/2009; 74(2):128-35. DOI: 10.1212/WNL.0b013e3181ca9cff
Source: PubMed

ABSTRACT

There is currently no instrument to stratify patients presenting with ischemic stroke according to early risk of recurrent stroke. We sought to develop a comprehensive prognostic score to predict 90-day risk of recurrent stroke.
We analyzed data on 1,458 consecutive ischemic stroke patients using a Cox regression model with time to recurrent stroke as the response and clinical and imaging features typically available to physician at admission as covariates. The 90-day risk of recurrent stroke was calculated by summing up the number of independent predictors weighted by their corresponding beta-coefficients. The resultant score was called recurrence risk estimator at 90 days or RRE-90 score (available at: http://www.nmr.mgh.harvard.edu/RRE-90/).
Sixty recurrent strokes (54 had baseline imaging) occurred during the follow-up period. The risk adjusted for time to follow-up was 6.0%. Predictors of recurrence included admission etiologic stroke subtype, prior history of TIA/stroke, and topography, age, and distribution of brain infarcts. The RRE-90 score demonstrated adequate calibration and good discrimination (area under the ROC curve [AUC] = 0.70-0.80), which was maintained when applied to a separate cohort of 433 patients (AUC = 0.70-0.76). The model's performance was also maintained for predicting early (14-day) risk of recurrence (AUC = 0.80).
The RRE-90 is a Web-based, easy-to-use prognostic score that integrates clinical and imaging information available in the acute setting to quantify early risk of recurrent stroke. The RRE-90 demonstrates good predictive performance, suggesting that, if validated externally, it has promise for use in creating individualized patient management algorithms and improving clinical practice in acute stroke care.

Download full-text

Full-text

Available from: Walter J Koroshetz
  • Source
    • "Given that about 85% of the 795,000 patients who experience a stroke each year in the US [15] survive at least 30 days [16], and up to an additional 500,000 suffer from a TIA [17], these results suggest that 297,850 stroke and TIA survivors in the United States alone will develop PTSD symptoms due to the event annually. Within 90 days of the index stroke, 6% of survivors experience a recurrent stroke [18], and recurrence rates increase substantially over longer term follow up [19]. We do not yet know if stroke or TIA-induced PTSD is associated with increased risk for a recurrent cerebrovascular attack, but given the doubling of ACS recurrence risk due to ACS-induced PTSD [3] and recent research showing that PTSD is strongly associated with medication nonadherence [13], such research is sorely needed. "
    [Show abstract] [Hide abstract]
    ABSTRACT: Posttraumatic stress disorder (PTSD) is common in survivors of acute life-threatening illness, but little is known about the burden of PTSD in survivors of stroke and transient ischemic attack (TIA). This study estimated the prevalence of stroke or TIA-induced posttraumatic stress disorder (PTSD) using systematic review and meta-analysis. Potentially relevant peer-reviewed journal articles were identified by searching the Ovid MEDLINE, PsycINFO, PILOTS Database, The Cochrane Library and Scopus from inception to January 2013; all searches were conducted on January 31, 2013. Observational cohort studies that assessed PTSD with specific reference to a stroke or TIA that occurred at least 1 month prior to the PTSD assessment were included. PTSD rates and characteristics of the study and sample were abstracted from all included studies. The coding of all articles included demographics, sample size, study country, and method and timing of PTSD assessment. Nine studies (N = 1,138) met our inclusion criteria. PTSD rates varied significantly across studies by timing of PTSD assessment (i.e., within 1 year of stroke/TIA versus greater than 1 year post-stroke/TIA; 55% of heterogeneity explained; Q 1 = 10.30; P = .001). Using a random effects model, the estimated rate of PTSD following stroke or TIA was 23% (95% CI, 16%-33%) within 1 year of the stroke or TIA and 11% (95% CI, 8%-14%) after 1 year. Although PTSD is commonly thought to be triggered by external events such as combat or sexual assault, these results suggest that 1 in 4 stroke or TIA survivors develop significant PTSD symptoms due to the stroke or TIA. Screening for PTSD in a large population-based prospective cohort study with cardiovascular outcome assessments is needed to yield definitive prevalence, and determine whether stroke or TIA-induced PTSD is a risk factor for subsequent cardiovascular events or mortality.
    Full-text · Article · Jun 2013 · PLoS ONE
  • Source
    • "Back propagation is by far the most popular neural network training algorithm that has been used to perform learning for multilayer feed-forward neural networks (Russell and Norving, 1995). Ay et al. (2010) there is currently no instrument to stratify patients presenting with ischemic stroke according to early risk of recurrent stroke. However, in the Communications and Public Liaison, (2008) the symptoms of stroke are distinct because they happen quickly, for instance Sudden numbness or weakness of the face, arm, or leg (especially on one side of the body), Sudden confusion, trouble speaking or understanding speech, Sudden trouble seeing in one or both eyes, Sudden trouble walking, dizziness, loss of balance or coordination and Sudden severe headache with no known cause. "
    [Show abstract] [Hide abstract]
    ABSTRACT: Problem statement: Most important problems of medical diagnosis. When there is a cerebrovascular accident attach the chances of a successful treatment depends essentially on the early diagnosis. In practice the part of medical errors while diagnosing a stroke type comes to 20-45% even for experienced doctors and the scope of methods of neurovisualization at stroke diagnosis are limited. Approach: In this research study, attempt was made to model the application of Artificial Neural Networks to the classification of patient Cerebrovascular Accident Attack. The Network for the consisted of a three-layer feed forward artificial neural network with back-propagation error method. Results: Data were collected from 100 records of patients at Federal Medical Centre Owo, Nigeria and the Artificial Neural Networks classifier was trained using gradient decent backward propagation algorithm with flexible sigmoid activation function at one hidden layer, with 16 inputs nodes representing stroke onset symptoms at the input layer, 10 nodes at the hidden layer and one node at the output layer representing the type of the attack. Conclusion: The learning Rate γ was set between 0.1 and 0.9 while the epoch set at 150. Initial weight set at Rand (-0.5 and 0.5). The simulation results showed that the model was capable of producing a reasonable forecasting accuracy in short.
    Preview · Article · Jan 2012 · Journal of Computer Science
  • [Show abstract] [Hide abstract]
    ABSTRACT: Trunk reservation is often used as protection against overload traffic in circuit-switched networks employing adaptive routing. This paper presents a two-moment method for modelling multiple traffic streams that are subject to trunk reservation. The approach used in this study has been to model the various traffic streams offered to a link in terms of their aggregate, determine the blocking experienced by the aggregate stream due to trunk reservation and then use a splitting formula to determine the individual blocking probabilities. The proposed method was tested using a simple circuit and was shown to approximate simulation results better than an existing method for underload, nominal load and overload conditions
    No preview · Conference Paper · Dec 1996
Show more