Ethnic differences in ischemic stroke subtypes in young-onset stroke: the Stroke Prevention in Young Adults Study

Trivedi, Megh M.; Ryan, Kathleen A.; Cole, John W.

doi:10.1186/s12883-015-0461-7

Cited by 13 publications

(8 citation statements)

References 28 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Finally, patients’ demographics (DEMO) and substance use behaviors (SU) were shown to be influential, which were consistent with the literature findings. [ 6 , 11 , 20 ] In particular, the CT/MRI and SS were the most predictive variables and they yielded more than 98% of the performance gain ( Fig 4 ). The relative importance of these variables could help physicians weigh the information when chart reviewing a patient’s record.…”

Section: Discussionmentioning

confidence: 97%

“…[ 17 – 19 ] In addition to clinical characteristics, patient demographics, family history, and substance use behaviors are considered influential factors on their risk of stroke. [ 6 , 11 , 20 ] Despite these findings, no single factor or group of factors would make a definite diagnosis. Rule-based approaches have been developed to heuristically combine the predictors to identify stroke cases, but large variability in reported sensitivities and specificities exists for the assessments.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Towards phenotyping stroke: Leveraging data from a large-scale epidemiological study to detect stroke diagnosis

Ni¹,

Alwell²,

Moomaw³

et al. 2018

PLoS ONE

View full text Add to dashboard Cite

Objective1) To develop a machine learning approach for detecting stroke cases and subtypes from hospitalization data, 2) to assess algorithm performance and predictors on real-world data collected by a large-scale epidemiology study in the US; and 3) to identify directions for future development of high-precision stroke phenotypic signatures.Materials and methodsWe utilized 8,131 hospitalization events (ICD-9 codes 430–438) collected from the Greater Cincinnati/Northern Kentucky Stroke Study in 2005 and 2010. Detailed information from patients’ medical records was abstracted for each event by trained research nurses. By analyzing the broad list of demographic and clinical variables, the machine learning algorithms predicted whether an event was a stroke case and, if so, the stroke subtype. The performance was validated on gold-standard labels adjudicated by stroke physicians, and results were compared with stroke classifications based on ICD-9 discharge codes, as well as labels determined by study nurses.ResultsThe best performing machine learning algorithm achieved a performance of 88.57%/93.81%/92.80%/93.30%/89.84%/98.01% (accuracy/precision/recall/F-measure/area under ROC curve/area under precision-recall curve) on stroke case detection. For detecting stroke subtypes, the algorithm yielded an overall accuracy of 87.39% and greater than 85% precision on individual subtypes. The machine learning algorithms significantly outperformed the ICD-9 method on all measures (P value<0.001). Their performance was comparable to that of study nurses, with better tradeoff between precision and recall. The feature selection uncovered a subset of predictive variables that could facilitate future development of effective stroke phenotyping algorithms.Discussion and conclusionsBy analyzing a broad array of patient data, the machine learning technologies held promise for improving detection of stroke diagnosis, thus unlocking high statistical power for subsequent genetic and genomic studies.

show abstract

Section: Discussionmentioning

confidence: 97%

Section: Introductionmentioning

confidence: 99%

Towards phenotyping stroke: Leveraging data from a large-scale epidemiological study to detect stroke diagnosis

Ni¹,

Alwell²,

Moomaw³

et al. 2018

PLoS ONE

View full text Add to dashboard Cite

show abstract

“…8-10 Specifically, higher proportion of small vessel disease (SVD)/lacunar stroke and intracranial atherosclerosis have been described among minorities. 9-12 Establishing these disparities in ischemic stroke subtypes is important in understanding the predominant stroke mechanism among the high-risk ethnic group, which may result in more focused primary and secondary stroke prevention strategy for that community.…”

Section: Introductionmentioning

confidence: 99%

Ethnic Comparison of Clinical Characteristics and Ischemic Stroke Subtypes Among Young Adult Patients With Stroke in Hawaii

Nakagawa

Ito

King

2017

Stroke

View full text Add to dashboard Cite

Background and Purpose Native Hawaiians and other Pacific Islanders (NHOPI) with ischemic stroke have younger age of stroke onset compared to whites. However, ethnic differences in stroke subtypes in this population have been inadequately studied. Methods Consecutive young adult patients (age ≤55 years) who were hospitalized for ischemic stroke between 2006 and 2012 at a tertiary center in Honolulu were studied. Clinical characteristics and stroke subtypes based on pathophysiological Trial of Org 10172 (TOAST) classification of NHOPI and Asians were compared to whites. Results A total of 427 consecutive young adult (mean age 46.7±7.8 years) patients (NHOPI 45%, Asians 38% and whites 17%) were studied. NHOPI had a higher prevalence of hypertension, diabetes, prosthetic valve, higher body mass index, hemoglobin A1c and lower HDL compared to whites (all P<0.05). Stroke subtype distribution were not different between the ethnic groups. Specifically, the prevalence of small vessel disease was similar between NHOPI (26.6%), whites (28.4%) and Asians (24.8%). In the univariate analyses, the use of intravenous tissue plasminogen activator (IV tPA) was lower among NHOPI (4.7%, P=0.01) and Asians (3.1%, P=0.002) compared to whites (12.5%). In the multivariable model, NHOPI (OR: 0.35, 95% CI: 0.12–0.98) and Asians (OR: 0.23, 95% CI: 0.07–0.74) were less likely to be treated with IV tPA than whites. Conclusion NHOPI have greater cardiovascular risk factors than whites, but there were no differences in stroke subtypes between the ethnic groups. Furthermore, NHOPI and Asians may be less likely to be treated with IV tPA than whites.

show abstract

“…The lack of association among those of African ancestry might be due to limited power in that sample or transethnic differences in the genetic etiology of LAA. Of note, the atherothrombotic type is more common in European ancestry patients 43 . Finally, another possible common mechanism is cerebrovascular dysregulation and hypoperfusion 44 .…”

Section: Discussionmentioning

confidence: 98%

Polygenic Risk for Depression Increases Risk of Ischemic Stroke

Wassertheil‐Smoller

Qi²,

Dave

et al. 2018

Stroke

View full text Add to dashboard Cite

show abstract

Ethnic differences in ischemic stroke subtypes in young-onset stroke: the Stroke Prevention in Young Adults Study

Cited by 13 publications

References 28 publications

Towards phenotyping stroke: Leveraging data from a large-scale epidemiological study to detect stroke diagnosis

Towards phenotyping stroke: Leveraging data from a large-scale epidemiological study to detect stroke diagnosis

Ethnic Comparison of Clinical Characteristics and Ischemic Stroke Subtypes Among Young Adult Patients With Stroke in Hawaii

Polygenic Risk for Depression Increases Risk of Ischemic Stroke

Contact Info

Product

Resources

About