The Stroke RiskometerTM App: Validation of a data collection tool and stroke risk predictor

for the Stroke Riskometer

Research output: Contribution to journalArticle

40 Citations (Scopus)

Abstract

Background: The greatest potential to reduce the burden of stroke is by primary prevention of first-ever stroke, which constitutes three quarters of all stroke. In addition to population-wide prevention strategies (the 'mass' approach), the 'high risk' approach aims to identify individuals at risk of stroke and to modify their risk factors, and risk, accordingly. Current methods of assessing and modifying stroke risk are difficult to access and implement by the general population, amongst whom most future strokes will arise. To help reduce the burden of stroke on individuals and the population a new app, the Stroke RiskometerTM, has been developed. We aim to explore the validity of the app for predicting the risk of stroke compared with current best methods. Methods: 752 stroke outcomes from a sample of 9501 individuals across three countries (New Zealand, Russia and the Netherlands) were utilized to investigate the performance of a novel stroke risk prediction tool algorithm (Stroke RiskometerTM) compared with two established stroke risk score prediction algorithms (Framingham Stroke Risk Score [FSRS] and QStroke). We calculated the receiver operating characteristics (ROC) curves and area under the ROC curve (AUROC) with 95% confidence intervals, Harrels C-statistic and D-statistics for measure of discrimination, R2 statistics to indicate level of variability accounted for by each prediction algorithm, the Hosmer-Lemeshow statistic for calibration, and the sensitivity and specificity of each algorithm. Results: The Stroke RiskometerTM performed well against the FSRS five-year AUROC for both males (FSRS=75·0% (95% CI 72·3%-77·6%), Stroke RiskometerTM=74·0(95% CI 71·3%-76·7%) and females [FSRS=70·3% (95% CI 67·9%-72·8%, Stroke RiskometerTM=71·5% (95% CI 69·0%-73·9%)], and better than QStroke [males - 59·7% (95% CI 57·3%-62·0%) and comparable to females=71·1% (95% CI 69·0%-73·1%)]. Discriminative ability of all algorithms was low (C-statistic ranging from 0·51-0·56, D-statistic ranging from 0·01-0·12). Hosmer-Lemeshow illustrated that all of the predicted risk scores were not well calibrated with the observed event data (P<0·006). Conclusions: The Stroke RiskometerTM is comparable in performance for stroke prediction with FSRS and QStroke. All three algorithms performed equally poorly in predicting stroke events. The Stroke RiskometerTM will be continually developed and validated to address the need to improve the current stroke risk scoring systems to more accurately predict stroke, particularly by identifying robust ethnic/race ethnicity group and country specific risk factors. International Journal of Stroke

Original languageEnglish
Pages (from-to)231-244
Number of pages14
JournalInternational Journal of Stroke
Volume10
Issue number2
DOIs
Publication statusPublished - 1 Feb 2015

Fingerprint

Stroke
ROC Curve
Area Under Curve
Population
Russia
Primary Prevention

Keywords

  • Prevention
  • Stroke prediction
  • Stroke riskometer app
  • Validation

ASJC Scopus subject areas

  • Neurology

Cite this

The Stroke RiskometerTM App : Validation of a data collection tool and stroke risk predictor. / for the Stroke Riskometer.

In: International Journal of Stroke, Vol. 10, No. 2, 01.02.2015, p. 231-244.

Research output: Contribution to journalArticle

@article{65a1b5a64f6c42738ec2004220625878,
title = "The Stroke RiskometerTM App: Validation of a data collection tool and stroke risk predictor",
abstract = "Background: The greatest potential to reduce the burden of stroke is by primary prevention of first-ever stroke, which constitutes three quarters of all stroke. In addition to population-wide prevention strategies (the 'mass' approach), the 'high risk' approach aims to identify individuals at risk of stroke and to modify their risk factors, and risk, accordingly. Current methods of assessing and modifying stroke risk are difficult to access and implement by the general population, amongst whom most future strokes will arise. To help reduce the burden of stroke on individuals and the population a new app, the Stroke RiskometerTM, has been developed. We aim to explore the validity of the app for predicting the risk of stroke compared with current best methods. Methods: 752 stroke outcomes from a sample of 9501 individuals across three countries (New Zealand, Russia and the Netherlands) were utilized to investigate the performance of a novel stroke risk prediction tool algorithm (Stroke RiskometerTM) compared with two established stroke risk score prediction algorithms (Framingham Stroke Risk Score [FSRS] and QStroke). We calculated the receiver operating characteristics (ROC) curves and area under the ROC curve (AUROC) with 95{\%} confidence intervals, Harrels C-statistic and D-statistics for measure of discrimination, R2 statistics to indicate level of variability accounted for by each prediction algorithm, the Hosmer-Lemeshow statistic for calibration, and the sensitivity and specificity of each algorithm. Results: The Stroke RiskometerTM performed well against the FSRS five-year AUROC for both males (FSRS=75·0{\%} (95{\%} CI 72·3{\%}-77·6{\%}), Stroke RiskometerTM=74·0(95{\%} CI 71·3{\%}-76·7{\%}) and females [FSRS=70·3{\%} (95{\%} CI 67·9{\%}-72·8{\%}, Stroke RiskometerTM=71·5{\%} (95{\%} CI 69·0{\%}-73·9{\%})], and better than QStroke [males - 59·7{\%} (95{\%} CI 57·3{\%}-62·0{\%}) and comparable to females=71·1{\%} (95{\%} CI 69·0{\%}-73·1{\%})]. Discriminative ability of all algorithms was low (C-statistic ranging from 0·51-0·56, D-statistic ranging from 0·01-0·12). Hosmer-Lemeshow illustrated that all of the predicted risk scores were not well calibrated with the observed event data (P<0·006). Conclusions: The Stroke RiskometerTM is comparable in performance for stroke prediction with FSRS and QStroke. All three algorithms performed equally poorly in predicting stroke events. The Stroke RiskometerTM will be continually developed and validated to address the need to improve the current stroke risk scoring systems to more accurately predict stroke, particularly by identifying robust ethnic/race ethnicity group and country specific risk factors. International Journal of Stroke",
keywords = "Prevention, Stroke prediction, Stroke riskometer app, Validation",
author = "{for the Stroke Riskometer} and Priya Parmar and Rita Krishnamurthi and Ikram, {M. Arfan} and Albert Hofman and Mirza, {Saira S.} and Yury Varakin and Michael Kravchenko and Michael Piradov and Thrift, {Amanda G.} and Bo Norrving and Wenzhi Wang and Mandal, {Dipes Kumar} and Suzanne Barker-Collo and Ramesh Sahathevan and Stephen Davis and Gustavo Saposnik and Miia Kivipelto and Shireen Sindi and Bornstein, {Natan M.} and Maurice Giroud and Yannick B{\'e}jot and Michael Brainin and Richie Poulton and Narayan, {K. M Venkat} and Manuel Correia and Ant{\'o}nio Freire and Yoshihiro Kokubo and David Wiebers and George Mensah and Bindhim, {Nasser F.} and Barber, {P. Alan} and Pandian, {Jeyaraj Durai} and Hankey, {Graeme J.} and Mehndiratta, {Man Mohan} and Shobhana Azhagammal and {Mohamed Ibrahim}, Norlinah and Max Abbott and Elaine Rush and Patria Hume and Tasleem Hussein and Rohit Bhattacharjee and Mitali Purohit and Feigin, {Valery L.}",
year = "2015",
month = "2",
day = "1",
doi = "10.1111/ijs.12411",
language = "English",
volume = "10",
pages = "231--244",
journal = "International Journal of Stroke",
issn = "1747-4930",
publisher = "Wiley-Blackwell",
number = "2",

}

TY - JOUR

T1 - The Stroke RiskometerTM App

T2 - Validation of a data collection tool and stroke risk predictor

AU - for the Stroke Riskometer

AU - Parmar, Priya

AU - Krishnamurthi, Rita

AU - Ikram, M. Arfan

AU - Hofman, Albert

AU - Mirza, Saira S.

AU - Varakin, Yury

AU - Kravchenko, Michael

AU - Piradov, Michael

AU - Thrift, Amanda G.

AU - Norrving, Bo

AU - Wang, Wenzhi

AU - Mandal, Dipes Kumar

AU - Barker-Collo, Suzanne

AU - Sahathevan, Ramesh

AU - Davis, Stephen

AU - Saposnik, Gustavo

AU - Kivipelto, Miia

AU - Sindi, Shireen

AU - Bornstein, Natan M.

AU - Giroud, Maurice

AU - Béjot, Yannick

AU - Brainin, Michael

AU - Poulton, Richie

AU - Narayan, K. M Venkat

AU - Correia, Manuel

AU - Freire, António

AU - Kokubo, Yoshihiro

AU - Wiebers, David

AU - Mensah, George

AU - Bindhim, Nasser F.

AU - Barber, P. Alan

AU - Pandian, Jeyaraj Durai

AU - Hankey, Graeme J.

AU - Mehndiratta, Man Mohan

AU - Azhagammal, Shobhana

AU - Mohamed Ibrahim, Norlinah

AU - Abbott, Max

AU - Rush, Elaine

AU - Hume, Patria

AU - Hussein, Tasleem

AU - Bhattacharjee, Rohit

AU - Purohit, Mitali

AU - Feigin, Valery L.

PY - 2015/2/1

Y1 - 2015/2/1

N2 - Background: The greatest potential to reduce the burden of stroke is by primary prevention of first-ever stroke, which constitutes three quarters of all stroke. In addition to population-wide prevention strategies (the 'mass' approach), the 'high risk' approach aims to identify individuals at risk of stroke and to modify their risk factors, and risk, accordingly. Current methods of assessing and modifying stroke risk are difficult to access and implement by the general population, amongst whom most future strokes will arise. To help reduce the burden of stroke on individuals and the population a new app, the Stroke RiskometerTM, has been developed. We aim to explore the validity of the app for predicting the risk of stroke compared with current best methods. Methods: 752 stroke outcomes from a sample of 9501 individuals across three countries (New Zealand, Russia and the Netherlands) were utilized to investigate the performance of a novel stroke risk prediction tool algorithm (Stroke RiskometerTM) compared with two established stroke risk score prediction algorithms (Framingham Stroke Risk Score [FSRS] and QStroke). We calculated the receiver operating characteristics (ROC) curves and area under the ROC curve (AUROC) with 95% confidence intervals, Harrels C-statistic and D-statistics for measure of discrimination, R2 statistics to indicate level of variability accounted for by each prediction algorithm, the Hosmer-Lemeshow statistic for calibration, and the sensitivity and specificity of each algorithm. Results: The Stroke RiskometerTM performed well against the FSRS five-year AUROC for both males (FSRS=75·0% (95% CI 72·3%-77·6%), Stroke RiskometerTM=74·0(95% CI 71·3%-76·7%) and females [FSRS=70·3% (95% CI 67·9%-72·8%, Stroke RiskometerTM=71·5% (95% CI 69·0%-73·9%)], and better than QStroke [males - 59·7% (95% CI 57·3%-62·0%) and comparable to females=71·1% (95% CI 69·0%-73·1%)]. Discriminative ability of all algorithms was low (C-statistic ranging from 0·51-0·56, D-statistic ranging from 0·01-0·12). Hosmer-Lemeshow illustrated that all of the predicted risk scores were not well calibrated with the observed event data (P<0·006). Conclusions: The Stroke RiskometerTM is comparable in performance for stroke prediction with FSRS and QStroke. All three algorithms performed equally poorly in predicting stroke events. The Stroke RiskometerTM will be continually developed and validated to address the need to improve the current stroke risk scoring systems to more accurately predict stroke, particularly by identifying robust ethnic/race ethnicity group and country specific risk factors. International Journal of Stroke

AB - Background: The greatest potential to reduce the burden of stroke is by primary prevention of first-ever stroke, which constitutes three quarters of all stroke. In addition to population-wide prevention strategies (the 'mass' approach), the 'high risk' approach aims to identify individuals at risk of stroke and to modify their risk factors, and risk, accordingly. Current methods of assessing and modifying stroke risk are difficult to access and implement by the general population, amongst whom most future strokes will arise. To help reduce the burden of stroke on individuals and the population a new app, the Stroke RiskometerTM, has been developed. We aim to explore the validity of the app for predicting the risk of stroke compared with current best methods. Methods: 752 stroke outcomes from a sample of 9501 individuals across three countries (New Zealand, Russia and the Netherlands) were utilized to investigate the performance of a novel stroke risk prediction tool algorithm (Stroke RiskometerTM) compared with two established stroke risk score prediction algorithms (Framingham Stroke Risk Score [FSRS] and QStroke). We calculated the receiver operating characteristics (ROC) curves and area under the ROC curve (AUROC) with 95% confidence intervals, Harrels C-statistic and D-statistics for measure of discrimination, R2 statistics to indicate level of variability accounted for by each prediction algorithm, the Hosmer-Lemeshow statistic for calibration, and the sensitivity and specificity of each algorithm. Results: The Stroke RiskometerTM performed well against the FSRS five-year AUROC for both males (FSRS=75·0% (95% CI 72·3%-77·6%), Stroke RiskometerTM=74·0(95% CI 71·3%-76·7%) and females [FSRS=70·3% (95% CI 67·9%-72·8%, Stroke RiskometerTM=71·5% (95% CI 69·0%-73·9%)], and better than QStroke [males - 59·7% (95% CI 57·3%-62·0%) and comparable to females=71·1% (95% CI 69·0%-73·1%)]. Discriminative ability of all algorithms was low (C-statistic ranging from 0·51-0·56, D-statistic ranging from 0·01-0·12). Hosmer-Lemeshow illustrated that all of the predicted risk scores were not well calibrated with the observed event data (P<0·006). Conclusions: The Stroke RiskometerTM is comparable in performance for stroke prediction with FSRS and QStroke. All three algorithms performed equally poorly in predicting stroke events. The Stroke RiskometerTM will be continually developed and validated to address the need to improve the current stroke risk scoring systems to more accurately predict stroke, particularly by identifying robust ethnic/race ethnicity group and country specific risk factors. International Journal of Stroke

KW - Prevention

KW - Stroke prediction

KW - Stroke riskometer app

KW - Validation

UR - http://www.scopus.com/inward/record.url?scp=84921613442&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84921613442&partnerID=8YFLogxK

U2 - 10.1111/ijs.12411

DO - 10.1111/ijs.12411

M3 - Article

C2 - 25491651

AN - SCOPUS:84921613442

VL - 10

SP - 231

EP - 244

JO - International Journal of Stroke

JF - International Journal of Stroke

SN - 1747-4930

IS - 2

ER -