The Stroke Riskometer™ App: Validation of a Data Collection Tool and Stroke Risk Predictor

Abstract

BackgroundThe 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 Riskometer™, has been developed. We aim to explore the validity of the app for predicting the risk of stroke compared with current best methods.Methods752 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 Riskometer™) 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.ResultsThe Stroke Riskometer™ performed well against the FSRS five-year AUROC for both males (FSRS = 75·0% (95% CI 72·3%–77·6%), Stroke Riskometer™ = 74·0(95% CI 71·3%–76·7%) and females [FSRS = 70·3% (95% CI 67·9%–72·8%, Stroke Riskometer™ = 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).ConclusionsThe Stroke Riskometer™ is comparable in performance for stroke prediction with FSRS and QStroke. All three algorithms performed equally poorly in predicting stroke events. The Stroke Riskometer™ 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.

New Strategy to Reduce the Global Burden of Stroke

“…The Stroke Riskometer algorithm has been validated 58 and found to be comparable with the Framingham and QSTROKE stroke risk prevention algorithms commonly used in medical practice. Notably, as well as absolute risk, the app also provides users with their relative risk of having a stroke compared with someone of the same age and sex who does not have any risk factors at all.…”

“…57 The Stroke Riskometer App calculates the 5-year and 10-year risk of stroke for any individual aged ≥20 years, based on their responses to a short questionnaire. Full details of the app have been described in detail elsewhere 58 and are briefly described in Table I in the online-only Data Supplement.…”

Use of Mobile Devices, Social Media, and Crowdsourcing as Digital Strategies to Improve Emergency Cardiovascular Care

“…[11][12][13][14]16 Mobile devices may be used to help lay people and healthcare providers identify stroke, encourage activating an emergency response, and facilitate stroke risk assessment. [83][84][85][86] The American Stroke Association launched the "Spot a Stroke F.A.S.T." campaign, which included Internet-based video public service announcements and a free app for mobile devices.…”

Empowering Self-Management through M-Health Applications

“…Much more application like NW is being developed and can be downloaded via Google Play Store for Android phone users. Some of the M-Health system are for monitoring patient's health or self-monitoring [13][14][15], reminder [16], diagnosing diseases [17], non-communicable disease prevention [18], and clinical decision making [19].…”

“…The other application is for self-management and education of cardiac patients fighting against chronic diseases, especially heart diseases, whereby medical and users' activities are recorded including medication time reminder [15]. There are also applications developed to assist in monitoring and prevention of non-communicable diseases such as Stroke Riskometer which provides estimates of the absolute risk of stroke within the next 5 to 10 years for individuals aged 20 years and above, providing user a baseline risk comparison which allows them to compare their stroke risk with someone of the same age and gender who has no risk factors [18]. Since 5 to 10 years prediction of stroke risk is still inadequate, there are several other researches related to personalized modelling using spiking neural networks methods, aimed to predict stroke risk event several days earlier before stroke occurrences [20][21].…”