BACKGROUND The risk prediction of stroke recurrence for individual patients is a difficult task. Individualised prediction may enhance stroke survivors selfcare engagement. We have developed PRERISK: a statistical and Machine Learning (ML) classifier to predict individual stroke recurrence risk. METHODS We analysed clinical and socioeconomic data from a prospectively collected public healthcare-based dataset of 44623 patients admitted with stroke diagnosis in 88 public hospitals over 6 years in Catalonia-Spain. We trained several supervised-ML models to provide individualised risk along time and compared them with a Cox regression model. RESULTS Overall, 16% of patients presented a stroke recurrence along a median follow-up of 2.65 years. Models were trained for predicting early, late and long-term recurrence risk, within 90, 91-365 and >365 days, respectively. Most powerful predictors of stroke recurrence were time since index stroke, Barthel index, atrial fibrillation, dyslipidemia, haemoglobin and body mass index, which were used to create a simplified model with similar performance. The balanced AUROC were 0.77 (±0.01), 0.61 (±0.01) and 0.71 (±0.01) for early, late and long-term recurrence risk respectively (Cox risk class probability: 0.74(±0.01), 0.59(±0.01) and 0.68(±0.01), c-index 0.88). Overall, the ML approach showed statistically significant improvement over the Cox model. Stroke recurrence curves can be simulated for each patient under different degrees of control of modifiable factors. CONCLUSION PRERISK represents a novel approach that provides continuous, personalised and fairly accurate risk prediction of stroke recurrence along time according to the degree of modifiable risk factors control.
Personal prediction of stroke recurrence based on modifiable factors may enhance patient compliance to treatments and healthy lifestyles while optimizing resources of health centers. Vascular risk factors, socio-economic indicators and habits correlate with stroke morbidity and further recurrence. We aimed to estimate stroke recurrence probability as a function of time (3 months, < 1 year and > 1year), both at individual level and with larger classes of individuals. Clinical and socioeconomic public healthcare-based dataset of 41325 patients admitted with stroke diagnosis in 88 public hospitals over 6 years were analyzed. Overall, 8509 patients presented a stroke (one or more) recurrence (20.6%), with the following temporal distribution: 3 months, 1 year and > 1 year, 57%, 17% and 26% respectively. We developed a supervised-machine learning based study and identified modifiable and non-modifiable risk factors with stronger impact on risk of stroke recurrence. An algorithm able to provide individualized risk of stroke recurrence at 3 and 12 months was developed (AUROC = 0.80, for balanced classes). The risk can be continuously updated according to the status of modifiable risk factors. We also calculated the survival curve for each patient, to detect different risk recurrence periods along time. a) ROC curve for the three classes predicted. b) Feature importance to explain the model for features modifiable by the patient or not c) Probability over time of “No stroke recurrence” in an example patient according to optimal (orange) or poor (blue) control of vascular risk factors Machine learning analyses can improve risk prediction and offer individualized information to patients that can be used as feedback for secondary prevention strategies. Our approach is compatible with prevention strategies which, by continuous patient communication and feedbacks, make patients more likely to comply with treatment prescribed or lifestyle changes suggested.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.
customersupport@researchsolutions.com
10624 S. Eastern Ave., Ste. A-614
Henderson, NV 89052, USA
Copyright © 2024 scite LLC. All rights reserved.
Made with 💙 for researchers
Part of the Research Solutions Family.