Machine Learning and the Conundrum of Stroke Risk Prediction

Abstract

Stroke is a leading cause of death worldwide. With escalating healthcare costs, early non-invasive stroke risk stratification is vital. The current paradigm of stroke risk assessment and mitigation is focused on clinical risk factors and comorbidities. Standard algorithms predict risk using regression-based statistical associations, which, while useful and easy to use, have moderate predictive accuracy. This review summarises recent efforts to deploy machine learning (ML) to predict stroke risk and enrich the understanding of the mechanisms underlying stroke. The surveyed body of literature includes studies comparing ML algorithms with conventional statistical models for predicting cardiovascular disease and, in particular, different stroke subtypes. Another avenue of research explored is ML as a means of enriching multiscale computational modelling, which holds great promise for revealing thrombogenesis mechanisms. Overall, ML offers a new approach to stroke risk stratification that accounts for subtle physiologic variants between patients, potentially leading to more reliable and personalised predictions than standard regression-based statistical associations.

Super-resolution Left Ventricular Flow and Pressure Mapping by Navier-Stokes-Informed Neural Networks

“…Machine learning (ML) and AI are shaking the landscape of fluid mechanics research, offering unprecedented ability to study complex flows. In cardiovascular research, ML models are powerful tools to discover hidden relationships between clinical variables and diseases, offering valuable metrics for disease risk stratification [60][61][62]. The impact of deep learning (DL) models has been particularly significant [63].…”

Machine learning model for predicting left atrial thrombus or spontaneous echo contrast in non-valvular atrial fibrillation patients based on multimodal echocardiographic parameters

“…The copyright holder for this preprint this version posted April 12, 2024. ; https://doi.org/10.1101/2024.04. 10.24305639 doi: medRxiv preprint Changes in left atrial structure, function, and hemodynamics are instrumental for AF prediction and stroke risk evaluation. 5 A detailed assessment of left atrial function using echocardiography has been shown to be beneficial in assessing risk, notably in NVAF patients with low CHA 2 DS 2 -VASc scores.…”

“…8,9 The rise of machine learning technologies, especially when combined with multi-modal echocardiographic parameters, provides new perspectives for clinical risk assessment. 10 Prediction models of thrombosis risk in atrial fibrillation (AF) are used to guide treatment. 11 Although regression models have traditionally been the preferred analytical approach for prediction modeling, ML has emerged as a potentially more effective methodology.…”

Development and Validation of an Interpretable Risk Prediction Model for Perioperative Ischemic Stroke in Noncardiac, Nonvascular, and Nonneurosurgical Patients: A Retrospective Study

“…The incidence of perioperative stroke varies across surgery types, ranging from 0.1-1.9% in noncardiac surgeries to 1.9-9.7% in cardiovascular surgeries 2,3 . Although various risk factors for perioperative stroke have been identi ed, traditional statistical-based prediction models exhibit limitations in addressing nonlinearity and variable selection issues 4 . Recently, machine learning has been recognized as a promising tool for predicting perioperative stroke among patients undergoing noncardiac surgeries 5,6 .…”