Precision medicine in stroke: towards personalized outcome predictions using artificial intelligence

Abstract

Stroke ranks among the leading causes for morbidity and mortality worldwide. New and continuously improving treatment options such as thrombolysis and thrombectomy have revolutionized acute stroke treatment in recent years. Following modern rhythms, the next revolution might well be the strategic use of the steadily increasing amounts of patient-related data for generating models enabling individualized outcome predictions. Milestones have already been achieved in several health care domains, as big data and artificial intelligence (AI) have entered everyday life. The aim of this review is to synoptically illustrate and discuss how AI approaches may help to compute single-patient predictions in stroke outcome research in the acute, subacute and chronic stage. We will present approaches considering demographic, clinical and electrophysiological data as well as data originating from various imaging modalities and combinations thereof. We will outline their advantages, disadvantages, their potential pitfalls and the promises they hold with a special focus on a clinical audience. Throughout the review we will highlight methodological aspects of novel machine learning approaches as they are particularly crucial to realize precision medicine. We will finally provide an outlook on how AI approaches might contribute to enhancing favorable outcomes after stroke.

Development and Validation of Prediction Models for Severe Complications After Acute Ischemic Stroke: A Study Based on the Stroke Registry of Northwestern Germany

“…In contrast to the majority of previous studies, which primarily relied on logistic regression, we provide a comprehensive overview of the performance of multiple statistical learning approaches. 32 We opted for approaches representing various different learning architectures. Some of them, the k‐nearest neighbor and gradient boosting classifiers, can automatically extract nonlinear effects.…”

Personalized Approaches to Stroke: One Step Forward for Functional Recovery of Stroke Patients

“…Stroke is a leading cause of morbidity and mortality in the world [ 1 ]. Recent advances in diagnoses, management, and rehabilitation have had a significant impact on reducing mortality and functional recovery in stroke patients [ 2 , 3 ]. In spite of these medical advances, many stroke survivors still suffer from significant disability [ 4 ], and disability after stroke remains a burden to patients, caregivers, and society [ 5 ].…”

“…In spite of these medical advances, many stroke survivors still suffer from significant disability [ 4 ], and disability after stroke remains a burden to patients, caregivers, and society [ 5 ]. Most of the studies on stroke treatment and rehabilitation so far have been proposed through the analysis of average stroke patients [ 3 ]. Stroke is a complex disease caused by a combination of multiple risk factors [ 6 ].…”

“…Therefore, personalized medicine is more important than any other field in order to overcome the limitations of current stroke treatment. Recently, several review papers discuss the importance and necessity of a personalized approach to stroke treatment and rehabilitation [ 3 , 6 , 7 ].…”

“…Personalized medicine is a growing field in diagnosing, managing and predicting stroke and will enable clinicians to develop individually tailored care plans for stroke patients [ 3 , 6 , 7 , 22 ]. All papers published in this Special Issue will be able to contribute to the advance of personalized medicine in strokes [ 9 , 10 , 11 , 12 , 13 , 14 , 15 , 16 , 17 , 18 , 19 , 20 , 21 ].…”