Stroke is a leading cause of death and disability worldwide. The clinical validation of explainable and interpretable Artificial Intelligence (AI) solutions to assist a timely, personalised management of the acute phase of stroke, would have a major impact since it can greatly reduce the disability levels of patients. Also, the prediction of long-term outcomes is a crucial factor as it may determine critical decisions such as the discharge destination for the patient. Moreover, compliance with guideline-based secondary stroke prevention has been demonstrated to reduce stroke recurrence, but currently, only 40% of patients are adherent to preventive treatments 3 months after stroke. Therefore, patients´ outcomes can improve with proper patient communication and engagement packages. AI may have a dramatic impact on stroke patient journey, improving predictions, resulting in a better choice of secondary stroke strategies, as well as using evidence-based information to promote better adherence to treatment and reduction of vascular risk factors. The aim of this multicentre observational prospective study is to develop and validate AI-based tools to predict short and long-term outcomes in ischemic stroke patients. Specifically, this study aims to demonstrate the accuracy of AI models in predicting the functional outcome of ischaemic stroke patients as measured by the National Institutes of health Stroke Scale (NIHSS, 0-42) and the modified Rankin Scale (mRS, 0-6) scores at hospital discharge and at 3, 6 and 12 months after discharge. Prospective ischemic stroke patients from 3 Large European centres will be recruited. The training and testing of local AI models will be performed using hospitalization data, collected during the standard of care procedures for stroke patient pathways, and outpatient monitored data from a remote home-care system (NORA app) during the follow-up after discharge. These local models will then be integrated into a federated learning system, where only a global AI model, derived from combined insights of all local models, is shared across participating hospitals. The individual local models and the original data are not shared, ensuring data privacy and security. The accuracy and performance of prospectively optimized AI models in predicting clinical outcomes over a 12-month follow-up period will be evaluated and compared to the actual outcomes of the patients.
Study Type
OBSERVATIONAL
Enrollment
1,000
NORA app will be downloaded on the patient's mobile device, tablet or computer for clinical monitoring after discharge from the hospital at 3, 6 and 12 months after stroke. At the time of discharge, the patient will be provided with all the information and training necessary for its use. This application has been clinically validated in stroke patients, demonstrating to improve communication between professionals and patients. It improves the adherence of patients to prescribed therapy and their control of cardiovascular risk factors, with the the goal of preventing new episodes. Stroke patients have actively participated in the development of NORA, its use is simple and intuitive, and there are no age restrictions for its use. Through NORA patients will receive questionnaires to evaluate their clinical outcomes after stroke (Patient Reported Outcome Measures- PROMs and Patient Reported Experience Measures- PREMs).
KATHOLIEKE UNIVERSITEIT LEUVEN (KU Leuven)
Leuven, Belgium
Fondazione Policlinico Universitario A. Gemelli IRCCS, UOC Neurologia
Rome, Lazio, Italy
Hospital Vall D'Hebron- Institut de Recerca (Vhir)
Barcelona, Spain
AI model's accuracy in predicting short-term functional stroke outcomes
To evaluate the accuracy of the developed AI models in predicting functional outcomes of stroke patients, such as National Institute of Health Stroke Scale (NIHSS, 0-42) and modified Rankin Scale (mRS, 0-6) at hospital discharge (short-term outcome). Specifically, metrics such as Area Under the ROC Curve (AUROC) for classification tasks and R² for regression tasks will be evaluated, both for machine learning approaches such as Random Forest and XGBoost, and deep learning approaches, such as neural networks.
Time frame: 24 months
AI model's accuracy in predicting long-term functional outcomes
To evaluate the accuracy of the developed AI models in predicting National Institute of Health Stroke Scale (NIHSS, 0-42) and modified Rankin Scale (mRS, 0-6) at 3, 6 and 12 months after discharge. Moreover, other functional outcomes will be evaluated, such as Patient Reported Outcome Measures (PROMs) and Patient Reported Experience Measures (PREMs). Specifically, metrics such as Area Under the ROC Curve (AUROC) for classification tasks and R² for regression tasks will be evaluated, both for machine learning approaches such as Random Forest and XGBoost, and deep learning approaches, such as neural networks.
Time frame: 24 months
AI model's accuracy in predicting stroke associated risks
To evaluate the accuracy of AI models in predicting the probability of early supported discharge (1 week after the event), the probabilty of unplanned hospital readmission (at 30 days) and the personalized risk of stroke recurrence at 3 and at 12 months. Specifically, metrics such as Area Under the ROC Curve (AUROC) for classification tasks and R² for regression tasks will be evaluated, both for machine learning approaches such as Random Forest and XGBoost, and deep learning approaches, such as neural networks.
Time frame: 24 months
This platform is for informational purposes only and does not constitute medical advice. Always consult a qualified healthcare professional.