RESUMEN
INTRODUCTION: Formulating reliable prognosis for ischemic stroke patients remains a challenging task. We aimed to develop an artificial intelligence model able to formulate in the first 24 h after stroke an individualized prognosis in terms of NIHSS. PATIENTS AND METHODS: Seven hundred ninety four acute ischemic stroke patients were divided into a training (597) and testing (197) cohort. Clinical and instrumental data were collected in the first 24 h. We evaluated the performance of four machine-learning models (Random Forest, K-Nearest Neighbors, Support Vector Machine, XGBoost) in predicting NIHSS at discharge both in terms of variation between discharge and admission (regressor approach) and in terms of severity class namely NIHSS 0-5, 6-10, 11-20, >20 (classifier approach). We used Shapley Additive exPlanations values to weight features impact on predictions. RESULTS: XGBoost emerged as the best performing model. The classifier and regressor approaches perform similarly in terms of accuracy (80% vs 75%) and f1-score (79% vs 77%) respectively. However, the regressor has higher precision (85% vs 68%) in predicting prognosis of very severe stroke patients (NIHSS > 20). NIHSS at admission and 24 hours, GCS at 24 hours, heart rate, acute ischemic lesion on CT-scan and TICI score were the most impacting features on the prediction. DISCUSSION: Our approach, which employs an artificial intelligence based-tool, inherently able to continuously learn and improve its performance, could improve care pathway and support stroke physicians in the communication with patients and caregivers. CONCLUSION: XGBoost reliably predicts individualized outcome in terms of NIHSS at discharge in the first 24 hours after stroke.
RESUMEN
Disorders of Consciousness (DoCs) after severe acquired brain injury involve substantial impairment of cognition and physical functioning, requiring comprehensive rehabilitation and support. Technological interventions, such as immersive Virtual Reality (VR), have shown promising results in promoting neural activity and enhancing cognitive and motor recovery. VR can induce physical sensations that may activate the Autonomic Nervous System (ANS) and induce ANS-regulated responses. This study aimed to investigate the effects of immersive VR on the ANS in patients with DoCs through the analysis of the electrodermal activity (EDA). EDA was measured with a wearable device during a single immersive VR session consisting of static and dynamic videos depicting naturalistic environments. A pilot case-control study was conducted with 12 healthy participants and 12 individuals with DoCs. Results showed higher EDA values in patients than in healthy participants (p = 0.035), suggesting stronger autonomic activation during immersive VR exposure, while healthy subjects, in turn, showed a decrease in EDA values. Our results revealed a significant interaction between conditions and groups (p = 0.003), with patients showing significantly increased EDA values from the baseline compared to dynamic video observation (p = 0.014) and final rest (p = 0.007). These results suggest that immersive VR can elicit sympathetic arousal in patients with DoCs. This study highlights the potential of immersive VR as a tool to strengthen autonomic responses in patients with impaired consciousness.