The Use of Artificial Intelligence to Predict the Prognosis of Patients Undergoing Central Nervous System Rehabilitation: A Narrative Review

This review explores how artificial intelligence (AI) can predict the recovery of patients with central nervous system (CNS) disorders, such as stroke, traumatic brain injury, and spinal cord injury, who are undergoing rehabilitation. AI algorithms show potential in assessing a patient's prognosis, but face challenges in achieving high prediction accuracy for clinical use. The review suggests that more data, including medical imaging and collaboration between hospitals, could improve AI's predictive capabilities and transform patient care in CNS rehabilitation as healthcare professionals become more familiar with AI.

• 1
  AI algorithms, including random forests, deep neural networks, and convolutional neural networks, have been used to predict motor outcomes after stroke with AUCs ranging from 0.7 to 0.9.
• 2
  Studies using clinical data combined with MRI images as input variables have shown improved accuracy in predicting ambulatory outcomes in stroke patients.
• 3
  AI models have been developed to predict outcomes in traumatic brain injury (TBI) patients, but their performance varies, with some showing limited accuracy and others demonstrating potential for predicting adverse outcomes.