Every year, stroke affects millions of people worldwide. Timing is important in strokes and patient care. Therefore, early detection of stroke aids patients to receive optimal treatments and intervention, leading to improved prognosis. Earlier diagnosis of stroke can be aided by imaging and artificial intelligence, which is essential for treatment outcomes of stroke patients.

Artificial intelligence application using imaging helps enhance diagnostic accuracy and interventional prognosis in stroke patients. In this research, a machine learning is created to aid in improving the diagnosis and prognosis of patients with strokes.   

The model was developed with artificial intelligence algorithms using over 2,520 patient data from hospitals and clinics. They were utilized for the development, training, and testing of the machine learning model. To train it, 65% of the patient data were randomly selected; to test it, the remaining 35% of the patient data was used for testing its diagnosis of strokes and prognosis of interventional outcomes.  

The artificial intelligence model achieved an overall 89.1% diagnostic accuracy and prognosis for stroke outcomes after interventions using imaging and the clinical patient data.   

In conclusion, artificial intelligence can be used to help healthcare professionals and underserved communities with early diagnosis of stroke and improved prognosis of stroke patient outcomes.