• MALA K
• VINAY T P
• FAIZAN RAZAK S
• DEEPIKA B

In order to lessen the impact of cerebrovascular disorders on public health, early detection and intervention are essential. These diseases, which include stroke, are important causes of death and disability globally. Advances in machine learning (ML) have demonstrated potential in the identification of strokes, with the goal of supporting healthcare providers in making well-informed decisions about treatment and prophylactic measures. This study presents two approaches: one involved using brain CT images in conjunction with a genetic algorithm and a bidirectional long short-term memory (BiLSTM) to develop an early stroke detection system that achieved 96.5% accuracy. The other investigated the use of robust machine learning (ML) algorithms, such as logistic regression (LR), random forest (RF), and K- nearest neighbor (KNN), for the exceptional performance of 99% detection accuracy using ML.the ADASYN oversampling method combined with the RF algorithm. In the end, these methods improve patient outcomes by providing useful instruments for boosting clinical diagnosis and decision-making in stroke care.

, Logistic regression (LR), Random forest (RF), Knearest neighbor (KNN)

"Stroke Identification Using Machine Learning-Based Diagnostic Model", International Journal of Emerging Technologies and Innovative Research (www.jetir.org), ISSN:2349-5162, Vol.11, Issue 4, page no.d193-d196, April-2024, Available :http://www.jetir.org/papers/JETIR2404329.pdf

"Stroke Identification Using Machine Learning-Based Diagnostic Model", International Journal of Emerging Technologies and Innovative Research (www.jetir.org | UGC and issn Approved), ISSN:2349-5162, Vol.11, Issue 4, page no. ppd193-d196, April-2024, Available at : http://www.jetir.org/papers/JETIR2404329.pdf