Early diagnosis of stroke disorder using homogenous logistic regression ensemble classifier

Document Type : Research Paper


Department of CSE, PSG College of Technology, Coimbatore, India


A stroke occurs in the scenario wherein the blood supply to the brain is blocked, leading to a lack of oxygen to the blood. There is a need for the early diagnosis of the stroke to handle the emergency situations of stroke in an efficient manner. Integration of Artificial Intelligence (AI) in the early diagnosis of stroke provides efficiency and flexibility. Artificial Intelligence (AI), which is a mimic of human intelligence has a wide range of applications from small scale systems to high-end enterprise systems. Artificial Intelligence has emerged as an efficient and accurate decision-making system in healthcare systems. Machine Learning (ML) is a subset of Artificial Intelligence (AI). The incorporation of machine learning techniques in stroke diagnosis systems provides faster and precise decisions. The proposed system aims to develop an early diagnosis of stroke disorder using a homogenous logistic regression ensemble classifier. Logistic regression is a linear algorithm that uses maximum likelihood methodology for predictions and a standard machine learning model for two-class problems. The prediction is improved by accumulating the predictions of two or more logistic regression using a bagging ensemble classifier thereby increasing the accuracy of the stroke diagnosis system. The accumulation of prediction of two or more same models is known as a homogenous ensemble classifier. The results obtained show that the proposed homogenous logistic regression ensemble model has higher accuracy than single logistic regression.


[1] L. Amini, R. Azarpazhouh, M.T. Farzadfar, S.A. Mousavi, F. Jazaieri, F. Khorvash, R. Norouzi and N. Toghianfar,
Prediction and control of stroke by data mining, Int. J. Prev. Med. 4(Suppl. 2) (2013) 245–249.
[2] K.-L. Chien, T.-C. Su, H.-C. Hsu, W.-T. Chang, P.-C. Chen, F.-C. Sung, M.-F. Chen and Y.-T. Lee, Constructing
the prediction model for the risk of stroke in a Chinese population, Stroke 41(9) (2010) 1858–1864.
[3] J.N. Heo, J.G. Yoon, H. Park, Y.D. Kim, H.S. Nam and J.H. Heo, Machine learning–based model for prediction
of outcomes in acute stroke, Stroke 50(5) (2019) 1263–1265.
[4] S.N. Min, S.J. Park, D.J. Kim, M. Subramaniyam and K.S. Lee, Development of an algorithm for stroke prediction:
A national health insurance database study in Korea, Eur. Neurol 79(3-4) (2018) 214–220.
[5] K.G.M. Moons, M.L. Bots, J.T. Salonen, P. Elwood, D. Freire, Y. Nikitin, J. Sivenius, D. Inzitari, V. Benetou,
J. Tuomilehto, P. Koudstaal and D. Grobbee, Prediction of stroke in the general population in Europe (EUROSTROKE): Is there a role for fibrinogen and electrocardiography?, J. Epidemiol Community Health 56 (2002)
[6] M. Rajora, M. Rathod and N.S. Naik, Stroke prediction using machine learning in a distributed environment,
In: D. Goswami and T.A. Hoang (eds), Distributed Computing and Internet Technology, ICDCIT 2021, Lecture
Notes in Computer Science, 12582 (2021).
[7] S. Revanth, S. Sanjay, N. Sanjay and V. Vijayaganth, Stroke prediction using machine learning algorithms, Int.
J. Disaster Recovery and Business Contin. 11(1) (2020) 3081–308.
[8] M.S. Singh and P. Choudhary, Stroke prediction using artificial intelligence, 8th Annual Indust. Automa. Electromech. Engin. Conf.(2017) 158–161.
[9] J. Yu, S. Park, S.-H. Kwon, C.M.B. Ho, C.-S. Pyo and H. Lee, AI-based stroke disease prediction system using
real-time electromyography signals, Appl. Sci. 10(19) (2020) 6791.
Volume 12, Special Issue
December 2021
Pages 1649-1654
  • Receive Date: 25 July 2021
  • Revise Date: 22 October 2021
  • Accept Date: 13 November 2021