Predicting stroke with machine learning techniques in a sub-Saharan African population

Background: Stroke is the second leading cause of death and the third leading cause of disability globally, including Africa, which bears its largest burden. Accurate models are needed in Africa to predict and prevent stroke occurrence. The aim of this study was to identify the best machine learning...

Full description

Saved in:
Bibliographic Details
Main Authors: Benjamin Segun Aribisala, Deirdre Edward, Godwin Ogbole, Onoja M. Akpa, Segun Ayilara, Fred Sarfo, Olusola Olabanjo, Adekunle Fakunle, Babafemi Oluropo Macaulay, Joseph Yaria, Joshua Akinyemi, Albert Akpalu, Kolawole Wahab, Reginald Obiako, Morenikeji Komolafe, Lukman Owolabi, Godwin Osaigbovo, Akinkunmi Paul Okekunle, Arti Singh, Philip Ibinaye, Osahon Osawata, Adeniyi Sunday, Ijezie Chukwuonye, Carolyn Jenkins, Hemant K. Tiwari, Okechukwu Ogah, Ruth Y. Laryea, Daniel T. Lackland, Oyedunni Arulogun, Omotolani Ajala, Rufus Akinyemi, Bruce Ovbiagele, Steffen Sammet, Mayowa Owolabi
Format: Article
Language:English
Published: Elsevier 2025-09-01
Series:Neuroscience Informatics
Subjects:
Online Access:http://www.sciencedirect.com/science/article/pii/S2772528625000317
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1849229268284866560
author Benjamin Segun Aribisala
Deirdre Edward
Godwin Ogbole
Onoja M. Akpa
Segun Ayilara
Fred Sarfo
Olusola Olabanjo
Adekunle Fakunle
Babafemi Oluropo Macaulay
Joseph Yaria
Joshua Akinyemi
Albert Akpalu
Kolawole Wahab
Reginald Obiako
Morenikeji Komolafe
Lukman Owolabi
Godwin Osaigbovo
Akinkunmi Paul Okekunle
Arti Singh
Philip Ibinaye
Osahon Osawata
Adeniyi Sunday
Ijezie Chukwuonye
Carolyn Jenkins
Hemant K. Tiwari
Okechukwu Ogah
Ruth Y. Laryea
Daniel T. Lackland
Oyedunni Arulogun
Omotolani Ajala
Rufus Akinyemi
Bruce Ovbiagele
Steffen Sammet
Mayowa Owolabi
author_facet Benjamin Segun Aribisala
Deirdre Edward
Godwin Ogbole
Onoja M. Akpa
Segun Ayilara
Fred Sarfo
Olusola Olabanjo
Adekunle Fakunle
Babafemi Oluropo Macaulay
Joseph Yaria
Joshua Akinyemi
Albert Akpalu
Kolawole Wahab
Reginald Obiako
Morenikeji Komolafe
Lukman Owolabi
Godwin Osaigbovo
Akinkunmi Paul Okekunle
Arti Singh
Philip Ibinaye
Osahon Osawata
Adeniyi Sunday
Ijezie Chukwuonye
Carolyn Jenkins
Hemant K. Tiwari
Okechukwu Ogah
Ruth Y. Laryea
Daniel T. Lackland
Oyedunni Arulogun
Omotolani Ajala
Rufus Akinyemi
Bruce Ovbiagele
Steffen Sammet
Mayowa Owolabi
author_sort Benjamin Segun Aribisala
collection DOAJ
description Background: Stroke is the second leading cause of death and the third leading cause of disability globally, including Africa, which bears its largest burden. Accurate models are needed in Africa to predict and prevent stroke occurrence. The aim of this study was to identify the best machine learning (ML) algorithm for stroke prediction. Methods: We assessed medical data of 4,236 subjects comprising 2,118 stroke patients and 2,118 controls from the SIREN database. Sixteen established vascular risk factors were evaluated in this study. These are addition of salt to food at table during eating, cardiac disease, diabetes mellitus, dyslipidemia, education, family history of cardiovascular disease, hypertension, income, low green leafy vegetable consumption, obesity, physical inactivity, regular meat consumption, regular sugar consumption, smoking, stress and use of tobacco. From these, we also selected the 11 topmost risk factors using Population-Attributable Risk ranking. Eleven ML models were built and empirically investigated using the 16 and the 11 risk factors. Results: Our results showed that the 16 features-based classification (maximum AUC of 82.32%) had a slightly better performance than the 11 feature-based (maximum AUC 81.17%) algorithm. The result also showed that Artificial Neural Network (ANN) had the best performance amongst eleven algorithms investigated with AUC of 82.32%, sensitivity of 71.23%, specificity of 80.00%. Conclusion: Machine Learning algorithms predicted stroke occurrence employing major risk factors in Sub-Saharan Africa better than regression models. Machine Learning, especially Artificial Neural Network, is recommended to enhance Afrocentric stroke prediction models for stroke risk factor quantification and control in Africa.
format Article
id doaj-art-d2a3c97136a1460f87f0ef7cba28d0a6
institution Kabale University
issn 2772-5286
language English
publishDate 2025-09-01
publisher Elsevier
record_format Article
series Neuroscience Informatics
spelling doaj-art-d2a3c97136a1460f87f0ef7cba28d0a62025-08-22T04:58:47ZengElsevierNeuroscience Informatics2772-52862025-09-015310021610.1016/j.neuri.2025.100216Predicting stroke with machine learning techniques in a sub-Saharan African populationBenjamin Segun Aribisala0Deirdre Edward1Godwin Ogbole2Onoja M. Akpa3Segun Ayilara4Fred Sarfo5Olusola Olabanjo6Adekunle Fakunle7Babafemi Oluropo Macaulay8Joseph Yaria9Joshua Akinyemi10Albert Akpalu11Kolawole Wahab12Reginald Obiako13Morenikeji Komolafe14Lukman Owolabi15Godwin Osaigbovo16Akinkunmi Paul Okekunle17Arti Singh18Philip Ibinaye19Osahon Osawata20Adeniyi Sunday21Ijezie Chukwuonye22Carolyn Jenkins23Hemant K. Tiwari24Okechukwu Ogah25Ruth Y. Laryea26Daniel T. Lackland27Oyedunni Arulogun28Omotolani Ajala29Rufus Akinyemi30Bruce Ovbiagele31Steffen Sammet32Mayowa Owolabi33Department of Radiology, University of Chicago, Chicago, IL, USA; Department of Computer Science, Lagos State University, Lagos, Nigeria; Department of Computer Science, Oduduwa University, NigeriaDepartment of Radiology, University of Chicago, Chicago, IL, USADepartment of Radiology, University of Ibadan, Ibadan, NigeriaDepartment of Epidemiology and Medical Statistics, University of Ibadan, NigeriaDepartment of Radiology, University of Ibadan, Ibadan, NigeriaDepartment of Medicine, Kwame Nkrumah University of Science and Technology, Kumasi, GhanaDepartment of Computer Science, Lagos State University, Lagos, NigeriaDepartment of Public Health, College of Health Sciences, Osun State University, Osogbo, Nigeria; Department of Medicine, College of Medicine, University of Ibadan, Ibadan, NigeriaDepartment of Computer Science, Lagos State University, Lagos, NigeriaDepartment of Medicine, College of Medicine, University of Ibadan, Ibadan, NigeriaDepartment of Epidemiology and Medical Statistics, University of Ibadan, NigeriaDepartment of Medicine, University of Ghana Medical School, Accra, GhanaDepartment of Medicine, University of Ilorin Teaching Hospital, Ilorin, NigeriaDepartment of Medicine, Ahmadu Bello University, Zaria, NigeriaDepartment of Medicine, Obafemi Awolowo University Teaching Hospital, Ile-Ife, NigeriaDepartment of Medicine, Aminu Kano Teaching Hospital, Kano, NigeriaDepartment of Medicine, University of Jos, Jos, NigeriaDepartment of Food and Nutrition, Seoul National University, KoreaDepartment of Epidemiology and Biostatistics, Kwame Nkrumah University of Science and Technology, GhanaDepartment of Medicine, Ahmadu Bello University, Zaria, NigeriaDepartment of Epidemiology and Medical Statistics, University of Ibadan, NigeriaDepartment of Medicine, University of Ilorin Teaching Hospital, Ilorin, NigeriaDepartment of Medicine, Federal Medical Centre, Umuahia, NigeriaMedical University of South Carolina, Charleston, USAUniversity of Alabama at Birmingham, Birmingham, AL, USADepartment of Epidemiology and Medical Statistics, University of Ibadan, NigeriaDepartment of Medicine, Kwame Nkrumah University of Science and Technology, Kumasi, GhanaMedical University of South Carolina, Charleston, USADepartment of Health Promotion, University of Ibadan, Ibadan, NigeriaDepartment of Medicine, College of Medicine, University of Ibadan, Ibadan, NigeriaDepartment of Medicine, Federal Medical Centre, Abeokuta, Nigeria; Centre for Genomic and Precision Medicine, College of Medicine, University of Ibadan, NigeriaWeill Institute for Neurosciences, School of Medicine, University of California San-Francisco, USADepartment of Radiology, University of Chicago, Chicago, IL, USA; Corresponding author at: Department of Radiology, University of Chicago Medicine, 5841 S. Maryland Avenue, MC2026 Chicago, IL 60637, USA.Department of Medicine, College of Medicine, University of Ibadan, Ibadan, Nigeria; Centre for Genomic and Precision Medicine, College of Medicine, University of Ibadan, Nigeria; Corresponding author at: Center for Genomics and Precision Medicine, College of Medicine, University of Ibadan, Ibadan, University College Hospital, Ibadan, and Blossom Specialist Medical Center, Ibadan, Nigeria.Background: Stroke is the second leading cause of death and the third leading cause of disability globally, including Africa, which bears its largest burden. Accurate models are needed in Africa to predict and prevent stroke occurrence. The aim of this study was to identify the best machine learning (ML) algorithm for stroke prediction. Methods: We assessed medical data of 4,236 subjects comprising 2,118 stroke patients and 2,118 controls from the SIREN database. Sixteen established vascular risk factors were evaluated in this study. These are addition of salt to food at table during eating, cardiac disease, diabetes mellitus, dyslipidemia, education, family history of cardiovascular disease, hypertension, income, low green leafy vegetable consumption, obesity, physical inactivity, regular meat consumption, regular sugar consumption, smoking, stress and use of tobacco. From these, we also selected the 11 topmost risk factors using Population-Attributable Risk ranking. Eleven ML models were built and empirically investigated using the 16 and the 11 risk factors. Results: Our results showed that the 16 features-based classification (maximum AUC of 82.32%) had a slightly better performance than the 11 feature-based (maximum AUC 81.17%) algorithm. The result also showed that Artificial Neural Network (ANN) had the best performance amongst eleven algorithms investigated with AUC of 82.32%, sensitivity of 71.23%, specificity of 80.00%. Conclusion: Machine Learning algorithms predicted stroke occurrence employing major risk factors in Sub-Saharan Africa better than regression models. Machine Learning, especially Artificial Neural Network, is recommended to enhance Afrocentric stroke prediction models for stroke risk factor quantification and control in Africa.http://www.sciencedirect.com/science/article/pii/S2772528625000317StrokeSIRENSub-Sahara AfricaRisk factorsMachine learningArtificial neural network
spellingShingle Benjamin Segun Aribisala
Deirdre Edward
Godwin Ogbole
Onoja M. Akpa
Segun Ayilara
Fred Sarfo
Olusola Olabanjo
Adekunle Fakunle
Babafemi Oluropo Macaulay
Joseph Yaria
Joshua Akinyemi
Albert Akpalu
Kolawole Wahab
Reginald Obiako
Morenikeji Komolafe
Lukman Owolabi
Godwin Osaigbovo
Akinkunmi Paul Okekunle
Arti Singh
Philip Ibinaye
Osahon Osawata
Adeniyi Sunday
Ijezie Chukwuonye
Carolyn Jenkins
Hemant K. Tiwari
Okechukwu Ogah
Ruth Y. Laryea
Daniel T. Lackland
Oyedunni Arulogun
Omotolani Ajala
Rufus Akinyemi
Bruce Ovbiagele
Steffen Sammet
Mayowa Owolabi
Predicting stroke with machine learning techniques in a sub-Saharan African population
Neuroscience Informatics
Stroke
SIREN
Sub-Sahara Africa
Risk factors
Machine learning
Artificial neural network
title Predicting stroke with machine learning techniques in a sub-Saharan African population
title_full Predicting stroke with machine learning techniques in a sub-Saharan African population
title_fullStr Predicting stroke with machine learning techniques in a sub-Saharan African population
title_full_unstemmed Predicting stroke with machine learning techniques in a sub-Saharan African population
title_short Predicting stroke with machine learning techniques in a sub-Saharan African population
title_sort predicting stroke with machine learning techniques in a sub saharan african population
topic Stroke
SIREN
Sub-Sahara Africa
Risk factors
Machine learning
Artificial neural network
url http://www.sciencedirect.com/science/article/pii/S2772528625000317
work_keys_str_mv AT benjaminsegunaribisala predictingstrokewithmachinelearningtechniquesinasubsaharanafricanpopulation
AT deirdreedward predictingstrokewithmachinelearningtechniquesinasubsaharanafricanpopulation
AT godwinogbole predictingstrokewithmachinelearningtechniquesinasubsaharanafricanpopulation
AT onojamakpa predictingstrokewithmachinelearningtechniquesinasubsaharanafricanpopulation
AT segunayilara predictingstrokewithmachinelearningtechniquesinasubsaharanafricanpopulation
AT fredsarfo predictingstrokewithmachinelearningtechniquesinasubsaharanafricanpopulation
AT olusolaolabanjo predictingstrokewithmachinelearningtechniquesinasubsaharanafricanpopulation
AT adekunlefakunle predictingstrokewithmachinelearningtechniquesinasubsaharanafricanpopulation
AT babafemioluropomacaulay predictingstrokewithmachinelearningtechniquesinasubsaharanafricanpopulation
AT josephyaria predictingstrokewithmachinelearningtechniquesinasubsaharanafricanpopulation
AT joshuaakinyemi predictingstrokewithmachinelearningtechniquesinasubsaharanafricanpopulation
AT albertakpalu predictingstrokewithmachinelearningtechniquesinasubsaharanafricanpopulation
AT kolawolewahab predictingstrokewithmachinelearningtechniquesinasubsaharanafricanpopulation
AT reginaldobiako predictingstrokewithmachinelearningtechniquesinasubsaharanafricanpopulation
AT morenikejikomolafe predictingstrokewithmachinelearningtechniquesinasubsaharanafricanpopulation
AT lukmanowolabi predictingstrokewithmachinelearningtechniquesinasubsaharanafricanpopulation
AT godwinosaigbovo predictingstrokewithmachinelearningtechniquesinasubsaharanafricanpopulation
AT akinkunmipaulokekunle predictingstrokewithmachinelearningtechniquesinasubsaharanafricanpopulation
AT artisingh predictingstrokewithmachinelearningtechniquesinasubsaharanafricanpopulation
AT philipibinaye predictingstrokewithmachinelearningtechniquesinasubsaharanafricanpopulation
AT osahonosawata predictingstrokewithmachinelearningtechniquesinasubsaharanafricanpopulation
AT adeniyisunday predictingstrokewithmachinelearningtechniquesinasubsaharanafricanpopulation
AT ijeziechukwuonye predictingstrokewithmachinelearningtechniquesinasubsaharanafricanpopulation
AT carolynjenkins predictingstrokewithmachinelearningtechniquesinasubsaharanafricanpopulation
AT hemantktiwari predictingstrokewithmachinelearningtechniquesinasubsaharanafricanpopulation
AT okechukwuogah predictingstrokewithmachinelearningtechniquesinasubsaharanafricanpopulation
AT ruthylaryea predictingstrokewithmachinelearningtechniquesinasubsaharanafricanpopulation
AT danieltlackland predictingstrokewithmachinelearningtechniquesinasubsaharanafricanpopulation
AT oyedunniarulogun predictingstrokewithmachinelearningtechniquesinasubsaharanafricanpopulation
AT omotolaniajala predictingstrokewithmachinelearningtechniquesinasubsaharanafricanpopulation
AT rufusakinyemi predictingstrokewithmachinelearningtechniquesinasubsaharanafricanpopulation
AT bruceovbiagele predictingstrokewithmachinelearningtechniquesinasubsaharanafricanpopulation
AT steffensammet predictingstrokewithmachinelearningtechniquesinasubsaharanafricanpopulation
AT mayowaowolabi predictingstrokewithmachinelearningtechniquesinasubsaharanafricanpopulation