Optimizing anticoagulant use for stroke prevention: a systematic review of machine learning interventions

Objective: To identify and evaluate the use of machine learning interventions for optimizing anticoagulant use in stroke prevention among individuals at risk of stroke. Methods: This systematic review adhered to the PRISMA guidelines. Searches were conducted in PubMed and Google Scholar using MeSH...

Full description

Saved in:
Bibliographic Details
Main Authors: Feras Almarshad, Abdurrahman Mohammad Alshahrani, Abdurrahman Saad Al Faiz, Aamir Abbas, Muhammad Shabbir
Format: Article
Language:English
Published: Khyber Medical University 2024-12-01
Series:Khyber Medical University Journal
Subjects:
Online Access:https://www.kmuj.kmu.edu.pk/article/view/23682
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1849770256004808704
author Feras Almarshad
Abdurrahman Mohammad Alshahrani
Abdurrahman Saad Al Faiz
Aamir Abbas
Muhammad Shabbir
author_facet Feras Almarshad
Abdurrahman Mohammad Alshahrani
Abdurrahman Saad Al Faiz
Aamir Abbas
Muhammad Shabbir
author_sort Feras Almarshad
collection DOAJ
description Objective: To identify and evaluate the use of machine learning interventions for optimizing anticoagulant use in stroke prevention among individuals at risk of stroke. Methods: This systematic review adhered to the PRISMA guidelines. Searches were conducted in PubMed and Google Scholar using MeSH terms such as "Machine Learning," "Artificial Intelligence," "Anticoagulants," and "Decision Support System." Out of 333 screened articles, 36 were shortlisted based on titles, 24 after abstract review, and 15 after full-text evaluation. Included articles focused on machine learning's role in optimizing anticoagulant use for stroke prevention and analyzing primary data.  Data were extracted on study design, sample size, machine learning models used, and focus areas. Risk of bias was assessed using the Prediction Model Risk of Bias Assessment Tool. Results: Machine learning models, like logistic regression, deep neural networks, random forests, and XGBoost, outperformed traditional scoring systems like CHADS2 and CHA2DS2-VASc in predicting stroke risk. These models facilitated personalized treatment plans by incorporating genetic and metabolic data for dose optimization. Studies demonstrated the potential for machine learning to improve adherence to stroke prevention strategies, optimize anticoagulant doses, and enhance the rigor of observational studies. However, limitations included reliance on observational data and challenges in external validation and clinical utility assessments. Conclusion: Machine learning interventions show promise in optimizing anticoagulant use for stroke prevention, surpassing traditional tools in risk stratification and treatment personalization. However, further research is needed to validate these models in clinical settings and assess their impact on patient outcomes and adherence to stroke prevention strategies.
format Article
id doaj-art-b9fa66e18fa947dfac53cba4b47de302
institution DOAJ
issn 2305-2643
2305-2651
language English
publishDate 2024-12-01
publisher Khyber Medical University
record_format Article
series Khyber Medical University Journal
spelling doaj-art-b9fa66e18fa947dfac53cba4b47de3022025-08-20T03:03:05ZengKhyber Medical UniversityKhyber Medical University Journal2305-26432305-26512024-12-011643344110.35845/kmuj.2024.236822454Optimizing anticoagulant use for stroke prevention: a systematic review of machine learning interventionsFeras Almarshad0https://orcid.org/0000-0002-9468-1489Abdurrahman Mohammad Alshahrani1https://orcid.org/0000-0001-8814-9333Abdurrahman Saad Al Faiz2https://orcid.org/0009-0005-9488-0516Aamir Abbas3https://orcid.org/0000-0002-2634-2063Muhammad Shabbir4https://orcid.org/0000-0001-7449-8399Department of Medicine, College of Medicine, Shaqra University, Saudi ArabiaDepartment of Medicine, College of Medicine, Shaqra University, Saudi Arabia Department of Medicine, College of Medicine, Shaqra University, Saudi ArabiaDepartment of Global Health, PHC Global, PakistanDepartment of Medicine, College of Medicine, Shaqra University, Saudi ArabiaObjective: To identify and evaluate the use of machine learning interventions for optimizing anticoagulant use in stroke prevention among individuals at risk of stroke. Methods: This systematic review adhered to the PRISMA guidelines. Searches were conducted in PubMed and Google Scholar using MeSH terms such as "Machine Learning," "Artificial Intelligence," "Anticoagulants," and "Decision Support System." Out of 333 screened articles, 36 were shortlisted based on titles, 24 after abstract review, and 15 after full-text evaluation. Included articles focused on machine learning's role in optimizing anticoagulant use for stroke prevention and analyzing primary data.  Data were extracted on study design, sample size, machine learning models used, and focus areas. Risk of bias was assessed using the Prediction Model Risk of Bias Assessment Tool. Results: Machine learning models, like logistic regression, deep neural networks, random forests, and XGBoost, outperformed traditional scoring systems like CHADS2 and CHA2DS2-VASc in predicting stroke risk. These models facilitated personalized treatment plans by incorporating genetic and metabolic data for dose optimization. Studies demonstrated the potential for machine learning to improve adherence to stroke prevention strategies, optimize anticoagulant doses, and enhance the rigor of observational studies. However, limitations included reliance on observational data and challenges in external validation and clinical utility assessments. Conclusion: Machine learning interventions show promise in optimizing anticoagulant use for stroke prevention, surpassing traditional tools in risk stratification and treatment personalization. However, further research is needed to validate these models in clinical settings and assess their impact on patient outcomes and adherence to stroke prevention strategies.https://www.kmuj.kmu.edu.pk/article/view/23682machine learningstrokepredictive modelingartificial intelligenceanticoagulantsstroke preventionatrial fibrillationrisk stratificationintelligence
spellingShingle Feras Almarshad
Abdurrahman Mohammad Alshahrani
Abdurrahman Saad Al Faiz
Aamir Abbas
Muhammad Shabbir
Optimizing anticoagulant use for stroke prevention: a systematic review of machine learning interventions
Khyber Medical University Journal
machine learning
stroke
predictive modeling
artificial intelligence
anticoagulants
stroke prevention
atrial fibrillation
risk stratification
intelligence
title Optimizing anticoagulant use for stroke prevention: a systematic review of machine learning interventions
title_full Optimizing anticoagulant use for stroke prevention: a systematic review of machine learning interventions
title_fullStr Optimizing anticoagulant use for stroke prevention: a systematic review of machine learning interventions
title_full_unstemmed Optimizing anticoagulant use for stroke prevention: a systematic review of machine learning interventions
title_short Optimizing anticoagulant use for stroke prevention: a systematic review of machine learning interventions
title_sort optimizing anticoagulant use for stroke prevention a systematic review of machine learning interventions
topic machine learning
stroke
predictive modeling
artificial intelligence
anticoagulants
stroke prevention
atrial fibrillation
risk stratification
intelligence
url https://www.kmuj.kmu.edu.pk/article/view/23682
work_keys_str_mv AT ferasalmarshad optimizinganticoagulantuseforstrokepreventionasystematicreviewofmachinelearninginterventions
AT abdurrahmanmohammadalshahrani optimizinganticoagulantuseforstrokepreventionasystematicreviewofmachinelearninginterventions
AT abdurrahmansaadalfaiz optimizinganticoagulantuseforstrokepreventionasystematicreviewofmachinelearninginterventions
AT aamirabbas optimizinganticoagulantuseforstrokepreventionasystematicreviewofmachinelearninginterventions
AT muhammadshabbir optimizinganticoagulantuseforstrokepreventionasystematicreviewofmachinelearninginterventions