Machine learning algorithm for characterizing risks of hypertension, at an early stage in Bangladesh.

Autor: Islam MM; Department of Statistics, University of Rajshahi, Rajshahi 6205, Bangladesh. Electronic address: merajul.stat4811@gmail.com., Rahman MJ; Department of Statistics, University of Rajshahi, Rajshahi 6205, Bangladesh. Electronic address: jahanurmj@gmail.com., Chandra Roy D; Department of Statistics, University of Rajshahi, Rajshahi 6205, Bangladesh. Electronic address: dulalroystat@yahoo.com., Tawabunnahar M; Department of Statistics, Jatiya Kabi Kazi Nazrul Islam University, Mymensingh 2220, Bangladesh. Electronic address: tnrupa.7777@gmail.com., Jahan R; Institution of Education and Research, University of Rajshahi, Rajshahi 6205, Bangladesh. Electronic address: rubaiyat.jahan@ru.ac.bd., Ahmed NAMF; Institution of Education and Research, University of Rajshahi, Rajshahi 6205, Bangladesh. Electronic address: fahmed889@gmail.com., Maniruzzaman M; Statistics Discipline, Khulna University, Khulna 9208, Bangladesh. Electronic address: monir.stat91@gmail.com.
Jazyk: angličtina
Zdroj: Diabetes & metabolic syndrome [Diabetes Metab Syndr] 2021 May-Jun; Vol. 15 (3), pp. 877-884. Date of Electronic Publication: 2021 Apr 20.
DOI: 10.1016/j.dsx.2021.03.035
Abstrakt: Background and Aims: Hypertension has become a major public health issue as the prevalence and risk of premature death and disability among adults due to hypertension has increased globally. The main objective is to characterize the risk factors of hypertension among adults in Bangladesh using machine learning (ML) algorithms.
Materials and Methods: The hypertension data was derived from Bangladesh demographic and health survey, 2017-18, which included 6965 people aged 35 and above. Two most promising risk factor identification methods, namely least absolute shrinkage operator (LASSO) and support vector machine recursive feature elimination (SVMRFE) are implemented to detect the critical risk factors of hypertension. Additionally, four well-known ML algorithms as artificial neural network, decision tree, random forest, and gradient boosting (GB) have been used to predict hypertension. Performance scores of these algorithms were evaluated by accuracy, precision, recall, F-measure, and area under the curve (AUC).
Results: The results clarify that age, BMI, wealth index, working status, and marital status for LASSO and age, BMI, marital status, diabetes and region for SVMRFE appear to be the top-most five significant risk factors for hypertension. Our findings reveal that the combination of SVMRFE-GB gives the maximum accuracy (66.98%), recall (97.92%), F-measure (78.99%), and AUC (0.669) compared to others.
Conclusion: GB-based algorithm confirms the best performer for prediction of hypertension, at an early stage in Bangladesh. Therefore, this study highly suggests that the policymakers make proper judgments for controlling hypertension using SVMRFE-GB-based combination to save time and reduce cost for Bangladeshi adults.
Competing Interests: Declaration of competing interest The authors have no conflict of interest to declare.
(Copyright © 2021 Diabetes India. Published by Elsevier Ltd. All rights reserved.)
Databáze: MEDLINE
Externí odkaz: