Hypertension distribution in the original dataset, and balanced class label distribution after applying the Synthetic Minority Oversampling Technique (SMOTE) for training and test data.

<p>Hypertension distribution in the original dataset, and balanced class label distribution after applying the Synthetic Minority Oversampling Technique (SMOTE) for training and test data.</p>

Saved in:
Bibliographic Details
Main Author: Probir Kumar Ghosh (6947282) (author)
Other Authors: Md. Aminul Islam (6750650) (author), Md. Ahshanul Haque (10525794) (author), Md. Tariqujjaman (7038959) (author), Novel Chandra Das (19742953) (author), Mohammad Ali (73095) (author), Md. Rasel Uddin (21648057) (author), Md. Golam Dostogir Harun (7208396) (author)
Published: 2025
Subjects:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1852018779071971328
author Probir Kumar Ghosh (6947282)
author2 Md. Aminul Islam (6750650)
Md. Ahshanul Haque (10525794)
Md. Tariqujjaman (7038959)
Novel Chandra Das (19742953)
Mohammad Ali (73095)
Md. Rasel Uddin (21648057)
Md. Golam Dostogir Harun (7208396)
author2_role author
author
author
author
author
author
author
author_facet Probir Kumar Ghosh (6947282)
Md. Aminul Islam (6750650)
Md. Ahshanul Haque (10525794)
Md. Tariqujjaman (7038959)
Novel Chandra Das (19742953)
Mohammad Ali (73095)
Md. Rasel Uddin (21648057)
Md. Golam Dostogir Harun (7208396)
author_role author
dc.creator.none.fl_str_mv Probir Kumar Ghosh (6947282)
Md. Aminul Islam (6750650)
Md. Ahshanul Haque (10525794)
Md. Tariqujjaman (7038959)
Novel Chandra Das (19742953)
Mohammad Ali (73095)
Md. Rasel Uddin (21648057)
Md. Golam Dostogir Harun (7208396)
dc.date.none.fl_str_mv 2025-07-02T18:00:59Z
dc.identifier.none.fl_str_mv 10.1371/journal.pcbi.1013211.g002
dc.relation.none.fl_str_mv https://figshare.com/articles/figure/Hypertension_distribution_in_the_original_dataset_and_balanced_class_label_distribution_after_applying_the_Synthetic_Minority_Oversampling_Technique_SMOTE_for_training_and_test_data_/29464125
dc.rights.none.fl_str_mv CC BY 4.0
info:eu-repo/semantics/openAccess
dc.subject.none.fl_str_mv Medicine
Biotechnology
Computational Biology
Mathematical Sciences not elsewhere classified
systolic blood pressure
shapley additive explanations
refined risk estimate
random forest model
individual conditional expectation
estimating causal relationships
double machine learning
diastolic blood pressure
assessing causal effect
90 &# 8201
79 &# 8211
140 &# 8201
07 &# 8211
body mass index
used logistic regression
nonlinear observed confounders
dataset included 11
biased methods provided
17 &# 8211
excessive body weight
shap plots reveal
identified older age
health surveys data
demonstrating complex interactions
ses ), self
body weight
used 11
ses ),
17 ),
nonlinear relation
health population
biased method
dml ),
hypertension data
xlink ">
targeted interventions
study aims
socioeconomic status
significantly contributed
shown effectiveness
mm hg
limited settings
key predictors
income countries
including age
identifying predictors
identify predictors
female gender
evaluation f1
average age
dc.title.none.fl_str_mv Hypertension distribution in the original dataset, and balanced class label distribution after applying the Synthetic Minority Oversampling Technique (SMOTE) for training and test data.
dc.type.none.fl_str_mv Image
Figure
info:eu-repo/semantics/publishedVersion
image
description <p>Hypertension distribution in the original dataset, and balanced class label distribution after applying the Synthetic Minority Oversampling Technique (SMOTE) for training and test data.</p>
eu_rights_str_mv openAccess
id Manara_4dfc183261b8a6ceebabac3bab40fd39
identifier_str_mv 10.1371/journal.pcbi.1013211.g002
network_acronym_str Manara
network_name_str ManaraRepo
oai_identifier_str oai:figshare.com:article/29464125
publishDate 2025
repository.mail.fl_str_mv
repository.name.fl_str_mv
repository_id_str
rights_invalid_str_mv CC BY 4.0
spelling Hypertension distribution in the original dataset, and balanced class label distribution after applying the Synthetic Minority Oversampling Technique (SMOTE) for training and test data.Probir Kumar Ghosh (6947282)Md. Aminul Islam (6750650)Md. Ahshanul Haque (10525794)Md. Tariqujjaman (7038959)Novel Chandra Das (19742953)Mohammad Ali (73095)Md. Rasel Uddin (21648057)Md. Golam Dostogir Harun (7208396)MedicineBiotechnologyComputational BiologyMathematical Sciences not elsewhere classifiedsystolic blood pressureshapley additive explanationsrefined risk estimaterandom forest modelindividual conditional expectationestimating causal relationshipsdouble machine learningdiastolic blood pressureassessing causal effect90 &# 820179 &# 8211140 &# 820107 &# 8211body mass indexused logistic regressionnonlinear observed confoundersdataset included 11biased methods provided17 &# 8211excessive body weightshap plots revealidentified older agehealth surveys datademonstrating complex interactionsses ), selfbody weightused 11ses ),17 ),nonlinear relationhealth populationbiased methoddml ),hypertension dataxlink ">targeted interventionsstudy aimssocioeconomic statussignificantly contributedshown effectivenessmm hglimited settingskey predictorsincome countriesincluding ageidentifying predictorsidentify predictorsfemale genderevaluation f1average age<p>Hypertension distribution in the original dataset, and balanced class label distribution after applying the Synthetic Minority Oversampling Technique (SMOTE) for training and test data.</p>2025-07-02T18:00:59ZImageFigureinfo:eu-repo/semantics/publishedVersionimage10.1371/journal.pcbi.1013211.g002https://figshare.com/articles/figure/Hypertension_distribution_in_the_original_dataset_and_balanced_class_label_distribution_after_applying_the_Synthetic_Minority_Oversampling_Technique_SMOTE_for_training_and_test_data_/29464125CC BY 4.0info:eu-repo/semantics/openAccessoai:figshare.com:article/294641252025-07-02T18:00:59Z
spellingShingle Hypertension distribution in the original dataset, and balanced class label distribution after applying the Synthetic Minority Oversampling Technique (SMOTE) for training and test data.
Probir Kumar Ghosh (6947282)
Medicine
Biotechnology
Computational Biology
Mathematical Sciences not elsewhere classified
systolic blood pressure
shapley additive explanations
refined risk estimate
random forest model
individual conditional expectation
estimating causal relationships
double machine learning
diastolic blood pressure
assessing causal effect
90 &# 8201
79 &# 8211
140 &# 8201
07 &# 8211
body mass index
used logistic regression
nonlinear observed confounders
dataset included 11
biased methods provided
17 &# 8211
excessive body weight
shap plots reveal
identified older age
health surveys data
demonstrating complex interactions
ses ), self
body weight
used 11
ses ),
17 ),
nonlinear relation
health population
biased method
dml ),
hypertension data
xlink ">
targeted interventions
study aims
socioeconomic status
significantly contributed
shown effectiveness
mm hg
limited settings
key predictors
income countries
including age
identifying predictors
identify predictors
female gender
evaluation f1
average age
status_str publishedVersion
title Hypertension distribution in the original dataset, and balanced class label distribution after applying the Synthetic Minority Oversampling Technique (SMOTE) for training and test data.
title_full Hypertension distribution in the original dataset, and balanced class label distribution after applying the Synthetic Minority Oversampling Technique (SMOTE) for training and test data.
title_fullStr Hypertension distribution in the original dataset, and balanced class label distribution after applying the Synthetic Minority Oversampling Technique (SMOTE) for training and test data.
title_full_unstemmed Hypertension distribution in the original dataset, and balanced class label distribution after applying the Synthetic Minority Oversampling Technique (SMOTE) for training and test data.
title_short Hypertension distribution in the original dataset, and balanced class label distribution after applying the Synthetic Minority Oversampling Technique (SMOTE) for training and test data.
title_sort Hypertension distribution in the original dataset, and balanced class label distribution after applying the Synthetic Minority Oversampling Technique (SMOTE) for training and test data.
topic Medicine
Biotechnology
Computational Biology
Mathematical Sciences not elsewhere classified
systolic blood pressure
shapley additive explanations
refined risk estimate
random forest model
individual conditional expectation
estimating causal relationships
double machine learning
diastolic blood pressure
assessing causal effect
90 &# 8201
79 &# 8211
140 &# 8201
07 &# 8211
body mass index
used logistic regression
nonlinear observed confounders
dataset included 11
biased methods provided
17 &# 8211
excessive body weight
shap plots reveal
identified older age
health surveys data
demonstrating complex interactions
ses ), self
body weight
used 11
ses ),
17 ),
nonlinear relation
health population
biased method
dml ),
hypertension data
xlink ">
targeted interventions
study aims
socioeconomic status
significantly contributed
shown effectiveness
mm hg
limited settings
key predictors
income countries
including age
identifying predictors
identify predictors
female gender
evaluation f1
average age