ML algorithms used in this study.

<div><p>Depression presents a significant challenge to global mental health, often intertwined with factors including oxidative stress. Although the precise relationship with mitochondrial pathways remains elusive, recent advances in machine learning present an avenue for further investi...

وصف كامل

محفوظ في:
التفاصيل البيبلوغرافية
المؤلف الرئيسي: Toheeb Salahudeen (21368040) (author)
مؤلفون آخرون: Maher Maalouf (6318215) (author), Ibrahim (Abe) M. Elfadel (21368043) (author), Herbert F. Jelinek (7039787) (author)
منشور في: 2025
الموضوعات:
الوسوم: إضافة وسم
لا توجد وسوم, كن أول من يضع وسما على هذه التسجيلة!
_version_ 1852020393757376512
author Toheeb Salahudeen (21368040)
author2 Maher Maalouf (6318215)
Ibrahim (Abe) M. Elfadel (21368043)
Herbert F. Jelinek (7039787)
author2_role author
author
author
author_facet Toheeb Salahudeen (21368040)
Maher Maalouf (6318215)
Ibrahim (Abe) M. Elfadel (21368043)
Herbert F. Jelinek (7039787)
author_role author
dc.creator.none.fl_str_mv Toheeb Salahudeen (21368040)
Maher Maalouf (6318215)
Ibrahim (Abe) M. Elfadel (21368043)
Herbert F. Jelinek (7039787)
dc.date.none.fl_str_mv 2025-05-15T14:57:23Z
dc.identifier.none.fl_str_mv 10.1371/journal.pone.0320955.t005
dc.relation.none.fl_str_mv https://figshare.com/articles/dataset/ML_algorithms_used_in_this_study_/29075070
dc.rights.none.fl_str_mv CC BY 4.0
info:eu-repo/semantics/openAccess
dc.subject.none.fl_str_mv Cell Biology
Biotechnology
Science Policy
Biological Sciences not elsewhere classified
Chemical Sciences not elsewhere classified
Information Systems not elsewhere classified
machine learning present
machine learning models
global mental health
56 %, respectively
26 %, respectively
1 %, respectively
unbalanced data sets
aid clinical assessment
multiclass classification scenarios
including random forest
random forest
clinical indicators
three classes
significant challenge
shedding light
rf achieved
recent advances
precise relationship
often intertwined
mitochondrial peptides
five classes
findings underscore
f1 score
diabetes mellitus
comorbid conditions
balanced data
dc.title.none.fl_str_mv ML algorithms used in this study.
dc.type.none.fl_str_mv Dataset
info:eu-repo/semantics/publishedVersion
dataset
description <div><p>Depression presents a significant challenge to global mental health, often intertwined with factors including oxidative stress. Although the precise relationship with mitochondrial pathways remains elusive, recent advances in machine learning present an avenue for further investigation. This study employed advanced machine learning techniques to classify major depressive disorders based on clinical indicators and mitochondrial oxidative stress markers. Six machine learning algorithms, including Random Forest, were applied and their performance was investigated in balanced and unbalanced data sets with respect to binary and multiclass classification scenarios. Results indicate promising accuracy and precision, particularly with Random Forest on balanced data. RF achieved an average accuracy of 92.7% and an F1 score of 83.95% for binary classification, 90.36% and 90.1%, respectively, for the classification of three classes of severity of depression and 89.76% and 88.26%, respectively, for the classification of five classes. Including only oxidative stress markers resulted in accuracy and an F1 score of 79.52% and 80.56%, respectively. Notably, including mitochondrial peptides alongside clinical factors significantly enhances predictive capability, shedding light on the interplay between depression severity and mitochondrial oxidative stress pathways. These findings underscore the potential for machine learning models to aid clinical assessment, particularly in individuals with comorbid conditions such as hypertension, diabetes mellitus, and cardiovascular disease.</p></div>
eu_rights_str_mv openAccess
id Manara_7df6f9a4e654724724182982cdcd0892
identifier_str_mv 10.1371/journal.pone.0320955.t005
network_acronym_str Manara
network_name_str ManaraRepo
oai_identifier_str oai:figshare.com:article/29075070
publishDate 2025
repository.mail.fl_str_mv
repository.name.fl_str_mv
repository_id_str
rights_invalid_str_mv CC BY 4.0
spelling ML algorithms used in this study.Toheeb Salahudeen (21368040)Maher Maalouf (6318215)Ibrahim (Abe) M. Elfadel (21368043)Herbert F. Jelinek (7039787)Cell BiologyBiotechnologyScience PolicyBiological Sciences not elsewhere classifiedChemical Sciences not elsewhere classifiedInformation Systems not elsewhere classifiedmachine learning presentmachine learning modelsglobal mental health56 %, respectively26 %, respectively1 %, respectivelyunbalanced data setsaid clinical assessmentmulticlass classification scenariosincluding random forestrandom forestclinical indicatorsthree classessignificant challengeshedding lightrf achievedrecent advancesprecise relationshipoften intertwinedmitochondrial peptidesfive classesfindings underscoref1 scorediabetes mellituscomorbid conditionsbalanced data<div><p>Depression presents a significant challenge to global mental health, often intertwined with factors including oxidative stress. Although the precise relationship with mitochondrial pathways remains elusive, recent advances in machine learning present an avenue for further investigation. This study employed advanced machine learning techniques to classify major depressive disorders based on clinical indicators and mitochondrial oxidative stress markers. Six machine learning algorithms, including Random Forest, were applied and their performance was investigated in balanced and unbalanced data sets with respect to binary and multiclass classification scenarios. Results indicate promising accuracy and precision, particularly with Random Forest on balanced data. RF achieved an average accuracy of 92.7% and an F1 score of 83.95% for binary classification, 90.36% and 90.1%, respectively, for the classification of three classes of severity of depression and 89.76% and 88.26%, respectively, for the classification of five classes. Including only oxidative stress markers resulted in accuracy and an F1 score of 79.52% and 80.56%, respectively. Notably, including mitochondrial peptides alongside clinical factors significantly enhances predictive capability, shedding light on the interplay between depression severity and mitochondrial oxidative stress pathways. These findings underscore the potential for machine learning models to aid clinical assessment, particularly in individuals with comorbid conditions such as hypertension, diabetes mellitus, and cardiovascular disease.</p></div>2025-05-15T14:57:23ZDatasetinfo:eu-repo/semantics/publishedVersiondataset10.1371/journal.pone.0320955.t005https://figshare.com/articles/dataset/ML_algorithms_used_in_this_study_/29075070CC BY 4.0info:eu-repo/semantics/openAccessoai:figshare.com:article/290750702025-05-15T14:57:23Z
spellingShingle ML algorithms used in this study.
Toheeb Salahudeen (21368040)
Cell Biology
Biotechnology
Science Policy
Biological Sciences not elsewhere classified
Chemical Sciences not elsewhere classified
Information Systems not elsewhere classified
machine learning present
machine learning models
global mental health
56 %, respectively
26 %, respectively
1 %, respectively
unbalanced data sets
aid clinical assessment
multiclass classification scenarios
including random forest
random forest
clinical indicators
three classes
significant challenge
shedding light
rf achieved
recent advances
precise relationship
often intertwined
mitochondrial peptides
five classes
findings underscore
f1 score
diabetes mellitus
comorbid conditions
balanced data
status_str publishedVersion
title ML algorithms used in this study.
title_full ML algorithms used in this study.
title_fullStr ML algorithms used in this study.
title_full_unstemmed ML algorithms used in this study.
title_short ML algorithms used in this study.
title_sort ML algorithms used in this study.
topic Cell Biology
Biotechnology
Science Policy
Biological Sciences not elsewhere classified
Chemical Sciences not elsewhere classified
Information Systems not elsewhere classified
machine learning present
machine learning models
global mental health
56 %, respectively
26 %, respectively
1 %, respectively
unbalanced data sets
aid clinical assessment
multiclass classification scenarios
including random forest
random forest
clinical indicators
three classes
significant challenge
shedding light
rf achieved
recent advances
precise relationship
often intertwined
mitochondrial peptides
five classes
findings underscore
f1 score
diabetes mellitus
comorbid conditions
balanced data