Academic Journal
Προβολή σε EDS

Challenges and recent advances in methods for handling imbalanced multiclass classification problems: a methodological review.

Λεπτομέρειες βιβλιογραφικής εγγραφής
Τίτλος: Challenges and recent advances in methods for handling imbalanced multiclass classification problems: a methodological review.
Συγγραφείς: Acharya S; Department of Applied Statistics and Data Science, Prasanna School of Public Health, Manipal Academy of Higher Education, Manipal, Karnataka, 576104, India., Poojari S; Department of Applied Statistics and Data Science, Prasanna School of Public Health, Manipal Academy of Higher Education, Manipal, Karnataka, 576104, India. satya.narayana@manipal.edu., R VL; Department of Health Technology and Informatics, Prasanna School of Public Health, Manipal Academy of Higher Education, Manipal, Karnataka, 576104, India., Kamath A; Department of Applied Statistics and Data Science, Prasanna School of Public Health, Manipal Academy of Higher Education, Manipal, Karnataka, 576104, India.
Πηγή: BMC medical research methodology [BMC Med Res Methodol] 2026 Jun 20; Vol. 26 (1). Date of Electronic Publication: 2026 Jun 20.
Τύπος έκδοσης: Journal Article; Review
Γλώσσα: English
Στοιχεία περιοδικού: Publisher: BioMed Central Country of Publication: England NLM ID: 100968545 Publication Model: Electronic Cited Medium: Internet ISSN: 1471-2288 (Electronic) Linking ISSN: 14712288 NLM ISO Abbreviation: BMC Med Res Methodol Subsets: MEDLINE
Imprint Name(s): Original Publication: London : BioMed Central, [2001-
Ιατρικοί όροι (MeSH): Classification Algorithms* , Medical Informatics*, Humans
Περίληψη: Background: Class imbalance is a common challenge in real-world health science applications, including medical diagnosis, rare disease detection, and ICU mortality prediction, where one or more classes are underrepresented. Although several methods address imbalance in binary classification, multiclass imbalance remains particularly challenging due to multiple minority classes, often leading to biased performance and reduced predictive accuracy. Despite several advancements, most classification models struggle to identify patterns in imbalanced data, limiting their effectiveness in real-world applications.
Methods: A structured literature search was conducted to identify methodological studies on imbalanced multiclass classification, including algorithmic strategies and advances in performance evaluation. Articles published up to 2024 were retrieved from Scopus and Web of Science using predefined keywords. Studies were screened through titles and abstracts based on predefined inclusion and exclusion criteria, with additional backward citation searching for methodologically relevant studies. In total, 75 studies were included in the final methodological review to synthesize key challenges and recent advances.
Results: Despite the introduction of several metrics for assessing multiclass imbalance, the Imbalance Ratio (IR) remains the most commonly used measure for quantifying imbalance severity. Existing balancing techniques mainly rely on distance-based, cluster-based, and distribution-based approaches, reflecting methodological diversity. In multiclass settings, various decomposition strategies, classification algorithms, and performance metrics have been proposed to address imbalance; however, repeated use of imbalance-handling mechanisms, such as class weight adjustments across decomposition, training, and evaluation stages, may introduce bias. The effectiveness of these strategies depends on data characteristics including dimensionality, sample size, distribution, number of classes, and imbalance severity. Notably, insufficient reporting of these characteristics in many studies limits the assessment of feasibility and generalizability across diverse data settings.
Conclusions: This review synthesizes the strengths and limitations of existing methods for handling imbalanced multiclass classification, offering practical insights for improving model robustness and predictive performance. Effective management of class imbalance supports several Sustainable Development Goals by promoting equitable decision-making and enhancing reliable analysis across diverse health, societal, and environmental challenges, making it essential for developing robust and generalizable models across diverse domains.
(© 2026. The Author(s).)
Competing Interests: Declarations. Ethics approval and consent to participate: Not applicable. Consent for publication: Not applicable. Competing interests: The authors declare no competing interests.
References: IEEE Trans Cybern. 2016 May;46(5):1078-91. (PMID: 25955858)
Sci Rep. 2024 May 10;14(1):10759. (PMID: 38730045)
Sensors (Basel). 2021 Oct 04;21(19):. (PMID: 34640936)
IEEE Trans Neural Netw Learn Syst. 2020 Aug;31(8):2818-2831. (PMID: 31247563)
IEEE Trans Syst Man Cybern B Cybern. 2012 Aug;42(4):1119-30. (PMID: 22438514)
Contributed Indexing: Keywords: Binarization; Class imbalance; Imbalance measure; Imbalance ratio; Multiclass classification; Multiclass imbalance
Entry Date(s): Date Created: 20260620 Date Completed: 20260902 Latest Revision: 20260908
Update Code: 20260909
PubMed Central ID: PMC13536707
DOI: 10.1186/s12874-026-02899-w
PMID: 42323527
Βάση Δεδομένων: MEDLINE
FullText Text:
  Availability: 0
CustomLinks:
  – Url: https://resolver.ebsco.com/c/fiv2js/result?sid=EBSCO:cmedm&genre=article&issn=14712288&ISBN=&volume=26&issue=1&date=20260620&spage=&pages=&title=BMC medical research methodology&atitle=Challenges%20and%20recent%20advances%20in%20methods%20for%20handling%20imbalanced%20multiclass%20classification%20problems%3A%20a%20methodological%20review.&aulast=Acharya%20S&id=DOI:10.1186/s12874-026-02899-w
    Name: Full Text Finder (for New FTF UI) (ns324271)
    Category: fullText
    Text: Full Text Finder
    MouseOverText: Full Text Finder
Header DbId: cmedm
DbLabel: MEDLINE
An: 42323527
AccessLevel: 3
PubType: Academic Journal
PubTypeId: academicJournal
PreciseRelevancyScore: 0
IllustrationInfo
Items – Name: Title
  Label: Title
  Group: Ti
  Data: Challenges and recent advances in methods for handling imbalanced multiclass classification problems: a methodological review.
– Name: Author
  Label: Authors
  Group: Au
  Data: <searchLink fieldCode="AU" term="%22Acharya+S%22">Acharya S</searchLink>; Department of Applied Statistics and Data Science, Prasanna School of Public Health, Manipal Academy of Higher Education, Manipal, Karnataka, 576104, India.<br /><searchLink fieldCode="AU" term="%22Poojari+S%22">Poojari S</searchLink>; Department of Applied Statistics and Data Science, Prasanna School of Public Health, Manipal Academy of Higher Education, Manipal, Karnataka, 576104, India. satya.narayana@manipal.edu.<br /><searchLink fieldCode="AU" term="%22R+VL%22">R VL</searchLink>; Department of Health Technology and Informatics, Prasanna School of Public Health, Manipal Academy of Higher Education, Manipal, Karnataka, 576104, India.<br /><searchLink fieldCode="AU" term="%22Kamath+A%22">Kamath A</searchLink>; Department of Applied Statistics and Data Science, Prasanna School of Public Health, Manipal Academy of Higher Education, Manipal, Karnataka, 576104, India.
– Name: TitleSource
  Label: Source
  Group: Src
  Data: <searchLink fieldCode="JN" term="%22100968545%22">BMC medical research methodology</searchLink> [BMC Med Res Methodol] 2026 Jun 20; Vol. 26 (1). <i>Date of Electronic Publication: </i>2026 Jun 20.
– Name: TypePub
  Label: Publication Type
  Group: TypPub
  Data: Journal Article; Review
– Name: Language
  Label: Language
  Group: Lang
  Data: English
– Name: TitleSource
  Label: Journal Info
  Group: Src
  Data: <i>Publisher: </i><searchLink fieldCode="PB" term="%22BioMed+Central%22">BioMed Central </searchLink><i>Country of Publication: </i>England <i>NLM ID: </i>100968545 <i>Publication Model: </i>Electronic <i>Cited Medium: </i>Internet <i>ISSN: </i>1471-2288 (Electronic) <i>Linking ISSN: </i><searchLink fieldCode="IS" term="%2214712288%22">14712288 </searchLink><i>NLM ISO Abbreviation: </i>BMC Med Res Methodol <i>Subsets: </i>MEDLINE
– Name: PublisherInfo
  Label: Imprint Name(s)
  Group: PubInfo
  Data: <i>Original Publication</i>: London : BioMed Central, [2001-
– Name: SubjectMESH
  Label: MeSH Terms
  Group: Su
  Data: <searchLink fieldCode="MM" term="%22Classification+Algorithms%22">Classification Algorithms*</searchLink> <br /><searchLink fieldCode="MM" term="%22Medical+Informatics%22">Medical Informatics*</searchLink><br /><searchLink fieldCode="MH" term="%22Humans%22">Humans</searchLink>
– Name: Abstract
  Label: Abstract
  Group: Ab
  Data: Background: Class imbalance is a common challenge in real-world health science applications, including medical diagnosis, rare disease detection, and ICU mortality prediction, where one or more classes are underrepresented. Although several methods address imbalance in binary classification, multiclass imbalance remains particularly challenging due to multiple minority classes, often leading to biased performance and reduced predictive accuracy. Despite several advancements, most classification models struggle to identify patterns in imbalanced data, limiting their effectiveness in real-world applications.<br />Methods: A structured literature search was conducted to identify methodological studies on imbalanced multiclass classification, including algorithmic strategies and advances in performance evaluation. Articles published up to 2024 were retrieved from Scopus and Web of Science using predefined keywords. Studies were screened through titles and abstracts based on predefined inclusion and exclusion criteria, with additional backward citation searching for methodologically relevant studies. In total, 75 studies were included in the final methodological review to synthesize key challenges and recent advances.<br />Results: Despite the introduction of several metrics for assessing multiclass imbalance, the Imbalance Ratio (IR) remains the most commonly used measure for quantifying imbalance severity. Existing balancing techniques mainly rely on distance-based, cluster-based, and distribution-based approaches, reflecting methodological diversity. In multiclass settings, various decomposition strategies, classification algorithms, and performance metrics have been proposed to address imbalance; however, repeated use of imbalance-handling mechanisms, such as class weight adjustments across decomposition, training, and evaluation stages, may introduce bias. The effectiveness of these strategies depends on data characteristics including dimensionality, sample size, distribution, number of classes, and imbalance severity. Notably, insufficient reporting of these characteristics in many studies limits the assessment of feasibility and generalizability across diverse data settings.<br />Conclusions: This review synthesizes the strengths and limitations of existing methods for handling imbalanced multiclass classification, offering practical insights for improving model robustness and predictive performance. Effective management of class imbalance supports several Sustainable Development Goals by promoting equitable decision-making and enhancing reliable analysis across diverse health, societal, and environmental challenges, making it essential for developing robust and generalizable models across diverse domains.<br /> (© 2026. The Author(s).)
– Name: Abstract
  Label: Competing Interests
  Group: Ab
  Data: Declarations. Ethics approval and consent to participate: Not applicable. Consent for publication: Not applicable. Competing interests: The authors declare no competing interests.
– Name: Ref
  Label: References
  Group: RefInfo
  Data: IEEE Trans Cybern. 2016 May;46(5):1078-91. (PMID: <searchLink fieldCode="PM" term="%2225955858%22">25955858)</searchLink><br />Sci Rep. 2024 May 10;14(1):10759. (PMID: <searchLink fieldCode="PM" term="%2238730045%22">38730045)</searchLink><br />Sensors (Basel). 2021 Oct 04;21(19):. (PMID: <searchLink fieldCode="PM" term="%2234640936%22">34640936)</searchLink><br />IEEE Trans Neural Netw Learn Syst. 2020 Aug;31(8):2818-2831. (PMID: <searchLink fieldCode="PM" term="%2231247563%22">31247563)</searchLink><br />IEEE Trans Syst Man Cybern B Cybern. 2012 Aug;42(4):1119-30. (PMID: <searchLink fieldCode="PM" term="%2222438514%22">22438514)</searchLink>
– Name: SubjectMinor
  Label: Contributed Indexing
  Group:
  Data: <i>Keywords: </i>Binarization; Class imbalance; Imbalance measure; Imbalance ratio; Multiclass classification; Multiclass imbalance
– Name: DateEntry
  Label: Entry Date(s)
  Group: Date
  Data: <i>Date Created: </i>20260620 <i>Date Completed: </i>20260902 <i>Latest Revision: </i>20260908
– Name: DateUpdate
  Label: Update Code
  Group: Date
  Data: 20260909
– Name: PubmedCentralID
  Label: PubMed Central ID
  Group: ID
  Data: PMC13536707
– Name: DOI
  Label: DOI
  Group: ID
  Data: 10.1186/s12874-026-02899-w
– Name: AN
  Label: PMID
  Group: ID
  Data: 42323527
PLink https://search.ebscohost.com/login.aspx?direct=true&site=eds-live&db=cmedm&AN=42323527
RecordInfo BibRecord:
  BibEntity:
    Identifiers:
      – Type: doi
        Value: 10.1186/s12874-026-02899-w
    Languages:
      – Code: eng
        Text: English
    Subjects:
      – SubjectFull: Humans
        Type: general
      – SubjectFull: Classification Algorithms
        Type: general
      – SubjectFull: Medical Informatics
        Type: general
    Titles:
      – TitleFull: Challenges and recent advances in methods for handling imbalanced multiclass classification problems: a methodological review.
        Type: main
  BibRelationships:
    HasContributorRelationships:
      – PersonEntity:
          Name:
            NameFull: Acharya S
      – PersonEntity:
          Name:
            NameFull: Poojari S
      – PersonEntity:
          Name:
            NameFull: R VL
      – PersonEntity:
          Name:
            NameFull: Kamath A
    IsPartOfRelationships:
      – BibEntity:
          Dates:
            – D: 20
              M: 06
              Text: 2026 Jun 20
              Type: published
              Y: 2026
          Identifiers:
            – Type: issn-electronic
              Value: 1471-2288
          Numbering:
            – Type: volume
              Value: 26
            – Type: issue
              Value: 1
          Titles:
            – TitleFull: BMC medical research methodology
              Type: main
ResultId 1