EUVIMEDEUVIMED entdecken
Scoping ReviewOpen Access

Strategies to Mitigate Age-Related Bias in Machine Learning: Scoping Review

Strategien zur Minderung altersbezogener Verzerrungen in Machine Learning: Scoping Review

Charlene Chu iD, Simon Donato-Woodger iD, Shehroz S Khan iD, Tianyu Shi iD, Kathleen Leslie iD, Samira Abbasgholizadeh-Rahimi iD, Rune Nyrup iD, Amanda Grenier iD

JMIR Aging · 22.03.2024 · 7 · e53564

DOI: 10.2196/53564 ↗

Auf einen Blick

Das Scoping Review identifizierte 8 Publikationen zu Strategien gegen altersbezogene Verzerrungen in ML. Verzerrungen entstanden vor allem durch die geringe Repräsentation älterer Menschen in den Daten.

Fragestellung

Welche Strategien wurden beschrieben, um altersbezogene Verzerrungen in ML-Modellen zu verringern, und wie wirksam sind sie?

Methode

Scoping Review nach Arksey und O’Malley; Suche in 6 Datenbanken und 2 Grauliteratur-Datenbanken.

Ergebnisse

8 Publikationen. Altersbezogene Verzerrungen beruhten meist auf fehlender Repräsentation älterer Erwachsener. Die Strategien: ausgeglichenere Datensätze, Datenaugmentierung/-ergänzung und direkte Algorithmusänderung.

Schlussfolgerung der Autor:innen

Die Identifikation und Minderung entsprechender Verzerrungen in ML-Modellen ist laut Autor:innen wichtig. Es besteht weiterhin Bedarf an rigoroser Forschung und wirksamen Minderungstrategien.

Kernaussagen

  • 8 Publikationen zu altersbezogener Bias-Minderung in ML
  • Hauptursache: geringe Repräsentation älterer Erwachsener
  • 3 Strategien: Datenbalance, Datenaugmentation, Algorithmusmodifikation

Deutsche Zusammenfassung: KI-gestützt aus dem Original-Abstract erstellt; alle Zahlen wurden automatisch mit dem Original abgeglichen. Maßgeblich ist der Original-Abstract.

Kurz gefasst

Scoping Review in der Zeitschrift JMIR Aging, online erschienen am 22.03.2024. Verfasst von Charlene Chu und 7 weiteren Autor:innen. Beteiligte Einrichtung: Lawrence Bloomberg Faculty of Nursing, University of Toronto, Toronto, ON, Canada. Hauptthemen laut MEDLINE: Ageism. Die Arbeit wurde bisher 20-mal zitiert (Crossref) und nennt 51 Literaturangaben. Der Volltext ist frei in PubMed Central verfügbar.

Auf einen BlickAbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Background

Research suggests that digital ageism, that is, age-related bias, is present in the development and deployment of machine learning (ML) models. Despite the recognition of the importance of this problem, there is a lack of research that specifically examines the strategies used to mitigate age-related bias in ML models and the effectiveness of these strategies.

Objective

To address this gap, we conducted a scoping review of mitigation strategies to reduce age-related bias in ML.

Methods

We followed a scoping review methodology framework developed by Arksey and O’Malley. The search was developed in conjunction with an information specialist and conducted in 6 electronic databases (IEEE Xplore, Scopus, Web of Science, CINAHL, EMBASE, and the ACM digital library), as well as 2 additional gray literature databases (OpenGrey and Grey Literature Report).

Results

We identified 8 publications that attempted to mitigate age-related bias in ML approaches. Age-related bias was introduced primarily due to a lack of representation of older adults in the data. Efforts to mitigate bias were categorized into one of three approaches: (1) creating a more balanced data set, (2) augmenting and supplementing their data, and (3) modifying the algorithm directly to achieve a more balanced result.

Conclusions

Identifying and mitigating related biases in ML models is critical to fostering fairness, equity, inclusion, and social benefits. Our analysis underscores the ongoing need for rigorous research and the development of effective mitigation approaches to address digital ageism, ensuring that ML systems are used in a way that upholds the interests of all individuals. Trial Registration Open Science Framework AMG5P; https://osf.io/amg5p

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

AgeismHumansAgedAlgorithmsBiasDatabases, FactualMachine Learning

Stichwörter der Autor:innen

ageageingageismagingalgorithmalgorithmic biasartificial intelligencebiasdigital ageismelderelderlygeriatricgerontologymachine learningolder adult

Autor:innen und Institutionen

  • Lawrence Bloomberg Faculty of Nursing, University of Toronto, Toronto, ON, Canada.
  • Knowledge, Innovation, Talent, Everywhere (KITE), Toronto Rehabilitation Institute, University Health Network, Toronto, ON, Canada.
  • Institute for Life Course and Aging, Faculty of Social Work, University of Toronto, Toronto, ON, Canada.
  • Rehabilitation Sciences Institute, University of Toronto, Toronto, ON, Canada.
  • Institute of Biomedical Engineering, University of Toronto, Toronto, ON, Canada.
  • Department of Civil Engineering, University of Toronto, Toronto, ON, Canada.

ORCID-Profile: Charlene Chu, Simon Donato-Woodger, Shehroz S Khan, Tianyu Shi, Kathleen Leslie, Samira Abbasgholizadeh-Rahimi, Rune Nyrup, Amanda Grenier

Zitieren

APA

Chu, C., Donato-Woodger, S., Khan, S. S., Shi, T., Leslie, K., Abbasgholizadeh-Rahimi, S., Nyrup, R., & Grenier, A. (2024). Strategies to Mitigate Age-Related Bias in Machine Learning: Scoping Review. JMIR Aging, 7, e53564. https://doi.org/10.2196/53564

Vancouver

Chu C, Donato-Woodger S, Khan SS, Shi T, Leslie K, Abbasgholizadeh-Rahimi S, et al. Strategies to Mitigate Age-Related Bias in Machine Learning: Scoping Review. JMIR Aging. 2024;7:e53564. doi:10.2196/53564

BibTeX
@article{Chu2024,
  author = {Chu, Charlene and Donato-Woodger, Simon and Khan, Shehroz S and Shi, Tianyu and Leslie, Kathleen and Abbasgholizadeh-Rahimi, Samira and Nyrup, Rune and Grenier, Amanda},
  title = {Strategies to Mitigate Age-Related Bias in Machine Learning: Scoping Review},
  journal = {JMIR Aging},
  year = {2024},
  volume = {7},
  pages = {e53564},
  doi = {10.2196/53564}
}
Kostenlos starten →