EUVIMEDEUVIMED entdecken
VergleichsstudieOpen Access

Characterizing multimorbidity in ALIVE: comparing single and ensemble clustering methods

Jacqueline E Rudolph iD, Bryan Lau iD, Becky L Genberg iD, Jing Sun, Gregory D Kirk, Shruti H Mehta

American Journal of Epidemiology · 2024

DOI: 10.1093/aje/kwae031 ↗

Kurz gefasst

Vergleichsstudie in der Zeitschrift American Journal of Epidemiology, 2024. Verfasst von Jacqueline E Rudolph und 5 weiteren Autor:innen. Beteiligte Einrichtung: Department of Epidemiology, Bloomberg School of Public Health, Johns Hopkins University, Baltimore, MD 21205, United States. Hauptthemen laut MEDLINE: Multimorbidity, Algorithms. Die Arbeit wurde bisher 2-mal zitiert (Crossref) und nennt 35 Literaturangaben. Der Volltext ist frei in PubMed Central verfügbar. Gefördert von: NIDA NIH HHS, NIAID NIH HHS, NIH HHS.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Multimorbidity, defined as having 2 or more chronic conditions, is a growing public health concern, but research in this area is complicated by the fact that multimorbidity is a highly heterogenous outcome. Individuals in a sample may have a differing number and varied combinations of conditions. Clustering methods, such as unsupervised machine learning algorithms, may allow us to tease out the unique multimorbidity phenotypes. However, many clustering methods exist, and choosing which to use is challenging because we do not know the true underlying clusters. Here, we demonstrate the use of 3 individual algorithms (partition around medoids, hierarchical clustering, and probabilistic clustering) and a clustering ensemble approach (which pools different clustering approaches) to identify multimorbidity clusters in the AIDS Linked to the Intravenous Experience cohort study. We show how the clusters can be compared based on cluster quality, interpretability, and predictive ability. In practice, it is critical to compare the clustering results from multiple algorithms and to choose the approach that performs best in the domain(s) that aligns with plans to use the clusters in future analyses.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

MultimorbidityAlgorithmsHumansCluster AnalysisFemaleMaleMiddle AgedUnsupervised Machine LearningAdult

Stichwörter der Autor:innen

clusteringensemble clusteringhierarchical clusteringmultimorbiditypartition around medoidsprobabilistic clusteringunsupervised machine learning

Autor:innen und Institutionen

  • Department of Epidemiology, Bloomberg School of Public Health, Johns Hopkins University, Baltimore, MD 21205, United States.
  • Division of Infectious Diseases, Johns Hopkins School of Medicine, Baltimore, MD 21205, United States.

ORCID-Profile: Jacqueline E Rudolph, Bryan Lau, Becky L Genberg

Förderung

  • NIDA NIH HHS
  • NIAID NIH HHS
  • NIH HHS
  • NIAAA NIH HHS
  • National Institutes of Health

Zitieren

APA

Rudolph, J. E., Lau, B., Genberg, B. L., Sun, J., Kirk, G. D., & Mehta, S. H. (2024). Characterizing multimorbidity in ALIVE: comparing single and ensemble clustering methods. American Journal of Epidemiology. https://doi.org/10.1093/aje/kwae031

Vancouver

Rudolph JE, Lau B, Genberg BL, Sun J, Kirk GD, Mehta SH. Characterizing multimorbidity in ALIVE: comparing single and ensemble clustering methods. American Journal of Epidemiology. 2024. doi:10.1093/aje/kwae031

BibTeX
@article{Rudolph2024,
  author = {Rudolph, Jacqueline E and Lau, Bryan and Genberg, Becky L and Sun, Jing and Kirk, Gregory D and Mehta, Shruti H},
  title = {Characterizing multimorbidity in ALIVE: comparing single and ensemble clustering methods},
  journal = {American Journal of Epidemiology},
  year = {2024},
  doi = {10.1093/aje/kwae031}
}
Kostenlos starten →