Unsupervised meta-clustering identifies risk clusters in acute myeloid leukemia based on clinical and genetic profiles.

ABSTRACT:

Background

Increasingly large and complex biomedical data sets challenge conventional hypothesis-driven analytical approaches, however, data-driven unsupervised learning can detect inherent patterns in such data sets.

Methods

While unsupervised analysis in the medical literature commonly only utilizes a single clustering algorithm for a given data set, we developed a large-scale model with 605 different combinations of target dimensionalities as well as transformation and clustering algorithms and subsequent meta-clustering of individual results. With this model, we investigated a large cohort of 1383 patients from 59 centers in Germany with newly diagnosed acute myeloid leukemia for whom 212 clinical, laboratory, cytogenetic and molecular genetic parameters were available.<

SUBMITTER: Eckardt JN 

PROVIDER: S-EPMC10192332 | biostudies-literature | 2023 May

REPOSITORIES: biostudies-literature