Identifying homogeneous subgroups of patients and important features: a topological machine learning approach

• Main Authors: Carr, E. (Author), Carrière, M. (Author), Chazal, F. (Author), Iniesta, R. (Author), Michel, B. (Author)
• Format: Article
• Language: English
• Published: BioMed Central Ltd 2021
• Subjects: adult; algorithm; Algorithms; article; bootstrapping; cluster analysis; Cluster Analysis; Clustering; Clustering algorithms; Clustering process; Complex data; data analysis; Data Analysis; Graph algorithms; human; Humans; Important features; licence; machine learning; Machine learning; Machine Learning; Machine learning approaches; Mixed data types; pipeline; Pipelines; Prior knowledge; Topological data analysis; Topological features; Topology
• Online Access: View Fulltext in Publisher

 Background: This paper exploits recent developments in topological data analysis to present a pipeline for clustering based on Mapper, an algorithm that reduces complex data into a one-dimensional graph. Results: We present a pipeline to identify and summarise clusters based on statistically significant topological features from a point cloud using Mapper. Conclusions: Key strengths of this pipeline include the integration of prior knowledge to inform the clustering process and the selection of optimal clusters; the use of the bootstrap to restrict the search to robust topological features; the use of machine learning to inspect clusters; and the ability to incorporate mixed data types. Our pipeline can be downloaded under the GNU GPLv3 license at https://github.com/kcl-bhi/mapper-pipeline. © 2021, The Author(s).