@article{fdi:010086977,
  title = {{Q}luster : an easy-to-implement generic workflow for robust clustering of health data},
  author = {{E}snault, {C}. and {R}ollot, {M}. and {G}uilmin, {P}. and {Z}ucker, {J}ean-{D}aniel},
  editor = {},
  language = {{ENG}},
  abstract = {{T}he exploration of heath data by clustering algorithms allows to better describe the populations of interest by seeking the sub-profiles that compose it. {T}his therefore reinforces medical knowledge, whether it is about a disease or a targeted population in real life. {N}evertheless, contrary to the so-called conventional biostatistical methods where numerous guidelines exist, the standardization of data science approaches in clinical research remains a little discussed subject. {T}his results in a significant variability in the execution of data science projects, whether in terms of algorithms used, reliability and credibility of the designed approach. {T}aking the path of parsimonious and judicious choice of both algorithms and implementations at each stage, this article proposes {Q}luster, a practical workflow for performing clustering tasks. {I}ndeed, this workflow makes a compromise between (1) genericity of applications (e.g. usable on small or big data, on continuous, categorical or mixed variables, on database of high-dimensionality or not), (2) ease of implementation (need for few packages, few algorithms, few parameters, ...), and (3) robustness (e.g. use of proven algorithms and robust packages, evaluation of the stability of clusters, management of noise and multicollinearity). {T}his workflow can be easily automated and/or routinely applied on a wide range of clustering projects. {I}t can be useful both for data scientists with little experience in the field to make data clustering easier and more robust, and for more experienced data scientists who are looking for a straightforward and reliable solution to routinely perform preliminary data mining. {A} synthesis of the literature on data clustering as well as the scientific rationale supporting the proposed workflow is also provided. {F}inally, a detailed application of the workflow on a concrete use case is provided, along with a practical discussion for data scientists. {A}n implementation on the {D}ataiku platform is available upon request to the authors.},
  keywords = {clustering ; easy-to-implement algorithm ; robustness ; health data ; genericity},
  booktitle = {},
  journal = {{F}rontiers in {A}rtificial {I}ntelligence},
  volume = {5},
  numero = {},
  pages = {1055294 [20 p.]},
  year = {2023},
  DOI = {10.3389/frai.2022.1055294},
  URL = {https://www.documentation.ird.fr/hor/fdi:010086977},
}