Semi-supervised Phenotype Discovery

Semi-Supervised Phenotype Discovery is a computational approach in biomedical informatics that integrates a limited set of labeled phenotypic data with a larger pool of unlabeled data to identify novel, clinically meaningful subgroups of traits or diseases, distinguished from unsupervised and fully supervised methods by its strategic use of partial expert-annotated guidance within an otherwise data-driven clustering framework.

13

Publications

530

Citations

76

Authors

40

Institutions

Publications per year

2017–2026

10

Authors

76

  1. BK
    Brett K. Beaulieu‐Jones

    Harvard University, United States

    2 publications · 247 citations

    2

    h-index

  2. CS
    Casey S. Greene

    University of Pennsylvania, United States

    2 publications · 247 citations

    2

    h-index

  3. CF
    Christian F. Beckmann

    Radboud University Nijmegen, Netherlands

    1 publications · 22 citations

    1

    h-index

  4. CG
    Catherine Goetzinger

    University of Luxembourg, Luxembourg

    1 publications · 14 citations

    1

    h-index

  5. JK
    Jennifer K Quint

    Imperial College London, United Kingdom

    1 publications · 17 citations

    1

    h-index

1–5 of 76

Venues

  1. IEEE Transactions on Medical Imaging

    2 publications · 43 citations

    2

    h-index

  2. Journal of the American Medical Informatics Association

    JAMIA · 1 publications · 27 citations

    1

    h-index

  3. PubMed

    Repository · 1 publications · 23 citations

    1

    h-index

  4. Biometrics

    1 publications · 18 citations

    1

    h-index

  5. JAMIA Open

    1 publications · 17 citations

    1

    h-index

1–5