Your browser doesn't support javascript.
loading
Deep learning for clustering of multivariate clinical patient trajectories with missing values.
de Jong, Johann; Emon, Mohammad Asif; Wu, Ping; Karki, Reagon; Sood, Meemansa; Godard, Patrice; Ahmad, Ashar; Vrooman, Henri; Hofmann-Apitius, Martin; Fröhlich, Holger.
Affiliation
  • de Jong J; UCB Biosciences GmbH, Alfred-Nobel-Strasse 10, 40789 Monheim, Germany.
  • Emon MA; Fraunhofer Institute for Algorithms and Scientific Computing, Schloss Birlinghoven, Konrad-Adenauer-Strasse, 53754 Sankt Augustin, Germany.
  • Wu P; Bonn-Aachen International Center for IT, University of Bonn, Konrad-Adenauer-Strasse, 53115 Bonn, Germany.
  • Karki R; UCB Pharma, Bath Road 216, Slough SL1 3WE, UK.
  • Sood M; Fraunhofer Institute for Algorithms and Scientific Computing, Schloss Birlinghoven, Konrad-Adenauer-Strasse, 53754 Sankt Augustin, Germany.
  • Godard P; Bonn-Aachen International Center for IT, University of Bonn, Konrad-Adenauer-Strasse, 53115 Bonn, Germany.
  • Ahmad A; Fraunhofer Institute for Algorithms and Scientific Computing, Schloss Birlinghoven, Konrad-Adenauer-Strasse, 53754 Sankt Augustin, Germany.
  • Vrooman H; Bonn-Aachen International Center for IT, University of Bonn, Konrad-Adenauer-Strasse, 53115 Bonn, Germany.
  • Hofmann-Apitius M; UCB Pharma, Chemin du Foriest 1, 1420 Braine-l'Alleud, Belgium.
  • Fröhlich H; Bonn-Aachen International Center for IT, University of Bonn, Konrad-Adenauer-Strasse, 53115 Bonn, Germany.
Gigascience ; 8(11)2019 11 01.
Article in En | MEDLINE | ID: mdl-31730697
BACKGROUND: Precision medicine requires a stratification of patients by disease presentation that is sufficiently informative to allow for selecting treatments on a per-patient basis. For many diseases, such as neurological disorders, this stratification problem translates into a complex problem of clustering multivariate and relatively short time series because (i) these diseases are multifactorial and not well described by single clinical outcome variables and (ii) disease progression needs to be monitored over time. Additionally, clinical data often additionally are hindered by the presence of many missing values, further complicating any clustering attempts. FINDINGS: The problem of clustering multivariate short time series with many missing values is generally not well addressed in the literature. In this work, we propose a deep learning-based method to address this issue, variational deep embedding with recurrence (VaDER). VaDER relies on a Gaussian mixture variational autoencoder framework, which is further extended to (i) model multivariate time series and (ii) directly deal with missing values. We validated VaDER by accurately recovering clusters from simulated and benchmark data with known ground truth clustering, while varying the degree of missingness. We then used VaDER to successfully stratify patients with Alzheimer disease and patients with Parkinson disease into subgroups characterized by clinically divergent disease progression profiles. Additional analyses demonstrated that these clinical differences reflected known underlying aspects of Alzheimer disease and Parkinson disease. CONCLUSIONS: We believe our results show that VaDER can be of great value for future efforts in patient stratification, and multivariate time-series clustering in general.
Subject(s)
Key words

Full text: 1 Collection: 01-internacional Database: MEDLINE Main subject: Parkinson Disease / Databases, Factual / Disease Progression / Precision Medicine / Alzheimer Disease / Deep Learning / Models, Neurological Type of study: Prognostic_studies Limits: Female / Humans / Male Language: En Journal: Gigascience Year: 2019 Document type: Article Affiliation country: Germany Country of publication: United States

Full text: 1 Collection: 01-internacional Database: MEDLINE Main subject: Parkinson Disease / Databases, Factual / Disease Progression / Precision Medicine / Alzheimer Disease / Deep Learning / Models, Neurological Type of study: Prognostic_studies Limits: Female / Humans / Male Language: En Journal: Gigascience Year: 2019 Document type: Article Affiliation country: Germany Country of publication: United States