Skip to main content
KBS_Icon_questionmark link-ico

Introduction to dCVnet – software for clinical prediction - 15 September 2021

Please note that this event has passed.


Presenter: Dr Andrew Lawrence, Postdoctoral Research Associate (Psychological Medicine)

Q&A panel:

  • Daniel Stahl, Professor of Medical Statistics and Statistical Learning
  • Paola Dazzan, Professor of Neurobiology of Psychosis
  • Roland Zahn, Reader in the Neurocognitive Bases of Mood Disorders

Background: dCVnet is a software tool (R package) for prediction modelling. It produces tuned elastic-net regression models with cross-validated prediction performance measures. This approach can be useful in smaller samples or with many predictors. The tool is fast, easy to use and, in contrast to more general prediction modelling software, requires minimal statistical programming experience. dCVnet was developed recently with support from the Biomedical Research Centre for Mental Health at the South London and Maudsley NHS Trust and King’s College London and is freely available (https://github.com/AndrewLawrence/dCVnet). Methodological details and successful application to predicting recurrence risk in major depressive disorder have been described in a recent paper (Lawrence et al 2021 https://doi.org/10.1016/j.bpsc.2021.06.010).

Objectives:

  • Learn about the features of dCVnet (elastic-net regression with nested cross-validation) software and its rationale
  • Learn how to use dCVnet to produce cross-validated prediction performance measures

Target Audience:

Clinical researchers and clinicians with an interest in prediction within the Institute of Psychiatry, Psychology and Neuroscience, King’s College London (also open to external guests)

Presenter MiniBio:

Andrew is a postdoc in Prof. Paola Dazzan’s group in the Department of Psychological Medicine, Institute of Psychiatry, Psychology and Neuroscience (King’s College London, London, UK). From a background in experimental psychology and neuropsychology his research interests now include structural and functional MRI networks and application of longitudinal and prediction modelling methods to psychiatric research.


Search for another event