• Login
    View Item 
    •   ORKA Home
    • Conditions, Lifestyle Factors & Interventions
    • Conditions
    • Depressive Disorders
    • View Item
    •   ORKA Home
    • Conditions, Lifestyle Factors & Interventions
    • Conditions
    • Depressive Disorders
    • View Item
    JavaScript is disabled for your browser. Some features of this site may not work without it.

    Development and validation of a meta-learner for combining statistical and machine learning prediction models in individuals with depression

    Thumbnail
    View/Open
    Main article (17.32Mb)
    Date
    2022-05
    Author
    De Crescenzo, Franco
    Ostinelli, Edoardo
    Tomlinson, Anneka
    Cipriani, Andrea
    Metadata
    Show full item record
    Citation
    Qiang Liu, Georgia Salanti, Franco De Crescenzo, Edoardo Giuseppe Ostinelli, Zhenpeng Li, Anneka Tomlinson, Andrea Cipriani & Orestis Efthimiou Development and validation of a meta-learner for combining statistical and machine learning prediction models in individuals with depression. BMC Psychiatry volume 22, Article number: 337 (2022)
    Abstract
    The debate of whether machine learning models offer advantages over standard statistical methods when making predictions is ongoing. We discuss the use of a meta-learner model combining both approaches as an alternative. Methods To illustrate the development of a meta-learner, we used a dataset of 187,757 people with depression. Using 31 variables, we aimed to predict two outcomes measured 60 days after initiation of antidepressant treatment: severity of depressive symptoms (continuous) and all-cause dropouts (binary). We fitted a ridge regression and a multi-layer perceptron (MLP) deep neural network as two separate prediction models (“base-learners”). We then developed two “meta-learners”, combining predictions from the two base-learners. To compare the performance across the different methods, we calculated mean absolute error (MAE, for continuous outcome) and the area under the receiver operating characteristic curve (AUC, for binary outcome) using bootstrapping. Results Compared to the best performing base-learner (MLP base-learner, MAE at 4.63, AUC at 0.59), the best performing meta-learner showed a 2.49% decrease in MAE at 4.52 for the continuous outcome and a 6.47% increase in AUC at 0.60 for the binary outcome. Conclusions A meta-learner approach may effectively combine multiple prediction models. Choosing between statistical and machine learning models may not be necessary in practice.
    Description
    Open access
    URI
    https://oxfordhealth-nhs.archive.knowledgearc.net/handle/123456789/1048
    Published online at:
    https://doi.org/10.1186/s12888-022-03986-0
    Collections
    • Depressive Disorders [107]

    Oxford Health copyright © 2019
    Contact Us | Send Feedback | JSPUI
    Powered by KnowledgeArc
     

     

    Browse

    All of ORKACommunities & CollectionsBy Issue DateAuthorsTitlesSubjectsContributor DisciplineThis CollectionBy Issue DateAuthorsTitlesSubjectsContributor Discipline

    My Account

    Login

    Researcher Profiles

    Researchers

    Oxford Health copyright © 2019
    Contact Us | Send Feedback | JSPUI
    Powered by KnowledgeArc