• LOGIN
Repository logo

BORIS Portal

Bern Open Repository and Information System

  • Publication
  • Projects
  • Funding
  • Research Data
  • Organizations
  • Researchers
  • LOGIN
Repository logo
Unibern.ch
  1. Home
  2. Publications
  3. Development and validation of a meta-learner for combining statistical and machine learning prediction models in individuals with depression.
 

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

Options
  • Details
BORIS DOI
10.48350/170101
Date of Publication
May 16, 2022
Publication Type
Article
Division/Institute

Institut für Sozial- ...

Berner Institut für H...

Author
Liu, Qiang
Salanti, Georgiaorcid-logo
Institut für Sozial- und Präventivmedizin (ISPM)
De Crescenzo, Franco
Ostinelli, Edoardo Giuseppe
Li, Zhenpeng
Tomlinson, Anneka
Cipriani, Andrea
Efthimiou, Orestisorcid-logo
Berner Institut für Hausarztmedizin (BIHAM)
Institut für Sozial- und Präventivmedizin (ISPM)
Subject(s)

600 - Technology::610...

300 - Social sciences...

Series
BMC psychiatry
ISSN or ISBN (if monograph)
1471-244X
Publisher
BioMed Central
Language
English
Publisher DOI
10.1186/s12888-022-03986-0
PubMed ID
35578254
Uncontrolled Keywords

Depression Dropout Ma...

Description
BACKGROUND

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.
Handle
https://boris-portal.unibe.ch/handle/20.500.12422/85144
Show full item
File(s)
FileFile TypeFormatSizeLicensePublisher/Copright statementContent
s12888-022-03986-0.pdftextAdobe PDF1009.95 KBpublishedOpen
BORIS Portal
Bern Open Repository and Information System
Build: 360c85 [14.04. 8:05]
Explore
  • Projects
  • Funding
  • Publications
  • Research Data
  • Organizations
  • Researchers
More
  • About BORIS Portal
  • Send Feedback
  • Cookie settings
  • Service Policy
Follow us on
  • Mastodon
  • YouTube
  • LinkedIn
UniBe logo