Making the most out of timeseries symptom data: A machine learning study on symptom predictions of internet-based CBT

Research output: Journal contributionsJournal articlesResearchpeer-review

Authors

  • Nils Hentati Isacsson
  • Kirsten Zantvoort
  • Erik Forsell
  • Magnus Boman
  • Viktor Kaldo

Objective: Predicting who will not benefit enough from Internet-Based Cognitive Behavioral (ICBT) Therapy early on can assist in better allocation of limited mental health care resources. Repeated measures of symptoms during treatment is the strongest predictor of outcome, and we want to investigate if methods that explicitly account for time-dependency are superior to methods that do not, with data from (a) only two pre-treatment timepoints and (b) the pre-treatment timepoints and three timepoints during initial treatment. Methods: We use 1) commonly used time-independent methods (i.e., Linear Regression and Random Forest models) and 2) time-dependent methods (i.e., multilevel model regression, mixed-effects random forest, and a Long Short-Term Memory model) to predict symptoms during treatment, including the final outcome. This is done with symptom scores from 6436 ICBT patients from regular care, using robust multiple imputation and nested cross-validation methods. Results: The models had a 14 %–12 % root mean squared error (RMSE) in predicting the post-treatment outcome, corresponding to a balanced accuracy of 67–74 %. Time-dependent models did not have higher accuracies. Using data for the initial treatment period (b) instead of only from before treatment (a) increased prediction results by 1.3 % percentage points (12 % to 10.7 %) RMSE and 6 % percentage points BACC (69 % to 75 %). Conclusion: Training prediction models on only symptom scores of the first few weeks is a promising avenue for symptom predictions in treatment, regardless of which model is used. Further research is necessary to better understand the interaction between model complexity, dataset length and width, and the prediction tasks at hand.

Original languageEnglish
Article number100773
JournalInternet Interventions
Volume38
Number of pages8
ISSN2214-7829
DOIs
Publication statusPublished - 12.2024

Bibliographical note

Publisher Copyright:
© 2024 The Authors

    Research areas

  • Adaptive treatment strategy, Machine learning, Precision psychiatry, Prediction, Timeseries symptom, Treatment outcome

Recently viewed

Publications

  1. Robust approximate fixed-time tracking control for uncertain robot manipulators
  2. Unravelling insect declines: Can space replace time?
  3. Turning Good Intentions Into Actions by Using the Health Action Process Approach to Predict Adherence to Internet-Based Depression Prevention
  4. »HOW TO MAKE YOUR OWN SAMPLES«
  5. Aspect-oriented software development
  6. Effectiveness of a Web-Based Cognitive Behavioural Intervention for Subthreshold Depression
  7. Machine Learning and Data Mining for Sports Analytics
  8. Multidimensionality of tree communities structure host-parasitoid networks and their phylogenetic composition
  9. Experiments are needed to quantify the main causes of insect decline
  10. Time Use Research and Time Use Data
  11. Failing and the perception of failure in student-driven transdisciplinary projects
  12. Effect of thermo-mechanical conditions during constrained friction processing on the particle refinement of AM50 Mg-alloy phases
  13. Special Issue The Discourse of Redundancy Introduction
  14. Experimental investigation of the fluid-structure interaction during deep drawing of fiber metal laminates in the in-situ hybridization process
  15. Computational history of knowledge
  16. Student Game Design for Language Learning
  17. Assessing authenticity in modelling test items: deriving a theoretical model
  18. Higher Wages in Exporting Firms: Self-Selection, Export Effect, or Both?
  19. How Much Home Office is Ideal? A Multi-Perspective Algorithm
  20. Pushing the Envelope: Creating Public Value in the Labor Market
  21. Comparing two hybrid neural network models to predict real-world bus travel time
  22. Improving the representation of smallholder farmers’ adaptive behaviour in agent-based models