Making the most out of timeseries symptom data: A machine learning study on symptom predictions of internet-based CBT
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.
Authors
- Magnus Boman (ORCID: https://orcid.org/0000-0001-7949-1815)
- Kirsten Zantvoort (ORCID: https://orcid.org/0000-0001-9876-054X)
- Viktor Kaldo (ORCID: https://orcid.org/0000-0002-6443-5279)
- Nils Hentati Isacsson (ORCID: https://orcid.org/0000-0002-5749-5310)
- Erik Forsell (ORCID: https://orcid.org/0000-0001-8236-4323)
Institutions
- Leuphana University of Lüneburg (DE)
- Linnaeus University (SE)
- Karolinska Institutet (SE)
- Stockholm Health Care Services (SE)
- University College London (GB)
Publication Details
- Journal
- Internet Interventions
- Published
- 2024-09-12
- DOI
- https://doi.org/10.1016/j.invent.2024.100773
- Citations
- 3
- Primary Topic
- Digital Mental Health Interventions
- Type
- article
- Field-Weighted Citation Impact
- 1.23
Funders
- Familjen Erling-Perssons Stiftelse
- Stiftelsen för Strategisk Forskning
- Vetenskapsrådet