An Interpretable Model With Probabilistic Integrated Scoring for Mental Health Treatment Prediction: Design Study
We have demonstrated a mental health treatment ML model that supported a graphical interpretation of prediction class probability distributions. Their spread and overlap can inform clinicians of competing treatment possibilities for patients and uncertainty in treatment predictions. With the ML model achieving 79% balanced accuracy, we expect that the model will be clinically useful in both screening new patients and informing clinical interviews.
Authors
- Eoin Martino Grua (ORCID: https://orcid.org/0000-0002-5471-4338)
- Pepijn W.J. van de Ven (ORCID: https://orcid.org/0000-0003-3321-450X)
- Esben Skov Jensen (ORCID: https://orcid.org/0000-0002-9689-3776)
- Anthony Kelly (ORCID: https://orcid.org/0000-0003-1798-1506)
- Kim Mathiasen (ORCID: https://orcid.org/0000-0001-6067-8866)
Institutions
- University of Southern Denmark (DK)
- Aarhus University (DK)
- University of Limerick (IE)
- Quality of Life Research Center (DK)
Publication Details
- Journal
- JMIR Medical Informatics
- Published
- 2025-02-16
- DOI
- https://doi.org/10.2196/64617
- Citations
- 7
- Primary Topic
- Machine Learning in Healthcare
- Type
- article
- Field-Weighted Citation Impact
- 17.37