Hans Jacob Westbye
Research Subjects
Research Interests
Hans Jacob Westbye has a total of 3 co-authors. Here are the top co-authors by number of shared publications:
- Andrew Athan McAleavey
District General Hospital of Førde
3 shared publications - Christian Moltu
Department of Psychiatry, District General Hospital of Førde, Førde, Norway; Department of Health and Caring Sciences, Western Norway University of Applied Sciences, Førde, Norway
2 shared publications Christian Moltu
1 shared publication
Latest Publications
- Open Access
- 2 October 2026
- Published by Center for Open Science in PsyArXiv
Predicting dropout from psychotherapy with routine measurement-based care data: Which patients benefit from more complex prediction models?
Background. Treatment discontinuation in mental health care represents a significant individual and systemic challenge, with considerable associated costs. Machine learning (ML) may be able to accurately predict risk of dropout, which could be useful in psychotherapy. Methods. Data on 26,877 individual patients were extracted from the electronic encounter records and self-report databases of mental healthcare settings in Norway. We predicted risk of early treatment termination after attending one psychotherapy session, using data that would be available at (or shortly after) the first treatment session. We compared eXtreme Gradient Boosted decision trees (XGBoost) to penalized regression and standard logistic regression models. Results. Dropout prevalence was estimated at 19.7% of the sample. Of the tested models, XGBoost achieved very slightly better accuracy than the other models in AUC ROC (0.620 vs. 0.611-0.613 for the regression-based models). Exploratory analyses indicated that the small average increase in predictive accuracy was primarily due to better performance at the high end of the prediction scale. Discussion. While complex models only modestly improved overall prediction accuracy, exploratory analysis indicated that this small benefit may mask a strength of complex models for individuals with uncommon presentations and high or low risk for dropout. A stepped approach to model complexity may be appropriate in practice: many patients may only benefit from simple data collection and simple modeling strategies, while more detailed analysis could be useful when simple models identify unusual responses.
- 2 October 2026
- Published by Center for Open Science in PsyArXiv
Open AccessPredicting dropout from psychotherapy with routine measurement-based care data: Which patients benefit from more complex prediction models?
Background. Treatment discontinuation in mental health care represents a significant individual and systemic challenge, with considerable associated costs. Machine learning (ML) may be able to accurately predict risk of dropout, which could be useful in psychotherapy. Methods. Data on 26,877 individual patients were extracted from the electronic encounter records and self-report databases of mental healthcare settings in Norway. We predicted risk of early treatment termination after attending one psychotherapy session, using data that would be available at (or shortly after) the first treatment session. We compared eXtreme Gradient Boosted decision trees (XGBoost) to penalized regression and standard logistic regression models. Results. Dropout prevalence was estimated at 19.7% of the sample. Of the tested models, XGBoost achieved very slightly better accuracy than the other models in AUC ROC (0.620 vs. 0.611-0.613 for the regression-based models). Exploratory analyses indicated that the small average increase in predictive accuracy was primarily due to better performance at the high end of the prediction scale. Discussion. While complex models only modestly improved overall prediction accuracy, exploratory analysis indicated that this small benefit may mask a strength of complex models for individuals with uncommon presentations and high or low risk for dropout. A stepped approach to model complexity may be appropriate in practice: many patients may only benefit from simple data collection and simple modeling strategies, while more detailed analysis could be useful when simple models identify unusual responses.
- Open Access
- 2 May 2024
- Published by Wiley in Counselling and Psychotherapy Research
- Vol. 25 (1)
eXplainableAI for routine outcome monitoring and clinical feedback
Artificial intelligence (AI), specifically machine learning (ML), is adept at identifying patterns and insights from vast amounts of data from routine outcome monitoring (ROM) and clinical feedback during treatment. When applied to patient feedback data, AI/ML models can assist clinicians in predicting treatment outcomes. Common reasons for clinician resistance to integrating data‐driven decision‐support tools in clinical practice include concerns about the reliability, relevance and usefulness of the technology coupled with perceived conflicts between data‐driven recommendations and clinical judgement. While AI/ML‐based tools might be precise in guiding treatment decisions, it might not be possible to realise their potential at present, due to implementation, acceptability and ethical concerns. In this article, we will outline the concept of eXplainable AI (XAI), a potential solution to these concerns. XAI refers to a form of AI designed to articulate its purpose, rationale and decision‐making process in a manner that is comprehensible to humans. The key to this approach is that end‐users see a clear and understandable pathway from input data to recommendations. We use real Norse Feedback data to present an AI/ML example demonstrating one use case for XAI. Furthermore, we discuss key learning points that we will employ in future XAI implementations.
- 2 May 2024
- Published by Wiley in Counselling and Psychotherapy Research
- Vol. 25 (1)
Open AccesseXplainableAI for routine outcome monitoring and clinical feedback
Artificial intelligence (AI), specifically machine learning (ML), is adept at identifying patterns and insights from vast amounts of data from routine outcome monitoring (ROM) and clinical feedback during treatment. When applied to patient feedback data, AI/ML models can assist clinicians in predicting treatment outcomes. Common reasons for clinician resistance to integrating data‐driven decision‐support tools in clinical practice include concerns about the reliability, relevance and usefulness of the technology coupled with perceived conflicts between data‐driven recommendations and clinical judgement. While AI/ML‐based tools might be precise in guiding treatment decisions, it might not be possible to realise their potential at present, due to implementation, acceptability and ethical concerns. In this article, we will outline the concept of eXplainable AI (XAI), a potential solution to these concerns. XAI refers to a form of AI designed to articulate its purpose, rationale and decision‐making process in a manner that is comprehensible to humans. The key to this approach is that end‐users see a clear and understandable pathway from input data to recommendations. We use real Norse Feedback data to present an AI/ML example demonstrating one use case for XAI. Furthermore, we discuss key learning points that we will employ in future XAI implementations.
- Open Access
- 14 March 2024
- Published by Springer Nature
- p. 80-105
Patient Self-reports for Explainable Machine Learning Predictions of Risks to Psychotherapy Outcomes
Prioritizing the right patients and providing personalized treatment in a timely manner is crucial to improve access to healthcare. In psychotherapy, at least 1 in 3 patients drop out of treatment, with therapeutic alliance among the common predictors. Recommendations to safeguard retention include strengthening the patient-therapist bond through developing shared goals and checking in on progress and treatment path. Using a sample of 11,095 mental health patients from the USA, we used machine learning to develop a clinical support tool for treatment personalization. A gradient-boosted decision tree was trained on patient-reported data to establish global and individual predictions/predictors for early treatment dropout, treatment length, and symptom outcomes conditional on different treatment lengths in out-of-sample patients. The models demonstrated marginal to moderate improvements in performance versus baseline predictions. The resulting decision support tool could assist in the collaborative selection of treatment goals, appropriate treatment intensity, and optimal allocation of resources. Results are discussed in the context of explainable AI emphasizing interpretability in a clinical context.
- 14 March 2024
- Published by Springer Nature
- p. 80-105
Open AccessPatient Self-reports for Explainable Machine Learning Predictions of Risks to Psychotherapy Outcomes
Prioritizing the right patients and providing personalized treatment in a timely manner is crucial to improve access to healthcare. In psychotherapy, at least 1 in 3 patients drop out of treatment, with therapeutic alliance among the common predictors. Recommendations to safeguard retention include strengthening the patient-therapist bond through developing shared goals and checking in on progress and treatment path. Using a sample of 11,095 mental health patients from the USA, we used machine learning to develop a clinical support tool for treatment personalization. A gradient-boosted decision tree was trained on patient-reported data to establish global and individual predictions/predictors for early treatment dropout, treatment length, and symptom outcomes conditional on different treatment lengths in out-of-sample patients. The models demonstrated marginal to moderate improvements in performance versus baseline predictions. The resulting decision support tool could assist in the collaborative selection of treatment goals, appropriate treatment intensity, and optimal allocation of resources. Results are discussed in the context of explainable AI emphasizing interpretability in a clinical context.