AMAndrew Athan McAleavey

Andrew Athan McAleavey

*This is an algorithmically generated author record based on publicly available information.

Andrew Athan McAleavey has a total of 70 co-authors. Here are the top co-authors by number of shared publications:


Latest Publications

  • Open Access

    Predicting dropout from psychotherapy with routine measurement-based care data: Which patients benefit from more complex prediction models?

    by Andrew Athan McAleavey, Hans Jacob Westbye, Christian Moltu

    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

    Developing therapist self-efficacy in clinical psychology students: a randomised controlled study of an apprenticeship training

    by Steffen André Fagerbakk, Heidi Brattland, Nina Jakhelln Laugen, Katrine Høyer Holgersen, Andrew Athan McAleavey, Truls Ryum

    One primary goal of training and education in clinical psychology is to help students acquire sufficient skills and knowledge to have the necessary competence to perform their duties as therapists....

  • Open Access

    Improving interpersonal skills in therapists: A waitlist-controlled trial of facilitative interpersonal and relational skills training

    by Steffen André Fagerbakk, Heidi Brattland, Martin Schevik Lindberg, Andrew Athan McAleavey, Truls Ryum

    Clinical significance of this article: This study provides preliminary evidence that facilitative interpersonal skills in experienced therapists may be modestly improved through brief deliberate pr...


  • Open Access

    Feasibility of Mobile Phone-Based Virtual Reality as a Non-pharmacologic Acute Procedural Pain Management Intervention in an Inpatient Burn Center

    by Mariel Emrich, Andrew A. McAleavey, Katarzyna Wyka, Andrew Greenway, Abraham P. Houng, Philip H. Chang, Constance Zhou, JoAnn Difede

    Burn patients often experience severe procedural pain throughout hospitalization, and poorly controlled pain is a significant predictor of long-term psychological adjustment post-injury. Virtual Reality (VR) presents a promising adjunctive approach to pharmacological analgesics by redirecting patients’ attention away from painful stimuli using immersive, multidimensional environments. Recent technological advances have made VR more affordable, portable, and hands-free permitting the head-mounted display to be easily transported with minimal set up, particularly conducive to hospital environments. This proof-of-concept randomized pilot trial compared VR-enhanced distraction to treatment as usual (TAU) during painful procedures (e.g., wound dressing changes) in hospitalized burn patients. Of 51 patients approached, 15 adults enrolled and 100% completed the study. VR was rated as highly enjoyable (M = 77.5/100) and moderately immersive (M = 63.3/100) with minimal side effects. Descriptively, VR participants demonstrated smaller increases in peri-procedural pain and anxiety relative to TAU and reported reduced cognitive pain during the procedure (i.e., time thinking about pain; M = 33.3 vs. 94.0). Within six hours post-procedure, fewer VR participants required pharmacologic analgesia compared to TAU participants (50.0% vs. 71.4%). Preliminary data indicate that portable VR appears to be a highly feasible and acceptable adjunct to traditional pharmacologic interventions for acute procedural pain in an inpatient burn center. Clinicaltrials.gov: NCT04685486.


  • Linking overall satisfaction after bariatric surgery with health-related quality of life: a cross-sectional study across varied postoperative time points

    by John Roger Andersen, Ronette L. Kolotkin, Ingrid S. Følling, Andrew A. McAleavey, Åsne Ask Hyldmo, Hege Tevik Bjøru, Magnus Strømmen

  • A Dynamic Feedback Tool for Clinical Practice: Norse Feedback

    by Andrew A. McAleavey, Stian Sørheim Espevoll, Sam Nordberg, Christian Moltu

  • Open Access

    Response processes for patients providing quantitative self-report data: a qualitative study

    by Øyvind Grindheim, Andrew McAleavey, Valentina Iversen, Christian Moltu, Kristin Tømmervik, Hege Govasmark, Heidi Brattland

    Objective: To identify factors that influence response processes for patients providing quantitative self-report data. Secondly, due to the lack of integrative and explanatory models in this area, to develop a model of patients’ response processes that can guide what to look for when considering validity evidence and interpreting scores on individual items. Methods: Participants (n = 13) were recruited from a specialized substance use disorder treatment clinic and interviewed while responding to items from a clinical feedback system implemented for routine outcome monitoring in that setting. The interview approach was based on cognitive interviewing. Data collection and analysis were inspired by a grounded theory approach. Results: We identified several variables that influenced the participants’ response processes. The variables were organized into five categories: context-related variables; item-related variables; response base variables; reasoning strategies; and response selection strategies. We also found that the participants’ responses for many items were affected by different aspects of the response process in ways that are relevant to interpretation but not necessarily discernible from the numerical scores alone, and we developed response categories to capture this. Conclusion: The findings suggest that patients providing quantitative self-report data encounter conditions in the response process that challenge and influence their ability to convey meaning and accuracy. This results in responses that for many of the items reflect messages important for interpretation and follow-up, even if it does not appear from the numerical scores alone. The proposed model may be a useful tool when developing items, assessing validity, and interpreting responses.


  • Open Access

    eXplainableAI for routine outcome monitoring and clinical feedback

    by Hans Jacob Westbye, Christian Moltu, Andrew A. McAleavey

    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

    Patient Self-reports for Explainable Machine Learning Predictions of Risks to Psychotherapy Outcomes

    by Hans Jacob Westbye, Andrew A. McAleavey, Christian Moltu

    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.