RESUMO
Introduction: Routine Outcome Monitoring (ROM) has emerged as a strong candidate to improve psychotherapy processes and outcome. However, its use and implementation are greatly understudied in Latin-America. Therefore, the aim of the present pilot study conducted in Argentina was to implement a ROM and feedback system grounded on a psychometrically sound instrument to measure session by session outcome in psychotherapy. Methods: The sample consisted of 40 patients and 13 therapists. At baseline, the patients completed the Patient Health Questionnaire-9 and the Generalized Anxiety Disorder-7, and they also completed the Hopkins Symptom Checklist-11 before each of the first five sessions. To estimate patient change during the first sessions, we conducted a quantitative analysis using Hierarchical Linear Models. Furthermore, we conducted a qualitative analysis using Consensual Qualitative Research to analyze therapist perception regarding the ROM and feedback system. Results: Results showed a significant reduction in patients' symptomatic severity during the first five sessions. Additionally, baseline depression significantly predicted the estimated severity at the end of the fifth session. Feedback was given to the therapists after the first four sessions based on these analyses. With regard to the perception of the feedback system, clinicians underlined its usefulness and user-friendly nature. They also mentioned that there was a match between the information provided and their clinical judgment. Furthermore, they provided suggestions to enhance the system that was incorporated in a new and improved version. Discussion: Limitations and clinical implications are discussed.
RESUMO
OBJECTIVE: We aimed to develop and test an algorithm for individual patient predictions of problem coping experiences (PCE) (i.e., patients' understanding and ability to deal with their problems) effects in cognitive-behavioral therapy. Method: In an outpatient sample with a variety of diagnoses (n=1010), we conducted Dynamic Structural Equation Modelling to estimate within-patient cross-lagged PCE effects on outcome during the first ten sessions. In a randomly selected training sample (2/3 of the cases), we tried different machine learning algorithms (i.e., ridge regression, LASSO, elastic net, and random forest) to predict PCE effects (i.e., the degree to which PCE was a time-lagged predictor of symptoms), using baseline demographic, diagnostic, and clinically-relevant patient features. Then, we validated the best algorithm on a test sample (1/3 of the cases). RESULTS: The random forest algorithm performed best, explaining 14.7% of PCE effects variance in the training set. The results remained stable in the test set, explaining 15.4% of PCE effects variance. CONCLUSIONS: The results show the suitability to perform individual predictions of process effects, based on patients' initial information. If the results are replicated, the algorithm might have the potential to be implemented in clinical practice by integrating it into monitoring and therapist feedback systems.