The influence of deliberate practice on skill performance in therapeutic practice: A systematic review of early studies

OBJECTIVE

Deliberate practice (DP) is recommended as a new approach to facilitate the acquisition of discrete therapeutic skills, however, its implementation and effectiveness in psychotherapy remains unclear.

METHOD

A systematic search on DP for therapeutic skills among psychotherapy trainees and psychotherapists yielded eleven studies for inclusion. Nine were randomized controlled studies (RCTs), including seven unique RCTs, and two were within-group studies.

RESULTS

Risk of bias was assessed as "high" for one RCT, "some concerns" for the remaining RCTs, and "serious" for within-group studies. All RCTs found the DP group performed better than the control group. All studies involved efforts to improve performance based on learning objectives and iterative practice but varied in the source of expert guidance and feedback. The included studies provide limited insight into best practice for delivering DP.

CONCLUSION

The results highlight the paucity of research in this field; however they offer insight into current applications of DP and provide preliminary empirical support DP for as a model for promoting the development of discrete therapeutic skills. Given the rapid dissemination of DP publications and manuals in psychotherapy, future research is strongly encouraged.

Automatic rating of therapist facilitative interpersonal skills in text: A natural language processing application

Background

While message-based therapy has been shown to be effective in treating a range of mood disorders, it is critical to ensure that providers are meeting a consistently high standard of care over this medium. One recently developed measure of messaging quality–The Facilitative Interpersonal Skills Task for Text (FIS-T)–provides estimates of therapists’ demonstrated ability to convey psychotherapy's common factors (e.g., hopefulness, warmth, persuasiveness) over text. However, the FIS-T's scoring procedure relies on trained human coders to manually code responses, thereby rendering the FIS-T an unscalable quality control tool for large messaging therapy platforms.

Objective

In the present study, researchers developed two algorithms to automatically score therapist performance on the FIS-T task.

Methods

The FIS-T was administered to 978 messaging therapists, whose responses were then manually scored by a trained team of raters. Two machine learning algorithms were then trained on task-taker messages and coder scores: a support vector regressor (SVR) and a transformer-based neural network (DistilBERT).

Results

The DistilBERT model had superior performance on the prediction task while providing a distribution of ratings that was more closely aligned with those of human raters, versus SVR. Specifically, the DistilBERT model was able to explain 58.8% of the variance (R2 = 0.588) in human-derived ratings and realized a prediction mean absolute error of 0.134 on a 1–5 scale.

Conclusions

Algorithms can be effectively used to ensure that digital providers meet a consistently high standard of interactions in the course of messaging therapy. Natural language processing can be applied to develop new quality assurance systems in message-based digital psychotherapy.