Behind the Scenes of Online Therapeutic Feedback in Blended Therapy for Depression: Mixed-Methods Observational Study.

BACKGROUND: In Internet-delivered cognitive behavioral therapies (iCBT), written feedback by therapists is a substantial part of therapy. However, it is not yet known how this feedback should be given best and which specific therapist behaviors and content are most beneficial for patients. General instructions for written feedback are available, but the uptake and effectiveness of these instructions in iCBT have not been studied yet. OBJECTIVE: This study aimed to identify therapist behaviors in written online communication with patients in blended CBT for adult depression in routine secondary mental health care, to identify the extent to which the therapists adhere to feedback instructions, and to explore whether therapist behaviors and adherence to feedback instructions are associated with patient outcome. METHODS: Adults receiving blended CBT (10 online sessions in combination with 5 face-to-face sessions) for depression in routine mental health care were recruited in the context of the European implementation project MasterMind. A qualitative content analysis was used to identify therapist behaviors in online written feedback messages, and a checklist for the feedback instruction adherence of the therapists was developed. Correlations were explored between the therapist behaviors, therapist instruction adherence, and patient outcomes (number of completed online sessions and symptom change scores). RESULTS: A total of 45 patients (73%, 33/45 female, mean age 35.9 years) received 219 feedback messages given by 19 therapists (84%, 16/19 female). The most frequently used therapist behaviors were informing, encouraging, and affirming. However, these were not related to patient outcomes. Although infrequently used, confronting was positively correlated with session completion (ρ=.342, P=.02). Therapists adhered to most of the feedback instructions. Only 2 feedback aspects were correlated with session completion: the more therapists adhere to instructions containing structure (limiting to 2 subjects and sending feedback within 3 working days) and readability (short sentences and short paragraphs), the less online sessions were completed (ρ=-.340, P=.02 and ρ=-.361, P=.02, respectively). No associations were found with depression symptom change scores. CONCLUSIONS: The therapist behaviors found in this study are comparable to previous research. The findings suggest that online feedback instructions for therapists provide sufficient guidance to communicate in a supportive and positive manner with patients. However, the instructions might be improved by adding more therapeutic techniques besides the focus on style and form.

Embodied Conversational Agents in Clinical Psychology: A Scoping Review.

BACKGROUND: Embodied conversational agents (ECAs) are computer-generated characters that simulate key properties of human face-to-face conversation, such as verbal and nonverbal behavior. In Internet-based eHealth interventions, ECAs may be used for the delivery of automated human support factors. OBJECTIVE: We aim to provide an overview of the technological and clinical possibilities, as well as the evidence base for ECA applications in clinical psychology, to inform health professionals about the activity in this field of research. METHODS: Given the large variety of applied methodologies, types of applications, and scientific disciplines involved in ECA research, we conducted a systematic scoping review. Scoping reviews aim to map key concepts and types of evidence underlying an area of research, and answer less-specific questions than traditional systematic reviews. Systematic searches for ECA applications in the treatment of mood, anxiety, psychotic, autism spectrum, and substance use disorders were conducted in databases in the fields of psychology and computer science, as well as in interdisciplinary databases. Studies were included if they conveyed primary research findings on an ECA application that targeted one of the disorders. We mapped each study's background information, how the different disorders were addressed, how ECAs and users could interact with one another, methodological aspects, and the study's aims and outcomes. RESULTS: This study included N=54 publications (N=49 studies). More than half of the studies (n=26) focused on autism treatment, and ECAs were used most often for social skills training (n=23). Applications ranged from simple reinforcement of social behaviors through emotional expressions to sophisticated multimodal conversational systems. Most applications (n=43) were still in the development and piloting phase, that is, not yet ready for routine practice evaluation or application. Few studies conducted controlled research into clinical effects of ECAs, such as a reduction in symptom severity. CONCLUSIONS: ECAs for mental disorders are emerging. State-of-the-art techniques, involving, for example, communication through natural language or nonverbal behavior, are increasingly being considered and adopted for psychotherapeutic interventions in ECA research with promising results. However, evidence on their clinical application remains scarce. At present, their value to clinical practice lies mostly in the experimental determination of critical human support factors. In the context of using ECAs as an adjunct to existing interventions with the aim of supporting users, important questions remain with regard to the personalization of ECAs' interaction with users, and the optimal timing and manner of providing support. To increase the evidence base with regard to Internet interventions, we propose an additional focus on low-tech ECA solutions that can be rapidly developed, tested, and applied in routine practice.

Does it blend? Exploring therapist fidelity in blended CBT for anxiety disorders.

Blended cognitive-behavioural therapy (bCBT) combines face-to-face CBT (FtFCBT) and Internet-based CBT (iCBT) into one integrated treatment protocol, opening up new ways to deliver therapy, increase cost-effectiveness and resolve scarcity of therapist availability. When traditional therapy is transformed into a new format, there is a need to evaluate whether principles of the new protocol are consistently applied. This study aimed to explore therapist fidelity to bCBT protocols for anxiety disorders in specialised mental health care and to assess whether fidelity is related to patient characteristics. Adult patients (N = 44) received bCBT within a randomised controlled trial. Ratio of FtF to online sessions, session frequency and therapist adherence to instructions were assessed. Overall therapist fidelity with regard to ratio of blending, session frequency and instructions was high. Correlations were found between patients' share of online sessions and both session frequency (r = 0.373, p = .013), as well as patient computer experience (r = 0.314, p = .038). Adherence to instructions in FtF sessions was based on a subset of patients (n = 23) and should therefore be interpreted with caution. The blended approach was generally delivered as intended, indicating that the format is feasible in specialised mental health.

Improving adherence to an online intervention for low mood with a virtual coach: study protocol of a pilot randomized controlled trial.

BACKGROUND: Internet-based cognitive-behavioral therapy (iCBT) is more effective when it is guided by human support than when it is unguided. This may be attributable to higher adherence rates that result from a positive effect of the accompanying support on motivation and on engagement with the intervention. This protocol presents the design of a pilot randomized controlled trial that aims to start bridging the gap between guided and unguided interventions. It will test an intervention that includes automated support delivered by an embodied conversational agent (ECA) in the form of a virtual coach. METHODS/DESIGN: The study will employ a pilot two-armed randomized controlled trial design. The primary outcomes of the trial will be (1) the effectiveness of iCBT, as supported by a virtual coach, in terms of improved intervention adherence in comparison with unguided iCBT, and (2) the feasibility of a future, larger-scale trial in terms of recruitment, acceptability, and sample size calculation. Secondary aims will be to assess the virtual coach's effect on motivation, users' perceptions of the virtual coach, and general feasibility of the intervention as supported by a virtual coach. We will recruit N = 70 participants from the general population who wish to learn how they can improve their mood by using Moodbuster Lite, a 4-week cognitive-behavioral therapy course. Candidates with symptoms of moderate to severe depression will be excluded from study participation. Included participants will be randomized in a 1:1 ratio to either (1) Moodbuster Lite with automated support delivered by a virtual coach or (2) Moodbuster Lite without automated support. Assessments will be taken at baseline and post-study 4 weeks later. DISCUSSION: The study will assess the preliminary effectiveness of a virtual coach in improving adherence and will determine the feasibility of a larger-scale RCT. It could represent a significant step in bridging the gap between guided and unguided iCBT interventions. TRIAL REGISTRATION: Netherlands Trial Register (NTR) NL8110 . Registered on 23 October 2019.

Validating Automated Sentiment Analysis of Online Cognitive Behavioral Therapy Patient Texts: An Exploratory Study.

INTRODUCTION: Sentiment analysis may be a useful technique to derive a user's emotional state from free text input, allowing for more empathic automated feedback in online cognitive behavioral therapy (iCBT) interventions for psychological disorders such as depression. As guided iCBT is considered more effective than unguided iCBT, such automated feedback may help close the gap between the two. The accuracy of automated sentiment analysis is domain dependent, and it is unclear how well the technology is applicable to iCBT. This paper presents an empirical study in which automated sentiment analysis by an algorithm for the Dutch language is validated against human judgment. METHODS: A total of 493 iCBT user texts were evaluated on overall sentiment and the presence of five specific emotions by an algorithm, and by 52 psychology students who evaluated 75 randomly selected texts each, providing about eight human evaluations per text. Inter-rater agreement (IRR) between algorithm and humans, and humans among each other, was analyzed by calculating the intra-class correlation under a numerical interpretation of the data, and Cohen's kappa, and Krippendorff's alpha under a categorical interpretation. RESULTS: All analyses indicated moderate agreement between the algorithm and average human judgment with respect to evaluating overall sentiment, and low agreement for the specific emotions. Somewhat surprisingly, the same was the case for the IRR among human judges, which means that the algorithm performed about as well as a randomly selected human judge. Thus, considering average human judgment as a benchmark for the applicability of automated sentiment analysis, the technique can be considered for practical application. DISCUSSION/CONCLUSION: The low human-human agreement on the presence of emotions may be due to the nature of the texts, it may simply be difficult for humans to agree on the presence of the selected emotions, or perhaps trained therapists would have reached more consensus. Future research may focus on validating the algorithm against a more solid benchmark, on applying the algorithm in an application in which empathic feedback is provided, for example, by an embodied conversational agent, or on improving the algorithm for the iCBT domain with a bottom-up machine learning approach.