Use of Machine-Learning Algorithms Based on Text, Audio and Video Data in the Prediction of Anxiety and Post-Traumatic Stress in General and Clinical Populations: A Systematic Review.

Research in machine-learning (ML) algorithms using natural behavior (i.e., text, audio, and video data) suggests that these techniques could contribute to personalization in psychology and psychiatry. However, a systematic review of the current state-of-the-art is missing. Moreover, individual studies often target ML experts, and may overlook potential clinical implications of their findings. In a narrative accessible to mental health professionals, we present a systematic review, conducted in 5 psychology and 2 computer-science databases. We included 128 studies assessing the predictive power of ML algorithms using text, audio, and/or video data in the prediction of anxiety and post-traumatic stress (PTSD). Most studies (n = 87) aimed at predicting anxiety, the remainder (n = 41) focused on PTSD. They were mostly published since 2019, in computer science journals, and tested algorithms using text (n = 72), as opposed to audio or video. They focused mainly on general populations (n = 92), less on laboratory experiments (n = 23) or clinical populations (n = 13). Methodological quality varied, as did reported metrics of the predictive power, hampering comparison across studies. Two thirds of studies, focusing on both disorders, reported acceptable to very good predictive power (including high-quality studies only). Results of 33 studies were uninterpretable, mainly due to missing information. Research into ML algorithms using natural behavior is in its infancy, but shows potential to contribute to diagnostics of mental disorders, such as anxiety and PTSD, in the future, if standardization of methods, reporting of results, and research in clinical populations are improved.

Feasibility of Digital Cognitive Behavioral Therapy for Depressed Older Adults With the Moodbuster Platform: Protocol for 2 Pilot Feasibility Studies.

BACKGROUND: Internet-based interventions can be effective in the treatment of depression. However, internet-based interventions for older adults with depression are scarce, and little is known about their feasibility and effectiveness. OBJECTIVE: To present the design of 2 studies aiming to assess the feasibility of internet-based cognitive behavioral treatment for older adults with depression. We will assess the feasibility of an online, guided version of the Moodbuster platform among depressed older adults from the general population as well as the feasibility of a blended format (combining integrated face-to-face sessions and internet-based modules) in a specialized mental health care outpatient clinic. METHODS: A single-group, pretest-posttest design will be applied in both settings. The primary outcome of the studies will be feasibility in terms of (1) acceptance and satisfaction (measured with the Client Satisfaction Questionnaire-8), (2) usability (measured with the System Usability Scale), and (3) engagement (measured with the Twente Engagement with eHealth Technologies Scale). Secondary outcomes include (1) the severity of depressive symptoms (measured with the 8-item Patient Health Questionnaire depression scale), (2) participant and therapist experience with the digital technology (measured with qualitative interviews), (3) the working alliance between patients and practitioners (from both perspectives; measured with the Working Alliance Inventory-Short Revised questionnaire), (4) the technical alliance between patients and the platform (measured with the Working Alliance Inventory for Online Interventions-Short Form questionnaire), and (5) uptake, in terms of attempted and completed modules. A total of 30 older adults with mild to moderate depressive symptoms (Geriatric Depression Scale 15 score between 5 and 11) will be recruited from the general population. A total of 15 older adults with moderate to severe depressive symptoms (Geriatric Depression Scale 15 score between 8 and 15) will be recruited from a specialized mental health care outpatient clinic. A mixed methods approach combining quantitative and qualitative analyses will be adopted. Both the primary and secondary outcomes will be further explored with individual semistructured interviews and synthesized descriptively. Descriptive statistics (reported as means and SDs) will be used to examine the primary and secondary outcome measures. Within-group depression severity will be analyzed using a 2-tailed, paired-sample t test to investigate differences between time points. The interviews will be recorded and analyzed using thematic analysis. RESULTS: The studies were funded in October 2019. Recruitment started in September 2022. CONCLUSIONS: The results of these pilot studies will show whether this platform is feasible for use by the older adult population in a blended, guided format in the 2 settings and will represent the first exploration of the size of the effect of Moodbuster in terms of decreased depressive symptoms. INTERNATIONAL REGISTERED REPORT IDENTIFIER (IRRID): PRR1-10.2196/41445.

E-mental health implementation in inpatient care: Exploring its potential and future challenges.

Background: There is a great evidence base today for the effectiveness of e-mental health, or the use of technology in mental healthcare. However, large-scale implementation in mental healthcare organisations is lacking, especially in inpatient specialized mental healthcare settings. Aim: The current study aimed to gain insights into the factors that promote or hinder the implementation of e-mental health applications on organisational, professional and patient levels in Belgium. Methods: Four Belgian psychiatric hospitals and psychiatric departments of general hospitals invited their professionals and patients to use Moodbuster, which is a modular web-based platform with a connected smartphone application for monitoring. The platform was used in addition to treatment as usual for three to four months. The professionals and patients completed pre- and post-implementation questionnaires on their reasons to participate or to decline participation and experiences with the Moodbuster platform. Results: Main reasons for the organisations to participate in the implementation study were a general interest in e-mental health and seeing it is a helpful add-on to regular treatment. The actual use of Moodbuster by professionals and patients proved to be challenging with only 10 professionals and 24 patients participating. Implementation was hindered by technical difficulties and inpatient care specific factors such as lack of structural facilities to use e-mental health and patient-specific factors. Professionals saw value in using e-mental health applications for bridging the transition from inpatient to outpatient care. Twenty-two professionals and 31 patients completed the questionnaire on reasons not to participate. For the patients, lack of motivation because of too severe depressive symptoms was the most important reason not to participate. For professionals, it was lack of time and high workload. Conclusions: The current implementation study reveals several important barriers to overcome in order to successfully implement e-mental health in inpatient psychiatric care.