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.
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.
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.
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.
Anxiety disorders are highly prevalent and cause substantial economic burden. Blended cognitive-behavioural therapy (bCBT), which integrates Internet-based CBT and face-to-face CBT (ftfCBT), is an ...attractive and potentially cost-saving treatment alternative to conventional CBT for patients with anxiety disorders in specialised mental health care. However, little is known about the effectiveness of bCBT in routine care. We examined the acceptability, effectiveness and cost-effectiveness of bCBT versus ftfCBT in outpatient specialised care to patients with panic disorder, social anxiety disorder and generalised anxiety disorder.
Patients with anxiety disorders were randomised to bCBT (n = 52) or ftfCBT (n = 62). Acceptability of bCBT and ftfCBT were evaluated by assessing treatment preference, adherence, satisfaction and therapeutic alliance. Costs and effects were assessed at post-treatment and one-year follow-up. Primary outcome measure was the Beck Anxiety Inventory (BAI). Secondary outcomes were depressive symptoms, general psychopathology, work and social adjustment, quality of life and mastery. Incremental cost-effectiveness ratios (ICERs) were computed from societal and healthcare perspectives by calculating the incremental costs per incremental quality-adjusted life year (QALY). No significant differences between bCBT and ftfCBT were found on acceptability or effectiveness measures at post-treatment (Cohen's d between-group effect size on BAI = 0.15, 95% CI -0.30 to 0.60) or at one-year follow-up (d = -0.38, 95% CI -0.84 to 0.09). The modelled point estimates of societal costs (bCBT €10945, ftfCBT €10937) were higher and modelled point estimates of direct medical costs (bCBT €3748, ftfCBT €3841) were lower in bCBT. The acceptability curves showed that bCBT was expected to be a cost-effective intervention. Results should be carefully interpreted due to the small sample size.
bCBT appears an acceptable, clinically effective and potentially cost-saving alternative option for treating patients with anxiety disorders. Trials with larger samples are needed to further investigate cost-effectiveness.
Netherlands Trial Register: NTR4912.
The integration of digital treatments into national mental health services is on the agenda in the European Union. The E-COMPARED consortium conducted a survey aimed at exploring stakeholders' ...knowledge, acceptance and expectations of digital treatments for depression, and at identifying factors that might influence their opinions when considering the implementation of these approaches.
An online survey was conducted in eight European countries: France, Germany, Netherlands, Poland, Spain, Sweden, Switzerland and The United Kingdom. Organisations representing government bodies, care providers, service-users, funding/insurance bodies, technical developers and researchers were invited to participate in the survey. The participating countries and organisations reflect the diversity in health care infrastructures and e-health implementation across Europe.
A total of 764 organisations were invited to the survey during the period March–June 2014, with 175 of these organisations participating in our survey. The participating stakeholders reported moderate knowledge of digital treatments and considered cost-effectiveness to be the primary incentive for integration into care services. Low feasibility of delivery within existing care services was considered to be a primary barrier. Digital treatments were regarded more suitable for milder forms of depression. Stakeholders showed greater acceptability towards blended treatment (the integration of face-to-face and internet sessions within the same treatment protocol) compared to standalone internet treatments. Organisations in countries with developed e-health solutions reported greater knowledge and acceptability of digital treatments.
Mental health stakeholders in Europe are aware of the potential benefits of digital interventions. However, there are variations between countries and stakeholders in terms of level of knowledge about such interventions and their feasibility within routine care services. The high acceptance of blended treatments is an interesting finding that indicates a gradual integration of technology into clinical practice may fit the attitudes and needs of stakeholders. The potential of the blended treatment approach, in terms of enhancing acceptance of digital treatment while retaining the benefit of cost-effectiveness in delivery, should be further explored.
The E-COMPARED project has received funding from the European Union Seventh Framework Programme (FP7/2007–2013) under grant agreement no. 603098.
•Digital treatments were rated as more acceptable for milder forms of depression.•Stakeholders demonstrated greater acceptability towards blended treatment compared to standalone digital treatment.•Cost-effectiveness was identified as the primary incentive for integrating of treatments into routine care.•Care systems being viewed as unprepared for internet-based treatments was identified as the primary barrier.•Stakeholders in countries with developed e-health solutions demonstrated higher knowledge towards digital treatments.
Earlier research has revealed a strong relationship between alcohol use and sickness absence. The aim of this review was to explore and uncover this relationship by looking at differences in type of ...design (cross-sectional vs. longitudinal), type of data (self-reported vs. registered data), and type of sickness absence (long-term vs. short term).
Six databases were searched through June 2020. Observational and experimental studies from 1980 to 2020, in English or Scandinavian languages reporting the results of the association between alcohol consumption and sickness absence among working population were included. Quality assessment, and statistical analysis focusing on differences in the likelihood of sickness absence on subgroup levels were performed on each association, not on each study. Differences in the likelihood of sickness absence were analyzed by means of meta-analysis. PROSPERO registration number: CRD42018112078.
Fifty-nine studies (58% longitudinal) including 439,209 employees (min. 43, max. 77,746) from 15 countries were included. Most associations indicating positive and statistically significant results were based on longitudinal data (70%) and confirmed the strong/causal relationship between alcohol use and sickness absence. The meta-analysis included eight studies (ten samples). The increased risk for sickness absence was likely to be found in cross-sectional studies (OR: 8.28, 95% CI: 6.33-10.81), studies using self-reported absence data (OR: 5.16, 95% CI: 3.16-8.45), and those reporting short-term sickness absence (OR: 4.84, 95% CI: 2.73-8.60).
This review supports, but also challenges earlier evidence on the association between alcohol use and sickness absence. Certain types of design, data, and types of sickness absence may produce large effects. Hence, to investigate the actual association between alcohol and sickness absence, research should produce and review longitudinal designed studies using registry data and do subgroup analyses that cover and explain variability of this association.
Internet-based cognitive behavioral therapy (iCBT) has been demonstrated to be cost- and clinically effective. There is a need, however, for increased therapist contact for some patient groups. ...Combining iCBT with traditional face-to-face (FtF) consultations in a blended format may produce a new treatment format (B-CBT) with multiple benefits from both traditional CBT and iCBT, such as individual adaptation, lower costs than traditional therapy, wide geographical and temporal availability, and possibly lower threshold to implementation. The primary aim of this study is to compare directly the clinical effectiveness of B-CBT with FtF-CBT for adult major depressive disorder. A 2-arm randomized controlled noninferiority trial compared B-CBT for adult depression with treatment as usual (TAU). The trial was researcher blinded (unblinded for participants and clinicians). B-CBT comprised 6 sessions of FtF-CBT alternated with 6-8 web-based CBT self-help modules. TAU comprised 12 sessions of FtF-CBT. All participants were aged 18 or older and met the diagnostic criteria for major depressive disorder and were recruited via a national iCBT clinic. The primary outcome was change in depression severity on the 9-item Patient Health Questionnaire (PHQ-9). Secondary analyses included client satisfaction (8-item Client Satisfaction Questionnaire CSQ-8), patient expectancy (Credibility and Expectancy Questionnaire CEQ), and working (Working Alliance Inventory WAI and Technical Alliance Inventory TAI). The primary outcome was analyzed by a mixed effects model including all available data from baseline, weekly measures, 3-, 6, and 12-month follow-up. A total of 76 individuals were randomized, with 38 allocated to each treatment group. Age ranged from 18 to 71 years (SD 13.96) with 56 (74%) females. Attrition rate was 20% (n=15), which was less in the FtF-CBT group (n=6, 16%) than in the B-CBT group (n=9, 24%). As many as 53 (70%) completed 9 or more sessions almost equally distributed between the groups (nFtF-CBT=27, 71%; nB-CBT=26, 68%). PHQ-9 reduced 11.38 points in the FtF-CBT group and 8.10 in the B-CBT group. At 6 months, the mean difference was a mere 0.17 points. The primary analyses confirmed large and significant within-group reductions in both groups (FtF-CBT: β=–.03; standard error SE 0.00; P<.001 and B-CBT: β=–.02; SE 0.00; P<.001). A small but significant interaction effect was observed between groups (β=.01; SE 0.00; P=.03). Employment status influenced the outcome differently between groups, where the B-CBT group was seen to profit more from not being full-time employed than the FtF group. With large within-group effects in both treatment arms, the study demonstrated feasibility of B-CBT in Denmark. At 6 months’ follow-up, there appeared to be no difference between the 2 treatment formats, with a small but nonsignificant difference at 12 months. The study seems to demonstrate that B-CBT is capable of producing treatment effects that are close to FtF-CBT and that completion rates and satisfaction rates were comparable between groups. However, the study was limited by small sample size and should be interpreted with caution.
Background
Evidence shows that online interventions could prevent depression. However, to improve the effectiveness of preventive online interventions in individuals with subthreshold depression, it ...is worthwhile to study factors influencing intervention outcomes. Outcome expectancy has been shown to predict treatment outcomes in psychotherapy for depression. However, little is known about whether this also applies to depression prevention. The aim of this study was to investigate the role of participants' outcome expectancy in an online depression prevention intervention.
Methods
A secondary data analysis was conducted using data from two randomised‐controlled trials (N = 304). Multilevel modelling was used to explore the effect of outcome expectancy on depressive symptoms and close‐to‐symptom‐free status postintervention (6–7 weeks) and at follow‐up (3–6 months). In a subsample (n = 102), Cox regression was applied to assess the effect on depression onset within 12 months. Explorative analyses included baseline characteristics as possible moderators. Outcome expectancy did not predict posttreatment outcomes or the onset of depression.
Results
Small effects were observed at follow‐up for depressive symptoms (β = −.39, 95% confidence interval CI: −0.75, −0.03, p = .032, padjusted = .130) and close‐to‐symptom‐free status (relative risk = 1.06, 95% CI: 1.01, 1.11, p = .013, padjusted = 0.064), but statistical significance was not maintained when controlling for multiple testing. Moderator analyses indicated that expectancy could be more influential for females and individuals with higher initial symptom severity.
Conclusion
More thoroughly designed, predictive studies targeting outcome expectancy are necessary to assess the full impact of the construct for effective depression prevention.
Patient or Public Contribution
This secondary analysis did not involve patients, service users, care‐givers, people with lived experience or members of the public. However, the findings incorporate the expectations of participants using the preventive online intervention, and these exploratory findings may inform the future involvement of participants in the design of indicated depression prevention interventions for adults.
Clinical Trial Registration
Original studies: DRKS00004709, DRKS00005973; secondary analysis: osf.io/9xj6a.
Objective The primary purpose of this randomized controlled trial (RCT) was to evaluate the efficacy of internet-based problem-solving training (iPST) for employees in the educational sector ...(teachers) with depressive symptoms. The results of training were compared to those of a waitlist control group (WLC). Methods One-hundred and fifty teachers with elevated depressive symptoms (Center for Epidemiologie Studies Depression Scale, CES-D ≥16) were assigned to either the iPST or WLC group. The iPST consisted of five lessons, including problem-solving and rumination techniques. Symptoms were assessed before the intervention began and in follow-up assessments after seven weeks, three months, and six months. The primary outcome was depressive symptom severity (CES-D). Secondary outcomes included general and work-specific self-efficacy, perceived stress, pathological worries, burnout symptoms, general physical and mental health, and absenteeism. Results iPST participants displayed a significantly greater reduction in depressive symptoms after the intervention (d=0.59, 95% CI 0.26-0.92), after three months (d=0.37, 95% CI 0.05-0.70) and after six months (d=0.38, 95% CI 0.05-0.70) compared to the control group. The iPST participants also displayed significantly higher improvements in secondary outcomes. However, workplace absenteeism was not significantly affected. Conclusion iPST is effective in reducing symptoms of depression among teachers. Disseminated on a large scale, iPST could contribute to reducing the burden of stress-related mental health problems among teachers. Future studies should evaluate iPST approaches for use in other working populations.
E-health offers great potential in the field of traumatic stress to deliver training, assessment, prevention, and treatment of adverse outcomes after trauma worldwide. In order to encourage research ...on E-health applications in the field of traumatic stress, this current special issue of the European Journal of Psychotraumatology presents a series of papers divided into three emergent topics: I) development of digital interventions, II) the use of digital interventions to foster self-management and deliver therapy, and III) digital methods to improve prediction, assessment, and monitoring of post-trauma outcomes. These studies show acceptance of the tools by various end-user groups and improvements of current research and clinical practices, but also areas for improvement regarding the development process and making even better use of technological capabilities of E-Health. We propose three general themes to accelerate the quality of e-Health interventions and studies in this area in the coming years: optimizing user engagement and adherence, conducting more (innovative) research, and increasing implementation and dissemination activities. This issue appears in the midst of the COVID-19 pandemic. It is exactly at times like these that we need effective online interventions and we see an enormous increase in the use of e-Health. We hope this issue will contribute to help those affected and to serve the community worldwide.
A growing body of literature indicates that adolescent girls who talk with close friends about interpersonal problems or worries in an excessive, speculative way, and with an intense focus on ...distress (i.e., co-rumination) are at heightened risk for developing internalizing symptoms and disorders as well as reduced friendship quality. However, to date, there are no prevention programs available that target high levels of co-rumination between adolescent girls. As such, we developed the blended school-based mindfulness prevention program Happy Friends, Positive Minds (HFPM) that targets co-rumination at the dyadic level, i.e., between two close female friends. The aim of this trial is to evaluate the effectiveness of HFPM to reduce co-rumination and internalizing problems and to enhance wellbeing and social-emotional behavior in Dutch adolescent girls.
A cluster Randomized Controlled Trial (cRCT) will be conducted to evaluate HFPM effectiveness. We will recruit 160 female friendship dyads (n = 320 girls) aged 13 to 15 years who will be characterized by high levels of self-reported co-rumination. The cRCT has two arms: (1) an intervention condition in which 160 girls (80 friendship dyads) will receive the 14-week HFPM program in two consecutive cohorts (cohort 1 in academic year 2023/2024 and cohort 2 in academic year 2024/2025, and (2) a control condition in which 160 girls (80 dyads) will receive care-as-usual (CAU) in two consecutive cohorts (cohort 1 in academic year 2023/2024 and cohort 2 in academic year 2024/2025). Data will be collected at baseline (T0), during the program (T1;T2; T3), immediately after the program (T4), and at 1-year follow-up (T5). Participant-level self-reported risk for (early onset) depression and anxiety, self-reported and observed co-rumination, self- and friend-reported friendship quality, self-reported positive and negative affect, self-reported interpersonal responses to positive affect, and self-reported anhedonia symptoms will be the outcome variables.
This study will provide insights into the short-term and long-term effects of the HFPM program on girls' internalizing problems, wellbeing, and social-emotional behavior.
International Standard Randomized Controlled Trials, identifier: ISRCTN54246670. Registered on 27 February 2023.
Depression and anxiety are common mental health conditions in college and university student populations. Offering transdiagnostic, web-based prevention programs such as ICare Prevent to those with ...subclinical complaints has the potential to reduce some barriers to receiving help (eg, availability of services, privacy considerations, and students' desire for autonomy). However, uptake of these interventions is often low, and accounts of recruitment challenges are needed to complement available effectiveness research in student populations.
The aims of this study were to describe recruitment challenges together with effective recruitment strategies for ICare Prevent and provide basic information on the intervention's effectiveness.
A 3-arm randomized controlled trial was conducted in a student sample with subclinical symptoms of depression and anxiety on the effectiveness of an individually guided (human support and feedback on exercises provided after each session, tailored to each participant) and automatically guided (computer-generated messages provided after each session, geared toward motivation) version of ICare Prevent, a web-based intervention with transdiagnostic components for the indicated prevention of depression and anxiety. The intervention was compared with care as usual. Descriptive statistics were used to outline recruitment challenges and effective web-based and offline strategies as well as students' use of the intervention. A basic analysis of intervention effects was conducted using a Bayesian linear mixed model, with Bayes factors reported as the effect size.
Direct recruitment through students' email addresses via the central student administration was the most effective strategy. Data from 35 participants were analyzed (individually guided: n=14, 40%; automatically guided: n=8, 23%; care as usual: n=13, 37%). Use of the intervention was low, with an average of 3 out of 7 sessions (SD 2.9) completed. The analyses did not suggest any intervention effects other than anecdotal evidence (all Bayes factors
≤2.7).
This report adds to the existing literature on recruitment challenges specific to the student population. Testing the feasibility of recruitment measures and the greater involvement of the target population in their design, as well as shifting from direct to indirect prevention, can potentially help future studies in the field. In addition, this report demonstrates an alternative basic analytical strategy for underpowered randomized controlled trials.
International Clinical Trials Registry Platform NTR6562; https://tinyurl.com/4rbexzrk.
RR2-10.1186/s13063-018-2477-y.