Increasing demand for school counselling through a lay counsellor-delivered classroom sensitisation intervention: a stepped-wedge cluster randomised controlled trial in New Delhi, India.

INTRODUCTION: We evaluated a classroom-based sensitisation intervention that was designed to reduce demand-side barriers affecting referrals to a school counselling programme. The sensitisation intervention was offered in the context of a host trial evaluating a low-intensity problem-solving treatment for common adolescent mental health problems. METHODS: We conducted a stepped-wedge, cluster randomised controlled trial with 70 classes in 6 secondary schools serving low-income communities in New Delhi, India.The classes were randomised to receive a classroom sensitisation session involving a brief video presentation and moderated group discussion, delivered by a lay counsellor over one class period (intervention condition, IC), in two steps of 4 weeks each. The control condition (CC) was whole-school sensitisation (teacher-meetings and whole-school activities such as poster displays). The primary outcome was the proportion of students referred into the host trial. Secondary outcomes were the proportion of students who met mental health caseness criteria and the proportion of self-referred adolescents. RESULTS: Between 20 August 2018 and 9 December 2018, 835 students (23.3% of all students) were referred into the host trial. The referred sample included 591 boys (70.8%), and had a mean age of 15.8 years, SD=0.06; 194 students (31.8% of 610 with complete data) met mental health caseness criteria. The proportion of students referred in each trial conditionwas significantly higher in the IC (IC=21.7%, CC=1.5%, OR=111.36, 95% CI 35.56 to 348.77, p<0.001). The proportion of self-referred participants was also higher in the IC (IC=98.1%, CC=89.1%, Pearson χ2 (1)=16.92, p<0.001). Although the proportion of referred students meeting caseness criteria was similar in both conditions (IC=32.0% vs CC=28.1%), the proportion weighted for the total student population was substantially higher in the IC (IC=5.2%, CC=0.3%, OR=52.39, 95% CI 12.49 to 219.66,p<0.001). CONCLUSION: A single, lay counsellor-delivered, classroom sensitisation session increased psychological help-seeking for common mental health problems among secondary school pupils from urban, low-income communities in India. TRIAL REGISTRATION NUMBER: NCT03633916.

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.

Tailored implementation of internet-based cognitive behavioural therapy in the multinational context of the ImpleMentAll project: a study protocol for a stepped wedge cluster randomized trial.

BACKGROUND: Internet-based Cognitive Behavioural Therapy (iCBT) is found effective in treating common mental disorders. However, the use of these interventions in routine care is limited. The international ImpleMentAll study is funded by the European Union's Horizon 2020 programme. It is concerned with studying and improving methods for implementing evidence-based iCBT services for common mental disorders in routine mental health care. A digitally accessible implementation toolkit (ItFits-toolkit) will be introduced to mental health care organizations with the aim to facilitate the ongoing implementation of iCBT services within local contexts. This study investigates the effectiveness of the ItFits-toolkit by comparing it to implementation-as-usual activities. METHODS: A stepped wedge cluster randomized controlled trial (SWT) design will be applied. Over a trial period of 30 months, the ItFits-toolkit will be introduced sequentially in twelve routine mental health care organizations in primary and specialist care across nine countries in Europe and Australia. Repeated measures are applied to assess change over time in the outcome variables. The effectiveness of the ItFits-toolkit will be assessed in terms of the degree of normalization of the use of the iCBT services. Several exploratory outcomes including uptake of the iCBT services will be measured to feed the interpretation of the primary outcome. Data will be collected via a centralized data collection system and analysed using generalized linear mixed modelling. A qualitative process evaluation of routine implementation activities and the use of the ItFits-toolkit will be conducted within this study. DISCUSSION: The ImpleMentAll study is a large-scale international research project designed to study the effectiveness of tailored implementation. Using a SWT design that allows to examine change over time, this study will investigate the effect of tailored implementation on the normalization of the use of iCBT services and their uptake. It will provide a better understanding of the process and methods of tailoring implementation strategies. If found effective, the ItFits-toolkit will be made accessible for mental health care service providers, to help them overcome their context-specific implementation challenges. TRIAL REGISTRATION: ClinicalTrials.gov NCT03652883 . Retrospectively registered on 29 August 2018.

Dimensionality of the system usability scale among professionals using internet-based interventions for depression: a confirmatory factor analysis.

BACKGROUND: The System Usability Scale (SUS) is used to measure usability of internet-based Cognitive Behavioural Therapy (iCBT). However, whether the SUS is a valid instrument to measure usability in this context is unclear. The aim of this study is to assess the factor structure of the SUS, measuring usability of iCBT for depression in a sample of professionals. In addition, the psychometric properties (reliability, convergent validity) of the SUS were tested. METHODS: A sample of 242 professionals using iCBT for depression from 6 European countries completed the SUS. Confirmatory Factor Analysis (CFA) was conducted to test whether a one-factor, two-factor, tone-model or bi-direct model would fit the data best. Reliability was assessed using complementary statistical indices (e.g. omega). To assess convergent validity, the SUS total score was correlated with an adapted Client Satisfaction Questionnaire (CSQ-3). RESULTS: CFA supported the one-factor, two-factor and tone-model, but the bi-factor model fitted the data best (Comparative Fit Index = 0.992, Tucker Lewis Index = 0.985, Root Mean Square Error of Approximation = 0.055, Standardized Root Mean Square Residual = 0.042 (respectively χ2diff (9) = 69.82, p < 0.001; χ2diff (8) = 33.04, p < 0.001). Reliability of the SUS was good (ω = 0.91). The total SUS score correlated moderately with the CSQ-3 (CSQ1 rs = .49, p < 0.001; CSQ2 rs = .46, p < 0.001; CSQ3 rs = .38, p < 0.001), indicating convergent validity. CONCLUSIONS: Although the SUS seems to have a multidimensional structure, the best model showed that the total sumscore of the SUS appears to be a valid and interpretable measure to assess the usability of internet-based interventions when used by professionals in mental healthcare.

Working Alliance in Blended Versus Face-to-Face Cognitive Behavioral Treatment for Patients with Depression in Specialized Mental Health Care.

This study investigates working alliance in blended cognitive behavioral therapy (bCBT) for depressed adults in specialized mental health care. Patients were randomly allocated to bCBT (n = 47) or face-to-face CBT (n = 45). After 10 weeks of treatment, both patients and therapists in the two groups rated the therapeutic alliance on the Working Alliance Inventory Short-Form Revised (WAI-SR; Task, Bond, Goal, and composite scores). No between-group differences were found in relation to either patient or therapist alliance ratings, which were high in both groups. In the full sample, a moderate positive association was found between patient and therapist ratings on Task (ρ = 0.41, 95% CI 0.20; 0.59), but no significant associations emerged on other components or composite scores. At 30 weeks, within-and between-group associations between alliance and changes in depression severity (QIDS, Quick Inventory of Depressive Symptomatology) were analyzed with linear mixed models. The analyses revealed an association between depression over time, patient-rated alliance, and group (p < 0.001). In face-to-face CBT, but not in bCBT, lower depression scores were associated with higher alliance ratings. The online component in bCBT may have led patients to evaluate the working alliance differently from patients receiving face-to-face CBT only.

Cost and Effectiveness of Blended Versus Standard Cognitive Behavioral Therapy for Outpatients With Depression in Routine Specialized Mental Health Care: Pilot Randomized Controlled Trial.

BACKGROUND: Cognitive behavioral therapy (CBT) is an effective treatment, but access is often restricted due to costs and limited availability of trained therapists. Blending online and face-to-face CBT for depression might improve cost-effectiveness and treatment availability. OBJECTIVE: This pilot study aimed to examine the costs and effectiveness of blended CBT compared with standard CBT for depressed patients in specialized mental health care to guide further research and development of blended CBT. METHODS: Patients were randomly allocated to blended CBT (n=53) or standard CBT (n=49). Blended CBT consisted of 10 weekly face-to-face sessions and 9 Web-based sessions. Standard CBT consisted of 15 to 20 weekly face-to-face sessions. At baseline and 10, 20, and 30 weeks after start of treatment, self-assessed depression severity, quality-adjusted life-years (QALYs), and costs were measured. Clinicians, blinded to treatment allocation, assessed psychopathology at all time points. Data were analyzed using linear mixed models. Uncertainty intervals around cost and effect estimates were estimated with 5000 Monte Carlo simulations. RESULTS: Blended CBT treatment duration was mean 19.0 (SD 12.6) weeks versus mean 33.2 (SD 23.0) weeks in standard CBT (P<.001). No significant differences were found between groups for depressive episodes (risk difference [RD] 0.06, 95% CI -0.05 to 0.19), response to treatment (RD 0.03, 95% CI -0.10 to 0.15), and QALYs (mean difference 0.01, 95% CI -0.03 to 0.04). Mean societal costs for blended CBT were €1183 higher than standard CBT. This difference was not significant (95% CI -399 to 2765). Blended CBT had a probability of being cost-effective compared with standard CBT of 0.02 per extra QALY and 0.37 for an additional treatment response, at a ceiling ratio of €25,000. For health care providers, mean costs for blended CBT were €176 lower than standard CBT. This difference was not significant (95% CI -659 to 343). At €0 per additional unit of effect, the probability of blended CBT being cost-effective compared with standard CBT was 0.75. The probability increased to 0.88 at a ceiling ratio of €5000 for an added treatment response, and to 0.85 at €10,000 per QALY gained. For avoiding new depressive episodes, blended CBT was deemed not cost-effective compared with standard CBT because the increase in costs was associated with negative effects. CONCLUSIONS: This pilot study shows that blended CBT might be a promising way to engage depressed patients in specialized mental health care. Compared with standard CBT, blended CBT was not considered cost-effective from a societal perspective but had an acceptable probability of being cost-effective from the health care provider perspective. Results should be carefully interpreted due to the small sample size. Further research in larger replication studies focused on optimizing the clinical effects of blended CBT and its budget impact is warranted. TRIAL REGISTRATION: Netherlands Trial Register NTR4650; https://www.trialregister.nl/trial/4408. INTERNATIONAL REGISTERED REPORT IDENTIFIER (IRRID): RR2-10.1186/s12888-014-0290-z.

The effectiveness of a low-intensity problem-solving intervention for common adolescent mental health problems in New Delhi, India: protocol for a school-based, individually randomized controlled trial with an embedded stepped-wedge, cluster randomized controlled recruitment trial.

BACKGROUND: Conduct, anxiety, and depressive disorders account for over 75% of the adolescent mental health burden globally. The current protocol will test a low-intensity problem-solving intervention for school-going adolescents with common mental health problems in India. The protocol also tests the effects of a classroom-based sensitization intervention on the demand for counselling services in an embedded recruitment trial. METHODS/DESIGN: We will conduct a two-arm, individually randomized controlled trial in six Government-run secondary schools in New Delhi. The targeted sample is 240 adolescents in grades 9-12 with persistent, elevated mental health symptoms and associated distress/impairment. Participants will receive either a brief problem-solving intervention delivered over 3 weeks by lay counsellors (intervention) or enhanced usual care comprised of problem-solving booklets (control). Self-reported adolescent mental health symptoms and idiographic problems will be assessed at 6 weeks (co-primary outcomes) and again at 12 weeks post-randomization. In addition, adolescent-reported distress/impairment, perceived stress, mental wellbeing, and clinical remission, as well as parent-reported adolescent mental health symptoms and impact scores, will be assessed at 6 and 12 weeks post-randomization. We will also complete a parallel process evaluation, including estimations of the costs of delivering the interventions. An embedded recruitment trial will apply a stepped-wedge, cluster (class)-randomized controlled design in 70 classes across the six schools. This will evaluate the added effect of a classroom-based sensitization intervention over and above school-level sensitization activities on the primary outcome of referral rate into the host trial. Other outcomes will be the proportion of referrals eligible to participate in the host trial, proportion of self-generated referrals, and severity and pattern of symptoms among referred adolescents in each condition. Power calculations were undertaken separately for each trial. A detailed statistical analysis plan will be developed separately for each trial prior to unblinding. DISCUSSION: Both trials were initiated on 20 August 2018. A single research protocol for both trials offers a resource-efficient methodology for testing the effectiveness of linked procedures to enhance uptake and outcomes of a school-based psychological intervention for common adolescent mental health problems. TRIAL REGISTRATION: Both trials are registered prospectively with the National Institute of Health registry ( www.clinicaltrials.gov ), registration numbers NCT03633916 and NCT03630471 , registered on 16th August, 2018 and 14th August, 2018 respectively).

Unraveling the Black Box: Exploring Usage Patterns of a Blended Treatment for Depression in a Multicenter Study.

BACKGROUND: Blended treatments, combining digital components with face-to-face (FTF) therapy, are starting to find their way into mental health care. Knowledge on how blended treatments should be set up is, however, still limited. To further explore and optimize blended treatment protocols, it is important to obtain a full picture of what actually happens during treatments when applied in routine mental health care. OBJECTIVE: The aims of this study were to gain insight into the usage of the different components of a blended cognitive behavioral therapy (bCBT) for depression and reflect on actual engagement as compared with intended application, compare bCBT usage between primary and specialized care, and explore different usage patterns. METHODS: Data used were collected from participants of the European Comparative Effectiveness Research on Internet-Based Depression Treatment project, a European multisite randomized controlled trial comparing bCBT with regular care for depression. Patients were recruited in primary and specialized routine mental health care settings between February 2015 and December 2017. Analyses were performed on the group of participants allocated to the bCBT condition who made use of the Moodbuster platform and for whom data from all blended components were available (n=200). Included patients were from Germany, Poland, the Netherlands, and France; 64.5% (129/200) were female and the average age was 42 years (range 18-74 years). RESULTS: Overall, there was a large variability in the usage of the blended treatment. A clear distinction between care settings was observed, with longer treatment duration and more FTF sessions in specialized care and a more active and intensive usage of the Web-based component by the patients in primary care. Of the patients who started the bCBT, 89.5% (179/200) also continued with this treatment format. Treatment preference, educational level, and the number of comorbid disorders were associated with bCBT engagement. CONCLUSIONS: Blended treatments can be applied to a group of patients being treated for depression in routine mental health care. Rather than striving for an optimal blend, a more personalized blended care approach seems to be the most suitable. The next step is to gain more insight into the clinical and cost-effectiveness of blended treatments and to further facilitate uptake in routine mental health care.

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.

Toward an Objective Assessment of Implementation Processes for Innovations in Health Care: Psychometric Evaluation of the Normalization Measure Development (NoMAD) Questionnaire Among Mental Health Care Professionals.

BACKGROUND: Successfully implementing eMental health (eMH) interventions in routine mental health care constitutes a major challenge. Reliable instruments to assess implementation progress are essential. The Normalization MeAsure Development (NoMAD) study developed a brief self-report questionnaire that could be helpful in measuring implementation progress. Based on the Normalization Process Theory, this instrument focuses on 4 generative mechanisms involved in implementation processes: coherence, cognitive participation, collective action, and reflexive monitoring. OBJECTIVE: The aim of this study was to translate the NoMAD questionnaire to Dutch and to confirm the factor structure in Dutch mental health care settings. METHODS: Dutch mental health care professionals involved in eMH implementation were invited to complete the translated NoMAD questionnaire. Confirmatory factor analysis (CFA) was conducted to verify interpretability of scale scores for 3 models: (1) the theoretical 4-factor structure, (2) a unidimensional model, and (3) a hierarchical model. Potential improvements were explored, and correlated scale scores with 3 control questions were used to assess convergent validity. RESULTS: A total of 262 professionals from mental health care settings in the Netherlands completed the questionnaire (female: 81.7%; mean age: 45 [SD=11]). The internal consistency of the 20-item questionnaire was acceptable (.62≤alpha≤.85). The theorized 4-factor model fitted the data slightly better in the CFA than the hierarchical model (Comparative Fit Index=0.90, Tucker Lewis Index=0.88, Root Mean Square Error of Approximation=0.10, Standardized Root Mean Square Residual=0.12, χ22=22.5, P≤.05). However, the difference is small and possibly not outweighing the practical relevance of a total score and subscale scores combined in one hierarchical model. One item was identified as weak (λCA.2=0.10). A moderate-to-strong convergent validity with 3 control questions was found for the Collective Participation scale (.47≤r≤.54, P≤.05). CONCLUSIONS: NoMAD's theoretical factor structure was confirmed in Dutch mental health settings to acceptable standards but with room for improvement. The hierarchical model might prove useful in increasing the practical utility of the NoMAD questionnaire by combining a total score with information on the 4 generative mechanisms. Future research should assess the predictive value and responsiveness over time and elucidate the conceptual interpretability of NoMAD in eMH implementation practices.

Smartphone-based safety planning and self-monitoring for suicidal patients: Rationale and study protocol of the CASPAR (Continuous Assessment for Suicide Prevention And Research) study.

BACKGROUND: It remains difficult to predict and prevent suicidal behaviour, despite growing understanding of the aetiology of suicidality. Clinical guidelines recommend that health care professionals develop a safety plan in collaboration with their high-risk patients, to lower the imminent risk of suicidal behaviour. Mobile health applications provide new opportunities for safety planning, and enable daily self-monitoring of suicide-related symptoms that may enhance safety planning. This paper presents the rationale and protocol of the Continuous Assessment for Suicide Prevention And Research (CASPAR) study. The aim of the study is two-fold: to evaluate the feasibility of mobile safety planning and daily mobile self-monitoring in routine care treatment for suicidal patients, and to conduct fundamental research on suicidal processes. METHODS: The study is an adaptive single cohort design among 80 adult outpatients or day-care patients, with the main diagnosis of major depressive disorder or dysthymia, who have an increased risk for suicidal behaviours. There are three measurement points, at baseline, at 1 and 3 months after baseline. Patients are instructed to use their mobile safety plan when necessary and monitor their suicidal symptoms daily. Both these apps will be used in treatment with their clinician. CONCLUSION: The results from this study will provide insight into the feasibility of mobile safety planning and self-monitoring in treatment of suicidal patients. Furthermore, knowledge of the suicidal process will be enhanced, especially regarding the transition from suicidal ideation to behaviour.The study protocol is currently under revision for medical ethics approval by the medical ethics board of the Vrije Universiteit Medical centre Amsterdam (METc number 2017.512/NL62795.029.17).

Navigating the development and dissemination of internet cognitive behavioral therapy (iCBT) for anxiety disorders in children and young people: A consensus statement with recommendations from the #iCBTLorentz Workshop Group.

Initial internet-based cognitive behavioral therapy (iCBT) programs for anxiety disorders in children and young people (CYP) have been developed and evaluated, however these have not yet been widely adopted in routine practice. The lack of guidance and formalized approaches to the development and dissemination of iCBT has arguably contributed to the difficulty in developing iCBT that is scalable and sustainable beyond academic evaluation and that can ultimately be adopted by healthcare providers. This paper presents a consensus statement and recommendations from a workshop of international experts in CYP anxiety and iCBT (#iCBTLorentz Workshop Group) on the development, evaluation, engagement and dissemination of iCBT for anxiety in CYP.

Predictive modeling in e-mental health: A common language framework.

Recent developments in mobile technology, sensor devices, and artificial intelligence have created new opportunities for mental health care research. Enabled by large datasets collected in e-mental health research and practice, clinical researchers and members of the data mining community increasingly join forces to build predictive models for health monitoring, treatment selection, and treatment personalization. This paper aims to bridge the historical and conceptual gaps between the distant research domains involved in this new collaborative research by providing a conceptual model of common research goals. We first provide a brief overview of the data mining field and methods used for predictive modeling. Next, we propose to characterize predictive modeling research in mental health care on three dimensions: 1) time, relative to treatment (i.e., from screening to post-treatment relapse monitoring), 2) types of available data (e.g., questionnaire data, ecological momentary assessments, smartphone sensor data), and 3) type of clinical decision (i.e., whether data are used for screening purposes, treatment selection or treatment personalization). Building on these three dimensions, we introduce a framework that identifies four model types that can be used to classify existing and future research and applications. To illustrate this, we use the framework to classify and discuss published predictive modeling mental health research. Finally, in the discussion, we reflect on the next steps that are required to drive forward this promising new interdisciplinary field.

Predicting short term mood developments among depressed patients using adherence and ecological momentary assessment data.

Technology driven interventions provide us with an increasing amount of fine-grained data about the patient. This data includes regular ecological momentary assessments (EMA) but also response times to EMA questions by a user. When observing this data, we see a huge variation between the patterns exhibited by different patients. Some are more stable while others vary a lot over time. This poses a challenging problem for the domain of artificial intelligence and makes on wondering whether it is possible to predict the future mental state of a patient using the data that is available. In the end, these predictions could potentially contribute to interventions that tailor the feedback to the user on a daily basis, for example by warning a user that a fall-back might be expected during the next days, or by applying a strategy to prevent the fall-back from occurring in the first place. In this work, we focus on short term mood prediction by considering the adherence and usage data as an additional predictor. We apply recurrent neural networks to handle the temporal aspects best and try to explore whether individual, group level, or one single predictive model provides the highest predictive performance (measured using the root mean squared error (RMSE)). We use data collected from patients from five countries who used the ICT4Depression/MoodBuster platform in the context of the EU E-COMPARED project. In total, we used the data from 143 patients (with between 9 and 425 days of EMA data) who were diagnosed with a major depressive disorder according to DSM-IV. Results show that we can make predictions of short term mood change quite accurate (ranging between 0.065 and 0.11). The past EMA mood ratings proved to be the most influential while adherence and usage data did not improve prediction accuracy. In general, group level predictions proved to be the most promising, however differences were not significant. Short term mood prediction remains a difficult task, but from this research we can conclude that sophisticated machine learning algorithms/setups can result in accurate performance. For future work, we want to use more data from the mobile phone to improve predictive performance of short term mood.

Using multi-relational data mining to discriminate blended therapy efficiency on patients based on log data.

INTRODUCTION: Clinical trials of blended Internet-based treatments deliver a wealth of data from various sources, such as self-report questionnaires, diagnostic interviews, treatment platform log files and Ecological Momentary Assessments (EMA). Mining these complex data for clinically relevant patterns is a daunting task for which no definitive best method exists. In this paper, we explore the expressive power of the multi-relational Inductive Logic Programming (ILP) data mining approach, using combined trial data of the EU E-COMPARED depression trial. METHODS: We explored the capability of ILP to handle and combine (implicit) multiple relationships in the E-COMPARED data. This data set has the following features that favor ILP analysis: 1) Time reasoning is involved; 2) there is a reasonable amount of explicit useful relations to be analyzed; 3) ILP is capable of building comprehensible models that might be perceived as putative explanations by domain experts; 4) both numerical and statistical models may coexist within ILP models if necessary. In our analyses, we focused on scores of the PHQ-8 self-report questionnaire (which taps depressive symptom severity), and on EMA of mood and various other clinically relevant factors. Both measures were administered during treatment, which lasted between 9 to 16 weeks. RESULTS: E-COMPARED trial data revealed different individual improvement patterns: PHQ-8 scores suggested that some individuals improved quickly during the first weeks of the treatment, while others improved at a (much) slower pace, or not at all. Combining self-reported Ecological Momentary Assessments (EMA), PHQ-8 scores and log data about the usage of the ICT4D platform in the context of blended care, we set out to unveil possible causes for these different trajectories. DISCUSSION: This work complements other studies into alternative data mining approaches to E-COMPARED trial data analysis, which are all aimed to identify clinically meaningful predictors of system use and treatment outcome. Strengths and limitations of the ILP approach given this objective will be discussed.

Predicting therapy success for treatment as usual and blended treatment in the domain of depression.

In this paper, we explore the potential of predicting therapy success for patients in mental health care. Such predictions can eventually improve the process of matching effective therapy types to individuals. In the EU project E-COMPARED, a variety of information is gathered about patients suffering from depression. We use this data, where 276 patients received treatment as usual and 227 received blended treatment, to investigate to what extent we are able to predict therapy success. We utilize different encoding strategies for preprocessing, varying feature selection techniques, and different statistical procedures for this purpose. Significant predictive power is found with average AUC values up to 0.7628 for treatment as usual and 0.7765 for blended treatment. Adding daily assessment data for blended treatment does currently not add predictive accuracy. Cost effectiveness analysis is needed to determine the added potential for real-world applications.

Do guided internet-based interventions result in clinically relevant changes for patients with depression? An individual participant data meta-analysis.

Little is known about clinically relevant changes in guided Internet-based interventions for depression. Moreover, methodological and power limitations preclude the identification of patients' groups that may benefit more from these interventions. This study aimed to investigate response rates, remission rates, and their moderators in randomized controlled trials (RCTs) comparing the effect of guided Internet-based interventions for adult depression to control groups using an individual patient data meta-analysis approach. Literature searches in PubMed, Embase, PsycINFO and Cochrane Library resulted in 13,384 abstracts from database inception to January 1, 2016. Twenty-four RCTs (4889 participants) comparing a guided Internet-based intervention with a control group contributed data to the analysis. Missing data were multiply imputed. To examine treatment outcome on response and remission, mixed-effects models with participants nested within studies were used. Response and remission rates were calculated using the Reliable Change Index. The intervention group obtained significantly higher response rates (OR = 2.49, 95% CI 2.17-2.85) and remission rates compared to controls (OR = 2.41, 95% CI 2.07-2.79). The moderator analysis indicated that older participants (OR = 1.01) and native-born participants (1.66) were more likely to respond to treatment compared to younger participants and ethnic minorities respectively. Age (OR = 1.01) and ethnicity (1.73) also moderated the effects of treatment on remission.Moreover, adults with more severe depressive symptoms at baseline were more likely to remit after receiving internet-based treatment (OR = 1.19). Guided Internet-based interventions lead to substantial positive treatment effects on treatment response and remission at post-treatment. Thus, such interventions may complement existing services for depression and potentially reduce the gap between the need and provision of evidence-based treatments.

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.

ULTEMAT: A mobile framework for smart ecological momentary assessments and interventions.

In this paper we introduce a new Android library, called ULTEMAT, for the delivery of ecological momentary assessments (EMAs) on mobile devices and we present its use in the MoodBuster app developed in the H2020 E-COMPARED project. We discuss context-aware, or event-based, triggers for the presentation of EMAs and discuss the potential they have to improve the effectiveness of mobile provision of mental health interventions as they allow for the delivery of assessments to the patients when and where these are most appropriate. Following this, we present the abilities of ULTEMAT to use such context-aware triggers to schedule EMAs and we discuss how a similar approach can be used for Ecological Momentary Interventions (EMIs).

Reactivity to smartphone-based ecological momentary assessment of depressive symptoms (MoodMonitor): protocol of a randomised controlled trial.

BACKGROUND: Ecological momentary assessment (EMA) of mental health symptoms may influence the symptoms that it measures, i.e. assessment reactivity. In the field of depression, EMA reactivity has received little attention. We aim to investigate whether EMA of depressive symptoms induces assessment reactivity. Reactivity will be operationalised as an effect of EMA on depressive symptoms measured by a retrospective questionnaire, and, secondly, as a change in response rate and variance of the EMA ratings. METHODS: This study is a 12-week randomised controlled trial comprising three groups: group 1 carries out EMA of mood and completes a retrospective questionnaire, group 2 carries out EMA of how energetic they feel and completes a retrospective questionnaire, group 3 is the control group, which completes only the retrospective questionnaire. The retrospective questionnaire (Centre for Epidemiologic Studies Depression scale; CES-D) assesses depressive symptoms and is administered at baseline, 6 weeks after baseline and 12 weeks after baseline. We aim to recruit 160 participants who experience mild to moderate depressive symptoms, defined as a Patient Health Questionnaire (PHQ-9) score of 5 to 15. This study is powered to detect a small between-groups effect, where no clinically relevant effect is defined as the effect size margin -0.25< d <0.25. DISCUSSION: To our knowledge, this is the first study to investigate whether self-rated EMA of depressive symptoms could induce assessment reactivity among mildly depressed individuals. TRIAL REGISTRATION: Netherlands Trial Register NTR5803. Registered 12 April 2016. http://www.trialregister.nl/trialreg/admin/rctview.asp?TC=5803 .