Enhancing the quality of cognitive behavioral therapy in community mental health through artificial intelligence generated fidelity feedback (Project AFFECT): a study protocol.

BACKGROUND: Each year, millions of Americans receive evidence-based psychotherapies (EBPs) like cognitive behavioral therapy (CBT) for the treatment of mental and behavioral health problems. Yet, at present, there is no scalable method for evaluating the quality of psychotherapy services, leaving EBP quality and effectiveness largely unmeasured and unknown. Project AFFECT will develop and evaluate an AI-based software system to automatically estimate CBT fidelity from a recording of a CBT session. Project AFFECT is an NIMH-funded research partnership between the Penn Collaborative for CBT and Implementation Science and Lyssn.io, Inc. ("Lyssn") a start-up developing AI-based technologies that are objective, scalable, and cost efficient, to support training, supervision, and quality assurance of EBPs. Lyssn provides HIPAA-compliant, cloud-based software for secure recording, sharing, and reviewing of therapy sessions, which includes AI-generated metrics for CBT. The proposed tool will build from and be integrated into this core platform. METHODS: Phase I will work from an existing software prototype to develop a LyssnCBT user interface geared to the needs of community mental health (CMH) agencies. Core activities include a user-centered design focus group and interviews with community mental health therapists, supervisors, and administrators to inform the design and development of LyssnCBT. LyssnCBT will be evaluated for usability and implementation readiness in a final stage of Phase I. Phase II will conduct a stepped-wedge, hybrid implementation-effectiveness randomized trial (N = 1,875 clients) to evaluate the effectiveness of LyssnCBT to improve therapist CBT skills and client outcomes and reduce client drop-out. Analyses will also examine the hypothesized mechanism of action underlying LyssnCBT. DISCUSSION: Successful execution will provide automated, scalable CBT fidelity feedback for the first time ever, supporting high-quality training, supervision, and quality assurance, and providing a core technology foundation that could support the quality delivery of a range of EBPs in the future. TRIAL REGISTRATION: ClinicalTrials.gov; NCT05340738 ; approved 4/21/2022.

Automated evaluation of psychotherapy skills using speech and language technologies.

With the growing prevalence of psychological interventions, it is vital to have measures which rate the effectiveness of psychological care to assist in training, supervision, and quality assurance of services. Traditionally, quality assessment is addressed by human raters who evaluate recorded sessions along specific dimensions, often codified through constructs relevant to the approach and domain. This is, however, a cost-prohibitive and time-consuming method that leads to poor feasibility and limited use in real-world settings. To facilitate this process, we have developed an automated competency rating tool able to process the raw recorded audio of a session, analyzing who spoke when, what they said, and how the health professional used language to provide therapy. Focusing on a use case of a specific type of psychotherapy called "motivational interviewing", our system gives comprehensive feedback to the therapist, including information about the dynamics of the session (e.g., therapist's vs. client's talking time), low-level psychological language descriptors (e.g., type of questions asked), as well as other high-level behavioral constructs (e.g., the extent to which the therapist understands the clients' perspective). We describe our platform and its performance using a dataset of more than 5000 recordings drawn from its deployment in a real-world clinical setting used to assist training of new therapists. Widespread use of automated psychotherapy rating tools may augment experts' capabilities by providing an avenue for more effective training and skill improvement, eventually leading to more positive clinical outcomes.

Knowledge and Attitudes Toward an Artificial Intelligence-Based Fidelity Measurement in Community Cognitive Behavioral Therapy Supervision.

To capitalize on investments in evidence-based practices, technology is needed to scale up fidelity assessment and supervision. Stakeholder feedback may facilitate adoption of such tools. This evaluation gathered stakeholder feedback and preferences to explore whether it would be fundamentally feasible or possible to implement an automated fidelity-scoring supervision tool in community mental health settings. A partially mixed, sequential research method design was used including focus group discussions with community mental health therapists (n = 18) and clinical leadership (n = 12) to explore typical supervision practices, followed by discussion of an automated fidelity feedback tool embedded in a cloud-based supervision platform. Interpretation of qualitative findings was enhanced through quantitative measures of participants' use of technology and perceptions of acceptability, appropriateness, and feasibility of the tool. Initial perceptions of acceptability, appropriateness, and feasibility of automated fidelity tools were positive and increased after introduction of an automated tool. Standard supervision was described as collaboratively guided and focused on clinical content, self-care, and documentation. Participants highlighted the tool's utility for supervision, training, and professional growth, but questioned its ability to evaluate rapport, cultural responsiveness, and non-verbal communication. Concerns were raised about privacy and the impact of low scores on therapist confidence. Desired features included intervention labeling and transparency about how scores related to session content. Opportunities for asynchronous, remote, and targeted supervision were particularly valued. Stakeholder feedback suggests that automated fidelity measurement could augment supervision practices. Future research should examine the relations among use of such supervision tools, clinician skill, and client outcomes.

How do you feel? Using natural language processing to automatically rate emotion in psychotherapy.

Emotional distress is a common reason for seeking psychotherapy, and sharing emotional material is central to the process of psychotherapy. However, systematic research examining patterns of emotional exchange that occur during psychotherapy sessions is often limited in scale. Traditional methods for identifying emotion in psychotherapy rely on labor-intensive observer ratings, client or therapist ratings obtained before or after sessions, or involve manually extracting ratings of emotion from session transcripts using dictionaries of positive and negative words that do not take the context of a sentence into account. However, recent advances in technology in the area of machine learning algorithms, in particular natural language processing, have made it possible for mental health researchers to identify sentiment, or emotion, in therapist-client interactions on a large scale that would be unattainable with more traditional methods. As an attempt to extend prior findings from Tanana et al. (2016), we compared their previous sentiment model with a common dictionary-based psychotherapy model, LIWC, and a new NLP model, BERT. We used the human ratings from a database of 97,497 utterances from psychotherapy to train the BERT model. Our findings revealed that the unigram sentiment model (kappa = 0.31) outperformed LIWC (kappa = 0.25), and ultimately BERT outperformed both models (kappa = 0.48).

Can a computer detect interpersonal skills? Using machine learning to scale up the Facilitative Interpersonal Skills task.

Objective: Therapist interpersonal skills are foundational to psychotherapy. However, assessment is labor intensive and infrequent. This study evaluated if machine learning (ML) tools can automatically assess therapist interpersonal skills. Method: Data were drawn from a previous study in which 164 undergraduate students (i.e., not clinical trainees) completed the Facilitative Interpersonal Skills (FIS) task. This task involves responding to video vignettes depicting interpersonally challenging moments in psychotherapy. Trained raters scored the responses. We used an elastic net model on top of a term frequency-inverse document frequency representation to predict FIS scores. Results: Models predicted FIS total and item-level scores above chance (rhos = .27-.53, ps < .001), achieving 31-60% of human reliability. Models explained 13-24% of the variance in FIS total and item-level scores on a held out set of data (R2), with the exception of the two items most reliant on vocal cues (verbal fluency, emotional expression), for which models explained ≤1% of variance. Conclusion: ML may be a promising approach for automating assessment of constructs like interpersonal skill previously coded by humans. ML may perform best when the standardized stimuli limit the "space" of potential responses (vs. naturalistic psychotherapy) and when models have access to the same data available to raters (i.e., transcripts).

Investigating voice as a biomarker: Deep phenotyping methods for early detection of Parkinson's disease.

Voice technology has grown tremendously in recent years and using voice as a biomarker has also been gaining evidence. We demonstrate the potential of voice in serving as a deep phenotype for Parkinson's Disease (PD), the second most common neurodegenerative disorder worldwide, by presenting methodology for voice signal processing for clinical analysis. Detection of PD symptoms typically requires an exam by a movement disorder specialist and can be hard to access and inconsistent in findings. A vocal digital biomarker could supplement the cumbersome existing manual exam by detecting and quantifying symptoms to guide treatment. Specifically, vocal biomarkers of PD are a potentially effective method of assessing symptoms and severity in daily life, which is the focus of the current research. We analyzed a database of PD patient and non-PD subjects containing voice recordings that were used to extract paralinguistic features, which served as inputs to machine learning models to predict PD severity. The results are presented here and the limitations are discussed given the nature of the recordings. We note that our methodology only advances biomarker research and is not cleared for clinical use. Specifically, we demonstrate that conventional machine learning models applied to voice signals can be used to differentiate participants with PD who exhibit little to no symptoms from healthy controls. This work highlights the potential of voice to be used for early detection of PD and indicates that voice may serve as a deep phenotype for PD, enabling precision medicine by improving the speed, accuracy, accessibility, and cost of PD management.

Machine learning and natural language processing in psychotherapy research: Alliance as example use case.

Artificial intelligence generally and machine learning specifically have become deeply woven into the lives and technologies of modern life. Machine learning is dramatically changing scientific research and industry and may also hold promise for addressing limitations encountered in mental health care and psychotherapy. The current paper introduces machine learning and natural language processing as related methodologies that may prove valuable for automating the assessment of meaningful aspects of treatment. Prediction of therapeutic alliance from session recordings is used as a case in point. Recordings from 1,235 sessions of 386 clients seen by 40 therapists at a university counseling center were processed using automatic speech recognition software. Machine learning algorithms learned associations between client ratings of therapeutic alliance exclusively from session linguistic content. Using a portion of the data to train the model, machine learning algorithms modestly predicted alliance ratings from session content in an independent test set (Spearman's ρ = .15, p < .001). These results highlight the potential to harness natural language processing and machine learning to predict a key psychotherapy process variable that is relatively distal from linguistic content. Six practical suggestions for conducting psychotherapy research using machine learning are presented along with several directions for future research. Questions of dissemination and implementation may be particularly important to explore as machine learning improves in its ability to automate assessment of psychotherapy process and outcome. (PsycInfo Database Record (c) 2020 APA, all rights reserved).

Coregulation of therapist and client emotion during psychotherapy.

OBJECTIVE: Close interpersonal relationships are fundamental to emotion regulation. Clinical theory suggests that one role of therapists in psychotherapy is to help clients regulate emotions, however, if and how clients and therapists serve to regulate each other's emotions has not been empirically tested. Emotion coregulation - the bidirectional emotional linkage of two people that promotes emotional stability - is a specific, temporal process that provides a framework for testing the way in which therapists' and clients' emotions may be related on a moment to moment basis in clinically relevant ways. METHOD: Utilizing 227 audio recordings from a relationally oriented treatment (Motivational Interviewing), we estimated continuous values of vocally encoded emotional arousal via mean fundamental frequency. We used dynamic systems models to examine emotional coregulation, and tested the hypothesis that each individual's emotional arousal would be significantly associated with fluctuations in the other's emotional state over the course of a psychotherapy session. RESULTS: Results indicated that when clients became more emotionally labile over the course of the session, therapists became less so. When changes in therapist arousal increased, the client's tendency to become more aroused during session slowed. Alternatively, when changes in client arousal increased, the therapist's tendency to become less aroused slowed.

The accuracy of passive phone sensors in predicting daily mood.

BACKGROUND: Smartphones provide a low-cost and efficient means to collect population level data. Several small studies have shown promise in predicting mood variability from smartphone-based sensor and usage data, but have not been generalized to nationally recruited samples. This study used passive smartphone data, demographic characteristics, and baseline depressive symptoms to predict prospective daily mood. METHOD: Daily phone usage data were collected passively from 271 Android phone users participating in a fully remote randomized controlled trial of depression treatment (BRIGHTEN). Participants completed daily Patient Health Questionnaire-2. A machine learning approach was used to predict daily mood for the entire sample and individual participants. RESULTS: Sample-wide estimates showed a marginally significant association between physical mobility and self-reported daily mood (B = -0.04, P < 0.05), but the predictive models performed poorly for the sample as a whole (median R2 ∼ 0). Focusing on individuals, 13.9% of participants showed significant association (FDR < 0.10) between a passive feature and daily mood. Personalized models combining features provided better prediction performance (median area under the curve [AUC] > 0.50) for 80.6% of participants and very strong prediction in a subset (median AUC > 0.80) for 11.8% of participants. CONCLUSIONS: Passive smartphone data with current features may not be suited for predicting daily mood at a population level because of the high degree of intra- and interindividual variation in phone usage patterns and daily mood ratings. Personalized models show encouraging early signs for predicting an individual's mood state changes, with GPS-derived mobility being the top most important feature in the present sample.

Development and Evaluation of ClientBot: Patient-Like Conversational Agent to Train Basic Counseling Skills.

BACKGROUND: Training therapists is both expensive and time-consuming. Degree-based training can require tens of thousands of dollars and hundreds of hours of expert instruction. Counseling skills practice often involves role-plays, standardized patients, or practice with real clients. Performance-based feedback is critical for skill development and expertise, but trainee therapists often receive minimal and subjective feedback, which is distal to their skill practice. OBJECTIVE: In this study, we developed and evaluated a patient-like neural conversational agent, which provides real-time feedback to trainees via chat-based interaction. METHODS: The text-based conversational agent was trained on an archive of 2354 psychotherapy transcripts and provided specific feedback on the use of basic interviewing and counseling skills (ie, open questions and reflections-summary statements of what a client has said). A total of 151 nontherapists were randomized to either (1) immediate feedback on their use of open questions and reflections during practice session with ClientBot or (2) initial education and encouragement on the skills. RESULTS: Participants in the ClientBot condition used 91% (21.4/11.2) more reflections during practice with feedback (P<.001) and 76% (14.1/8) more reflections after feedback was removed (P<.001) relative to the control group. The treatment group used more open questions during training but not after feedback was removed, suggesting that certain skills may not improve with performance-based feedback. Finally, after feedback was removed, the ClientBot group used 31% (32.5/24.7) more listening skills overall (P<.001). CONCLUSIONS: This proof-of-concept study demonstrates that practice and feedback can improve trainee use of basic counseling skills.

Modeling empathy as synchrony in clinician and patient vocally encoded emotional arousal: A failure to replicate.

Empathy is a well-defined active ingredient in clinical encounters. To measure empathy, the current gold standard is behavioral coding (i.e., trained coders attribute overall ratings of empathy to clinician behaviors within an encounter), which is labor intensive and subject to important reliability challenges. Recently, an alternative measurement has been proposed: capturing empathy as synchrony in vocally encoded arousal, which can be measured as the mean fundamental frequency of the voice (mean F0). This method has received preliminary support by one study (Imel, Barco, et al., 2014). We aimed to replicate this study by using 2 large samples of clinical interactions (alcohol brief motivational interventions with young adults, N = 208; general practice consultations, N = 204). Audio files were segmented to identify respective speakers and mean F0 was measured using speech signal processing software. All sessions were independently rated by behavioral coders using 2 validated empathy scales. Synchrony between clinician and patient F0 was analyzed using multivariate multilevel models and compared with high and low levels of empathy derived from behavioral coding. Findings showed no support for our hypothesis that mean F0 synchrony between clinicians and patients would be higher in high-empathy sessions. This lack of replication was consistent for both clinical samples, both behavioral coding instruments, and using measures of F0 synchrony occurring at both the session-level and minute-level. We considered differences in culture and language, patients' characteristics, and setting as explanations for this failure to replicate. Further replication testing and new developments regarding measurement methods and modeling are needed. (PsycINFO Database Record (c) 2019 APA, all rights reserved).

Task-shifting to improve the reach of mental health interventions for trauma patients: findings from a pilot study of trauma nurse training in patient-centered activity scheduling for PTSD and depression.

Despite high rates of posttraumatic stress disorder (PTSD) and depression among traumatically injured patients, engagement in session-based psychotherapy early after trauma is limited due to various service utilization and readiness barriers. Task-shifting brief mental health interventions to routine trauma center providers is an understudied but potentially critical part of the continuum of care. This pilot study assessed the feasibility of training trauma nurses to engage patients in patient-centered activity scheduling based on a Behavioral Activation paradigm, which is designed to counteract dysfunctional avoidance/withdrawal behavior common among patients after injury. Nurses (N = 4) and patients (N = 40) were recruited from two level II trauma centers. A portion of a one day in-person workshop included didactics, demonstrations, and experiential activities to teach brief intervention delivery. Nurses completed pre- and posttraining standardized patient role-plays prior to and two months after training, which were coded for adherence to the intervention. Nurses also completed exit interviews to assess their perspectives on the training and addressing patient mental health concerns. Findings support the feasibility of training trauma nurses in a brief mental health intervention. Task-shifting brief interventions holds promise for reaching more of the population in need of posttrauma mental health care.

When the "U" is not Inverted: Trajectories of Expressed Emotional Arousal Predict Relationship Satisfaction.

Maladaptive emotional reactivity and dysfunctional communication during couple conflict are both destructive to couple functioning, and observational research has elucidated how conflict escalates. However, much of the evidence is based on measures that combine content (i.e., what was said) and the emotion with which it was said, which are then examined using sequential analyses. Despite the general presumptions about underlying emotional reactivity and escalation in negative emotions as part of relationship distress and deterioration, little empirical data are available that directly examine these continuous shifts in emotions. The current study examined concurrent and longitudinal associations between relationship satisfaction and trajectories of change in vocally expressed emotional arousal during couple conflict in 62 couples who participated in a relationship education program. Contrary to expectations and patterns found in distressed couples, trajectories followed a U-shape rather than an inverted U-shape curve, with steeper and more persistent decreases in emotional arousal predicting more stable relationship satisfaction over time. In addition, there were within-couple effects. These results suggest that early signs for relationship deterioration may be less in the form of overt escalation as would be seen in distressed couples. Instead, couples who subsequently deteriorate more are less effective in calming emotional arousal. They also are less able to remain at lower emotional arousal. It is possible that the more pronounced escalation toward the end of the conversation in more at-risk couples is a precursor of the greater escalation patterns seen in distressed couples; this should be examined empirically. Limitations and implications are discussed.

La reactividad emocional desadaptativa y la comunicación disfuncional durante el conflicto de pareja son destructivas para el funcionamiento de la pareja, y la investigación observacional ha dilucidado cómo escala el conflicto. Sin embargo, gran parte de la evidencia está basada en mediciones que combinan el contenido (p. ej.: lo que se dijo) y la emoción con la que se dijo, que luego se analizan usando análisis secuenciales. A pesar de las presunciones generales acerca de la reactividad emocional subyacente y la escalada de las emociones negativas como parte del distrés y el deterioro de la relación, existen pocos datos empíricos que analicen directamente estos cambios continuos en las emociones. El presente estudio analizó las asociaciones simultáneas y longitudinales entre la satisfacción con la relación y las trayectorias de cambio en la agitación emocional expresada vocalmente durante el conflicto de pareja en 62 parejas que participaron en un programa de capacitación en relaciones. Contrariamente a las expectativas y los patrones hallados en las parejas problemáticas, las trayectorias siguieron una forma de U en lugar de una curva con forma de U invertida, con disminuciones más pronunciadas y más constantes de la agitación emocional que predicen una satisfacción más estable con la relación en el transcurso del tiempo. Además, hubo efectos dentro de la pareja. Estos resultados sugieren que las primeras señales de deterioro de la relación pueden ser menores en forma de escalada abierta de lo que se vería en las parejas problemáticas. En cambio, las parejas que posteriormente se deterioran más son menos eficaces a la hora de calmar la agitación emocional. También son menos capaces de permanecer en una agitación emocional más baja. Es posible que la escalada más pronunciada hacia el final de la conversación en las parejas con mayor riesgo sea una precursora de los patrones de mayor escalada observados en las parejas problemáticas; esto debería analizarse empíricamente. Se debaten las limitaciones y las consecuencias.

Association Between Sleep Problems and Perceived Cognitive Dysfunction Over 12 Months in Individuals with Multiple Sclerosis.

Sleep problems are highly prevalent among individuals with multiple sclerosis (MS); however, the relationship between sleep problems and cognitive dysfunction is poorly understood in this population. In the present study, 163 individuals with MS and depression, fatigue, or pain completed self-report measures of sleep, cognitive dysfunction, and relevant demographic and clinical characteristics (e.g., disability severity, depressive symptomatology, pain intensity, fatigue impact) at four time points over 12 months. Mixed-effects regression demonstrated that poorer sleep was independently associated with worse perceived cognitive dysfunction (ß = -0.05, p = .001), beyond the influence of depressive symptomatology. Fatigue impact was found to partially mediate this relationship. Results suggest that for individuals with MS and depression, fatigue, or pain, self-reported sleep problems are related to perceived cognitive dysfunction, and that fatigue impact accounts for part of this relationship.

Comparing Approaches to Mobile Depression Assessment for Measurement-Based Care: Prospective Study.

BACKGROUND: To inform measurement-based care, practice guidelines suggest routine symptom monitoring, often on a weekly or monthly basis. Increasingly, patient-provider contacts occur remotely (eg, by telephone and Web-based portals), and mobile health tools can now monitor depressed mood daily or more frequently. However, the reliability and utility of daily ratings are unclear. OBJECTIVE: This study aimed to examine the association between a daily depressive symptom measure and the Patient Health Questionnaire-9 (PHQ-9), the most widely adopted depression self-report measure, and compare how well these 2 assessment methods predict patient outcomes. METHODS: A total of 547 individuals completed smartphone-based measures, including the Patient Health Questionnaire-2 (PHQ-2) modified for daily administration, the PHQ-9, and the Sheehan Disability Scale. Multilevel factor analyses evaluated the reliability of latent depression based on the PHQ-2 (for repeated measures) between weeks 2 and 4 and its correlation with the PHQ-9 at week 4. Regression models predicted week 8 depressive symptoms and disability ratings with daily PHQ-2 and PHQ-9. RESULTS: The daily PHQ-2 and PHQ-9 are highly reliable (range: 0.80-0.88) and highly correlated (r=.80). Findings were robust across demographic groups (age, gender, and ethnic minority status). Daily PHQ-2 and PHQ-9 were comparable in predicting week 8 disability and were independent predictors of week 8 depressive symptoms and disability, though the unique contribution of the PHQ-2 was small in magnitude. CONCLUSIONS: Daily completion of the PHQ-2 is a reasonable proxy for the PHQ-9 and is comparable to the PHQ-9 in predicting future outcomes. Mobile assessment methods offer researchers and clinicians reliable and valid new methods for depression assessment that may be leveraged for measurement-based depression care.

Digital technology and clinical decision making in depression treatment: Current findings and future opportunities.

Clinical decision making encompasses a broad set of processes that contribute to the effectiveness of depression treatments. There is emerging interest in using digital technologies to support effective and efficient clinical decision making. In this paper, we provide "snapshots" of research and current directions on ways that digital technologies can support clinical decision making in depression treatment. Practical facets of clinical decision making are reviewed, then research, design, and implementation opportunities where technology can potentially enhance clinical decision making are outlined. Discussions of these opportunities are organized around three established movements designed to enhance clinical decision making for depression treatment, including measurement-based care, integrated care, and personalized medicine. Research, design, and implementation efforts may support clinical decision making for depression by (1) improving tools to incorporate depression symptom data into existing electronic health record systems, (2) enhancing measurement of treatment fidelity and treatment processes, (3) harnessing smartphone and biosensor data to inform clinical decision making, (4) enhancing tools that support communication and care coordination between patients and providers and within provider teams, and (5) leveraging treatment and outcome data from electronic health record systems to support personalized depression treatment. The current climate of rapid changes in both healthcare and digital technologies facilitates an urgent need for research, design, and implementation of digital technologies that explicitly support clinical decision making. Ensuring that such tools are efficient, effective, and usable in frontline treatment settings will be essential for their success and will require engagement of stakeholders from multiple domains.

Dementia and co-occurring chronic conditions: a systematic literature review to identify what is known and where are the gaps in the evidence?

OBJECTIVE: The challenges posed by people living with multiple chronic conditions are unique for people with dementia and other significant cognitive impairment. There have been recent calls to action to review the existing literature on co-occurring chronic conditions and dementia in order to better understand the effect of cognitive impairment on disease management, mobility, and mortality. METHODS: This systematic literature review searched PubMed databases through 2011 (updated in 2016) using key constructs of older adults, moderate-to-severe cognitive impairment (both diagnosed and undiagnosed dementia), and chronic conditions. Reviewers assessed papers for eligibility and extracted key data from each included manuscript. An independent expert panel rated the strength and quality of evidence and prioritized gaps for future study. RESULTS: Four thousand thirty-three articles were identified, of which 147 met criteria for review. We found that moderate-to-severe cognitive impairment increased risks of mortality, was associated with prolonged institutional stays, and decreased function in persons with multiple chronic conditions. There was no relationship between significant cognitive impairment and use of cardiovascular or hypertensive medications for persons with these comorbidities. Prioritized areas for future research include hospitalizations, disease-specific outcomes, diabetes, chronic pain, cardiovascular disease, depression, falls, stroke, and multiple chronic conditions. CONCLUSIONS: This review summarizes that living with significant cognitive impairment or dementia negatively impacts mortality, institutionalization, and functional outcomes for people living with multiple chronic conditions. Our findings suggest that chronic-disease management interventions will need to address co-occurring cognitive impairment. Copyright © 2017 John Wiley & Sons, Ltd.

Technology-enhanced human interaction in psychotherapy.

Psychotherapy is on the verge of a technology-inspired revolution. The concurrent maturation of communication, signal processing, and machine learning technologies begs an earnest look at how these technologies may be used to improve the quality of psychotherapy. Here, we discuss 3 research domains where technology is likely to have a significant impact: (1) mechanism and process, (2) training and feedback, and (3) technology-mediated treatment modalities. For each domain, we describe current and forthcoming examples of how new technologies may change established applications. Moreover, for each domain we present research questions that touch on theoretical, systemic, and implementation issues. Ultimately, psychotherapy is a decidedly human endeavor, and thus the application of modern technology to therapy must capitalize on-and enhance-our human capacities as counselors, students, and supervisors. (PsycINFO Database Record

Computational Analysis and Simulation of Empathic Behaviors: a Survey of Empathy Modeling with Behavioral Signal Processing Framework.

Empathy is an important psychological process that facilitates human communication and interaction. Enhancement of empathy has profound significance in a range of applications. In this paper, we review emerging directions of research on computational analysis of empathy expression and perception as well as empathic interactions, including their simulation. We summarize the work on empathic expression analysis by the targeted signal modalities (e.g., text, audio, and facial expressions). We categorize empathy simulation studies into theory-based emotion space modeling or application-driven user and context modeling. We summarize challenges in computational study of empathy including conceptual framing and understanding of empathy, data availability, appropriate use and validation of machine learning techniques, and behavior signal processing. Finally, we propose a unified view of empathy computation and offer a series of open problems for future research.

The Use and Effectiveness of Mobile Apps for Depression: Results From a Fully Remote Clinical Trial.

BACKGROUND: Mobile apps for mental health have the potential to overcome access barriers to mental health care, but there is little information on whether patients use the interventions as intended and the impact they have on mental health outcomes. OBJECTIVE: The objective of our study was to document and compare use patterns and clinical outcomes across the United States between 3 different self-guided mobile apps for depression. METHODS: Participants were recruited through Web-based advertisements and social media and were randomly assigned to 1 of 3 mood apps. Treatment and assessment were conducted remotely on each participant's smartphone or tablet with minimal contact with study staff. We enrolled 626 English-speaking adults (≥18 years old) with mild to moderate depression as determined by a 9-item Patient Health Questionnaire (PHQ-9) score ≥5, or if their score on item 10 was ≥2. The apps were (1) Project: EVO, a cognitive training app theorized to mitigate depressive symptoms by improving cognitive control, (2) iPST, an app based on an evidence-based psychotherapy for depression, and (3) Health Tips, a treatment control. Outcomes were scores on the PHQ-9 and the Sheehan Disability Scale. Adherence to treatment was measured as number of times participants opened and used the apps as instructed. RESULTS: We randomly assigned 211 participants to iPST, 209 to Project: EVO, and 206 to Health Tips. Among the participants, 77.0% (482/626) had a PHQ-9 score >10 (moderately depressed). Among the participants using the 2 active apps, 57.9% (243/420) did not download their assigned intervention app but did not differ demographically from those who did. Differential treatment effects were present in participants with baseline PHQ-9 score >10, with the cognitive training and problem-solving apps resulting in greater effects on mood than the information control app (χ22=6.46, P=.04). CONCLUSIONS: Mobile apps for depression appear to have their greatest impact on people with more moderate levels of depression. In particular, an app that is designed to engage cognitive correlates of depression had the strongest effect on depressed mood in this sample. This study suggests that mobile apps reach many people and are useful for more moderate levels of depression. CLINICALTRIAL: Clinicaltrials.gov NCT00540865; https://www.clinicaltrials.gov/ct2/show/NCT00540865 (Archived by WebCite at http://www.webcitation.org/6mj8IPqQr).