A new era in Internet interventions: The advent of Chat-GPT and AI-assisted therapist guidance

How Digital Solutions Might Provide a World of New Opportunities for Holistic and Empathic Support of Patients with Hidradenitis Suppurativa

Hidradenitis suppurativa (HS) is a complex chronic relapsing inflammatory condition anchored in the hair follicle wherein painful abscesses, nodules, and tunnels form under the skin with the potential for intermittent pus drainage and tissue scarring. Current estimates of incidence are 1-4% globally with the disease three times more prevalent in women and higher rates among Black populations. Patients with HS are also more likely to suffer from depression, anxiety, and loneliness underscoring the need for carefully approached strategies on disease awareness and interventions. Delays in formal diagnosis, which have been estimated at 7-10 years on average, impede timely provision of optimal care. Despite best intent, when patients present at a physician's office, stigmas relating to physical appearance can be exacerbated by negative interactions experienced by patients. In addition to long wait times and the dearth of available HS expert dermatology professionals, patients perceive heightened physician focus on two of the HS flare risk factors (smoking and body mass index [BMI]) as negatively impacting their care. Given the need for continual, personal, and sensitive patient support, herein we advocate for re-examination of approach to care and the leveraging of highly personalized digital support solutions. New medications which can directly or indirectly control elements of the disease and its comorbidities are also entering the marketplace. Collectively, we posit that these new developments provide opportunity for a holistic approach for patients with HS, leading to long-term engagement and improved outcomes.

The efficacy of automated feedback after internet-based depression screening (DISCOVER): an observer-masked, three-armed, randomised controlled trial in Germany

BACKGROUND

Despite the availability of effective treatments, most depressive disorders remain undetected and untreated. Internet-based depression screening combined with automated feedback of screening results could reach people with depression and lead to evidence-based care. We aimed to test the efficacy of two versions of automated feedback after internet-based screening on depression severity compared with no feedback.

METHODS

DISCOVER was an observer-masked, three-armed, randomised controlled trial in Germany. We recruited individuals (aged ≥18 years) who were undiagnosed with depression and screened positive for depression on an internet-based self-report depression rating scale (Patient Health Questionnaire-9 [PHQ-9] ≥10 points). Participants were randomly assigned 1:1:1 to automatically receive no feedback, non-tailored feedback, or tailored feedback on the depression screening result. Randomisation was stratified by depression severity (moderate: PHQ-9 score 10-14 points; severe: PHQ-9 score ≥15 points). Participants could not be masked but were kept unaware of trial hypotheses to minimise expectancy bias. The non-tailored feedback included the depression screening result, a recommendation to seek professional diagnostic advice, and brief general information about depression and its treatment. The tailored feedback included the same basic information but individually framed according to the participants' symptom profiles, treatment preferences, causal symptom attributions, health insurance, and local residence. Research staff were masked to group allocation and outcome assessment as these were done using online questionnaires. The primary outcome was change in depression severity, defined as change in PHQ-9 score 6 months after random assignment. Analyses were conducted following the intention-to-treat principle for participants with at least one follow-up visit. This trial was registered at ClinicalTrials.gov, NCT04633096.

FINDINGS

Between Jan 12, 2021, and Jan 31, 2022, 4878 individuals completed the internet-based screening. Of these, 1178 (24%) screened positive for depression (mean age 37·1 [SD 14·2] years; 824 [70%] woman, 344 [29%] men, and 10 [1%] other gender identity). 6 months after random assignment, depression severity decreased by 3·4 PHQ-9 points in the no feedback group (95% CI 2·9-4·0; within-group d 0·67; 325 participants), by 3·5 points in the non-tailored feedback group (3·0-4·0; within-group d 0·74; 319 participants), and by 3·7 points in the tailored feedback group (3·2-4·3; within-group d 0·71; 321 participants), with no significant differences among the three groups (p=0·72). The number of participants seeking help for depression or initiating psychotherapy or antidepressant treatment did not differ among study groups. The results remained consistent when adjusted for fulfilling the DSM-5-based criteria for major depressive disorder or subjective belief of having a depressive disorder. Negative effects were reported by less than 1% of the total sample 6 months after random assignment.

INTERPRETATION

Automated feedback following internet-based depression screening did not reduce depression severity or prompt sufficient depression care in individuals previously undiagnosed with but affected by depression.

FUNDING

German Research Foundation.

A Chatbot-Delivered Stress Management Coaching for Students (MISHA App): Pilot Randomized Controlled Trial

BACKGROUND

Globally, students face increasing mental health challenges, including elevated stress levels and declining well-being, leading to academic performance issues and mental health disorders. However, due to stigma and symptom underestimation, students rarely seek effective stress management solutions. Conversational agents in the health sector have shown promise in reducing stress, depression, and anxiety. Nevertheless, research on their effectiveness for students with stress remains limited.

OBJECTIVE

This study aims to develop a conversational agent-delivered stress management coaching intervention for students called MISHA and to evaluate its effectiveness, engagement, and acceptance.

METHODS

In an unblinded randomized controlled trial, Swiss students experiencing stress were recruited on the web. Using a 1:1 randomization ratio, participants (N=140) were allocated to either the intervention or waitlist control group. Treatment effectiveness on changes in the primary outcome, that is, perceived stress, and secondary outcomes, including depression, anxiety, psychosomatic symptoms, and active coping, were self-assessed and evaluated using ANOVA for repeated measure and general estimating equations.

RESULTS

The per-protocol analysis revealed evidence for improvement of stress, depression, and somatic symptoms with medium effect sizes (Cohen d=-0.36 to Cohen d=-0.60), while anxiety and active coping did not change (Cohen d=-0.29 and Cohen d=0.13). In the intention-to-treat analysis, similar results were found, indicating reduced stress (β estimate=-0.13, 95% CI -0.20 to -0.05; P<.001), depressive symptoms (β estimate=-0.23, 95% CI -0.38 to -0.08; P=.003), and psychosomatic symptoms (β estimate=-0.16, 95% CI -0.27 to -0.06; P=.003), while anxiety and active coping did not change. Overall, 60% (42/70) of the participants in the intervention group completed the coaching by completing the postintervention survey. They particularly appreciated the quality, quantity, credibility, and visual representation of information. While individual customization was rated the lowest, the target group fitting was perceived as high.

CONCLUSIONS

Findings indicate that MISHA is feasible, acceptable, and effective in reducing perceived stress among students in Switzerland. Future research is needed with different populations, for example, in students with high stress levels or compared to active controls.

TRIAL REGISTRATION

German Clinical Trials Register DRKS 00030004; https://drks.de/search/en/trial/DRKS00030004.

Effects of a single session low-threshold digital intervention for procrastination behaviors among university students (Focus): Findings from a randomized controlled trial

Introduction

Procrastination behaviors are common among university students, and have been found to be associated with stress, symptoms of depression, anxiety, and poorer academic performance. There is a need for interventions that can reach students at scale, and therefore this study aimed to estimate the effects of a single session low-threshold digital intervention (Focus) for procrastination behaviors among university students in Sweden.

Methods and analysis

A two-arm, parallel groups (1:1), single blind randomized controlled trial was conducted between February 8 to April 26, 2023. The study used email to invite university students across Sweden to participate in the trial. Both the intervention and the control group were invited to assess their current procrastination behaviors using the Pure Procrastination Scale (PPS). The intervention group immediately received feedback and behavior change advice by means of an interactive website, while the control group was shown their total PPS score without any further feedback. Students were included in the study if they scored 20 points or more on the PPS. Our primary outcome was procrastination behavior measured at 2 months post-randomization. Analyses were conducted using multilevel regression models estimated with Bayesian inference.

Results

A total of 2209 participants (intervention: 1109, control: 1100) were randomized. The average age of participants was 26.4 years (SD = 7.8) and 65 % were women (n = 1442). The mean PPS score at baseline was 35.6 points (of a maximum of 60). Primary outcome data were available for 45 % (n = 498) of the intervention group and 55 % (n = 601) of the control group. The evidence suggested no marked difference between groups regarding any of the outcomes, although there was weak evidence of lower physical activity in the intervention group. Qualitative findings from open-ended responses uncovered a variety of views on procrastination and perceived problems that may follow. Those not feeling supported by Focus explained having troubles adopting the advice given and converting their intentions into action without more continuous support.

Conclusions

Access to a single session of feedback and behavior change advice by means of an interactive website did not produce differential self-reported procrastination among university students who took the opportunity to self-assess their behaviors. The findings are limited by assessment reactivity due to screening at baseline and attrition to follow-up.

The Artificial Third: A Broad View of the Effects of Introducing Generative Artificial Intelligence on Psychotherapy

Unlabelled

This paper explores a significant shift in the field of mental health in general and psychotherapy in particular following generative artificial intelligence's new capabilities in processing and generating humanlike language. Following Freud, this lingo-technological development is conceptualized as the "fourth narcissistic blow" that science inflicts on humanity. We argue that this narcissistic blow has a potentially dramatic influence on perceptions of human society, interrelationships, and the self. We should, accordingly, expect dramatic changes in perceptions of the therapeutic act following the emergence of what we term the artificial third in the field of psychotherapy. The introduction of an artificial third marks a critical juncture, prompting us to ask the following important core questions that address two basic elements of critical thinking, namely, transparency and autonomy: (1) What is this new artificial presence in therapy relationships? (2) How does it reshape our perception of ourselves and our interpersonal dynamics? and (3) What remains of the irreplaceable human elements at the core of therapy? Given the ethical implications that arise from these questions, this paper proposes that the artificial third can be a valuable asset when applied with insight and ethical consideration, enhancing but not replacing the human touch in therapy.

A pilot feasibility and acceptability trial of an internet indicated prevention program for perfectionism to reduce eating disorder symptoms in adolescents

PURPOSE

Perfectionism is a transdiagnostic risk factor for eating disorders. Treating perfectionism can reduce symptoms of eating disorders. No research has examined an indicated prevention trial using internet-based Cognitive-Behavioural Therapy for Perfectionism (ICBT-P) in adolescent girls at elevated risk for eating disorders. Our aim was to conduct a preliminary feasibility trial using a co-designed ICBT-P intervention. It was hypothesised that a higher proportion of participants in the ICBT-P condition would achieve reliable and clinically significant change on perfectionism, eating disorders, anxiety and depression, compared to waitlist control.

METHODS

Twenty-one adolescent girls with elevated symptoms of eating disorders (M age = 16.14 years) were randomised to a 4-week online feasibility trial of a co-designed ICBT-P prevention program or waitlist control. Qualitative surveys were used to gain participant perspectives.

RESULTS

The ICBT-P condition had a higher proportion of participants achieve reliable change and classified as recovered on perfectionism and symptoms of eating disorders and anxiety, compared to waitlist control. Qualitative findings indicated that 100% of participants found the program helpful.

CONCLUSION

The results indicate ICBT-P is a feasible and acceptable program for adolescent girls with elevated eating disorder symptoms. Future research is required to examine outcomes in a randomised controlled trial.

LEVEL OF EVIDENCE

Level III: Evidence obtained from well-designed cohort or case-control analytic studies.

TRIAL REGISTRATION NUMBER

This trial was prospectively registered with Australian and New Zealand Clinical Trials Registry (ACTRN12620000951954P) on 23/09/2020.

Can ChatGPT Replace an Otolaryngologist in Guiding Parents on Tonsillectomy?

Background: ChatGPT is an artificial intelligence tool, which utilizes machine learning to analyze and generate human-like text. The user-friendly accessibility of this tool enables patients conveniently access medical information without intricate terminology challenges. The objective of this study was to assess the accuracy of ChatGPT in providing insights into indications and management of complications after tonsillectomy, a common pediatric otolaryngology procedure. Methods: The responses generated by ChatGPT were compared to the "Clinical practice guidelines: tonsillectomy in children-executive summary" developed by the American Academy of Otolaryngology-Head and Neck Surgery Foundation (AAO-HNSF). An assessment was carried out by presenting predetermined questions regarding indications and complications post tonsillectomy to ChatGPT, followed by a comparison of its responses with the established guideline by 2 otolaryngology experts. The responses of both parties were reviewed by the senior author. Results: A total of 16 responses generated by ChatGPT were assessed. After a comprehensive review, it was concluded that 15 out of 16 (93.8%) responses demonstrated a high degree of reliability and accuracy, closely adhering to the standard established by the AAO-HNSF guideline. Conclusion: The results validate the potential of using ChatGPT to enhance healthcare delivery making guidelines more accessible to patients while also emphasizing the importance of ensuring the provision of accurate and reliable medical advice to patients.

Bridging the adherence gap in internet interventions: A randomized controlled trial study protocol investigating context-specific self-efficacy

Low adherence in self-guided internet interventions is linked to poorer outcomes. Although some predictors of adherence have been identified, few are modifiable for widespread application. One personal variable with the potential to increase adherence in internet interventions is context-specific self-efficacy. This protocol outlines a randomized controlled trial design, divided into two phases. In Phase 1 (students, N = 216), participants will complete a self-efficacy-enhancing exercise, which will be compared to a waitlist control group to test its effectiveness in increasing internet intervention adherence self-efficacy. Phase 2 will be the main two-arm trial, where all participants (medical students, N = 952) will undergo an internet intervention called Med-Stress Student. In the experimental group, the program will be preceded by the self-efficacy-enhancing exercise developed in Phase 1. We anticipate that participants in the experimental group will show higher adherence (primary outcome) to the intervention and greater improvement in intervention outcomes (secondary outcomes i.e., lower stress and higher work engagement) at posttest, as well as at six-month and one-year follow-ups. If effective, enhancing context-specific self-efficacy could be recommended before any internet intervention as a relatively simple way to boost participants' adherence.

A pilot study of the perceptions and acceptability of guidance using artificial intelligence in internet cognitive behaviour therapy for perfectionism in young people

Perfectionism is a transdiagnostic process associated with a range of psychological disorders. Cognitive Behaviour Therapy for Perfectionism (CBT-P) has been demonstrated as efficacious across guided and unguided internet delivered interventions in reducing perfectionism and psychopathology. The aim of this pilot study was to understand perceptions and acceptability of an artificial intelligence supplemented CBT-P intervention (AI-CBT-P) in young people with lived experience of anxiety and depression (n = 8; age range 19-29 years, M = 24 years, SD = 3.77; 50 % female, 38 % male, 12 % non-binary). Young people reported that they were frequent users of artificial intelligence for study, work and general information, were positive about the intervention and using artificial intelligence for guidance in a self-help intervention, but also noted several concerns. Young people perceived numerous benefits to AI-CBT-P, including ease of access, low cost, lack of stigma and benefits for individuals with social anxiety. Overall, young people appear to be interested in, and have a positive view of, AI-CBT-P. Further research is now required to examine the feasibility and acceptability of the intervention.

CuentosIE: can a chatbot about "tales with a message" help to teach emotional intelligence?

In this article, we present CuentosIE (TalesEI: chatbot of tales with a message to develop Emotional Intelligence), an educational chatbot on emotions that also provides teachers and psychologists with a tool to monitor their students/patients through indicators and data compiled by CuentosIE. The use of "tales with a message" is justified by their simplicity and easy understanding, thanks to their moral or associated metaphors. The main contributions of CuentosIE are the selection, collection, and classification of a set of highly specialized tales, as well as the provision of tools (searching, reading comprehension, chatting, recommending, and classifying) that are useful for both educating users about emotions and monitoring their emotional development. The preliminary evaluation of the tool has obtained encouraging results, which provides an affirmative answer to the question posed in the title of the article.

The latest developments with internet-based psychological treatments for depression

INTRODUCTION

Internet-based psychological treatments for depression have been around for more than 20 years. There has been a continuous line of research with new research questions being asked and studies conducted.

AREAS COVERED

In this paper, the author reviews studies with a focus on papers published from 2020 and onwards based on a Medline and Scopus search. Internet-based cognitive behavior therapy (ICBT) programs have been developed and tested for adolescents, older adults, immigrant groups and to handle a societal crisis (e.g. COVID-19). ICBT works in regular clinical settings and long-term effects can be obtained. Studies on different treatment orientations and approaches such as acceptance commitment therapy, unified protocol, and tailored treatments have been conducted. Effects on quality-of-life measures, knowledge acquisition and ecological momentary assessment as a research tool have been reported. Factorial design trials and individual patient data meta-analysis are increasingly used in association with internet intervention research. Finally, prediction studies and recent advances in artificial intelligence are mentioned.

EXPERT OPINION

Internet-delivered treatments are effective, in particular if therapist guidance is provided. More target groups have been covered but there are many remaining challenges including how new tools like artificial intelligence will be used when treating depression.

A randomized controlled trial of the online OurRelationship program with varying levels of coach support

Online programs that reduce relationship distress fill a critical need; however, their scalability is limited by their reliance on coach calls. To determine the effectiveness of the online OurRelationship program with varying levels of coach support, we conducted a comparative effectiveness trial with 740 low-income couples in the United States. Couples were randomly assigned to full-coach (ncouples = 226; program as originally designed), automated-coach (ncouples = 145; as a stand-alone program with tailored automated emails only), contingent-coach (ncouples = 145; as an adaptive program where tailored automated emails are followed by more coaching if couples did not meet progress milestones), or a waitlist control condition (ncouples = 224). All analyses were conducted within a Bayesian framework. Completion rates were comparable across conditions (full-coach: 65 %, automated-coach: 59 %, contingent-coach: 54 %). All intervention couples reported reliable pre-post gains in relationship satisfaction compared to waitlist control couples (dfull = 0.46, dcontingent = 0.47, and dautomated = 0.40) with no reliable differences across intervention conditions. Over four-month follow-up, couples in full- and contingent-coach conditions maintained gains in relationship satisfaction and couples in the automated-coach condition continued to improve. Given the comparable completion rates and minimal differences in effect sizes across intervention conditions, all three coaching models appear viable; therefore, the choice of model can vary depending on available resources as well as couple or stakeholder preferences. This study was preregistered (ClinicalTrials.govNCT03568565).

Low-intensity online mindfulness-based intervention for university students with anxiety during the COVID-19 pandemic-A randomized controlled trial with 3-month follow-up

Objective

This study investigated the effectiveness of a low-intensity online mindfulness-based Intervention (iMBI) for alleviating anxiety in university students during the COVID-19 pandemic.

Methods

In a randomized controlled trial involving 134 participants from a local university in Hong Kong, subjects were randomly assigned to either the intervention group (n = 67) or the inactive control group (n = 67). The intervention group participated in a low-intensity iMBI comprising 16 online modules and two half-day online mindfulness workshops over an eight-week period. Outcomes were measured via an online platform using standardized assessment scales, including the Beck Anxiety Inventory and the Chinese Five Facets Mindfulness Questionnaire, at three different time points: pre-intervention, post-intervention and at a three-month follow-up.

Results

Intent-to-treat analysis using 2 (group) × 3 (time) repeated measures of covariance (ANCOVA) showed that the intervention group, compared to the control group, showed a significant reduction in anxiety symptoms with a medium effect size (Cohen's d = 0.5) and a significant improvement in mindfulness skills with a medium effect size (Cohen's d = 0.5) at post-intervention. The effects of the intervention in reducing anxiety and improving mindfulness persisted at the three-month follow-up.

Conclusion

The results of this study demonstrate the effectiveness of the low-intensity iMBI in alleviating anxiety among university students.

Can ChatGPT Guide Parents on Tympanostomy Tube Insertion?

BACKGROUND

The emergence of ChatGPT, a state-of-the-art language model developed by OpenAI, has introduced a novel avenue for patients to seek medically related information. This technology holds significant promise in terms of accessibility and convenience. However, the use of ChatGPT as a source of accurate information enhancing patient education and engagement requires careful consideration. The objective of this study was to assess the accuracy and reliability of ChatGPT in providing information on the indications and management of complications post-tympanostomy, the most common pediatric procedure in otolaryngology.

METHODS

We prompted ChatGPT-3.5 with questions and compared its generated responses with the recommendations provided by the latest American Academy of Otolaryngology-Head and Neck Surgery Foundation (AAO-HNSF) "Clinical Practice Guideline: Tympanostomy Tubes in Children (Update)".

RESULTS

A total of 23 responses were generated by ChatGPT against the AAO-HNSF guidelines. Following a thorough review, it was determined that 22/23 (95.7%) responses exhibited a high level of reliability and accuracy, closely aligning with the gold standard.

CONCLUSION

Our research study indicates that ChatGPT may be of assistance to parents in search of information regarding tympanostomy tube insertion and its clinical implications.

Crossover of the dimensions of work-family and family-work conflict in couples: Protocol for a qualitative study

Conflict between work and non-work is a bidirectional and a multidimensional construct that has garnered much attention from researchers and practitioners alike. Previously, studies with a dyadic design demonstrated that interrole conflict can cross over between partners in romantic relationships. The aim of the present study is to explore-from an individual and dyadic perspective-how partners perceive dimensions of interrole conflict (that is: time, strain, behaviour, and possibly others) and whether crossover between partners is dimension-dependent. This protocol outlines a qualitative interview study. Participants (N = 40) will be dual-earner couples that meet two inclusion criteria: both partners need to be professionally active, and the couples need to have lived together for at least a year. Interviews will be conducted separately with each partner. To analyse the data at the individual level we will use reflexive thematic analysis. To analyse the data at the dyadic level we will apply an adapted version of the framework method. We anticipate that findings of this study will have the potential to advance theoretical models depicting crossover processes and, more generally, the interface between work and family lives. Moreover, insights into how couples experience dimension-based interrole conflict will be important for the development of targeted interventions.

Low-effort internet intervention to reduce students' stress delivered with Meta's Messenger chatbot (Stressbot): A randomized controlled trial

In order to be more accessible and overcome the challenges of low adherence and high dropout, self-guided internet interventions need to seek new delivery formats. In this study, we tested whether a widely-adopted social media app - Meta's (Facebook) Messenger - would be a suitable conveyor of such an internet intervention. Specifically, we verified the efficacy of Stressbot: a Messenger chatbot-delivered intervention focused on enhancing coping self-efficacy to reduce stress and improve quality of life in university students. Participants (N = 372) were randomly assigned to two conditions: (1) an experimental group with access to the Stressbot intervention, and (2) a waitlist control group. Three outcomes, namely coping self-efficacy, stress, and quality of life, were assessed at three time points: a baseline, post-test, and one-month follow-up. Linear Mixed Effects Models were used to analyze the data. At post-test, we found improvements in the Stressbot condition compared to the control condition for stress (d = -0.33) and coping self-efficacy (d = 0.50), but not for quality of life. A sensitivity analysis revealed that the positive short-term intervention effects were robust. At the follow-up, there were no differences between groups, indicating that the intervention was effective only in the short term. In sum, the results suggest that the Messenger app is a viable means to deliver a self-guided internet intervention. However, modifications such as a more engaging design or boosters are required for the effects to persist.