Personalized prediction of smartphone-based psychotherapeutic micro-intervention success using machine learning

Effects of app-based relaxation techniques on perceived momentary relaxation: Observational data analysis in people with cancer

OBJECTIVE

To examine the effects of six relaxation techniques on perceived momentary relaxation and a possible association of relaxation effects with time and practice experience in people with cancer.

METHODS

We used data from participants with cancer in a larger study practicing app-based relaxation techniques over 10 weeks, assessed momentary relaxation before and after every third relaxation practice, and analyzed momentary relaxation changes with a linear mixed-effects model.

RESULTS

The sample included 611 before-after observations from 91 participants (70 females (76.9%)) with a mean age of 55.43 years (SD 10.88). We found moderate evidence for variations in momentary relaxation changes across different techniques (P = .026), with short meditation, mindfulness meditation, guided imagery, and progressive muscle relaxation more frequently observed and leading to more relaxation than body scan and walking meditation. Furthermore, we found moderate evidence for increasing momentary relaxation changes over time (P = .046), but no evidence for an association between momentary relaxation and the number of previous observations (proxy for practice experience; P = .47).

CONCLUSION

We compared six app-based relaxation techniques in a real-life setting of people with cancer. The observed variations in perceived momentary relaxation appear to correspond with the popularity of the techniques used: The most popular relaxation techniques were the most effective and the least popular were the least effective. The effects increased over time, likely caused by dropout of individuals who gained no immediate benefit. Our findings open an interesting avenue for future research to better understand which relaxation techniques work best for whom in which situations.

TRIAL REGISTRATION

DRKS00027546; https://drks.de/search/en/trial/DRKS00027546.

Detecting major depressive disorder presence using passively-collected wearable movement data in a nationally-representative sample

Major Depressive Disorder (MDD) is a heterogeneous disorder, resulting in challenges with early detection. However, changes in sleep and movement patterns may help improve detection. Thus, this study aimed to explore the utility of wrist-worn actigraphy data in combination with machine learning (ML) and deep learning techniques to detect MDD using a commonly used screening method: Patient Health Questionnaire-9 (PHQ-9). Participants (N = 8,378; MDD Screening = 766 participants) completed the and wore Actigraph GT3X+ for one week as part of the National Health and Nutrition Examination Survey (NHANES). Leveraging minute-level, actigraphy data, we evaluated the efficacy of two commonly used ML approaches and identified actigraphy-derived biomarkers indicative of MDD. We employed two ML modeling strategies: (1) a traditional ML approach with theory-driven feature derivation, and (2) a deep learning Convolutional Neural Network (CNN) approach, coupled with gramian angular field transformation. Findings revealed movement-related features to be the most influential in the traditional ML approach and nighttime movement to be the most influential in the CNN approach for detecting MDD. Using a large, nationally-representative sample, this study highlights the potential of using passively-collected, actigraphy data for understanding MDD to better improve diagnosing and treating MDD.

Individualisation, personalisation and person-centredness in mental healthcare: a scoping review of concepts and linguistic network visualisation

BACKGROUND

Targeted mental health interventions are increasingly described as individualised, personalised or person-centred approaches. However, the definitions for these terms vary significantly. Their interchangeable use prevents operationalisations and measures.

OBJECTIVE

This scoping review provides a synthesis of key concepts, definitions and the language used in the context of these terms in an effort to delineate their use for future research.

STUDY SELECTION AND ANALYSIS

Our search on PubMed, EBSCO and Cochrane provided 2835 relevant titles. A total of 176 titles were found eligible for extracting data. A thematic analysis was conducted to synthesise the underlying aspects of individualisation, personalisation and person-centredness. Network visualisations of co-occurring words in 2625 abstracts were performed using VOSViewer.

FINDINGS

Overall, 106 out of 176 (60.2%) articles provided concepts for individualisation, personalisation and person-centredness. Studies using person-centredness provided a conceptualisation more often than the others. A thematic analysis revealed medical, psychological, sociocultural, biological, behavioural, economic and environmental dimensions of the concepts. Practical frameworks were mostly found related to person-centredness, while theoretical frameworks emerged in studies on personalisation. Word co-occurrences showed common psychiatric words in all three network visualisations, but differences in further contexts.

CONCLUSIONS AND CLINICAL IMPLICATIONS

The use of individualisation, personalisation and person-centredness in mental healthcare is multifaceted. While individualisation was the most generic term, personalisation was often used in biomedical or technological studies. Person-centredness emerged as the most well-defined concept, with many frameworks often related to dementia care. We recommend that the use of these terms follows a clear definition within the context of their respective disorders, treatments or medical settings.

SCOPING REVIEW REGISTRATION

Open Science Framework: osf.io/uatsc.

Predicting Individual Response to a Web-Based Positive Psychology Intervention: A Machine Learning Approach

Positive psychology interventions (PPIs) are effective at increasing happiness and decreasing depressive symptoms. PPIs are often administered as self-guided web-based interventions, but not all persons benefit from web-based interventions. Therefore, it is important to identify whether someone is likely to benefit from web-based PPIs, in order to triage persons who may not benefit from other interventions. In the current study, we used machine learning to predict individual response to a web-based PPI, in order to investigate baseline prognostic indicators of likelihood of response (N = 120). Our models demonstrated moderate correlations (happiness: r Test = 0.30 ± 0.09; depressive symptoms: r Test = 0.39 ± 0.06), indicating that baseline features can predict changes in happiness and depressive symptoms at a 6-month follow-up. Thus, machine learning can be used to predict outcome changes from a web-based PPI and has important clinical implications for matching individuals to PPIs based on their individual characteristics.

Applying ensemble machine learning models to predict individual response to a digitally delivered worry postponement intervention

OBJECTIVE

Generalized anxiety disorder (GAD) is a prevalent mental health disorder that often goes untreated. A core aspect of GAD is worry, which is associated with negative health outcomes, accentuating a need for simple treatments for worry. The present study leveraged pretreatment individual differences to predict personalized treatment response to a digital intervention.

METHODS

Linear mixed-effect models were used to model changes in daytime and nighttime worry duration and frequency for 163 participants who completed a six-day worry postponement intervention. Ensemble-based machine learning regression and classification models were implemented to predict changes in worry across the intervention. Model feature importance was derived using SHapley Additive exPlanation (SHAP).

RESULTS

Moderate predictive performance was obtained for predicting changes in daytime worry duration (test r2 = 0.221, AUC = 0.77) and nighttime worry frequency (test r2 = 0.164, AUC = 0.72), while poor predictive performance was obtained for nighttime worry duration and daytime worry frequency. Baseline levels of worry and subjective health complaints were most important in driving model predictions.

LIMITATIONS

A complete-case analysis was leveraged to analyze the present data, which was collected from participants that were Dutch and majority female.

CONCLUSIONS

This study suggests that treatment response to a digital intervention for GAD can be accurately predicted using baseline characteristics. Particularly, this worry postponement intervention may be most beneficial for individuals with high baseline worry but fewer subjective health complaints. The present findings highlight the complexities of and need for further research into daily worry dynamics and the personalizable utility of digital interventions.

Digital tools for the assessment of pharmacological treatment for depressive disorder: State of the art

Depression is an invalidating disorder, marked by phenotypic heterogeneity. Clinical assessments for treatment adjustments and data-collection for pharmacological research often rely on subjective representations of functioning. Better phenotyping through digital applications may add unseen information and facilitate disentangling the clinical characteristics and impact of depression and its pharmacological treatment in everyday life. Researchers, physicians, and patients benefit from well-understood digital phenotyping approaches to assess the treatment efficacy and side-effects. This review discusses the current possibilities and pitfalls of wearables and technology for the assessment of the pharmacological treatment of depression. Their applications in the whole spectrum of treatment for depression, including diagnosis, treatment of an episode, and monitoring of relapse risk and prevention are discussed. Multiple aspects are to be considered, including concerns that come with collecting sensitive data and health recordings. Also, privacy and trust are addressed. Available applications range from questionnaire-like apps to objective assessment of behavioural patterns and promises in handling suicidality. Nonetheless, interpretation and integration of this high-resolution information with other phenotyping levels, remains challenging. This review provides a state-of-the-art description of wearables and technology in digital phenotyping for monitoring pharmacological treatment in depression, focusing on the challenges and opportunities of its application in clinical trials and research.

Praxisorientierte Forschung in der Psychotherapie

Zusammenfassung. In den letzten Jahrzehnten hat sich durch randomisiert-kontrollierte Studien (RCTs) eine breite Evidenzbasis von Psychotherapie mit mittleren bis großen Effekten für verschiedene psychische Störungen gebildet. Neben der Bestimmung dieser Wirksamkeit („Efficacy“) ebneten Studien zur Wirksamkeit unter alltäglichen Routinebedingungen („Effectiveness“) historisch den Weg zur Entwicklung eines praxisorientierten Forschungsparadigmas. Im Beitrag wird argumentiert, dass im Rahmen dieses Paradigmas praxisbasierte Studien eine wertvolle Ergänzung zu RCTs darstellen, da sie existierende Probleme in der Psychotherapieforschung adressieren können. In der gegenwärtigen praxisorientierten Forschung liefern dabei neue Ansätze aus der personalisierten Medizin und Methoden aus der ‚Computational Psychiatry‘ wichtige Anhaltspunkte zur Optimierung von Effekten in der Psychotherapie. Im Kontext der Personalisierung werden bspw. klinische multivariable Prädiktionsmodelle entwickelt, welche durch Rückmeldeschleifen an Praktiker_innen kurzfristig ein evidenzbasiertes Outcome-Monitoring ermöglicht und langfristig das Praxis-Forschungsnetzwerk in Deutschland stärkt. Am Ende des Beitrags werden zukünftige Richtungen für die praxisorientierte Forschung im Sinne des ‘Precision Mental Health Care’ -Paradigmas abgeleitet und diskutiert.

Using AI chatbots to provide self-help depression interventions for university students: A randomized trial of effectiveness

BACKGROUND

Depression impacts the lives of a large number of university students. Mobile-based therapy chatbots are increasingly being used to help young adults who suffer from depression. However, previous trials have short follow-up periods. Evidence of effectiveness in pragmatic conditions are still in lack.

OBJECTIVE

This study aimed to compare chatbot therapy to bibliotherapy, which is a widely accepted and proven-useful self-help psychological intervention. The main objective of this study is to add to the evidence of effectiveness for chatbot therapy as a convenient, affordable, interactive self-help intervention for depression.

METHODS

An unblinded randomized controlled trial with 83 university students was conducted. The participants were randomly assigned to either a chatbot test group (n = 41) to receive a newly developed chatbot-delivered intervention, or a bibliotherapy control group (n = 42) to receive a minimal level of bibliotherapy. A set of questionnaires was implemented as measurements of clinical variables at baseline and every 4 weeks for a period of 16 weeks, which included the Patient Health Questionnaire-9 (PHQ-9), the Generalized Anxiety Disorder scale (GAD-7), the Positive and Negative Affect Scale (PANAS). The Client Satisfaction Questionnaire-8 (CSQ-8) and the Working Alliance Inventory-Short Revised (WAI-SR) were used to measure satisfaction and therapeutic alliance after the intervention. Participants' self-reported adherence and feedback on the therapy chatbot were also collected.

RESULTS

Participants were all university students (undergraduate students (n = 31), postgraduate students (n = 52)). They were between 19 and 28 years old (mean = 23.08, standard deviation (SD) = 1.76) and 55.42% (46/83) female. 24.07% (20/83) participants were lost to follow-up. No significant group difference was found at baseline. In the intention-to-treat analysis, individuals in the chatbot test group showed a significant reduction in the PHQ-9 scores (F = 22.89; P < 0.01) and the GAD-7 scores (F = 5.37; P = 0.02). Follow-up analysis of completers suggested that the reduction of anxiety was significant only in the first 4 weeks. The WAI-SR scores in the chatbot group were higher compared to the bibliotherapy group (t = 7.29; P < 0.01). User feedback showed that process factors were more influential than the content factors.

CONCLUSIONS

The chatbot-delivered self-help depression intervention was proven to be superior to the minimal level of bibliotherapy in terms of reduction on depression, anxiety, and therapeutic alliance achieved with participants.

Predicting symptom response and engagement in a digital intervention among individuals with schizophrenia and related psychoses

INTRODUCTION

Despite existing work examining the effectiveness of smartphone digital interventions for schizophrenia at the group level, response to digital treatments is highly variable and requires more research to determine which persons are most likely to benefit from a digital intervention.

MATERIALS AND METHODS

The current work utilized data from an open trial of patients with psychosis (N = 38), primarily schizophrenia spectrum disorders, who were treated with a psychosocial intervention using a smartphone app over a one-month period. Using an ensemble of machine learning models, pre-intervention data, app use data, and semi-structured interview data were utilized to predict response to change in symptom scores, engagement patterns, and qualitative impressions of the app.

RESULTS

Machine learning models were capable of moderately (r = 0.32-0.39, R² = 0.10-0.16, MAE _norm = 0.13-0.29) predicting interaction and experience with the app, as well as changes in psychosis-related psychopathology.

CONCLUSION

The results suggest that individual smartphone digital intervention engagement is heterogeneous, and symptom-specific baseline data may be predictive of increased engagement and positive qualitative impressions of digital intervention in patients with psychosis. Taken together, interrogating individual response to and engagement with digital-based intervention with machine learning provides increased insight to otherwise ignored nuances of treatment response.

Ethics and Law in Research on Algorithmic and Data-Driven Technology in Mental Health Care: Scoping Review

BACKGROUND

Uncertainty surrounds the ethical and legal implications of algorithmic and data-driven technologies in the mental health context, including technologies characterized as artificial intelligence, machine learning, deep learning, and other forms of automation.

OBJECTIVE

This study aims to survey empirical scholarly literature on the application of algorithmic and data-driven technologies in mental health initiatives to identify the legal and ethical issues that have been raised.

METHODS

We searched for peer-reviewed empirical studies on the application of algorithmic technologies in mental health care in the Scopus, Embase, and Association for Computing Machinery databases. A total of 1078 relevant peer-reviewed applied studies were identified, which were narrowed to 132 empirical research papers for review based on selection criteria. Conventional content analysis was undertaken to address our aims, and this was supplemented by a keyword-in-context analysis.

RESULTS

We grouped the findings into the following five categories of technology: social media (53/132, 40.1%), smartphones (37/132, 28%), sensing technology (20/132, 15.1%), chatbots (5/132, 3.8%), and miscellaneous (17/132, 12.9%). Most initiatives were directed toward detection and diagnosis. Most papers discussed privacy, mainly in terms of respecting the privacy of research participants. There was relatively little discussion of privacy in this context. A small number of studies discussed ethics directly (10/132, 7.6%) and indirectly (10/132, 7.6%). Legal issues were not substantively discussed in any studies, although some legal issues were discussed in passing (7/132, 5.3%), such as the rights of user subjects and privacy law compliance.

CONCLUSIONS

Ethical and legal issues tend to not be explicitly addressed in empirical studies on algorithmic and data-driven technologies in mental health initiatives. Scholars may have considered ethical or legal matters at the ethics committee or institutional review board stage. If so, this consideration seldom appears in published materials in applied research in any detail. The form itself of peer-reviewed papers that detail applied research in this field may well preclude a substantial focus on ethics and law. Regardless, we identified several concerns, including the near-complete lack of involvement of mental health service users, the scant consideration of algorithmic accountability, and the potential for overmedicalization and techno-solutionism. Most papers were published in the computer science field at the pilot or exploratory stages. Thus, these technologies could be appropriated into practice in rarely acknowledged ways, with serious legal and ethical implications.

Ecological momentary interventions for mental health: A scoping review

BACKGROUND

The development of mobile computing technology has enabled the delivery of psychological interventions while people go about their everyday lives. The original visions of the potential of these "ecological momentary interventions" were presented over a decade ago, and the widespread adoption of smartphones in the intervening years has led to a variety of research studies exploring the feasibility of these aspirations. However, there is a dearth of research describing the different dimensions, characteristics, and features of these interventions, as constructed.

OBJECTIVE

To provide an overview of the definitions given for "ecological momentary interventions" in the treatment of common mental health disorders, and describe the set of technological and interaction possibilities which have been used in the design of these interventions.

METHODS

A systematic search identified relevant literature published between 2009 and 2020 in the PubMed, PsycInfo, and ACM Guide to the Computing Literature databases. Following screening, data were extracted from eligible articles using a standardized extraction worksheet. Selected articles were then thematically categorized.

RESULTS

The search identified 583 articles of which 64 met the inclusion criteria. The interventions target a range of mental health problems, with diverse aims, intervention designs and evaluation approaches. The studies employed a variety of features for intervention delivery, but recent research is overwhelmingly comprised of studies based on smartphone apps (30 of 42 papers that described an intervention). Twenty two studies employed sensors for the collection of data in order to provide just-in-time support or predict psychological states.

CONCLUSIONS

With the shift towards smartphone apps, the vision for EMIs has begun to be realised. Recent years have seen increased exploration of the use of sensors and machine learning, but the role of humans in the delivery of EMI is also varied. The variety of capabilities exhibited by EMIs motivates development of a more precise vocabulary for capturing both automatic and human tailoring of these interventions.

Induction of Efficacy Expectancies in an Ambulatory Smartphone-Based Digital Placebo Mental Health Intervention: Randomized Controlled Trial

BACKGROUND

There is certain evidence on the efficacy of smartphone-based mental health interventions. However, the mechanisms of action remain unclear. Placebo effects contribute to the efficacy of face-to-face mental health interventions and may also be a potential mechanism of action in smartphone-based interventions.

OBJECTIVE

This study aimed to investigate whether different types of efficacy expectancies as potential factors underlying placebo effects could be successfully induced in a smartphone-based digital placebo mental health intervention, ostensibly targeting mood and stress.

METHODS

We conducted a randomized, controlled, single-blinded, superiority trial with a multi-arm parallel design. Participants underwent an Android smartphone-based digital placebo mental health intervention for 20 days. We induced prospective efficacy expectancies via initial instructions on the purpose of the intervention and retrospective efficacy expectancies via feedback on the success of the intervention at days 1, 4, 7, 10, and 13. A total of 132 healthy participants were randomized to a prospective expectancy-only condition (n=33), a retrospective expectancy-only condition (n=33), a combined expectancy condition (n=34), or a control condition (n=32). As the endpoint, we assessed changes in efficacy expectancies with the Credibility Expectancy Questionnaire, before the intervention and on days 1, 7, 14, and 20. For statistical analyses, we used a random effects model for the intention-to-treat sample, with intervention day as time variable and condition as two factors: prospective expectancy (yes vs no) and retrospective expectancy (yes vs no), allowed to vary over participant and intervention day.

RESULTS

Credibility (β=-1.63; 95% CI -2.37 to -0.89; P<.001) and expectancy (β=-0.77; 95% CI -1.49 to -0.05; P=.04) decreased across the intervention days. For credibility and expectancy, we found significant three-way interactions: intervention day×prospective expectancy×retrospective expectancy (credibility: β=2.05; 95% CI 0.60-3.50; P=.006; expectancy: β=1.55; 95% CI 0.14-2.95; P=.03), suggesting that efficacy expectancies decreased least in the combined expectancy condition and the control condition.

CONCLUSIONS

To our knowledge, this is the first empirical study investigating whether efficacy expectancies can be successfully induced in a specifically designed placebo smartphone-based mental health intervention. Our findings may pave the way to diminish or exploit digital placebo effects and help to improve the efficacy of digital mental health interventions.

TRIAL REGISTRATION

Clinicaltrials.gov NCT02365220; https://clinicaltrials.gov/ct2/show/NCT02365220.

Constructing Emotional Machines: A Case of a Smartphone-Based Emotion System

In this study, an emotion system was developed and installed on smartphones to enable them to exhibit emotions. The objective of this study was to explore factors that developers should focus on when developing emotional machines. This study also examined user attitudes and emotions toward emotional messages sent by machines and the effects of emotion systems on user behavior. According to the results of this study, the degree of attention paid to emotional messages determines the quality of the emotion system, and an emotion system triggers certain behaviors in users. This study recruited 124 individuals with more than one year of smartphone use experience. The experiment lasted for two weeks, during which time participants were allowed to operate the system freely and interact with the system agent. The majority of the participants took interest in emotional messages, were influenced by emotional messages and were convinced that the developed system enabled their smartphone to exhibit emotions. The smartphones generated 11,264 crucial notifications in total, among which 76% were viewed by the participants and 68.1% enabled the participants to resolve unfavorable smartphone conditions in a timely manner and allowed the system agent to provide users with positive emotional feedback.

Digital solutions for shaping mood and behavior among individuals with mood disorders

Mood disorders present on-going challenges to the medical field, with difficulties ranging from establishing effective treatments to understanding complexities of one's mood. One solution is the use of mobile apps and wearables for measuring physiological symptoms and real-time mood in order to shape mood and behavior. Current digital research is focused on increasing engagement in monitoring mood, uncovering mood dynamics, predicting mood, and providing digital microinterventions. This review discusses the importance and risks of user engagement, as well as barriers to improving it. Research on mood dynamics highlights the possibility to reveal data-driven computational phenotypes that could guide treatment. Mobile apps are being used to track voice patterns, GPS, and phone usage for predicting mood and treatment response. Future directions include utilizing mobile apps to deliver and evaluate microinterventions. To continue these advances, standardized reporting and study designs should be considered to improve digital solutions for mood disorders.