Can digital data diagnose mental health problems? A sociological exploration of 'digital phenotyping'

Entanglements of Technologies, Agency and Selfhood: Exploring the Complexity in Attitudes Toward Mental Health Chatbots

Whilst chatbots for mental health are becoming increasingly prevalent, research on user experiences and expectations is relatively scarce and also equivocal on their acceptability and utility. This paper asks how people formulate their understandings of what might be appropriate in this space. We draw on data from a group of non-users who have experienced a need for support, and so can imagine self as therapeutic target-enabling us to tap into their imaginative speculations of the self in relation to the chatbot other and the forms of agency they see as being at play; unconstrained by a specific actual chatbot. Analysis points towards ambiguity over some key issues: whether the apps were seen as having a role in specific episodes of mental health or in relation to an ongoing project of supporting wellbeing; whether the chatbot could be viewed as having a therapeutic agency or was a mere tool; and how far these issues related to matters of the user's personal qualities or the specific nature of the mental health condition. A range of traditions, norms and practices were used to construct diverse expectations on whether chatbots could offer a solution to cost-effective mental health support at scale.

The Ubuntu Way: Ensuring Ethical AI Integration in Health Research

The integration of artificial intelligence (AI) in health research has grown rapidly, particularly in African nations, which have also been developing data protection laws and AI strategies. However, the ethical frameworks governing AI use in health research are often based on Western philosophies, focusing on individualism, and may not fully address the unique challenges and cultural contexts of African communities. This paper advocates for the incorporation of African philosophies, specifically Ubuntu, into AI health research ethics frameworks to better align with African values and contexts. This study explores the concept of Ubuntu, a philosophy that emphasises communalism, interconnectedness, and collective well-being, and its application to AI health research ethics. By analysing existing global AI ethics frameworks and contrasting them with the Ubuntu philosophy, a new ethics framework is proposed that integrates these perspectives. The framework is designed to address ethical challenges at individual, community, national, and environmental levels, with a particular focus on the African context. The proposed framework highlights four key principles derived from Ubuntu: communalism and openness, harmony and support, research prioritisation and community empowerment, and community-oriented decision-making. These principles are aligned with global ethical standards such as justice, beneficence, transparency, and accountability but are adapted to reflect the communal and relational values inherent in Ubuntu. The framework aims to ensure that AI-driven health research benefits communities equitably, respects local contexts and promotes long-term sustainability. Integrating Ubuntu into AI health research ethics can address the limitations of current frameworks that emphasise individualism. This approach not only aligns with African values but also offers a model that could be applied more broadly to enhance the ethical governance of AI in health research worldwide. By prioritising communal well-being, inclusivity, and environmental stewardship, the proposed framework has the potential to foster more responsible and contextually relevant AI health research practices in Africa.

The techno-politics of computing the mind: Opening the black box of digital psychiatry

Psychiatry has recently witnessed the launch of digital phenotyping as a new research agenda. According to digital phenotyping's hypothesis, data about a patient's daily behavior can be continuously collected through wearable monitoring devices and used to build software that would send warnings of mental relapse or would tailor treatment choices. The research is exploratory, and the claims upon which it is based are contentious. Drawing on interviews, we followed a research team that aspired to build a digital system that could send such warnings to patients with mental health disorders like depression and epilepsy. This enabled us to learn how a new instrument to measure mental function becomes constructed and what translations take place in this process. Here we pay particular attention to the role of patients as research collaborators. We observed the frictions and debates in the research team between different mental health knowledge regimes, seeing them before they were black-boxed and lost from sight. We aimed to understand how actors anticipate software and data analytics to function alongside physicians and patients, as well as how different accounts reconstitute the 'mental', 'therapy', or the 'social' itself. We discuss several 'dissociations' that occur along the research trajectory regarding: less motivated and underrepresented patients, the role of clinical knowledge derived from patient self-reporting, and the social, political, and economic aspects of a patient's life affecting mental health. In this sense, we want to open the black box of this new behavioral technoscience.

Benchmarking Mental Health Status Using Passive Sensor Data: Protocol for a Prospective Observational Study

BACKGROUND

Computational psychiatry has the potential to advance the diagnosis, mechanistic understanding, and treatment of mental health conditions. Promising results from clinical samples have led to calls to extend these methods to mental health risk assessment in the general public; however, data typically used with clinical samples are neither available nor scalable for research in the general population. Digital phenotyping addresses this by capitalizing on the multimodal and widely available data created by sensors embedded in personal digital devices (eg, smartphones) and is a promising approach to extending computational psychiatry methods to improve mental health risk assessment in the general population.

OBJECTIVE

Building on recommendations from existing computational psychiatry and digital phenotyping work, we aim to create the first computational psychiatry data set that is tailored to studying mental health risk in the general population; includes multimodal, sensor-based behavioral features; and is designed to be widely shared across academia, industry, and government using gold standard methods for privacy, confidentiality, and data integrity.

METHODS

We are using a stratified, random sampling design with 2 crossed factors (difficulties with emotion regulation and perceived life stress) to recruit a sample of 400 community-dwelling adults balanced across high- and low-risk for episodic mental health conditions. Participants first complete self-report questionnaires assessing current and lifetime psychiatric and medical diagnoses and treatment, and current psychosocial functioning. Participants then complete a 7-day in situ data collection phase that includes providing daily audio recordings, passive sensor data collected from smartphones, self-reports of daily mood and significant events, and a verbal description of the significant daily events during a nightly phone call. Participants complete the same baseline questionnaires 6 and 12 months after this phase. Self-report questionnaires will be scored using standard methods. Raw audio and passive sensor data will be processed to create a suite of daily summary features (eg, time spent at home).

RESULTS

Data collection began in June 2022 and is expected to conclude by July 2024. To date, 310 participants have consented to the study; 149 have completed the baseline questionnaire and 7-day intensive data collection phase; and 61 and 31 have completed the 6- and 12-month follow-up questionnaires, respectively. Once completed, the proposed data set will be made available to academic researchers, industry, and the government using a stepped approach to maximize data privacy.

CONCLUSIONS

This data set is designed as a complementary approach to current computational psychiatry and digital phenotyping research, with the goal of advancing mental health risk assessment within the general population. This data set aims to support the field's move away from siloed research laboratories collecting proprietary data and toward interdisciplinary collaborations that incorporate clinical, technical, and quantitative expertise at all stages of the research process.

INTERNATIONAL REGISTERED REPORT IDENTIFIER (IRRID)

DERR1-10.2196/53857.

Tracing Tomorrow: young people's preferences and values related to use of personal sensing to predict mental health, using a digital game methodology

BACKGROUND

Use of personal sensing to predict mental health risk has sparked interest in adolescent psychiatry, offering a potential tool for targeted early intervention.

OBJECTIVES

We investigated the preferences and values of UK adolescents with regard to use of digital sensing information, including social media and internet searching behaviour. We also investigated the impact of risk information on adolescents' self-understanding.

METHODS

Following a Design Bioethics approach, we created and disseminated a purpose-built digital game (www.tracingtomorrow.org) that immersed the player-character in a fictional scenario in which they received a risk assessment for depression Data were collected through game choices across relevant scenarios, with decision-making supported through clickable information points.

FINDINGS

The game was played by 7337 UK adolescents aged 16-18 years. Most participants were willing to personally communicate mental health risk information to their parents or best friend. The acceptability of school involvement in risk predictions based on digital traces was mixed, due mainly to privacy concerns. Most participants indicated that risk information could negatively impact their academic self-understanding. Participants overwhelmingly preferred individual face-to-face over digital options for support.

CONCLUSIONS

The potential of digital phenotyping in supporting early intervention in mental health can only be fulfilled if data are collected, communicated and actioned in ways that are trustworthy, relevant and acceptable to young people.

CLINICAL IMPLICATIONS

To minimise the risk of ethical harms in real-world applications of preventive psychiatric technologies, it is essential to investigate young people's values and preferences as part of design and implementation processes.

Reconciling healthism and techno-solutionism: An observational study of a digital mental health trial

In a growing trend in digital psychiatry, algorithmic systems are used to determine correlations between data that is collected using wearable devices and self-reports of mood. They then offer recommendations for behaviour modification for improved mood. The present study consists of observations of the development of one of these systems. Descriptions of the trial emphasise the powerful role of the intrinsically motivated, responsible participant on one hand and the empowering machine learning (ML)-based technology on the other. This conceptualisation is shown to extend the neoliberal paradox of a freedom that, to be maintained, must be continually adjusted through discipline. Because of the paradoxical nature of this formulation, laboratory members disagree about the balance of agency between the objective machine learning system and the empowered participant. The guides who help participants interpret ML outputs and implement system recommendations are ascribed a replaceable role in formal accounts. Observations of this guidance practice make clear not only the important role played by guides but also how their work is relegated to the technological side of the broader formulation of the trial and further how this conceptualisation affects the way they conduct their work.

Digital Phenotyping: Data-Driven Psychiatry to Redefine Mental Health

The term "digital phenotype" refers to the digital footprint left by patient-environment interactions. It has potential for both research and clinical applications but challenges our conception of health care by opposing 2 distinct approaches to medicine: one centered on illness with the aim of classifying and curing disease, and the other centered on patients, their personal distress, and their lived experiences. In the context of mental health and psychiatry, the potential benefits of digital phenotyping include creating new avenues for treatment and enabling patients to take control of their own well-being. However, this comes at the cost of sacrificing the fundamental human element of psychotherapy, which is crucial to addressing patients' distress. In this viewpoint paper, we discuss the advances rendered possible by digital phenotyping and highlight the risk that this technology may pose by partially excluding health care professionals from the diagnosis and therapeutic process, thereby foregoing an essential dimension of care. We conclude by setting out concrete recommendations on how to improve current digital phenotyping technology so that it can be harnessed to redefine mental health by empowering patients without alienating them.

Clinical Implication of Maumgyeol Basic Service-the 2 Channel Electroencephalography and a Photoplethysmogram-based Mental Health Evaluation Software

Objective

Maumgyeol Basic service is a mental health evaluation and grade scoring software using the 2 channels EEG and photoplethysmogram (PPG). This service is supposed to assess potential at-risk groups with mental illness more easily, rapidly, and reliably. This study aimed to evaluate the clinical implication of the Maumgyeol Basic service.

Methods

One hundred one healthy controls and 103 patients with a psychiatric disorder were recruited. Psychological evaluation (Mental Health Screening for Depressive Disorders [MHS-D], Mental Health Screening for Anxiety Disorders [MHS-A], cognitive stress response scale [CSRS], 12-item General Health Questionnaire [GHQ-12], Clinical Global Impression [CGI]) and digit symbol substitution test (DSST) were applied to all participants. Maumgyeol brain health score and Maumgyeol mind health score were calculated from 2 channel frontal EEG and PPG, respectively.

Results

Participants were divided into three groups: Maumgyeol Risky, Maumgyeol Good, and Maumgyeol Usual. The Maumgyeol mind health scores, but not brain health scores, were significantly lower in the patients group compared to healthy controls. Maumgyeol Risky group showed significantly lower psychological and cognitive ability evaluation scores than Maumgyeol Usual and Good groups. Maumgyel brain health score showed significant correlations with CSRS and DSST. Maumgyeol mind health score showed significant correlations with CGI and DSST. About 20.6% of individuals were classified as the No Insight group, who had mental health problems but were unaware of their illnesses.

Conclusion

This study suggests that the Maumgyeol Basic service can provide important clinical information about mental health and be used as a meaningful digital mental healthcare monitoring solution to prevent symptom aggravation.

Digital Phenotyping for Mental Health: Reviewing the Challenges of Using Data to Monitor and Predict Mental Health Problems

PURPOSE OF REVIEW

We review recent developments within digital phenotyping for mental health, a field dedicated to using digital data for diagnosing, predicting, and monitoring mental health problems. We especially focus on recent critiques and challenges to digital phenotyping from within the social sciences.

RECENT FINDINGS

Three significant strands of criticism against digital phenotyping for mental health have been developed within the social sciences. This literature problematizes the idea that digital data can be objective, that it can be unbiased, and argues that it has multiple ethical and practical challenges. Digital phenotyping for mental health is a rapidly growing and developing field, but with considerable challenges that are not easily solvable. This includes when, and if, data from digital phenotyping is actionable in practice; the involvement of user and patient perspectives in digital phenotyping research; the possibility of biased data; and challenges to the idea that digital phenotyping can be more objective than other forms of psychiatric assessment.

The environmental impact of data-driven precision medicine initiatives

Opportunities offered by precision medicine have long been promised in the medical and health literature. However, precision medicine - and the methodologies and approaches it relies on - also has adverse environmental impacts. As research into precision medicine continues to expand, there is a compelling need to consider these environmental impacts and develop means to mitigate them. In this article, we review the adverse environmental impacts associated with precision medicine, with a particular focus on those associated with its underlying need for data-intensive approaches. We illustrate the importance of considering the environmental impacts of precision medicine and describe the adverse health outcomes that are associated with climate change. We follow this with a description of how these environmental impacts are being addressed in both the health and data-driven technology sector. We then describe the (scant) literature on environmental impacts associated with data-driven precision medicine specifically. We finish by highlighting various environmental considerations that precision medicine researchers, and the field more broadly, should take into account.

Digitale Phänotypisierung in der Psychologie – ein Quantensprung in der psychologischen Forschung?

Zusammenfassung. Digitale Phänotypisierung stellt einen neuen, leistungsstarken Ansatz zur Realisierung psychodiagnostischer Aufgaben in vielen Bereichen der Psychologie und Medizin dar. Die Grundidee besteht aus der Nutzung digitaler Spuren aus dem Alltag, um deren Vorhersagekraft für verschiedenste Anwendungsmöglichkeiten zu überprüfen und zu nutzen. Voraussetzungen für eine erfolgreiche Umsetzung sind elaborierte Smart Sensing Ansätze sowie Big Data-basierte Extraktions- (Data Mining) und Machine Learning-basierte Analyseverfahren. Erste empirische Studien verdeutlichen das hohe Potential, aber auch die forschungsmethodischen sowie ethischen und rechtlichen Herausforderungen, um über korrelative Zufallsbefunde hinaus belastbare Befunde zu gewinnen. Hierbei müssen rechtliche und ethische Richtlinien sicherstellen, dass die Erkenntnisse in einer für Einzelne und die Gesellschaft als Ganzes wünschenswerten Weise genutzt werden. Für die Psychologie als Lehr- und Forschungsdomäne bieten sich durch Digitale Phänotypisierung vielfältige Möglichkeiten, die zum einen eine gelebte Zusammenarbeit verschiedener Fachbereiche und zum anderen auch curriculare Erweiterungen erfordern. Die vorliegende narrative Übersicht bietet eine theoretische, nicht-technische Einführung in das Forschungsfeld der Digitalen Phänotypisierung, mit ersten empirischen Befunden sowie einer Diskussion der Möglichkeiten und Grenzen sowie notwendigen Handlungsfeldern.

The Apple Watch for Monitoring Mental Health-Related Physiological Symptoms: Literature Review

BACKGROUND

An anticipated surge in mental health service demand related to COVID-19 has motivated the use of novel methods of care to meet demand, given workforce limitations. Digital health technologies in the form of self-tracking technology have been identified as a potential avenue, provided sufficient evidence exists to support their effectiveness in mental health contexts.

OBJECTIVE

This literature review aims to identify current and potential physiological or physiologically related monitoring capabilities of the Apple Watch relevant to mental health monitoring and examine the accuracy and validation status of these measures and their implications for mental health treatment.

METHODS

A literature review was conducted from June 2021 to July 2021 of both published and gray literature pertaining to the Apple Watch, mental health, and physiology. The literature review identified studies validating the sensor capabilities of the Apple Watch.

RESULTS

A total of 5583 paper titles were identified, with 115 (2.06%) reviewed in full. Of these 115 papers, 19 (16.5%) were related to Apple Watch validation or comparison studies. Most studies showed that the Apple Watch could measure heart rate acceptably with increased errors in case of movement. Accurate energy expenditure measurements are difficult for most wearables, with the Apple Watch generally providing the best results compared with peers, despite overestimation. Heart rate variability measurements were found to have gaps in data but were able to detect mild mental stress. Activity monitoring with step counting showed good agreement, although wheelchair use was found to be prone to overestimation and poor performance on overground tasks. Atrial fibrillation detection showed mixed results, in part because of a high inconclusive result rate, but may be useful for ongoing monitoring. No studies recorded validation of the Sleep app feature; however, accelerometer-based sleep monitoring showed high accuracy and sensitivity in detecting sleep.

CONCLUSIONS

The results are encouraging regarding the application of the Apple Watch in mental health, particularly as heart rate variability is a key indicator of changes in both physical and emotional states. Particular benefits may be derived through avoidance of recall bias and collection of supporting ecological context data. However, a lack of methodologically robust and replicated evidence of user benefit, a supportive health economic analysis, and concerns about personal health information remain key factors that must be addressed to enable broader uptake.

Day-to-day intrapersonal variability in mobility patterns and association with perceived stress: A cross-sectional study using GPS from 122 individuals in three European cities

Many aspects of our life are related to our mobility patterns and individuals can exhibit strong tendencies towards routine in their daily lives. Intrapersonal day-to-day variability in mobility patterns has been associated with mental health outcomes. The study aims were: (a) calculate intrapersonal day-to-day variability in mobility metrics for three cities; (b) explore interpersonal variability in mobility metrics by sex, season and city, and (c) describe intrapersonal variability in mobility and their association with perceived stress. Data came from the Physical Activity through Sustainable Transport Approaches (PASTA) project, 122 eligible adults wore location measurement devices over 7-consecutive days, on three occasions during 2015 (Antwerp: 41, Barcelona: 41, London: 40). Participants completed the Short Form Perceived Stress Scale (PSS-4). Day-to-day variability in mobility was explored via six mobility metrics using distance of GPS point from home (meters:m), distance travelled between consecutive GPS points (m) and energy expenditure (metabolic equivalents:METs) of each GPS point collected (n = 3,372,919). A Kruskal-Wallis H test determined whether the median daily mobility metrics differed by city, sex and season. Variance in correlation quantified day-to-day intrapersonal variability in mobility. Levene's tests or Kruskal-Wallis tests were applied to assess intrapersonal variability in mobility and perceived stress. There were differences in daily distance travelled, maximum distance from home and METS between individuals by sex, season and, for proportion of time at home also, by city. Intrapersonal variability across all mobility metrics were highly correlated; individuals had daily routines and largely stuck to them. We did not observe any association between stress and mobility. Individuals are habitual in their daily mobility patterns. This is useful for estimating environmental exposures and in fuelling simulation studies.

Clinical Targets and Attitudes Toward Implementing Digital Health Tools for Remote Measurement in Treatment for Depression: Focus Groups With Patients and Clinicians

BACKGROUND

Remote measurement technologies, such as smartphones and wearable devices, can improve treatment outcomes for depression through enhanced illness characterization and monitoring. However, little is known about digital outcomes that are clinically meaningful to patients and clinicians. Moreover, if these technologies are to be successfully implemented within treatment, stakeholders' views on the barriers to and facilitators of their implementation in treatment must be considered.

OBJECTIVE

This study aims to identify clinically meaningful targets for digital health research in depression and explore attitudes toward their implementation in psychological services.

METHODS

A grounded theory approach was used on qualitative data from 3 focus groups of patients with a current diagnosis of depression and clinicians with >6 months of experience with delivering psychotherapy (N=22).

RESULTS

Emerging themes on clinical targets fell into the following two main categories: promoters and markers of change. The former are behaviors that participants engage in to promote mental health, and the latter signal a change in mood. These themes were further subdivided into external changes (changes in behavior) or internal changes (changes in thoughts or feelings) and mapped with potential digital sensors. The following six implementation acceptability themes emerged: technology-related factors, information and data management, emotional support, cognitive support, increased self-awareness, and clinical utility.

CONCLUSIONS

The promoters versus markers of change differentiation have implications for a causal model of digital phenotyping in depression, which this paper presents. Internal versus external subdivisions are helpful in determining which factors are more susceptible to being measured by using active versus passive methods. The implications for implementation within psychotherapy are discussed with regard to treatment effectiveness, service provision, and patient and clinician experience.

A review of mathematical modeling of addiction regarding both (neuro-) psychological processes and the social contagion perspectives

Addiction is a complex biopsychosocial phenomenon, impacted by biological predispositions, psychological processes, and the social environment. Using mathematical and computational models that allow for surrogative reasoning may be a promising avenue for gaining a deeper understanding of this complex behavior. This paper reviews and classifies a selection of formal models of addiction focusing on the intra- and inter-individual dynamics, i.e., (neuro) psychological models and social models. We find that these modeling approaches to addiction are too disjoint and argue that in order to unravel the complexities of biopsychosocial processes of addiction, models should integrate intra- and inter-individual factors.

Mental health monitoring apps for depression and anxiety in children and young people: A scoping review and critical ecological analysis

There is considerable concern about increasing rates of anxiety and depression among children and young people (CYP). Mental health technologies, such as smartphone applications, are proposed as a potential solution. However, the effectiveness of mental health mobile applications for managing, moderating and treating anxiety and depression in CYP is uncertain. The purpose of this scoping review is to outline the extent of the clinical evidence base of mental health apps with monitoring functions for depression and anxiety in CYP, to categorise the range of monitoring features, to understand their various purposes, and to analyse these 'technical mechanisms' in apps from the perspective of critical ecological analysis. It provides a novel conceptual framework for researching how CYP may use and critically engage with mental health apps. We searched Ovid MEDLINE, PsycINFO, and Scopus databases, and 39 studies met the inclusion criteria. The analysis focuses attention on the ecological (mental, social and environmental) dimensions of life, health and emotional experience and the purposes of mental health monitoring apps. We evaluate the way that technical mechanisms, such as metrics are used in apps, examine their effects on responsibility for managing and treating distress and consider the rationalities that guide their development. The paper concludes that examination of the bioethics and neuroethics of these technologies is necessary and urgent. This requires paying closer attention to the social practices of technology-enabled self-monitoring, and the ways in which these frame mental health as a form of individualised emotional regulation.

Digital phenotyping and the (data) shadow of Alzheimer's disease

In this paper, we examine the practice and promises of digital phenotyping. We build on work on the 'data self' to focus on a medical domain in which the value and nature of knowledge and relations with data have been played out with particular persistence, that of Alzheimer's disease research. Drawing on research with researchers and developers, we consider the intersection of hopes and concerns related to both digital tools and Alzheimer's disease using the metaphor of the 'data shadow'. We suggest that as a tool for engaging with the nature of the data self, the shadow is usefully able to capture both the dynamic and distorted nature of data representations, and the unease and concern associated with encounters between individuals or groups and data about them. We then consider what the data shadow 'is' in relation to ageing data subjects, and the nature of the representation of the individual's cognitive state and dementia risk that is produced by digital tools. Second, we consider what the data shadow 'does', through researchers and practitioners' discussions of digital phenotyping practices in the dementia field as alternately empowering, enabling and threatening.

The environmental sustainability of data-driven health research: A scoping review

Data-Driven and Artificial Intelligence technologies are rapidly changing the way that health research is conducted, including offering new opportunities. This will inevitably have adverse environmental impacts. These include carbon dioxide emissions linked to the energy required to generate and process large amounts of data; the impact on the material environment (in the form of data centres); the unsustainable extraction of minerals for technological components; and e-waste (discarded electronic appliances) disposal. The growth of Data-Driven and Artificial Intelligence technologies means there is now a compelling need to consider these environmental impacts and develop means to mitigate them. Here, we offer a scoping review of how the environmental impacts of data storage and processing during Data-Driven and Artificial Intelligence health-related research are being discussed in the academic literature. Using the UK as a case study, we also offer a review of policies and initiatives that consider the environmental impacts of data storage and processing during Data-Driven and Artificial Intelligence health-related research in the UK. Our findings suggest little engagement with these issues to date. We discuss the implications of this and suggest ways that the Data-Driven and Artificial Intelligence health research sector needs to move to become more environmentally sustainable.

Digital Phenotyping: an Epistemic and Methodological Analysis

Some claim that digital phenotyping will revolutionize understanding of human psychology and experience and significantly promote human wellbeing. This paper investigates the nature of digital phenotyping in relation to its alleged promise. Unlike most of the literature to date on philosophy and digital phenotyping, which has focused on its ethical aspects, this paper focuses on its epistemic and methodological aspects. The paper advances a tetra-taxonomy involving four scenario types in which knowledge may be acquired from human "digitypes" by digital phenotyping. These scenarios comprise two causal relations and a correlative and constitutive relation that can exist between information generated by digital systems/devices on the one hand and psychological or behavioral phenomena on the other. The paper describes several modes of inference involved in deriving knowledge within these scenarios. After this epistemic mapping, the paper analyzes the possible knowledge potential and limitations of digital phenotyping. It finds that digital phenotyping holds promise of delivering insight into conditions and states as well producing potentially new psychological categories. It also argues that care must be taken that digital phenotyping does not make unwarranted conclusions and is aware of potentially distorting effects in digital sensing and measurement. If digital phenotyping is to truly revolutionize knowledge of human life, it must deliver on a range of fronts, including making accurate forecasts and diagnoses of states and behaviors, providing causal explanations of these phenomena, and revealing important constituents of human conditions, psychology, and experience.

Shift in Social Media App Usage During COVID-19 Lockdown and Clinical Anxiety Symptoms: Machine Learning-Based Ecological Momentary Assessment Study

BACKGROUND

Anxiety symptoms during public health crises are associated with adverse psychiatric outcomes and impaired health decision-making. The interaction between real-time social media use patterns and clinical anxiety during infectious disease outbreaks is underexplored.

OBJECTIVE

We aimed to evaluate the usage pattern of 2 types of social media apps (communication and social networking) among patients in outpatient psychiatric treatment during the COVID-19 surge and lockdown in Madrid, Spain and their short-term anxiety symptoms (7-item General Anxiety Disorder scale) at clinical follow-up.

METHODS

The individual-level shifts in median social media usage behavior from February 1 through May 3, 2020 were summarized using repeated measures analysis of variance that accounted for the fixed effects of the lockdown (prelockdown versus postlockdown), group (clinical anxiety group versus nonclinical anxiety group), the interaction of lockdown and group, and random effects of users. A machine learning-based approach that combined a hidden Markov model and logistic regression was applied to predict clinical anxiety (n=44) and nonclinical anxiety (n=51), based on longitudinal time-series data that comprised communication and social networking app usage (in seconds) as well as anxiety-associated clinical survey variables, including the presence of an essential worker in the household, worries about life instability, changes in social interaction frequency during the lockdown, cohabitation status, and health status.

RESULTS

Individual-level analysis of daily social media usage showed that the increase in communication app usage from prelockdown to lockdown period was significantly smaller in the clinical anxiety group than that in the nonclinical anxiety group (F1,72=3.84, P=.05). The machine learning model achieved a mean accuracy of 62.30% (SD 16%) and area under the receiver operating curve 0.70 (SD 0.19) in 10-fold cross-validation in identifying the clinical anxiety group.

CONCLUSIONS

Patients who reported severe anxiety symptoms were less active in communication apps after the mandated lockdown and more engaged in social networking apps in the overall period, which suggested that there was a different pattern of digital social behavior for adapting to the crisis. Predictive modeling using digital biomarkers-passive-sensing of shifts in category-based social media app usage during the lockdown-can identify individuals at risk for psychiatric sequelae.

Population health AI researchers' perceptions of the public portrayal of AI: A pilot study

This article reports how 18 UK and Canadian population health artificial intelligence researchers in Higher Education Institutions perceive the use of artificial intelligence systems in their research, and how this compares with their perceptions about the media portrayal of artificial intelligence systems. This is triangulated with a small scoping analysis of how UK and Canadian news articles portray artificial intelligence systems associated with health research and care. Interviewees had concerns about what they perceived as sensationalist reporting of artificial intelligence systems - a finding reflected in the media analysis. In line with Pickersgill's concept of 'epistemic modesty', they considered artificial intelligence systems better perceived as non-exceptionalist methodological tools that were uncertain and unexciting. Adopting 'epistemic modesty' was sometimes hindered by stakeholders to whom the research is disseminated, who may be less interested in hearing about the uncertainties of scientific practice, having implications on both research and policy.