Mental health is one of the most challenging issues facing our society due to the high prevalence of mental illness and the devastating effects it has on the individual and society. For instance, in 2020, one individual died by suicide every 40 seconds; by 2030, death by suicide will be the #1 disease burden. Common risk factors for poor mental health and wellbeing are high levels of stress and anxiety, sleep deprivation, and loneliness. These factors are relevant to prevention, early intervention, and the support of treatment. Also, chronic mental illnesses such as bipolar disorder, schizophrenia, and substance abuse require long-term self-management and monitoring to avoid deterioration of an individual’s mental health and wellbeing. This has led, in recent years, to an increase in the interest and exploration of the use of pervasive technologies such as mobile computing and sensors with machine learning for detecting symptoms, assisting in the diagnosis of mental health problems, and for improving access to, engagement with, and the outcomes of therapeutic treatment. They promise to offer new routes for improving the identification of risk factors, the prediction of disease progression, and the development of personalized health interventions.
Despite great potential, the realization of effective pervasive technologies for mental health remains extremely challenging. How can pervasive computing help diagnosis, treatment, and management for mental health? What are the gaps between technological innovations, and what is needed in clinical settings? How should we develop and evaluate pervasive technologies to help decision-making and ensure safety, accuracy, and fairness? How can we develop privacy-preserving pervasive computing systems for mental health?
This special issue seeks to discuss novel approaches, opportunities, and challenges for developing effective, ethical, and trustworthy pervasive computing technology for mental health. The guest editors invite original and high-quality submissions addressing any aspect of the role of pervasive computing in supporting mental health. Ethical dimensions of the research should be considered in all submissions. Review or summary articles—for example, critical evaluations of the state of the art, or an insightful analysis of established and upcoming technologies—may be accepted if they demonstrate academic rigor and relevance.
Topics of interest include, but are not limited to:
- Sensing, signal processing, and machine learning algorithms and applications for detecting and predicting mental health risks, diagnosing mental illness, discovering patient subtypes, or intervening in mental health and wellbeing
- Design and implementation of privacy-preserving pervasive computing platforms to collect, analyze, and manage human biobehavioral data
- Investigating new methodologies for intervention (such as conversational agents, smartphone app-based therapy, and augmented/virtual reality)
- Evaluation of pervasive computing technology to better understand factors related to mental health disorders and treatment efficacy
- Development of robust models that can handle sparsity of physiological, behavioral, and social data; handle label uncertainty; and infer mental health status and related biobehavioral markers
- Methods for sustaining user adherence and engagement over long periods of time
- Technology deployment in low-income communities/countries
- Design interfaces, interactions, and feedback that incorporate pervasive computing for patients and other stakeholders
- Development of human-in-the-loop pervasive computing technology to support clinical decision-making
- Challenges in conducting pervasive computing and mental health research in real-world settings or integrating pervasive computing technologies into existing healthcare infrastructures and government policy
- Evaluation of ethics, fairness, and bias aspects in developing pervasive computing technologies for mental health
Articles submitted to IEEE Pervasive Computing should not exceed 6,000 words, including all text, abstract, keywords, bibliography, biographies, and table text. The word count must include 250 words for each table and figure. References should be limited to at most 20 citations (40 for survey papers). Authors are encouraged, but not required, to use a template for submission (accepted articles will ultimately be typeset by magazine staff for publication). You can read the full Author Guidelines here.
In addition, for this special issue, we invite submissions of 300-word case studies. These should describe timely projects, systems, and activities that are relevant to this special issue. Case studies should describe the motivation and objectives of the work, highlight the deployment characteristics, and summarize any preliminary findings or results if available. We are happy to receive case studies for ongoing work. The accepted case studies will be curated and combined into a single report that will be published in this special issue. Case studies should be submitted using the same process as abstracts, and they should include an in-text reference or link that provides more information about the case study or project.
Manuscripts should not be published or currently submitted for publication elsewhere. When you are ready to submit, please go to https://mc.manuscriptcentral.com/pc-cs.
Contact the guest editors at firstname.lastname@example.org.
- Akane Sano (Rice University, USA)
- Mirco Musolesi (University College London, United Kingdom)
- Gavin Doherty (Trinity College Dublin, Ireland)
- Thomas Vaessen (KU Leuven, Belgium)