Hanneke Scholten C + S
Colloquium Prof. dr. Nick Allen
Title: Short Term Prediction of Suicidal Thoughts and Behaviors via Mobile Sensing
Abstract: Suicide is one of the leading causes of death among adolescents, but developing effective methods of prevention has been hampered by poor predictive methods, especially short-term prediction of changes in suicidal thoughts and behaviors (STBs). Currently, the most robust predictors of STBs are distal demographic or clinical indicators that have relatively weak predictive value, and provided no insight into short term risk. However, there is an emerging literature on short-term prediction of suicide risk that has identified a number of promising candidates, including (but not limited to) rapid escalation of: (a) emotional distress, (b) social dysfunction (i.e., bullying, rejection), and (c) sleep disturbance. In this presentation I will explore how to capitalize on recent developments in intensive real-time monitoring methods in order to address this fundamental challenge. Smartphone, wearable, and smart home technologies can collect intensive longitudinal assessments monitoring these putative risk factors with minimal participant burden. I will describe our current studies using passive sensing of smartphone sensors to track short term changes in STBs in at risk adolescents, and will describe the complex conceptual, computational, and ethical issues that will need to be resolved before large scale preventative application based on these approaches are feasible. However, if these challenges can be resolved, mobile sensing has the potential to facilitate the development of a new era of just-in time interventions that may pervade support at critical moments and save lives.
Information about the speaker:
Nick Allen is the Ann Swindells Professor of Clinical Psychology at the University of Oregon, where he Director of Clinical Training, and Director of the Center for Digital Mental Health. He is a leading researcher in the area of adolescent mental health, especially for his work on adolescent onset depression. His work has particularly addressed the interactions between multiple risk factors for adolescent emergent mental health disorders, including stress, family processes, brain development, autonomic physiology, genetic risk, immunology, and sleep. More recently, his work has focused on translating risk factors identified in his prospective longitudinal studies into innovative preventative approaches to adolescent mental health. This includes using mobile and wearable technology to monitor risk for poor mental health, using both active and passive sensing methods to provide intensive longitudinal assessment of behavior with minimal participant burden. The ultimate aim of developing these technologies is to facilitate the development of a new generation of “just in time” behavioral interventions for early intervention and prevention of adolescent health problems.
Lecture 1: Monika Lind
Title: The Effortless Assessment of Risk States (E.A.R.S.) Tool: An Interpersonal Approach to Mobile Sensing
Abstract: To predict and prevent mental health crises, we must develop new approaches that can provide a dramatic advance in the effectiveness, timeliness, and scalability of our interventions. However, current methods of predicting mental health crises (eg, clinical monitoring, screening) usually fail on most, if not all, of these criteria. Lucky for us, 77% of Americans carry with them an unprecedented opportunity to detect risk states and provide precise life-saving interventions. Smartphones present an opportunity to empower individuals to leverage the data they generate through their normal phone use to predict and prevent mental health crises. To facilitate the collection of high-quality, passive mobile sensing data, we built the Effortless Assessment of Risk States (EARS) tool to enable the generation of predictive machine learning algorithms to solve previously intractable problems and identify risk states before they become crises. The EARS tool captures multiple indices of a person’s social and affective behavior via their naturalistic use of a smartphone. Although other mobile data collection tools exist, the EARS tool places a unique emphasis on capturing the content as well as the form of social communication on the phone. Signals collected include facial expressions, acoustic vocal quality, natural language use, physical activity, music choice, and geographical location. Critically, the EARS tool collects these data passively, with almost no burden on the user. We programmed the EARS tool in Java for the Android mobile platform. In building the EARS tool, we concentrated on two main considerations: (1) privacy and encryption and (2) phone use impact. The EARS tool offers an innovative approach to passive mobile sensing by emphasizing the centrality of a person’s social life to their well-being. We built the EARS tool to power cutting-edge research, with the ultimate goal of leveraging individual big data to empower people and enhance mental health.
Information about the speaker: Monika Lind is a doctoral student in clinical psychology at the University of Oregon. She works with Dr. Nick Allen and Dr. Michelle Byrne in the Center for Digital Mental Health, and Dr. Jennifer Freyd in the Dynamics Lab. In her primary research, she aims to use mobile sensing and technology-enabled services to detect high-risk states in adolescents and to improve timely access to effective mental health care. Monika has a secondary interest in gendered experiences in adolescence that may contribute to the onset of mood disorders. For her dissertation, Monika will develop a mobile app targeted to adolescents who are experiencing distress and are unsure whether or how to seek treatment. The app, Therabee, will take into account user symptoms and preferences to offer treatment recommendations and facilitate intake scheduling.
Lecture 2: Prof. dr. Marloes Kleinjan
Title: The Clinical Potential of Augmented Reality
Abstract: Augmented reality (AR) is a rapidly-emerging technology that superimposes realistic digital objects onto real-world scenes as viewed in real time through a smartphone, tablet, or headset. Whereas AR has been adopted for retail, entertainment, and professional training uses, it also has potential as a novel, mobile, and efficacious treatment modality for psychological disorders. In particular, extinction-based therapies (e.g., for anxiety and substance use disorders) could utilize AR to present stimuli to clients in their natural environments, thereby enhancing generalizability beyond the laboratory or clinic. To date, the limited psychological literature on AR has mainly focused on the treatment of simple phobias. In this talk, I will describe AR, contrast it with virtual reality, review the theoretical foundation for its relevance to psychotherapies including cue-exposure therapies, and provide examples for the treatment of substance use disorders.
Abstract about the speaker: Marloes Kleinjan works as a professor of Youth Mental Health Promotion at Utrecht University and as program director of the Epidemiology & Research Support program at the Trimbos Institute. She is involved in several major national studies on the mental health and substance use of young people and adults. She is also working on various prevention and intervention projects in the field of mental health and substance use.
Lecture 3: Dr. Sander Bakkes
Title: Personalized Interactive Experiences and Automated Game Design
Abstract: Ideally, artificial intelligence (AI) in (applied) games provides satisfactory and effective game experiences for players regardless of gender, age, capabilities, or experience; it allows for the creation of personalized games, where the game experience is continuously tailored to fit the individual player. In this talk I will highlight which steps have already been taken to the end of tailoring game experiences to the individual player – while the player is still interacting with the game environment -, and I will provide accessible examples of how our research group has already incorporated such adaptive game technology into actual games.
Abstract about the speaker: Sander Bakkes is an Assistant Professor at Utrecht University, the Netherlands. He is a leading contributor to the emerging field of 'Personalized Gaming'. In this field, (psychologically-verified) user models are utilized to automatically generate a personal and meaningful user experience. In previous work, Dr. Bakkes investigated procedural content generation, player behavioral modelling, and adaptive video game artificial intelligence (AI), on which he authored over 50 publications for leading scientific journals, peer-reviewed international conferences, popular media, and a seminal book series. He is a lecturer in Applied Games and Game Design.