Skip to Content



MAPS: Mobile Assessment for the Prediction of Suicide

  • Suicide is the second leading cause of death among adolescents. In addition to deaths, 16% of adolescents report seriously considering suicide each year, and 8% make one or more attempts. Despite these alarming statistics, little is known about factors that confer imminent risk for suicide. The project will include high-risk adolescents (n = 200) aged 13-18 years recruited from outpatient and inpatient clinics: (a) recent suicide attempters with current ideation (n = 70), (b) current suicide ideators with no attempt history (n = 70), and (c) a psychiatric control group with no STB history (n = 60). The Effortless Assessment of Risk States (EARS) tool (see below) will be used to continuously measure variables relevant to key risk domains—emotional distress, social dysfunction, and sleep disturbance—through passive monitoring of participants’ smartphone use. First, we will test between-group differences in risk factors during an initial 2-week period and determine the extent to which risk factors derived from mobile phones improves discrimination over self-reported indicators. Second, we will use statistical techniques to test whether the risk factors improve short-term prediction of STBs (e.g., suicide attempts, hospitalization) during the 6-month follow-up period above and beyond clinical assessments. Third, computational machine learning techniques—based on a priori and learned features—will develop predictive models that utilize the full range of intensive longitudinal data collected by the active and passive monitoring methods to predict group membership and STB outcomes. Ultimately, by leveraging smartphone technology, we aim to improve the short-term STB prediction and provide clinicians and patients with reliable, scalable and actionable tools that will reduce the needless loss of life.

EARS (Effortless Assessment of Risk States)

  • Developments in consumer mobile and wearable computing (e.g., smart phones and fitness trackers) provide a historically novel opportunity to capture individual digital phenotypes (i.e., Jain, Powers, Hawkins, & Brownstein, 2015; Onnela & Rauch, 2016), which are continuously indexed, temporally rich individual-level data at multiple levels of analysis (i.e., voice tone, text message affective content, geolocation, physical mobility, autonomic activity, sleep, and social networks). Our lab has developed a suite of programs, the Effortless Assessment of Risk States (EARS) tool (Lind et al., 2018, JMIR:MH), that integrates these data into a background application on Android and iOS smartphone devices. The EARS tool collects data on language, facial expression, and voice tone along with many other signals as part of the person’s normal daily phone use. This data is then encrypted on the phone and pushed to a HIPAA compliant cloud service for automated analysis of affective states.
  • Based on these developments, in August 2016 our lab was selected to take part in a technology development “sprint” as part of the Opportunity Project, an Obama White House sponsored initiative to create new open digital tools to help communities. During this sprint, we worked on integrating our tool with location based data from open government data bases (e.g., location of nearest mental health services) that could be used in both assessment and intervention. As a result of this. in October 2016, we were invited to the White House to present The EARS tool. See
  • Our lab is currently running the Effortless Assessment of Stressful Environments (EASE) study, in which we are utilizing the EARS tool to quantify digital phenotypes amongst healthy undergraduate students both during the regular term (low-stress) and during exam periods (high-stress) in order to understand which aspects of these data are the best indicators of changes in psychological stress.

TAG (Transitions in Adolescent Girls Study)

  • This study will conduct a comprehensive multilevel investigation of the connections between social cognitive and biological changes during early adolescence, in order to reveal the ways in which these interconnected changes relate to risk for the emergence of a range of mental health problems that are known to be associated with pubertal development (i.e., symptoms of depression, anxiety, and deliberate self-harm). Specifically, we will accomplish this goal by conducting a prospective longitudinal neuroimaging study of adolescent girls including three waves of data collection separated by 18 months (initial N=170, age 11 ± 1 years). At each time point we will assess the following: i) hormones and other sex characteristics; ii) brain structure connectivity; iii) social cognitive brain functioning and behavior (in two paradigms measuring self-evaluation, perspective-taking, and intrinsic value of self-disclosure); and iv) mental health symptoms (particularly of depression, anxiety, and deliberate self-harm). The project will, therefore, inform a mechanistic model of the association between developmental and psychopathological processes during this stage of life, one that will critically inform early intervention and prevention strategies.

T-POT (Transitions in Parenting of Teenagers Study)

  • This study aims to establish the ways in which mothers’ responses to and processing of adolescent interpersonal affective behavior diverge as a function of maternal depression. To this end, we will use microsocial behavioral observation of mother-child interactions, neuroimaging, psychophysiological, and video-mediated recall protocols to identify differences between depressed and non-depressed mothers in cognitive-affective processing of child affective behavior, at the phenomenological, cognitive, psychological and neural levels. We will also examine the manner in, and extent to which, these neurobiological and cognitive-affective responses to adolescent affective behavior are associated with observed parenting and mother-adolescent interactional behavior, as well as the extent to which they account for the well-established association between maternal depression and these outcomes. Finally, we will assess whether, and to what extent, the associations observed in aims 1 and 2 are moderated by well established macro-influences on parenting behavior, including adolescent characteristics, paternal depression, and stressful life conditions.

SHARP (Safe, Healthy, Adolescent Relationships & Peers Study) Neuroimaging Study

  • It is well known that with any intervention there is significant variation between participants in terms of the degree of benefits that they experience. As a result it is important to understand the factors that might determine this variation in intervention outcomes by identifying variables that moderate intervention effects. The SHARP study, which is a large intervention study of which this is a sub-study, uses an intervention strategy targets self regulatory skills, particularly the ability to weigh long terms outcomes versus short terms outcomes in behavioral decision making. Given that these skills show significant developmental change across adolescence, we aim to examine whether adolescent cognitive and brain development might act as salient moderators of response to the intervention. Adolescent maturation is typically operationalized by measuring chronological age, although this measure provide only a modest estimation of psychological maturation, especially during adolescence when individuals at the same age can vary greatly in maturation due to individual differences in the timing of key developmental processes such as puberty and brain development. Accordingly, we are conducting an embedded study with a subset of the individuals taking part in the RCT phase of the study, whereby we will ask them to participate in a brain imaging assessment prior to the initiation of the intervention phase. Using this data to estimate brain maturation, we will explore whether indices of brain development act as salient moderators of intervention effects.


Skip to toolbar