Digital Monitoring of Impulsivity as a Proximal Risk Factor for Suicidal Outcomes

Background: Suicide is a leading cause of death, but progress in suicide prevention has been slowed by critical gaps in knowledge about predictors of imminent risk. Impulsivity is an ideal candidate for a proximal risk factor: it is a known transdiagnostic distal risk factor, it fluctuates over time within individuals, and it is a

modifiable target for intervention. Existing suicide research, however, has not examined multiple components of real-time, state impulsivity over high-risk periods — a necessary step to test (a) whether impulsivity reduces ability to resist suicidal urges in real time, (b) which components of this multi-faceted construct are associated

with suicide risk and when, and (c) whether patterns differ for individuals or subgroups. Research: We propose a fine-grained, intensive longitudinal investigation of associations between components of impulsivity and suicidal urges in two samples at high risk for suicide. Aim 1 will involve secondary data analysis of a digital

monitoring study of individuals presenting to an emergency department with suicidal thoughts to analyze real- time associations between impulsivity, suicidal urges, and ability to resist suicidal urges. We will test whether state impulsivity is predictive beyond the effect of trait impulsivity. In Aim 2, we will conduct a digital monitoring

study of 140 individuals hospitalized for suicidal thoughts to assess multiple components of state impulsivity using self-report, mobile tasks, and passive phone data, and we will test specific associations with suicidal urges and ability to resist them in real time. In Aim 3, we will compare group-level, subgroup-level, and

personalized models of these data using a combination of inferential statistics (network modeling) and predictive analytics (machine learning). This work will allow us to dramatically improve understanding of a key transdiagnostic process, laying the groundwork for development of detection and intervention strategies

targeted at specific elements of impulsivity at an optimal timescale. Candidate’s Career Development, Goals, and Environment: This proposal’s research aims and the candidate’s career development will be supported by the many resources available at Massachusetts General Hospital/Harvard Medical School as well as formal

training and mentorship in (T1) digital monitoring of patients at high risk for suicide, (T2) advanced multivariate longitudinal data analysis, (T3) digital phenotyping, and (T4) preparing for an intervention-focused R01 submission. The mentorship team includes Mentor Dr. Jordan Smoller, leading expert in precision psychiatry

and predictive analytics; Co-Mentors Dr. Matthew Nock, leader in the study of suicide; and Dr. Evan Kleiman, expert in real-time monitoring and digital phenotyping of suicidal states; and Consultants Dr. Aidan Wright, expert in multilevel and personalized statistical modeling; Dr. JP Onnela, leader in digital phenotyping and

statistical network science; and Dr. Laura Germine, pioneer in mobile task assessment. This award will provide the candidate with advanced training and skills necessary to launch an independent research program focused on using mobile technology to advance understanding of impulsive decision-making and suicide.