Predicting self-injurious thoughts in daily life using ambulatory assessment of state cognition

Frequency and predictors of virtual hope box use in individuals experiencing suicidal ideation: An ecological momentary assessment investigation

INTRODUCTION

The Virtual Hope Box (VHB) is a smartphone application designed to support emotion regulation when one is distressed, in a crisis, or experiencing suicidal ideation (SI). Initial proof of concept studies indicate that individuals are more likely to use the VHB than traditional hope boxes, and find it both easy to setup and helpful. To our knowledge, no studies have harnessed ambulatory assessment methodology to assess VHB use as it relates to incidence of suicidal thinking.

METHODS

As such, we recruited N = 50 undergraduates who endorsed SI either the past year or past 2 weeks to complete a 10-day investigation. At baseline, participants were oriented to the VHB and instructed on how to use the application. Over the next 10 days, participants responded to prompts five times per day on their personal smartphones regarding their current experiences of SI and stress as well as VHB usage.

RESULTS

Results found that most participants used the VHB at least once, rated its usefulness as high, and rated their perceived likelihood of future use as high. In addition, increases in state SI severity were related to subsequent VHB use.

CONCLUSION

The VHB may be a useful tool for managing crises in undergraduates experiencing suicidal thoughts.

Reflections on the nature of measurement in language-based automated assessments of patients' mental state and cognitive function

Modern advances in computational language processing methods have enabled new approaches to the measurement of mental processes. However, the field has primarily focused on model accuracy in predicting performance on a task or a diagnostic category. Instead the field should be more focused on determining which computational analyses align best with the targeted neurocognitive/psychological functions that we want to assess. In this paper we reflect on two decades of experience with the application of language-based assessment to patients' mental state and cognitive function by addressing the questions of what we are measuring, how it should be measured and why we are measuring the phenomena. We address the questions by advocating for a principled framework for aligning computational models to the constructs being assessed and the tasks being used, as well as defining how those constructs relate to patient clinical states. We further examine the assumptions that go into the computational models and the effects that model design decisions may have on the accuracy, bias and generalizability of models for assessing clinical states. Finally, we describe how this principled approach can further the goal of transitioning language-based computational assessments to part of clinical practice while gaining the trust of critical stakeholders.

Hill L, Kline A, Stanley BH, Interian A. Improving the prospective prediction of a near-term suicide attempt in veterans at risk for suicide, using a go/no-go task

BACKGROUND

Neurocognitive testing may advance the goal of predicting near-term suicide risk. The current study examined whether performance on a Go/No-go (GNG) task, and computational modeling to extract latent cognitive variables, could enhance prediction of suicide attempts within next 90 days, among individuals at high-risk for suicide.

METHOD

136 Veterans at high-risk for suicide previously completed a computer-based GNG task requiring rapid responding (Go) to target stimuli, while withholding responses (No-go) to infrequent foil stimuli; behavioral variables included false alarms to foils (failure to inhibit) and missed responses to targets. We conducted a secondary analysis of these data, with outcomes defined as actual suicide attempt (ASA), other suicide-related event (OtherSE) such as interrupted/aborted attempt or preparatory behavior, or neither (noSE), within 90-days after GNG testing, to examine whether GNG variables could improve ASA prediction over standard clinical variables. A computational model (linear ballistic accumulator, LBA) was also applied, to elucidate cognitive mechanisms underlying group differences.

RESULTS

On GNG, increased miss rate selectively predicted ASA, while increased false alarm rate predicted OtherSE (without ASA) within the 90-day follow-up window. In LBA modeling, ASA (but not OtherSE) was associated with decreases in decisional efficiency to targets, suggesting differences in the evidence accumulation process were specifically associated with upcoming ASA.

CONCLUSIONS

These findings suggest that GNG may improve prediction of near-term suicide risk, with distinct behavioral patterns in those who will attempt suicide within the next 90 days. Computational modeling suggests qualitative differences in cognition in individuals at near-term risk of suicide attempt.