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.

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.

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.

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.

Suicide risk is high in the 30 days after discharge from psychiatric hospital, but knowledge of the profiles of high-risk patients remains limited.

To examine sex-specific risk profiles for suicide in the 30 days after discharge from psychiatric hospital, using machine learning and Danish registry data.

We conducted a case–cohort study capturing all suicide cases occurring in the 30 days after psychiatric hospital discharge in Denmark from 1 January 1995 to 31 December 2015 (n = 1205). The comparison subcohort was a 5% random sample of all persons born or residing in Denmark on 1 January 1995, and who had a first psychiatric hospital admission between 1995 and 2015 (n = 24 559). Predictors included diagnoses, surgeries, prescribed medications and demographic information. The outcome was suicide death recorded in the Danish Cause of Death Registry.

For men, prescriptions for anxiolytics and drugs used in addictive disorders interacted with other characteristics in the risk profiles (e.g. alcohol-related disorders, hypnotics and sedatives) that led to higher risk of postdischarge suicide. In women, there was interaction between recurrent major depression and other characteristics (e.g. poisoning, low income) that led to increased risk of suicide. Random forests identified important suicide predictors: alcohol-related disorders and nicotine dependence in men and poisoning in women.

Our findings suggest that accurate prediction of suicide during the high-risk period immediately after psychiatric hospital discharge may require a complex evaluation of multiple factors for men and women.

This study evaluated whether natural language processing (NLP) of psychotherapy note text provides additional accuracy over and above currently used suicide prediction models.

We used a cohort of Veterans Health Administration (VHA) users diagnosed with post-traumatic stress disorder (PTSD) between 2004–2013. Using a case-control design, cases (those that died by suicide during the year following diagnosis) were matched to controls (those that remained alive). After selecting conditional matches based on having shared mental health providers, we chose controls using a 5:1 nearest-neighbor propensity match based on the VHA's structured Electronic Medical Records (EMR)-based suicide prediction model. For cases, psychotherapist notes were collected from diagnosis until death. For controls, psychotherapist notes were collected from diagnosis until matched case's date of death. After ensuring similar numbers of notes, the final sample included 246 cases and 986 controls. Notes were analyzed using Sentiment Analysis and Cognition Engine, a Python-based NLP package. The output was evaluated using machine-learning algorithms. The area under the curve (AUC) was calculated to determine models' predictive accuracy.

NLP derived variables offered small but significant predictive improvement (AUC = 0.58) for patients that had longer treatment duration. A small sample size limited predictive accuracy.

Study identifies a novel method for measuring suicide risk over time and potentially categorizing patient subgroups with distinct risk sensitivities. Findings suggest leveraging NLP derived variables from psychotherapy notes offers an additional predictive value over and above the VHA's state-of-the-art structured EMR-based suicide prediction model. Replication with a larger non-PTSD specific sample is required.