# A Pilot Study Using Frequent Inpatient Assessments of Suicidal Thinking to Predict Short-Term Postdischarge Suicidal Behavior

## TL;DR

This study shows that tracking changes in suicidal thoughts during hospitalization can better predict suicide attempts after discharge compared to traditional methods.

## Contribution

The study introduces dynamic modeling of real-time suicidal thinking as a novel approach to improve postdischarge suicide risk prediction.

## Key findings

- Models using dynamic changes in suicidal thoughts had the highest predictive accuracy (AUC of 0.89).
- Rapid fluctuations in suicidal thinking were the strongest predictors of postdischarge suicide attempts.
- Survey noncompletion emerged as an important predictor of suicide attempts after discharge.

## Abstract

Can prediction of suicide attempts after psychiatric hospitalization be improved using frequent assessments of the level and variability of an individual’s suicidal thoughts?

In this prognostic study of 83 adult psychiatric inpatients, prediction of posthospital suicide attempts was fair when using only baseline data, improved in a model using mean level of suicidal thinking during hospitalization, and improved further in a model including dynamic features of suicidal thoughts.

These findings suggest that data on real-time, dynamic changes in suicidal thoughts could improve prediction of suicide attempts during the high-risk period following psychiatric hospitalization.

This prognostic study tests whether modeling dynamic changes in real-time suicidal thoughts during psychiatric hospitalization can improve predictions of postdischarge suicide attempts vs using only baseline data or using the mean level of real-time suicidal thoughts during hospitalization.

The weeks following discharge from psychiatric hospitalization are the highest-risk period for suicide attempts. Real-time monitoring of suicidal thoughts via smartphone prompts may be more indicative of short-term risk than a single, cross-sectional assessment.

To test whether modeling dynamic changes in real-time suicidal thoughts during psychiatric hospitalization can improve predictions of postdischarge suicide attempts vs using only baseline (ie, admission) data or using the mean level of real-time suicidal thoughts during hospitalization.

In this prognostic study, 83 adults recruited from the inpatient psychiatric unit at Massachusetts General Hospital completed ecological momentary assessment surveys of suicidal thinking 4 to 6 times per day during hospitalization as well as brief follow-up surveys assessing suicide attempts at 2 and 4 weeks after discharge. Participants completed at least 3 real-time monitoring surveys. Inclusion criteria included hospitalization for suicidal thoughts and/or behaviors and English fluency. Data were collected from January 2016 to December 2018 and analyzed from January to December 2020.

The primary outcome was suicide attempt in the month after discharge.

Of 83 participants (mean [SD] age, 38.4 [13.6] years; 43 [51.8%] male participants; 69 [83.1%] White individuals), 9 (10.8%) made a suicide attempt in the month after discharge. Mean cross-validated AUC for elastic net models revealed predictive accuracy was fair for the model using baseline data (area under the curve [AUC], 0.71; first to third quartile, 0.55-0.88), good for the model using the mean level of real-time suicidal thoughts during hospitalization (AUC, 0.81; first to third quartile, 0.67-0.91), and best for the model using dynamic changes in real-time suicidal thoughts during hospitalization (AUC, 0.89; first to third quartile, 0.81-0.97); this pattern of results held for other classification metrics (eg, accuracy, positive predictive value, Brier score) and when using different cross-validation procedures. Features assessing rapid fluctuations in suicidal thinking emerged as the strongest predictors of posthospital suicide attempts. A final set of models incorporating percentage missingness further improved both the mean (mean AUC, 0.93; first to third quartile, 0.90-1.00) and dynamic feature (mean AUC, 0.93; first to third quartile, 0.88-1.00) models.

In this study, collecting real-time data about suicidal thinking during the course of hospitalization significantly improved short-term prediction of posthospitalization suicide attempts. Models including dynamic changes in suicidal thinking over time yielded the best prediction; features that captured rapid changes in suicidal thoughts were particularly strong predictors. Survey noncompletion also emerged as an important predictor of posthospitalization suicide attempts.