Robert Kneschke -

How an EHR Suicide Risk Assessment Tool Can Streamline Workflows

The EHR suicide risk assessment tool recorded 129 attempts for 85 individuals at a major health system.

An EHR suicide risk assessment tool can accurately predict suicide attempts and also mitigate clinician burnout in a non-psychiatric medical facility, according to a study published in JAMA Network Open.

Suicide prevention starts with risk identification and prognostication, both of which typically need face-to-face screening and provider interaction. However, behavioral health issues are an underfunded and overlooked area of the healthcare industry.

Although most suicide risk models are related to face-to-face screening data, it is difficult for a provider to rely on or optimize the clinical workflow, the study authors wrote.

“In some hospitals, universal screening occurs in the emergency department alone,” the study authors explained. “A model reliant solely on routine, passively collected clinical data, such as medication and diagnostic data, might scale to any clinical setting regardless of screening practices. Few real-world data exist on successes and pitfalls of translating such models into operational clinical systems in the presence or absence of universal screening.”

To improve care quality and reduce clinician burden, the research team implemented a real-time suicide risk prediction platform into the Vanderbilt Medical Center (VUMC) EHR system at its inpatient, emergency department, and ambulatory surgery areas.

The researchers observed 115,905 suicide predictions for 77,973 patients over 296 days. Overall, the solution recorded 129 suicide attempts for 85 individuals.

Through the first five months, suicide predictions were miscalibrated. After integrating logic recalibration utilizing data from those five months, the tool improved over the following five months.

“This study validated performance of a published suicide attempt risk model using real-time clinical prediction in the background of a vendor-supplied EHR,” wrote the study authors.

“Primary findings include accuracy at scale regardless of face-to-face screening in nonpsychiatric settings. We note feasible [number needed to screen] NNS in the highest predicted risk quantiles with potential for reduced screening workload for those at lowest risk. Overall performance was not sensitive to temporal length of EHRs. The decision of minimum length of EHR to display an alert or prediction for an individual patient, however, will be the subject of future decision support testing,” the study authors continued.

Implementing this tool into the EHR could impact screening practices, clinical decision-making, and care coordination, said the research team.

False negative and false positive screenings were considered a major weakness of EHR suicide risk tools.

“Here, we note very low false-negative rates in the lowest risk tiers both within (0.02%) and without (0.008%) universal screening settings,” the study authors explained. “Assuming that face-to-face screening takes, on average, 1 minute to conduct, automated screening for the lowest quantile alone would release 50 hours of clinician time per month.”

The study authors recommended clinical intervention to evaluate new symptoms, worsening symptoms, or life stressors that the tool cannot capture. Linking clinical intervention with the EHR tool could result in improved patient care.

EHR suicide risk tools could help enable longitudinal monitoring for individuals with longer-term suicide risk, such as one-to-two years and not 30 days.

“Current care coordination in many systems relies on manually curated patient tracking and local workflows by individual clinics or clinicians,” wrote the study authors. “Automated risk stratification with decision support might ameliorate challenges such as responding to messages from patients unfamiliar to the nurse or covering clinician, prompting telephone calls to those identified at risk who miss scheduled appointments, and facilitating coordinated care across disparate clinical departments.”

Overall, the study authors said scalable, real-time suicide risk prediction is possible through multidisciplinary collaboration.

“It requires careful pairing with low-cost, low-harm preventive strategies in a pragmatic trial to be evaluated for effectiveness in preventing suicidality in the future,” the study authors concluded.

Next Steps

Dig Deeper on Interoperability in healthcare

Cloud Computing
Mobile Computing