A Prescriptive Analytic Approach to Suicide Prevention
The same shame and stigma associated with depression apply to those at risk for suicide. Often people contemplating suicide mistakenly feel that they are a burden to those around them, making them even less likely to confide their dark thoughts to anyone. By the time someone writes a suicide note, it’s likely too late to intervene.
This tragedy touches far too many lives. Suicide leads all causes of death in all age groups. For people aged 15 to 34, only unintended non-lethal injury occurs more frequently. Between 1999 and 2014, the per capita rate of suicide increased 24 percent. Suicide took the lives of more than 44,000 people in 2015. Within the general population, the suicide attempt rate is about 0.5%.
The Jvion Machine applies artificial intelligence to understand comprehensive clinical, socioeconomic and other data to identify suicide risk within a community or patient population. The Jvion Suicide/Self-harm Vector helps tackle this growing problem by identifying those most at risk of having an emergency department or inpatient visit due to self-harm, suicidal ideation, suicide attempt, or suicide in the next six months.
Here’s one example of how AI-enabled prescriptive analytic technology, tuned rapidly to focus on self-harm and suicide risk, can identify risks that might otherwise go undetected. The Association for Suicide Prevention lists increased alcohol use among many factors that indicate suicide risk. A patient undergoing routine bloodwork might return an elevated liver enzyme panel—a possible marker for excessive alcohol intake. As an isolated data point, it may not raise alarm for depression or suicidal thoughts, especially if the patient isn’t forthcoming about his or her drinking habits. The doctor might schedule follow up such as a hepatitis panel, or simply tell the patient they will continue to monitor the enzyme counts in future visits.
The Jvion Machine, however, understands that clinical data as part of a comprehensive patient picture. Paired with other clinical and exogenous data, the machine can see risk that might go unseen (or unspoken) otherwise. It can identify the 5 percent of people who are at more than 10X risk of a suicide attempt. For 10,000 patients, the machine can narrow the scope of clinical action to the 500 who are at risk of whom 50 will attempt suicide. Recommendations for intervention focus on screening and matching individual patients with the most effective resources.
Suicide is the ultimate tragedy for victims and their loved ones. New frontiers in AI-enable prescriptive technology are providing hope and opportunities for prevention and intervention we couldn’t have imagined even a few years ago. It’s truly a miracle of healing potential.
- By identifying this patient’s challenges with medication compliance, Case Managers were able ensure medication adherence and lower the risk of depr...
Don’t Believe the Hype: Why You Should Second Guess Predictive Solutions that Claim to Impact Patient OutcomesPredictive analytic companies have been latching on to the idea of “impactability” and it is mask...