How social determinants of health and analytics can aid suicide prevention
VA programs to assist veterans may begin to incorporate relevant socioeconomic information to identify those who are at risk of harming themselves.
There’s growing urgency around the need to take proactive steps to prevent suicides by veterans. An average of 20 Veterans per day committed suicide in 2014, according to the Department of Veterans Affairs. Veterans, who constitute 8.5 percent of the U.S. population, accounted for 18 percent of all suicide deaths.
Despite the obvious challenge and risk of mortality, suicide prevention for veterans is a challenging service to provide. However, emerging interest in new types of social data—paired with medical information contained in veterans’ health records—holds new promise in assisting clinicians to find those who are at risk. And the increased use of analytics also may be able to sift through mounds of seemingly unrelated medical data to find crucial correlations that may identify suicide risks that warrant intervention.
Many behavioral experts say data is crucial in understanding the risks of suicide, and anticipating and intervening before something dire happens. The difference between an individual falling victim to suicide or not often is whether someone can intervene and prevent that individual from taking the ultimate step.
The Trump Administration has taken an important step toward improving veteran suicide prevention in issuing an Executive Order expanding the availability of mental health coverage. In doing so, the former VA-Secretary noted that veterans were most vulnerable to suicide during the 12-month period after leaving active duty service.
There is no simple solution for preventing veterans from committing suicide—people are complicated. But, that may be where we should begin: looking at the whole person.
The Veterans Health Administration has set a goal to increase the percent of veterans targeted through predictive modeling that receive core recommended interventions from 57 percent to 90 percent by Sept. 30, 2019. At the same time, it is critical that VA leverages third-party data in their efforts because it is complicated to locate and reach out to veterans. An estimated 60 percent of Veterans receive their care outside of the VA.
Socioeconomic data, often called Social Determinants of Health (SDOH), is the “X factor” needed to help identify who needs help. SDOH data includes:
Consider the following example: a Veteran visits his or her provider—whether that’s inside or outside of the VA—and complains of trouble sleeping while suffering increased stress. Those factors alone may or may not cause the provider concern. However, if the provider knew the same individual had high risk factors in his/her life—such as a recent divorced, secured a motorcycle license, had indications of financial distress and was living with parents—all linked to the individual through public records—a clearer picture emerges of the individual’s risk for suicide.
By looking at an individual through the lens of medical claims and socioeconomic factors, healthcare professionals have a better chance in intervening before it is too late.
As the VA considers suicide intervention and prevention approaches, SDOH data will increasingly become an important part of the equation. Using SDOH data, linking and analytics to identify previously unseen relationships between socioeconomic factors and healthcare offers profound opportunities to intervene and help prevent negative health outcomes.
But this type of linking illustrates the danger posed by siloed medical data, which, by itself, can tell only part of the suicide risk a veteran may be experiencing. It is critical that VA integrates third-party SDOH data into its analysis of medical data to predict risk.
SDOH has opened up a world of probabilistic matching to improve preventative care for veterans, offering the potential to save lives.
Despite the obvious challenge and risk of mortality, suicide prevention for veterans is a challenging service to provide. However, emerging interest in new types of social data—paired with medical information contained in veterans’ health records—holds new promise in assisting clinicians to find those who are at risk. And the increased use of analytics also may be able to sift through mounds of seemingly unrelated medical data to find crucial correlations that may identify suicide risks that warrant intervention.
Many behavioral experts say data is crucial in understanding the risks of suicide, and anticipating and intervening before something dire happens. The difference between an individual falling victim to suicide or not often is whether someone can intervene and prevent that individual from taking the ultimate step.
The Trump Administration has taken an important step toward improving veteran suicide prevention in issuing an Executive Order expanding the availability of mental health coverage. In doing so, the former VA-Secretary noted that veterans were most vulnerable to suicide during the 12-month period after leaving active duty service. There is no simple solution for preventing veterans from committing suicide—people are complicated. But, that may be where we should begin: looking at the whole person.
The Veterans Health Administration has set a goal to increase the percent of veterans targeted through predictive modeling that receive core recommended interventions from 57 percent to 90 percent by Sept. 30, 2019. At the same time, it is critical that VA leverages third-party data in their efforts because it is complicated to locate and reach out to veterans. An estimated 60 percent of Veterans receive their care outside of the VA.
Socioeconomic data, often called Social Determinants of Health (SDOH), is the “X factor” needed to help identify who needs help. SDOH data includes:
- Social and community context (such as accidents, crimes, weapons and sporting licenses, voter registration and relatives/associations)
- Neighborhood and built environment (for example, household demographics, housing types, crime and income indexes)
- Economic stability (factors including address stability, assets, income, professional licenses, liens and bankruptcies)
- Education (suchas the level, quality and area of study)
Consider the following example: a Veteran visits his or her provider—whether that’s inside or outside of the VA—and complains of trouble sleeping while suffering increased stress. Those factors alone may or may not cause the provider concern. However, if the provider knew the same individual had high risk factors in his/her life—such as a recent divorced, secured a motorcycle license, had indications of financial distress and was living with parents—all linked to the individual through public records—a clearer picture emerges of the individual’s risk for suicide.
By looking at an individual through the lens of medical claims and socioeconomic factors, healthcare professionals have a better chance in intervening before it is too late.
As the VA considers suicide intervention and prevention approaches, SDOH data will increasingly become an important part of the equation. Using SDOH data, linking and analytics to identify previously unseen relationships between socioeconomic factors and healthcare offers profound opportunities to intervene and help prevent negative health outcomes.
But this type of linking illustrates the danger posed by siloed medical data, which, by itself, can tell only part of the suicide risk a veteran may be experiencing. It is critical that VA integrates third-party SDOH data into its analysis of medical data to predict risk.
SDOH has opened up a world of probabilistic matching to improve preventative care for veterans, offering the potential to save lives.
More for you
Loading data for hdm_tax_topic #better-outcomes...