To achieve quality health outcomes, organizations must deliver excellent patient care.
However, patients may suffer poor outcomes - even if they have access to the best care in the world - if providers fail to consider social determinants of health, including factors such as socioeconomic status, education, social network support, access to care, access to transportation and employment.
The Centers for Disease Control notes that social determinants of health have a far greater impact on outcomes than the actual delivery of health services. Social and economic factors affect a wide range of health and quality-of-life issues that influence healthcare costs, as well as outcomes. As the industry continues to transition to value-based care models that reward providers for delivering high-quality, cost-effective care, providers must consider the social and economic conditions that impact the well-being of individual members.
Why social determinants of health matter
Providers need deep insights into the health of their patient populations in order to achieve clinical and financial success in a value-based care world. For example, under many value-based arrangements, providers are penalized when a patient is readmitted to the hospital within 30 days of discharge. To minimize this risk, hospitals must identify patients who are more likely to be readmitted and proactively take measures to keep those individuals healthy.
Providers can assess risk in a variety of ways – though some methods yield more precise results. A care manager could simply review the patient’s discharge summary and current medical record to get a snapshot of their health status. For a deeper dive, the organization could consult aggregated data to identify the typical social and economic conditions for individuals living in the patient’s same zip code. To more accurately assess an individual’s 30-day readmission risk- or the risk of an adverse event - providers need to look beyond a summary of patient medical treatments and aggregated population statistics, and analyze patient-specific social determinants of health data.
Consider, for example, a patient who is struggling financially and unable to pay for medication, or an individual who lacks access to reliable transportation to doctor appointments for follow-up care. Both might be at higher risk for readmission or an adverse event because of their inability to adhere to recommended care plans. Similarly, a patient who lives alone without in-home assistance may suffer a setback if she doesn’t have anyone to verify that she is eating properly and taking medications as prescribed. When providers are able to identify at-risk patients, they can intervene early and offer solutions that address an individual’s specific needs, thus increasing the likelihood of positive outcomes.
Social determinants of health data can also help predict the impactability of services. Through the use of analytics, a health system might learn that that a relatively expensive home visit is the more impactful option than a less expensive follow-up phone call for a patient who is known to live alone. In contrast, the analytics also identify which patients will benefit from less expensive calls.
Mission Health Partners: improving risk predictions
Mission Health Partners (MHP) is a Medicare Shared Savings Program (MSSP) Accountable Care Organization (ACO) committed to improving the quality of healthcare for its Medicare beneficiaries and to reducing the cost of care delivery. In an effort to meet their quality of care and financial objectives, MHP adopted a social determinants model of care coordination that focuses on identifying gaps in care, including those created by socioeconomic factors.
MHP serves over 90,000 commercial and ACO members across 18 North Carolina counties. Social determinants of have been key to the organization’s successful management of its patient population, according to MHP’s Medical Director, MD Rob Fields, MD. “It’s hard to manage care on a clinical basis without an appreciation of social determinants of health, which are a driver of outcomes. When high-risk patients are identified, we’re able to partner with agencies in the region to close gaps so that patients are empowered to better manage their care.”
MHP’s social determinants approach is making a difference. The ACO, which scored over 97 percent for quality for 2016, employs an upstream approach to reduce utilization and manage post-acute care costs. They rely heavily on analytics to identify their highest risk patients, as well as to predict which individuals would be most positively impacted by specific services. This allows MHP to not only find the patients at highest risk for an adverse event but also identify those whose outcomes would most likely be improved with specific interventions.
Unlike most organizations that just rely on claims and clinical data to predict population risk, MHP incorporates social determinants of health data into its analytics reporting tool. MHP has seen a 25 percent increase in the accuracy of its predictions, allowing MHP to focus on the specific programs and services that have the biggest impact on individual patient outcomes.
Armed for value-based care success
Predictive modeling tools that take into account social determinants of health are essential for providers and health systems working to achieve financial and clinical goals. By leveraging social determinants of health data, organizations can glean expanded insights into their patients’ health and create more impactful care plans.
MHP is already realizing value from its social determinants model of care coordination. In order to drive quality outcomes and achieve greater success under value-based care, health systems must arm themselves with more comprehensive information on the factors influencing patient health and outcomes.
By Michael Cousins, PhD, Chief Analytics Officer at Lumeris
The views, opinions and positions expressed within these guest posts are those of the author alone and do not represent those of Becker's Hospital Review/Becker's Healthcare. The accuracy, completeness and validity of any statements made within this article are not guaranteed. We accept no liability for any errors, omissions or representations. The copyright of this content belongs to the author and any liability with regards to infringement of intellectual property rights remains with them.