The Value of SDoH Analytics


How SDoH data can lead to better health outcomes and cost reduction

blog image analytics SDoH understanding revenue

Healthcare providers must deliver outstanding patient care to achieve positive health outcomes, but the challenge here is that even access to the best healthcare services won’t result in quality patient outcomes if social determinants of health (SDoH) is not an integral part of patient care plans.

Studies show that if SDoH isn’t a component of patient care, the likelihood of avoidable hospital readmissions, missed appointments or failure to pick up a prescription can lead to increased patient health costs. So the ability to identify at-risk patients or patients currently facing unmet social needs enables providers to apply early interventions and offer solutions that are unique to those patient populations, which can lead to better overall outcomes.

Patient care is evolving through the collection and analysis of holistic health data. Analytics that include patient-level SDoH datasets can enable healthcare organizations to create personalized, comprehensive care plans. When coupled with macro-level population health datasets, providers have a more robust view of the types of needs experienced by their patient populations, allowing for interventions that focus on quality care and creating healthier communities.

Providers and even payers have already begun to integrate patient-level and population-level data to develop care plans that include SDoH.

For example, the nonprofit health plan, Kaiser Permanente, has prioritized the expansion of healthcare into SDoH by committing to investing $200 million into addressing housing instability and homelessness in its communities. Based in California, Sutter Physician Services has also considered the value of addressing SDoH for its patient population. Specifically, how SDoH presents transportation challenges for many patients. As a result, Sutter Physician Services has partnered with Uber and Lyft to make sure patients can attend appointments.

But how does SDoH data and analytics impact the revenue of healthcare organizations and what can be done to improve it? Let’s look at two examples that use both to reduce costs and improve patient outcomes.

Geisinger and Food Insecurity

One example that blends both patient-level and population-level health data to address SDoH and lower patient care costs successfully is Geisinger’s Fresh Food Farmacy program.

What SDoH does it address?

Food insecurity, or a lack of access to nutritionally, adequate food, is the primary SDoH domain that Geisinger aims to address. Because food insecurity is widespread, impacting one in eight American adults and one in six children, individuals with restricted incomes often turn to inexpensive foods that lack nutrients, which can both cause and exacerbate diabetes.

How was population-level health data used?

Patients with type 2 diabetes that have trouble managing their condition were the target population for this program. Using a combination of screening questionnaires and specific EMR record datasets, a base group was identified. From there, nearly 30 percent of the initial diabetic population (base group) were eligible for the program and subsequently enrolled.

What was the financial impact?

Operationally, the Fresh Food Farmacy runs at the cost of about $2,400 per patient per year. Throughout 18 months, claims data shows that costs for pilot patients dropped by 80 percent, from an average of $240,000 per member per year to $48,000 per member per year.

University of Illinois Hospital & Housing

A second example where patient-level and population-level health data came together to address SDoH and reduce costs is the University of Illinois Hospital’s Better Health Through Housing program.

What SDoH does it address?

Lack of housing or inadequate housing has been shown to have severe implications on health. Without a home or adequate housing, individuals face health issues that could lead to chronic homelessness, further complicate existing health conditions or lead to the development of new conditions.

How was population-level health data used?

Patients who were experiencing homelessness and who could benefit from housing support were selected. Because homeless patients often suffer from chronic illnesses at disproportionate rates, such as mental illness, chronic obstructive pulmonary disease (COPD), HIV/AIDS, traumatic brain injury and others, they also tend to have high visits to the emergency department (ED)—eight times or more annually.

What was the financial impact?

UOI Hospital invested $250,000 into the 2015 pilot program and had seen average per patient monthly costs drop about 18 percent, from $5,879 per month before being placed into housing to $4,785 after being placed into housing, since the program launched. This program has improved the health of homeless individuals and reduced costly ED visits too.

By combining patient-level and population-level health data and analytics, healthcare organizations have the potential to address the needs of patients and achieve better health outcomes.

Topics: social determinants of health

Related posts