How analytics at the point-of-care can help close SDOH gaps

Digital technology has exponentially increased the amount of data available to clinicians, which on the surface is a great thing. When health care providers have more information about the person sitting in their examination room (or on their telehealth monitor), they can make evidence-based care decisions that produce better patient outcomes while increasing their efficiency.

However, for this to work, the data has to meet some important standards. First, it must be timely and relevant to the clinician at the point of care. Second, the data must be easily accessible and well-organized. And finally, it must be accurate, comprehensive and unbiased. Failure in any of these three areas is usually where things go awry in health care. In fact, a breakdown in any one of these areas can result in medical errors, worsening quality and decreasing provider efficiency.

Raw data by itself is of limited value and may lead to wasted provider time and diminished quality of care. To unlock the clinical and operational value of data from disparate sources – such as wearables, at-home medical devices, labs, payers, and other providers–many health care organizations are turning to advanced analytics to uncover patterns that can inform treatment decisions and identify ways to reduce costs. This is important as providers transition to value-based care (VBC) revenue models that reward outcomes and better control of costs and utilization.

Addressing Social Determinants of Health with Analytics

Clinicians provide better care when they understand the social and environmental factors that significantly affect the health of their patients. For example, knowing the neighborhood where a patient lives, whether the patient is employed, has access to transportation, or has food insecurities can give providers a holistic view of the patient that can’t be obtained from measurements of vital signs. These social determinants of health (SDOH) such as income, education, race/ethnicity, sexual orientation/gender identity and literacy, have been found to be the most important indicators of health. Thus, clinicians must have access to this information to meaningfully improve health outcomes and address health disparities.

A 360-degree view of the patient also is imperative for providers who are moving to alternative payment models that reward better patient outcomes and lower the cost of care. These new care delivery models require SDOH data to understand the overall health care needs and risks within a defined population.

Leveraging advanced analytics enables clinicians to quickly sift through volumes of data–including SDOH–to get actionable information at the point of care. Here are six ways analytics at the point of care can improve patient care:

Enabling evidence-based clinical decisions. When clinicians have full, accurate, and well-organized patient data at the point of care, they are far more likely to make decisions that result in better patient outcomes. Real-time advanced analytics provide clinicians with insights into a patient’s current health status, medical history, and non-clinical factors such as SDOH.

Identifying non-clinical factors that drive health inequities and impact patient outcomes. Capturing and analyzing SDOH data at the point of care helps providers recognize whether a patient has issues with food access, housing insecurity, lack of transportation, physical danger and other non-clinical factors that can affect individual health.

Armed with this information, as well as additional information gleaned during the patient’s visit, clinicians can offer actionable recommendations and referrals to community-based support programs. For example, if a clinician determines through analytics data that a patient lives in a food desert, it creates an opportunity for a conversation about food assistance programs and local food pantries.

Closing care gaps by addressing health behaviors. Tobacco use is far higher in some regions of the U.S. than others, and among certain population groups such as low-income individuals, military veterans, lesbian/gay/bisexual adults and people with behavioral health issues. Clinicians at the point of care can use analytics to identify patients at potentially higher risk of unhealthy behaviors and refer them to treatment, support groups or even clinical trials.

Gaining a meta view of the population. Advanced analytics can process data from all people treated at a health care facility to flag those who may need treatment for a chronic condition that has gone unchecked because they are overdue for an appointment with their primary care provider or a specialist. Health care organizations can reach out to these patients to schedule an appointment and determine whether they are adhering to prescribed medications.

Accelerating the transition to value-based care models. Information and insights provided through advanced analytics can improve operational efficiency across a health care organization. This is critical as the health care system transitions from a fee-for-service reimbursement model to one based on improving care while controlling costs. For example, by having the data they need at the point of care, clinicians can avoid the costs of duplicate testing because they have access to previous test results and don’t have to rely on patients to fill in the gaps.

Enabling team-based care delivery. The future of high-quality care delivery will depend upon interdisciplinary care teams working together from the same information and care plan. This type of coordinated care requires advanced analytics, so that each member of the team understands their role and works toward the same goal. For example, the care team should include a social worker who has access to SDOH data and can connect patients to needed resources in the community.

More medical and SDOH data is available now than ever before to clinicians, health care organizations and payors. Advanced analytics allows providers and health plans to make sense of this data, enabling evidence-based clinical decisions at the point of care that lead to better patient outcomes, enhance the quality of care and advance operational efficiency. In this way, analytics is a key driver of value-based care.

Dr. Michael Dulin is chief medical officer for Gray Matter Analytics and a professor at UNC- Charlotte in the Department of Public Health Sciences, where he directs the Academy for Population Health Innovation.