Population Level Health Management and Predictive Analytics

Recently there has been much discussion about the management of population health along with predictive analysis in the field of health care. Why? Most of those who are discussing these issues see it as a means to improve the health of patients and at the same time reduce the costs of doing so. Providing better service at lower costs is becoming necessary as payers begin to pay for quality results as they move away from the service fee.

What is the health of the population and how does predictive analysis fit in? Let me begin by defining the health of the population and illustrative predictive analysis. In statistics, the population reiterates the complete set of objects of interest for research. For example, it could have the temperature range of adolescents with measurements. It could be the individuals in a rural town who are prediabetic. These two are of interest in health. The population also applies to any other field of research. It could be the income level of adults in a county or ethnic groups living in a village.

In general, the management of the health of the population refers to the management of the health outcomes of the individuals looking at the collective group. For example, at the level of clinical practice, the management of the health of the population would refer to the effective care of all patients in the practice. Most practices segregate patients by diagnosis when using health management tools of the population, such as patients with hypertension. Practices generally focus on patients with high care costs so that they can be provided with more effective case management. Better case management of a population generally leads to more satisfied patients and lower costs.

The health of the population from the perspective of a county health department (as illustrated in last month's bulletin) refers to all residents of a county. Most of the services of a health department are not provided to individuals. Rather, the health of the residents of a county is improved by managing the environment in which they live. For example, health departments track the incidence of influenza in a county to alert providers and hospitals to be ready to provide the necessary levels of care.

You should be able to see that the population whose health is being managed depends on who is providing the service. Medical practices & # 39; The population are all patients of the practice. For county health departments, they are all residents of a county. For the CDC it is all residents of the United States.

Once the population is identified, the data that will be collected is identified. In a clinical setting, it is most likely that a quality or data team is the body that determines what data should be collected. Once the data is collected, trends in care can be identified. For example, one practice may find that most patients who are identified as hypertensive are managing their condition well. The quality team decides that more can be done to improve outcomes for those who do not have their blood pressure under control. By using the data factors that the team's applications collect, a statistical approach called predictive analysis is used to see if you can find factors that may be in common among those whose blood pressure is not well managed. For example, they may find that these patients lack the money to buy their medications constantly and have problems getting transportation to the clinic that provides their care. Once these factors are identified, a case manager in the clinic can work to overcome these barriers.

I will finish this overview of population health management and predictive analysis with two examples of providers that use the approach correctly. In August 2013, the Medical Group Management Association presented a webinar with speakers Benjamin Cox, the director of Finance and Planning for the Integrated Primary Care Organization at the Oregon Health Sciences University, an organization with 10 primary care physicians and 61 physicians, and Dr. Scott Fields, vice president of family medicine of the same organization. The title of the webinar was "Improve your practice with meaningful clinical data". Two of the objectives of the webinar were to define the skill set of its Quality Data Team, including who the members were and describe the process of creating a set of quality indicators.

The clinics were already collecting a variety of data to inform various groups. For example, they were reporting data for "meaningful use" and commercial payers, as well as groups of employees. They decided to take these data and more and organize them in dashboards that would be useful for the individual doctors and for the practice managers in each clinic. Some of the data collected were patient satisfaction data, hospital readmission data and obesity data. Medical scorecards were designed to meet the needs and requests of individual physicians, as well as for general practice. For example, a doctor may request that you develop a scorecard that identifies the individual patients who diagnosed the doctors who showed that the patient was outside the control limits for their diabetes. Knowing this, a doctor could spend more time improving the patient's quality of life.

Clinical scorecards indicated how well on-site physicians were administering patients with chronic diseases in general. With predictive analysis, clinic staff could identify which processes and actions helped improve patients' health. The most active case management may have proven to be effective for people with multiple chronic diseases.

Mr. Cox and Dr. Fields also stated that members of the quality data team were experts in understanding access, structuring data significantly, presenting data to clinicians effectively, and extracting data from a variety of sources. . The main objectives of the data team were to balance the competitiveness agendas of providing quality care, making sure that operations were efficient and that patient satisfaction was high.

A second example of population health management focuses on the prevention of cardiovascular disease in a rural county in Maine-Franklin County. Over a period of 40 years, beginning in the late 1960s, a voluntary nonprofit group and a clinical group worked together to improve the cardiovascular health of county residents. As the project progressed, a hospital joined the efforts.

At the beginning of prevention efforts, the cardiovascular health of this poor county was below the state average. As volunteers and clinical groups became more active in improving the health of their residents, several cardiovascular measures improved significantly and were actually better in some respects than the richest counties in the state that had better access to health services. quality. The improvements were driven by volunteers who came to the community to identify those at risk of developing cardiovascular problems related to classes to stop smoking, increase their physical activity and improve their diets. This led to lower blood pressure, lower cholesterol levels and improved endurance.

The results and details of this 40-year effort in Franklin County were published in the Journal of the American Medical Association in January 2015. The article is "Community Programs for the Prevention of Cardiovascular Disease related to improvements in health outcomes ".

As you can see, a population-based approach to population care provides effective results. A clinic can improve the outcomes of its patients with chronic diseases while balancing costs through greater efficiency by focusing on data at the population level. A community can improve the lives of its residents by adopting a population-level approach to preventive care. Population approaches to health care are varied and can be very successful if the population level theory is implemented correctly. You can get better results by matching it with predictive analytics.

Leave a comment