The use of big data in the health care industry is gathering steam, and analytics for enterprise population health management has gained a foothold in the industry. Leading health insurance plans and payers are turning to analytics to gather member data that helps them deliver better-informed, targeted interventions and care-management services.
These analytics capabilities help health plans see red flags that could point to individuals with a high risk of developing certain conditions or diseases, or to identify trends and other factors that could either be prevented or better managed.
When a health plan’s identification and stratification capabilities aren’t as effective as they could be, care managers could find themselves contacting a health plan member to set up care-management services, only to discover that the member doesn’t even have the identified condition at all.
The application of good analytics is proving increasingly critical as many health plans use these tools for information to aid in supporting their membership. This includes data on how to save costs by taking proactive measures to treat or manage chronic conditions before they become critical.
All of the benefits of care management analytics are based on the assumption that the analytics software is working optimally. When analytics readings are not in sync with reality, a health plan might end up with misleading information that could jeopardize their ability to target the right members for interventions.
Three signs that your care management analytics are in need of a tune-up include: incorrect flagging of members’ conditions, incorrect flagging of high-risk members, and low care coordination index scores.
1. Incorrect flagging of members’ conditions
When care managers report that people flagged as having a certain condition deny having the condition, it’s a sign that your care management analytics aren’t optimized to support your members’ needs. When it turns out that the result of the analytics is not the same as the reality, care managers have to retrace their steps. Such errors are not good for the image of the organization, or member and care manager satisfaction, and can be costly and time-consuming.
2. Incorrect flagging of high-risk members
Another indication that a tune-up is in order comes when you identify high-risk members, based on the information from your analytics solution, only to find out that the member is actually stable. When your analytics software is functioning properly, the information will be rendered to enable more accurate data integration.
3. Low care coordination index scores
Care coordination index scores refer to the deliberate organization of the activities that are involved in member care with the aim of dispensing safer and more effective care. One of the chief ways of achieving effective care coordination is through sharing information among the people involved in the care of members. When the information gathered for analytics is not available in a timely manner, decisions could be made without the benefit of data, potentially leading to unnecessary interventions and less-desirable outcomes.
A major goal of care-management analytics is to provide better services to members, and foster a reduction in the number of relapses and readmissions. Where the rate of readmissions and relapses start to climb after an initial drop following the adoption of analytics, the culprit could be analytics software that isn’t delivering the right insights. Advanced analytics help care managers gain understanding of their most impactable members, allowing those care managers to deliver timely and appropriate interventions.
This data-intensive analytical process must be fine-tuned to unlock the power of massive amounts of data – a process that requires continuously updated data science capabilities to improve the value of targeted care delivery.