Odds are you have lots of really bright analysts with expertise in your organization's electronic healthcare records (EHR) system and others who can do a deep analysis of your financial and insurance claims data. But as we enter the brave new world of accountable care organizations (ACOs) and Meaningful Use (MU) Stages 2 and 3, this brain trust just isn't enough.
When you signed a contract with your EHR vendor, for example, you were probably assured that its system had the capacity to collect all the data needed to meet the feds' MU requirements. That might have been true for MU Stage 1, but it's unlikely you can rely on those elementary reporting features to do everything that's needed to compete in the fast approaching pay-for-performance market.
Right now, the Centers for Medicare and Medicaid Services (CMS) is pushing healthcare providers to improve coordination and transition of care with the hope that it will reduce costs and improve patients' health. The reasoning is straightforward: If hospitals, outpatient clinicians, nursing homes, and home care agencies do a better job of working together, fewer discharged patients will fall through the cracks and not get the post-hospitalization care they need in a timely fashion. ACOs and MU Stage 2 have been set up in part to reach that goal.
[ Is it time to re-engineer your Clinical Decision Support system? See 10 Innovative Clinical Decision Support Programs. ]
To meet the CMS performance standards for ACOs, for instance, an organization has to meet 33 quality measures, many of which require data analysis that the typical EHR isn't capable of handling. As I've mentioned in previous columns, tracking patients' smoking status--one of those measures--is relatively easy to do using EHR data, but collecting the data and doing the analysis needed to reduce readmission rates for congestive heart failure is much more complicated.
There's a lot of important data outside an EHR that must be analyzed in conjunction with the EHR's clinical data, namely insurance claims, pharmacy data, length-of-stay stats, and cost-of-care data, said Laura Madsen, a health IT analyst with Lancet, a business intelligence consulting firm, in a recent phone interview.
That data must be collected and integrated into a data warehouse through extract, transform and load (ETL) processes. And once the warehouse is properly set up, you then need a business intelligence tool such as MicroStrategy, for example, and analysts with enterprise-wide--not siloed--expertise who can crunch the data to help you meet some of the more difficult performance metrics.
Are you ready to enter the brave new world of data warehouses? To remain competitive, it's time to start making plans.
When are emerging technologies ready for clinical use? In the new issue of InformationWeek Healthcare, find out how three promising innovations--personalized medicine, clinical analytics, and natural language processing--show the trade-offs. Download the issue now. (Free registration required.)