|
The system has been in continuous operation since 1990. It reviews thousands of patient medical histories per month, looking for temporal patterns of events which indicate scenarios of either hazardous or unnecessarily expensive prescribing. The reviews are retrospective, based on clinical information extracted from billing data. The output reports are reviewed by a peer review panel before a decision is made to intervene in writing to the doctors or nursing homes involved in the problems. The panel agrees with the computer about 70% of the time overall, although for some problem scenarios agreement is virtually 100%. This contrasts with commercial systems, not using ES technology, who are lucky to get 10% agreement.
Medicaid (the Colorado agency for indigent medical care) loves the system. It pays for itself in various kinds of savings, including some serendipitous discoveries of fraud and/or billing errors. We have a randomized trial which indicates that our intervention significantly changed prescribing behavior to less expensive non-steroidal anti-inflammatory drugs.
The program cost $500,000 and 7-person-years to develop. It runs on about $200,000/year. Two physicians, one pharmacist and three informatics specialists were the development team.
The local medical society and the American Medical Association believe that the program provides useful information to health-care providers about fragmentation of care, about the patient's drug-taking and care-seeking behavior, and about current standards of care.
|
