Computer Tools for Outcomes Analysis of Hip Replacement

In the drive to increase quality and decrease health care costs for elderly populations, providersare collecting data on outcomes of medical procedures to guide decision making, identify opportunitiesfor process improvements, and demonstrate the value of interventions. The key barrier to using thiscollected information is the lack of powerful, user-friendly programs to facilitate data analysis.Conventional statistical analysis applications have proven inadequate to identify important patterns thatmay be hidden in the recorded demographic procedural, and health outcomes data elements. Also, theapplication of conventional statistical techniques is difficult because of the enormous combination ofrecorded variables. We will apply proprietary neural networks (NN) techniques to develop user-friendlydata analysis systems which will facilitate exploration of complex datasets for outcome studies. Thenovel MSI approach is based on transformation of a decision tree into a layered NN. After training, thisspecial NN can also be used to generate a fixed set of expert system compatible rules suitable forutilization in guiding clinical decision making and employment in public health population studies. Todemonstrate concept feasibility, we will focus on hip replacement data that has been collected by theHenry Ford Health System.