Knowledge induction from medical databases with higher-order programming
Nittaya Kerdprasop, Kittisak Kerdprasop · 2009
Abstract:- Medical data mining is an emerging area of computational intelligence applied to automatically analyze patients ’ records aiming at the discovery of new knowledge potentially useful for medical decision making. Induced knowledge is anticipated not only to increase accurate diagnosis and successful disease treatment, but also to enhance safety by reducing medication-related errors. Modern healthcare organizations regularly generate huge amount of electronic data that could be used as a valuable resource for knowledge induction to support decision-making of medical practitioners. Unfortunately, a domain-specific decision support system that provides a suite of customized and flexible tools to efficiently induce knowledge from medical databases with representational heterogeneity does not currently exist. We, thus, design and develop a medical decision support system based on a powerful logic programming framework. The proposed system includes a knowledge induction component to induce knowledge from clinical data repositories and the induced knowledge can also be deployed to pre-treatment data from other sources. The implementation of knowledge induction engine has been presented to express the power of higher-order programming of logic-based language. The flexibility of our mining engine is obtained through the pattern matching and meta-programming facilities provided by logic-based language.