AN ONTOLOGICAL APPROACH TO DATA MINING FOR EMERGENCY MEDICINE

We propose a system for assisting emergency personnel in making evidencebased medical decisions in scenarios with constraints on time and knowledge. Our approach is based on the artificial intelligence technique of semantic data mining, focusing on the use of ontology-based knowledge representation to provide the precise definition of entities and their relationships. This is particularly useful in medical applications due to the heterogeneity of medical data and the diversity of health care environments. Leveraging the SNOMED-CT medical terminology encoding system, we are able to extract information by applying context-aware semantic reasoning. Our high level system architecture includes four primary layers: an aggregation of data repositories, an ontology, a reasoning engine, and the application interface. The backbone of the system consists of knowledge representation and a reasoning engine connected to an end user system via a natural language processing mechanism. We also compare our approach with other methodologies for medical decision making (under similar constraints), emphasizing the particular value offered by our ontological approach for these time critical environments.

[1]  M. Ebell,et al.  Analysis of questions asked by family doctors regarding patient care , 1999, BMJ.

[2]  Stephen B. Johnson,et al.  Accessing Heterogeneous Sources of Evidence to Answer Clinical Questions , 2001, J. Biomed. Informatics.

[3]  D. Covell,et al.  Information needs in office practice: are they being met? , 1985, Annals of internal medicine.

[4]  Peter E. Hart,et al.  Nearest neighbor pattern classification , 1967, IEEE Trans. Inf. Theory.

[5]  Nello Cristianini,et al.  An introduction to Support Vector Machines , 2000 .

[6]  Herbert A. Simon,et al.  Applications of machine learning and rule induction , 1995, CACM.

[7]  Günter Rudolph,et al.  Convergence analysis of canonical genetic algorithms , 1994, IEEE Trans. Neural Networks.

[8]  James T. Kwok.  Support vector mixture for classification and regression problems , 1998, ICPR.

[9]  Corinna Cortes,et al.  Support-Vector Networks , 1995, Machine Learning.

[10]  Jimmy J. Lin,et al.  Answering Clinical Questions with Knowledge-Based and Statistical Techniques , 2007, CL.

[11]  David H. Wolpert,et al.  No free lunch theorems for optimization , 1997, IEEE Trans. Evol. Comput..

[12]  John H. Holland,et al.  Induction: Processes of Inference, Learning, and Discovery , 1987, IEEE Expert.

[13]  L Poole David,et al.  Artificial Intelligence: Foundations of Computational Agents , 2010 .

[14]  Radmila Juric,et al.  Sharing e-Health Information through Ontological Layering , 2010, 2010 43rd Hawaii International Conference on System Sciences.

[15]  Leo Breiman,et al.  Classification and Regression Trees , 1984 .

[16]  Sholom M. Weiss,et al.  Predictive data mining - a practical guide , 1997 .

[17]  C. Brodley.  Recursive Automatic Bias Selection for Classifier Construction , 2004, Machine Learning.

[18]  R. Fisher.  THE USE OF MULTIPLE MEASUREMENTS IN TAXONOMIC PROBLEMS , 1936 .

[19]  P. Vivekanand,et al.  A Scalable Genetic Algorithm for Rule Discovery in Large Datasets , 2010 .

[20]  Vipin Kumar,et al.  Text Categorization Using Weight Adjusted k-Nearest Neighbor Classification , 2001, PAKDD.

[21]  Pierre Zweigenbaum,et al.  Knowledge and Reasoning for Medical Question-Answering , 2009 .

[22]  N. Pappa,et al.  GMC Design Based on SVM Model of Batch Reactor , 2010 .

[23]  N. Lavrac,et al.  Intelligent Data Analysis In Medicine And Pharmacology: An Overview , 1997 .