Genetic programming for knowledge discovery in chest pain diagnosis.pdf

Genetic programming for knowledge discovery in chest pain diagnosis Celia C. Bojarczuk 1 , Heitor S. Lopes 2 , Alex A. Freitas 3 1, 2 CEFET-PR / CPGEI, Av. 7 de setembro, 3165. Curitiba – PR, 80230-901. Brazil. {bojarczuk, hslopes}@cpgei.cefetpr.br 3 PUC-PR, PPGIA-CCET, Av. Imaculada Conceicao, 1155. Curitiba – PR, 80215-901. Brazil. alex@ppgia.pucpr.br, http://www.ppgia.pucpr.br/~alex Abstract This work aims at discovering classification rules for diagnosing certain pathologies. These rules are capable of discriminating among 12 different pathologies, whose main symptom is chest pain. In order to discover these rules we have used genetic programming as well as some concepts of data mining, with emphasis on the discovery of comprehensible knowledge. The fitness function used combines a measure of rule comprehensibility with two usual indicators in medical domain: sensitivity and specificity. Results regarding the predictive accuracy of the discovered rule set as a whole and the predictive accuracy of individual rules are presented and compared to other approaches. INTRODUCTION To classify and diagnose some pathology, one must verify which predicting attributes are most associated with that disease. In this work there are 165 predicting attributes and 12 different diseases (classes) whose main characteristic is the chest pain. The predicting attributes refer not only to the characteristics of the chest pain reported by the patient, but also to other symptoms, signals observed by the physician, details of clinical history and results of laboratory tests. The diseases are: stable angina, unstable angina, acute myocardial infarction, aortic dissection, cardiac tamponade, pulmonary embolism, pneumothorax, acute pericarditis, peptic ulcer, esophageal pain, musculoskeletal disorders, psychogenic chest pain. The goal is to predict which of those diseases a patient has, given the values of the 165 predicting attributes for the patient. Chest pain is a symptom related to