A hybrid approach to determining modification of clinical diagnoses

Health care providers that use electronic medical records maintain an administrative database of diagnoses generated by physicians in the course of medical care delivery. This database is subsequently used for billing and reimbursement but can also be used to identify patients for clinical research. In this paper we present a hybrid rule-based and machine learning technique for automatic determination of whether a diagnosis is confirmed, probable or represents a history of a disorder. The rule-based stage was able to classify 86% of test instances with an accuracy of 98.7%. The machine learning stage was able to classify the remaining 14% of the test instances with an accuracy of 91.61% using Perceptron neural network as the classification algorithm. A comparison between Naïve Bayes and Perceptron is also presented.