Association rule extraction from medical transcripts of diabetic patients

Medical databases serve as rich knowledge sources for effective medical diagnosis. Recent advances in medical technology and extensive usage of electronic medical record systems, helps in massive production of medical text data in hospitals and other health institutions. Most of this text data that contain valuable information are just filed and not utilized to the full extent. Proper usage of medical information can bring about tremendous changes in medical field. This paper present a new method of uncovering valid association rules from medical transcripts. The extracted rules describes association of disease with other diseases, symptoms of a particular disease, medications used for treating diseases, the most prominent age group of patients for developing a particular disease. NLP (Natural Language Processing) tools were combined with data mining algorithms (Apriori algorithm and FP-Growth algorithm) for the extraction of rules. Interesting rules were selected using the correlation measure, lift.