Identifying relevant medical reports from an assorted report collection using the naïve Bayes classifier and the UMLS
Bashyam, Vijayaraghavan; Morioka, Craig; El-Saden, Suzie; AT Bui, Alex and Taira, Ricky K. (2007) Identifying relevant medical reports from an assorted report collection using the naïve Bayes classifier and the UMLS. Indian Journal of Medical Informatics, 2 (1). pp. 1-8. ISSN 0973-9254
Full text available as:
A patient’s electronic medical record contains a large number of medical reports and imaging studies. Identifying the relevant information in order to make a diagnosis can be a time consuming process that can easily overwhelm the physician. Summarizing key clinical information for physicians evaluating brain tumor patients is an ongoing research project at our institution. Notably, identifying documents associated with brain tumor is an important step in collecting the data relevant for summarization. The lack of structured meta-information is common in today’s electronic medical records, necessitating content analysis methods for identifying relevant reports. We trained a multinomial naïve Bayes classifier to identify brain tumor related reports from the electronic medical record. We report the performance evaluation of this system.
Archive Staff Only: edit this record