Development of a medical-text parsing algorithm based on character adjacent probability distribution for Japanese radiology reports

• Published in: Methods of information in medicine Vol. 47; no. 6; p. 513
• Main Authors: Nishimoto, N, Terae, S, Uesugi, M, Ogasawara, K, Sakurai, T
• Format: Journal Article
• Language: English
• Published: Germany 01.01.2008
• Subjects: Access to Information; Algorithms; Humans; Japan; Markov Chains; Medical Informatics - methods; Medical Informatics - organization & administration; Models, Statistical; Models, Theoretical; Natural Language Processing; Probability; Radiology - methods; Radiology - organization & administration; Terminology as Topic; Tomography, X-Ray Computed; Unified Medical Language System; Japan
• ISSN: 0026-1270
• DOI: 10.3414/me9127

The objectives of this study were to investigate the transitional probability distribution of medical term boundaries between characters and to develop a parsing algorithm specifically for medical texts. Medical terms in Japanese computed tomography (CT) reports were identified using the ChaSen morphological analysis system. MeSH-based medical terms (51,385 entries), obtained from the metathesaurus in the Unified Medical Language System (UMLS, 2005AA), were added as a medical dictionary for ChaSen. A radiographer corrected the set of results containing 300 parsed CT reports. In addition, two radiologists checked the medical term parsing of 200 CT sentences. We obtained modified inter-annotator agreement scores for the text corrected by the radiologists. We retrieved the transitional probability as the conditional probability of a uni-gram, bi-gram, and tri-gram. The highest transitional probability P(Ci | Ci- 2(*)Ci- 1) was 1.00. For an example of anatomical location, the term "pulmonary hilum" was parsed as a tri-gram. Retrieval of transitional probability will improve the accuracy of parsing compound medical terms.