Subsequent patient visit detection in a high volume OPD using record linkage techniques
暂无分享,去创建一个
Record or data linkage techniques are used to link records which represent the same entity (e.g. patient, customer, citation, etc.) in one or more data sets where a unique identifier for each entity is not available in all or any of the data sets to be linked. A data set that has undergone record linkage is said to be linked. We consider the problem of discovering subsequent patient visit records in a high volume Out Patient Department (OPD), which due to various reasons (including loss of patient ID card and lack of time in ascertaining link to prior visit) is recorded as individual visits. We present a solution to this problem by adapting record linkage techniques that are typically used for identifying duplicate records. An experimental study conducted on real data obtained from a hospital's Out Patient Department demonstrates the effectiveness of our scheme.
[1] Esko Ukkonen,et al. Approximate String Matching with q-grams and Maximal Matches , 1992, Theor. Comput. Sci..
[2] Luis Gravano,et al. Approximate String Joins in a Database (Almost) for Free , 2001, VLDB.
[3] Vladimir I. Levenshtein,et al. Binary codes capable of correcting deletions, insertions, and reversals , 1965 .