@inproceedings{d7a240df72cb4ba9a05210ef43e513a7,
title = "Similarity search for the content of medical records",
abstract = "The paper presents the possibility of direct comparison of medical text content by using unstructured representation of document information in frequency matrix of terms. Dimensionality reduction is performed using Latent Semantic Indexing method. Two common metrics are used: Cosine distance and Jaccard metric. Cosine measure shows a lower sensitivity for finding similar documents. The analysis was performed using SAS Text Analytics elements on set of 400 cases of description of abdominal radiological diagnostic images.",
keywords = "Cosine distance, Jaccard metric, Medical records, Similarity search, Text mining",
author = "Dominik Spinczyk and Mariusz Dzieci{\c a}tko",
note = "Publisher Copyright: {\textcopyright} Springer International Publishing Switzerland 2016.; 5th International Conference on Information Technologies in Biomedicine, ITIB 2016 ; Conference date: 20-06-2016 Through 22-06-2016",
year = "2016",
doi = "10.1007/978-3-319-39796-2\_40",
language = "English",
isbn = "9783319397955",
series = "Advances in Intelligent Systems and Computing",
publisher = "Springer Verlag",
pages = "489--501",
editor = "Ewa Pi{\c e}tka and Pawel Badura and Jacek Kawa and Wojciech Wieclawek",
booktitle = "Information Technologies in Medicine - 5th International Conference, ITIB 2016, Proceedings",
address = "Germany",
}