Matching health information seekers' queries to medical terms

Abstract

BackgroundThe Internet is a major source of health information but most seekers are not familiar with medical vocabularies. Hence, their searches fail due to bad query formulation. Several methods have been proposed to improve information retrieval: query expansion, syntactic and semantic techniques or knowledge-based methods. However, it would be useful to clean those queries which are misspelled. In this paper, we propose a simple yet efficient method in order to correct misspellings of queries submitted by health information seekers to a medical online search tool.MethodsIn addition to query normalizations and exact phonetic term matching, we tested two approximate string comparators: the similarity score function of Stoilos and the normalized Levenshtein edit distance. We propose here to combine them to increase the number of matched medical terms in French. We first took a sample of query logs to determine the thresholds and processing times. In the second run, at a greater scale we tested different combinations of query normalizations before or after misspelling correction with the retained thresholds in the first run.ResultsAccording to the total number of suggestions (around 163, the number of the first sample of queries), at a threshold comparator score of 0.3, the normalized Levenshtein edit distance gave the highest F-Measure (88.15%) and at a threshold comparator score of 0.7, the Stoilos function gave the highest F-Measure (84.31%). By combining Levenshtein and Stoilos, the highest F-Measure (80.28%) is obtained with 0.2 and 0.7 thresholds respectively. However, queries are composed by several terms that may be combination of medical terms. The process of query normalization and segmentation is thus required. The highest F-Measure (64.18%) is obtained when this process is realized before spelling-correction.ConclusionsDespite the widely known high performance of the normalized edit distance of Levenshtein, we show in this paper that its combination with the Stoilos algorithm improved the results for misspelling correction of user queries. Accuracy is improved by combining spelling, phoneme-based information and string normalizations and segmentations into medical terms. These encouraging results have enabled the integration of this method into two projects funded by the French National Research Agency-Technologies for Health Care. The first aims to facilitate the coding process of clinical free texts contained in Electronic Health Records and discharge summaries, whereas the second aims at improving information retrieval through Electronic Health Records.

LexExp: a system for automatically expanding concept lexicons for noisy biomedical texts

“…The number of lexical variants of a given concept that may occur, although finite, cannot be predetermined. Biomedical concepts, such as symptoms and medications, are specifically likely to be misspelled compared to non-biomedical concepts ( Soualmia et al , 2012 ; Zhou et al , 2015 ). Despite advances in machine learning based sequence labeling approaches, which typically outperform lexicon-based approaches and can detect inexact concept expressions, the latter are frequently used in biomedical research.…”

Joint segmentation and named entity recognition using dual decomposition in Chinese discharge summaries

“…Electronic medical records have experienced a rapid growth in recent years. 1 While sophisticated algorithms have been developed for English medical records, [2][3][4][5][6][7][8] rare algorithms have been introduced to process Chinese medical records. On the other hand, China is the largest country in terms of the total number of population.…”

Improving information retrieval with multiple health terminologies in a quality-controlled gateway

“…To evaluate the catalogue and to ensure its continuous relevance, several studies and improvements have been carried out, in order to provide users with the best information. Many tools have been developed: they exploit techniques such as natural language processing, statistics, lexical and background knowledge [ 6 , 7 ], the structure of the MeSH thesaurus [ 8 ], but also simple spelling-correctors based on edit distances [ 9 ].…”