A frequency-based technique to improve the spelling suggestion rank in medical queries |
| |
| Institution: | 1. Lille University Hospital, CHU Lille, Thoracic Oncology Department, Lille, France;2. University Lille, Functional and Structural Platform, CHU Lille, Lille, France;3. Department of Pathology, Hospital Tenon, AP-HP, Paris, France;4. Department of Biochemistry and Molecular Biology, Hormonology Metabolism Nutrition Oncology, CHU Lille, Lille, France;5. University Lille, CNRS, Institut Pasteur de Lille, UMR 8161 - M3T - Mechanisms of Tumorigenesis and Targeted Therapies, F-59000 Lille, France;6. University Lille, CHU Lille, Institute of Pathology, UMR8161 CNRS, Institute of Biology of Lille, F-59000 Lille, France;7. Department of Molecular Oncology, Assistance Publique Hôpitaux de Marseille, Marseille, France;8. Department of Molecular Biology, Strasbourg University Hospital, Strasbourg, France;9. Unit of Pharmacogenomics, Department of Genetics, Institut Curie, Paris, France;10. Department of Pathology, CHU de Caen, Caen, France;11. Department of Pneumology, Nouvel Hôpital Civil, University Hospital, Strasbourg, France;12. Department of Pneumology, Grenoble University Hospital, Grenoble, France;13. Pneumology Department, Foch Hospital, Suresnes, France;14. Clinical Research Unit, French Cooperative Thoracic Intergroup (IFCT), Paris, France;15. Aix Marseille University, Assistance Publique Hôpitaux de Marseille, Multidisciplinary Oncology & Therapeutic Innovations Department, Marseille, France;p. Chest Department-Thoracic Oncology Expert Center, AP-HP, Groupe Hospitalier HUEP, Hopital Tenon, Paris, France, and Sorbonne University, Paris, France;1. Pharmaceutical Engineering Group, School of Pharmacy, Queen’s University Belfast, Belfast BT9 7BL, United Kingdom;2. China Medical University - Queen''s University Belfast joint College (CQC), No.77 Puhe Road, Shenyang North New Area, Shenyang, Liaoning Province, PR China;1. Georgia State University, Atlanta, GA, USA;2. Arizona State University, Tempe, AZ, USA;3. University of New Hampshire, Durham, NH, USA;4. University of Nebraska at Omaha, Omaha, NE, USA;1. FDA CDER Office of Biostatistics, Silver Spring, MD, United States;2. FDA CDER Office of Surveillance and Epidemiology, Silver Spring, MD, United States;3. FDA CDER Office of Translational Sciences, Silver Spring, MD, United States;4. FDA CBER Office of Biostatistics and Epidemiology, Silver Spring, MD, United States;5. Linguamatics Ltd., Cambridge, UK |
| |
| Abstract: | ObjectiveThere is an abundance of health-related information online, and millions of consumers search for such information. Spell checking is of crucial importance in returning pertinent results, so the authors propose a technique for increasing the effectiveness of spell-checking tools used for health-related information retrieval.DesignA sample of incorrectly spelled medical terms was submitted to two different spell-checking tools, and the resulting suggestions, derived under two different dictionary configurations, were re-sorted according to how frequently each term appeared in log data from a medical search engine.MeasurementsUnivariable analysis was carried out to assess the effect of each factor (spell-checking tool, dictionary type, re-sort, or no re-sort) on the probability of success. The factors that were statistically significant in the univariable analysis were then used in multivariable analysis to evaluate the independent effect of each of the factors.ResultsThe re-sorted suggestions proved to be significantly more accurate than the original list returned by the spell-checking tool. The odds of finding the correct suggestion in the number one rank were increased by 63% after re-sorting using the authors' method. This effect was independent of both the dictionary and the spell-checking tools that were used.ConclusionUsing knowledge about the frequency of a given word's occurrence in the medical domain can significantly improve spelling correction for medical queries. |
| |
| Keywords: | |
| 本文献已被 ScienceDirect 等数据库收录！ |
|
