Nastassia Tvardik1, Ivan Kergourlay2, André Bittar3, Frédérique Segond4, Stefan Darmoni5, Marie-Hélène Metzger6. 1. Université Lyon 1, CNRS UMR5558 Laboratoire de Biométrie et Biologie Evolutive, Villeurbanne, France. 2. University Hospital of Rouen, Department of Biomedical Informatics, CISMeF, Rouen, France. Electronic address: ivan.kergourlay@chu-rouen.fr. 3. Holmes Semantic Solutions, Grenoble, France. Electronic address: andre.bittar@kcl.ac.uk. 4. Viseo Technologies, Grenoble, France; INALCO ERTIM, Paris, France. 5. University Hospital of Rouen, Department of Biomedical Informatics, CISMeF, Rouen, France; TIBS, LITIS EA 4108, Normandy University, France; INSERM, U1142, LIMICS, Paris, France. Electronic address: stefan.darmoni@chu-rouen.fr. 6. Université Lyon 1, CNRS UMR5558 Laboratoire de Biométrie et Biologie Evolutive, Villeurbanne, France; Hospices Civils de Lyon, Hôpital de la Croix-Rousse, Unité d'hygiène et d'épidémiologie, Lyon, France. Electronic address: marie-helene.metzger@aphp.fr.
Abstract
OBJECTIVE: There is a growing interest in using natural language processing (NLP) for healthcare-associated infections (HAIs) monitoring. A French project consortium, SYNODOS, developed a NLP solution for detecting medical events in electronic medical records for epidemiological purposes. The objective of this study was to evaluate the performance of the SYNODOS data processing chain for detecting HAIs in clinical documents. MATERIALS AND METHODS: The collection of textual records in these hospitals was carried out between October 2009 and December 2010 in three French University hospitals (Lyon, Rouen and Nice). The following medical specialties were included in the study: digestive surgery, neurosurgery, orthopedic surgery, adult intensive-care units. Reference Standard surveillance was compared with the results of automatic detection using NLP. Sensitivity on 56 HAI cases and specificity on 57 non-HAI cases were calculated. RESULTS: The accuracy rate was 84% (n = 95/113). The overall sensitivity of automatic detection of HAIs was 83.9% (CI 95%: 71.7-92.4) and the specificity was 84.2% (CI 95%: 72.1-92.5). The sensitivity varies from one specialty to the other, from 69.2% (CI 95%: 38.6-90.9) for intensive care to 93.3% (CI 95%: 68.1-99.8) for orthopedic surgery. The manual review of classification errors showed that the most frequent cause was an inaccurate temporal labeling of medical events, which is an important factor for HAI detection. CONCLUSION: This study confirmed the feasibility of using NLP for the HAI detection in hospital facilities. Automatic HAI detection algorithms could offer better surveillance standardization for hospital comparisons.
OBJECTIVE: There is a growing interest in using natural language processing (NLP) for healthcare-associated infections (HAIs) monitoring. A French project consortium, SYNODOS, developed a NLP solution for detecting medical events in electronic medical records for epidemiological purposes. The objective of this study was to evaluate the performance of the SYNODOS data processing chain for detecting HAIs in clinical documents. MATERIALS AND METHODS: The collection of textual records in these hospitals was carried out between October 2009 and December 2010 in three French University hospitals (Lyon, Rouen and Nice). The following medical specialties were included in the study: digestive surgery, neurosurgery, orthopedic surgery, adult intensive-care units. Reference Standard surveillance was compared with the results of automatic detection using NLP. Sensitivity on 56 HAI cases and specificity on 57 non-HAI cases were calculated. RESULTS: The accuracy rate was 84% (n = 95/113). The overall sensitivity of automatic detection of HAIs was 83.9% (CI 95%: 71.7-92.4) and the specificity was 84.2% (CI 95%: 72.1-92.5). The sensitivity varies from one specialty to the other, from 69.2% (CI 95%: 38.6-90.9) for intensive care to 93.3% (CI 95%: 68.1-99.8) for orthopedic surgery. The manual review of classification errors showed that the most frequent cause was an inaccurate temporal labeling of medical events, which is an important factor for HAI detection. CONCLUSION: This study confirmed the feasibility of using NLP for the HAI detection in hospital facilities. Automatic HAI detection algorithms could offer better surveillance standardization for hospital comparisons.
Keywords:
Decision support systems, Clinical; Epidemiology; Healthcare-associated infections; Medical records systems, computerized; Natural language processing
Authors: Benjamin T Miller; Aldo Fafaj; Luciano Tastaldi; Hemasat Alkhatib; Samuel Zolin; Raha AlMarzooqi; Chao Tu; Diya Alaedeen; Ajita S Prabhu; David M Krpata; Michael J Rosen; Clayton C Petro Journal: J Gastrointest Surg Date: 2022-02-28 Impact factor: 3.267
Authors: Beatriz Villamarín-Bello; Berta Uriel-Latorre; Florentino Fdez-Riverola; María Sande-Meijide; Daniel Glez-Peña Journal: Biomed Res Int Date: 2019-09-23 Impact factor: 3.411