BACKGROUND Hospital administrative databases are a useful source of population-level data on injured patients; however, these databases use the International Classification of Diseases (ICD) system, which does not provide a direct means of estimating injury severity. We created and validated a crosswalk to derive Abbreviated Injury Scale (AIS) scores from injury-related diagnostic codes in the ...

Hypothesis / aims of study By law, all surgical procedures carried out at Danish hospitals are reported to the National Patient Registry (LPR) according to the ICD10 coding system. The following year a report is published. The codes for very different procedures are very much alike for which reason there is a potential risk of miscoding. Furthermore, there are no options to code for the complex...

Medical diagnosis process involves many levels and considerable amount of time and money are invariably spent for the first level of diagnosis usually made by the physician for all the patients every time. Hence there is a need for a computer based system which not only asks relevant questions to the patients but also aids the physician by giving a set of possible diseases from the symptoms obt...

Introduction In Louisiana, information contained on electronic laboratory reports is not able to identify the pregnancy status for the majority of HIV-infected women.1 Laboratories have access to ICD9/ICD10 codes which could provide information about pregnancy status, but few laboratories provide these codes to Health Departments. In some areas, such as New York City, the reporting of pregnancy...

This paper describes the participation of the KFU team in the CLEF eHealth 2017 challenge. Specifically, we participated in Task 1, namely “Multilingual Information Extraction ICD-10 coding” for which we implemented recurrent neural networks to automatically assign ICD10 codes to fragments of death certificates written in English. Our system uses Long Short-Term Memory (LSTM) to map the input s...

BACKGROUND the Core Subset of SNOMED CT is part of the UMLS-Core Project dedicated to study problem list vocabularies. SNOMED CT is not yet translated into French. OBJECTIVE to propose an automated method to assist the translation of the CORE Subset of SNOMED CT into French. MATERIAL the 2009 AA versions of the CORE Subset of SNOMED CT and UMLS; use of four French-language terminologies int...

PURPOSE To characterize the comorbidities associated with hospitalizations for obesity and the relationship of these co-morbidities with bariatric surgery and hospitalization costs during the period between 2000 and 2010 in Sao Paulo that were financed by the Brazilian Public Health System (SUS). METHODS We used data from the Hospital Information System of the Unified Health System (SIH-SUS) ...

In this geostatistical analysis we present the results of interrelation between unemployment rate and lung cancer incidence ratios in the Province of Opole, Poland. In the study, unemployment statistics and population data were analyzed together with the registered (histopathologically confirmed) lung cancer cases (C34, ICD10) in sex-stratified working age population (18-65 years). The data wer...

This paper reports on Task 1 of the 2017 CLEF eHealth evaluation lab which extended the previous information extraction tasks of ShARe/CLEF eHealth evaluation labs. The task continued with coding of death certificates, as introduced in CLEF eHealth 2016. This largescale classification task consisted of extracting causes of death as coded in the International Classification of Diseases, tenth re...