Evaluating Feature Types for Encoding Clinical Notes

نویسندگان

  • Jon Patrick
  • Yitao Zhang
  • Yefeng Wang
چکیده

This paper proposes a machine learning approach to the task of assigning the international standard on classification of diseases ICD-9-CM codes to clinical records. By treating the task as a text categorisation problem, a classification system was built which explores a variety of features including negation, different strategies of measuring gloss overlaps between the content of clinical records and ICD-9-CM code descriptions together with expansion of the glosses from the ICD-9-CM hierarchy. The best classifier achieved an overall F1 value of 88.2 on a data set of 978 free text clinical records, and was better than the performance of two out of three human annotators.

برای دانلود متن کامل این مقاله و بیش از 32 میلیون مقاله دیگر ابتدا ثبت نام کنید

ثبت نام

اگر عضو سایت هستید لطفا وارد حساب کاربری خود شوید

منابع مشابه

Receptive Field Encoding Model for Dynamic Natural Vision

Introduction: Encoding models are used to predict human brain activity in response to sensory stimuli. The purpose of these models is to explain how sensory information represent in the brain. Convolutional neural networks trained by images are capable of encoding magnetic resonance imaging data of humans viewing natural images. Considering the hemodynamic response function, these networks are ...

متن کامل

Genotyping of Pseudomonas aeruginosa strains as a multidrug resistant (MDR) bacterium and evaluating the prevalence of ESBLs and some virulence factors encoding genes by PFGE and ERIC-PCR methods

Pseudomonas aeruginosa is an important multi-drug resistant (MDR) opportunistic bacterium. 102 strains of Pseudomonas aeruginosa equally isolated from human and cow milk were subjected to Multiplex-PCR for detection of ESBLs and exoenzymes of U, T, S, OprI, and OprL, Integrons class A encoding genes and genotyping by the ERIC-PCR and PFGE methods. The disc diffusion and E-test based on CLSI (Cl...

متن کامل

Genotyping of Pseudomonas aeruginosa strains as a multidrug resistant (MDR) bacterium and evaluating the prevalence of ESBLs and some virulence factors encoding genes by PFGE and ERIC-PCR methods

Pseudomonas aeruginosa is an important multi-drug resistant (MDR) opportunistic bacterium. 102 strains of Pseudomonas aeruginosa equally isolated from human and cow milk were subjected to Multiplex-PCR for detection of ESBLs and exoenzymes of U, T, S, OprI, and OprL, Integrons class A encoding genes and genotyping by the ERIC-PCR and PFGE methods. The disc diffusion and E-test based on CLSI (Cl...

متن کامل

Effectiveness of different types of learning materials used by students in courses of basic medical sciences

Introduction. Learning materials (LMs), are submitted to students in different types, from class notes to referring students to different references, which can have different effectiveness. Therefore, evaluation of effectiveness of commonly used types can help the university faculties in selection of more appropriate LMs for students. Methods. 1. The data regarding the types of LMs used in di...

متن کامل

A Space-Aware Bytecode Verifier for Java Cards

The bytecode verification is a key point of the security chain of the Java Platform. However, it is an optional feature in many embedded devices since the memory requirements of the verification process are too high. In this paper we propose a verification algorithm that drastically reduces the memory use by performing the verification during multiple specialized passes. The algorithm reduces t...

متن کامل

ذخیره در منابع من


  با ذخیره ی این منبع در منابع من، دسترسی به آن را برای استفاده های بعدی آسان تر کنید

برای دانلود متن کامل این مقاله و بیش از 32 میلیون مقاله دیگر ابتدا ثبت نام کنید

ثبت نام

اگر عضو سایت هستید لطفا وارد حساب کاربری خود شوید

عنوان ژورنال:

دوره   شماره 

صفحات  -

تاریخ انتشار 2007