论文信息 - Automatic classification of medical reports, the CIREA project

Automatic classification of medical reports, the CIREA project

Choosing a patient's reasons for staying in hospital amongst the 52, 000 pathology codes listed in the ICD-10 (International Classification of Diseases) requires that the practitioner spends a large amount of time keyboarding and searching, which may discourage him. However these codes are mandatory in many countries when the patient leaves the hospital, for biostatistical and administrative studies. The aim of the CIREA project is to propose an automatic ICD coding approach by mining textual medical reports. For that purpose we have proposed new algorithms such the EDA desuffixer, the CLO3 classification algorithm and the K-measure indicator.

[1] B. Burnside,et al. Automated Indexing of Mammography Reports Using Linear Least Squares Fit , 2000 .

[2] Vladimir N. Vapnik,et al. The Nature of Statistical Learning Theory , 2000, Statistics for Engineering and Information Science.

[3] Pierre Zweigenbaum,et al. A Lexical Method for Assisted Extraction and Coding of ICD-10 Diagnoses from Free Text Patient Discharge Summaries , 1999, AMIA.

[4] Yiming Yang,et al. An example-based mapping method for text categorization and retrieval , 1994, TOIS.

[6] Elisabeth Métais,et al. EDA : algorithme de désuffixation du langage médical , 2006, EGC.

[7] Elisabeth Métais,et al. Evaluation and NLP , 2005, DEXA.

[8] Thorsten Joachims,et al. Text Categorization with Support Vector Machines: Learning with Many Relevant Features , 1998, ECML.

[9] George Hripcsak,et al. Medical text representations for inductive learning , 2000, AMIA.

[10] Alexander Dekhtyar,et al. Information Retrieval , 2018, Lecture Notes in Computer Science.

[11] Karen Spärck Jones. Automatic language and information processing: rethinking evaluation , 2001, Natural Language Engineering.

[12] George Hripcsak,et al. Using Knowledge Sources to Improve Classification of Medical Text Reports , 2000, KDD 2000.