Statistical Selector of the Best Multiple ICD-coding Method

The International Classification of Diseases 10th version (ICD-10) is one of the standard and most important disease classifications. Since computerized ICD-10 coding systems have drawn a great deal of attention in the medical field, a great number of different coding systems have been proposed. This paper proposes a hybrid architecture of different coding systems. First, given an input disease name, three coding systems output codes with their confidence scores. A C4.5-based system selector then selects the best output by using both input statistics and the confidence score from each system. The experimental results demonstrated that the selector significantly boosts the overall performance (+3.4 points).

[1]  D Deimel,et al.  [Computer-assisted classification of ICD-9/10 and IKPM in compliance with the new federal health care regulation--practice-oriented solution for trauma surgery and orthopedics]. , 1995, Der Unfallchirurg.

[2]  J. Ross Quinlan,et al.  Simplifying decision trees , 1987, Int. J. Hum. Comput. Stud..

[3]  Stephen E. Robertson,et al.  Relevance weighting of search terms , 1976, J. Am. Soc. Inf. Sci..

[4]  Christian Lovis,et al.  A Frame-based Representation of ICD-10 , 2003, MIE.

[5]  D Deimel,et al.  [Simple and valid ICD9-/10- and IKPM coding using an electronic data-assisted coding system "do it"--experiences after one years use]. , 1997, Zeitschrift fur Orthopadie und ihre Grenzgebiete.

[6]  T Hess,et al.  [Computer-based organization and documentation in orthopedics. A 5-year experience]. , 1999, Der Orthopade.

[7]  C R Rossi,et al.  Comparison between manual and automatic coding of medical record statistical cards at a university hospital. , 1993, Medical informatics = Medecine et informatique.

[8]  Sherri Alexander,et al.  Overview of inpatient coding. , 2003, American journal of health-system pharmacy : AJHP : official journal of the American Society of Health-System Pharmacists.

[9]  B. Ewigman,et al.  Child injury deaths: comparing prevention information from two coding systems. , 2005, Journal of pediatric psychology.

[10]  Olivier Bodenreider,et al.  Integration of the analytical and alphabetical ICD10 in a coding help system. Proposal of a theoretical model for the ICD representation , 1998, MedInfo.

[11]  G. Tagliabue,et al.  Consistency and accuracy of diagnostic cancer codes generated by automated registration: comparison with manual registration , 2006, Population health metrics.

[12]  Stephen E. Robertson,et al.  Okapi at TREC-3 , 1994, TREC.

[13]  Andrew McCallum,et al.  A comparison of event models for naive bayes text classification , 1998, AAAI 1998.

[14]  Kazuhiko Ohe,et al.  Information Retrieval System for Japanese Standard Disease-Code Master Using XML Web Service , 2003, AMIA.

[15]  Stephen E. Robertson,et al.  GatfordCentre for Interactive Systems ResearchDepartment of Information , 1996 .

[16]  J H Hohnloser,et al.  Improving coded data entry by an electronic patient record system. , 1996, Methods of information in medicine.

[17]  Vladimir I. Levenshtein,et al.  Binary codes capable of correcting deletions, insertions, and reversals , 1965 .

[18]  Christopher G. Chute,et al.  Research Paper: Automating the Assignment of Diagnosis Codes to Patient Encounters Using Example-based and Machine Learning Techniques , 2006, J. Am. Medical Informatics Assoc..

[19]  L Riddick,et al.  Automated coding of injuries from autopsy reports. , 1998, The American journal of forensic medicine and pathology.

[20]  Christian Lovis,et al.  Natural language processing tools for the computerised patient record: present and future , 1996 .

[21]  A Burgun,et al.  Automated Coding of Patient Discharge Summaries Using Conceptual Graphs , 1995, Methods of Information in Medicine.

[22]  Stephen Cox,et al.  Some statistical issues in the comparison of speech recognition algorithms , 1989, International Conference on Acoustics, Speech, and Signal Processing,.