Controlled vocabularies and standardized coding systems play a fundamental role in the healthcare domain. The International Classification of Diseases (ICD) is one of the most widely used classification systems for clinical problems and procedures. In Italy the 9th revision of the standard is used and recommended in primary care for encoding prescription documents. This paper describes a statistical and terminological study to assess ICD-9-CM use in primary care and its comparison to the International Classification of Primary Care (ICPC), specifically designed for primary care. The study has been conducted by analyzing the clinical records of about 199,000 patients provided by a set of 166 General Practitioners (GPs) in different Italian areas. The analysis has been based on several techniques for detecting coding practice and errors, like natural language processing and text-similarity comparison. Results showed that the selected GPs do not fully exploit the diseases and procedures descriptive capabilities of ICD-9-CM due to its complexity. Furthermore, compared to ICPC-2, it resulted less feasible in the primary care setting, particularly for the high granularity of the structure and for the lack of reasons for encounters.
Assessing ICD-9-CM and ICPC-2 Use in Primary Care. An Italian Case Study
Cardillo E;Pasceri E;Chiaravalloti M T
2015
Abstract
Controlled vocabularies and standardized coding systems play a fundamental role in the healthcare domain. The International Classification of Diseases (ICD) is one of the most widely used classification systems for clinical problems and procedures. In Italy the 9th revision of the standard is used and recommended in primary care for encoding prescription documents. This paper describes a statistical and terminological study to assess ICD-9-CM use in primary care and its comparison to the International Classification of Primary Care (ICPC), specifically designed for primary care. The study has been conducted by analyzing the clinical records of about 199,000 patients provided by a set of 166 General Practitioners (GPs) in different Italian areas. The analysis has been based on several techniques for detecting coding practice and errors, like natural language processing and text-similarity comparison. Results showed that the selected GPs do not fully exploit the diseases and procedures descriptive capabilities of ICD-9-CM due to its complexity. Furthermore, compared to ICPC-2, it resulted less feasible in the primary care setting, particularly for the high granularity of the structure and for the lack of reasons for encounters.I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.