Three- and four-digit ICD-10 is not a reliable classification system in primary care

Objective. The International Classification of Diseases 10th revision (ICD-10) is a standard international diagnostic classification for medical diagnoses. Reliable diagnostic coding is of high medical and epidemiological importance. Coding diagnoses with ICD-10 is the basis of reimbursement in some healthcare systems. Design. The ICD-10 coding of each case was performed by two raters to investigate the inter-rater agreement. The degree of agreement was assessed using Cohen's kappa. Kappa was divided into two groups: Kappa / = 0.61 meaning high or satisfactory and kappa / = 0.6 (incl. / = 0.000 and 0.000*) meaning low or unsatisfactory. Subjects. Cross-sectional data were collected from 8877 randomly selected patients. The 209 participating general practitioners used a standardized data collection form. The first of the reasons for encounter was taken into account on new and chronic managed problems. Results. Kappa values were satisfactory on the chapter level with on average 0.685 (chronic managed problems) and 0.675 (new managed problems). Kappa was unsatisfactory when the three-digit level was used (0.428) and lower for terminal codes (four-digit level) at 0.199 on average (chronic managed problems). For new managed problems the kappa values were at 0.384 (three-digit level) and 0.166 (four-digit level) on average. Conclusion. The ICD-10 is reliable for coding managed problems on the chapter level. Further refinement of ICD-10 with three- and four-digit codes leads to significant coding uncertainties. There is no reliable coding scheme that meets the demands of general practice. The use of coded data for healthcare reimbursement requires a simplification of ICD-10 to provide a realistic picture of morbidity.