Diseases and conditions are usually coded using the ICD coding system. ICD was started in 1899 and is revised (every 10 years) and maintained by the World Health Organization (WHO). As of 2016, the tenth revision (ICD-10) is the most recent, and consists of more than 68,000 unique diagnostic codes, more than any previous revision.

ICD-10 codes may consist of up to eight alphanumeric characters. The first three characters indicate the major disease category; for example, "N18" specifies chronic kidney disease. These characters are followed by a period and then the remaining characters, which can provide an extraordinary amount of clinical detail (Braunstein, 2014). For example, code "C50.211" specifies "malignant neoplasm of upper-inner quadrant of the right female breast." With all of its precision, ICD-10 facilitates the application of analytics in healthcare.