Review: Wide Variability in Dermatology ICD Code Validity

A systematic review published in JAMA Dermatology showed wide variability in the accuracy of International Classification of Diseases (ICD) codes used to identify dermatologic conditions in U.S. administrative datasets.

Study researchers analyzed 59 studies published since 2000, looking spcifically at algorithms based on ICD-9 and ICD-10 codes for conditions identified in claims, EHRs, and other administrative data sources.

Most studies assessed positive predictive value (PPV), while some evaluated sensitivity or specificity. A wide range of inflammatory, autoimmune, infectious, pigmentary, hair, and neoplastic disorders (such as psoriasis, hidradenitis suppurativa, cutaneous lupus, Stevens-Johnson syndrome, and melanoma) were assessed. The most accurate algorithms incorporated multiple codes, documentation from dermatologists, or adjunct prescription/procedural data. The authors reported PPVs in many cases were 90% or more in many cases. The review also identified gaps for several common conditions (seborrheic dermatitis, rosacea, and certain alopecia subtypes), which lacked any validated classification approach.

"This systematic review provides a summary of the most accurate classification approaches to identify various dermatologic conditions in large administrative datasets," the authors wrote. "These results may inform study designs when using these datasets. In addition, some common conditions lack validated classification approaches, highlighting important areas for future research. As administrative and electronic health record data increasingly support dermatology research, use of rigorously validated algorithms will be essential for generating trustworthy findings."

Source: Cheng D, et al. JAMA Dermatology. 2025. doi:10.1001/jamadermatol.2025.5268. Published online Jan. 7, 2026.