Development of a non-genetic risk prediction model for allopurinol-induced severe cutaneous adverse drug reactions: a multicenter retrospective observational study

Abstract

Objective: In addition to the Human Leukocyte Antigen B*58:01(HLA-B*58:01), several non-genetic factors have been associated with allopurinol hypersensitivity syndrome, particularly severe cutaneous adverse drug reactions (SCAR), which are clinically serious. However, the magnitude of the impact of these non-genetic factors on the development of SCAR remains unclear. This study aimed to develop a non-genetic risk prediction model for predicting allopurinol-induced SCAR. Methods: This retrospective observational study was performed during the same time period. SCAR cases were collected from tertiary care hospital centers, while the non-SCAR cases were collected from primary and tertiary care hospital centers. Non-genetic factors including sex, age, renal function, concomitant use of diuretics, starting dose of allopurinol, and serum urate (SU) were used for the development of the prediction models. Results: Of the 23,294 cases, 209 were SCAR and 23,085 were non-SCAR cases. Three risk stratification models were developed. Models 1A and 1B were applied for patients who did not have and had SU level at the time of starting allopurinol, respectively. Model 2 was applied for patients who had all non-genetic risk factors, started allopurinol within 60 days, but had not yet developed SCAR. The area under the receiver operating characteristic curve for Models 1A, 1B, and 2 was 0.73 (95% CI 0.68–0.77), 0.81 (95% CI 0.75–0.87), and 0.83 (95% CI 0.80–0.86), respectively, indicating good discriminative performance. Conclusions: The developed non-genetic prediction model demonstrated good discriminative performance. This prediction score could assist physicians’ decisions in prescribing allopurinol in the areas where HLA-B*58:01 is limited or unavailable. External validation in future studies is warranted. (Table presented.)