Low drug attributability of aplastic anemia in Thailand. The Aplastic Anemia Study Group

Abstract

From 1989 to 1994, a population-based, case-control study of aplastic anemia was conducted in Thailand, including the regions of Bangkok, Khonkaen in the northeast, and Songkla in the south. An annual incidence in Bangkok of 3.7 cases per million population, about twice as high as in Western countries, has been reported. To evaluate the etiologic role of drugs, 253 subjects were compared with 1,174 hospital controls. With multivariate adjustment for confounding, a significant association was identified for exposure 2 to 6 months before admission to thiazide diuretics (relative risk estimate 7.7; 1.5 to 40). There were crude associations with sulfonamides (relative risk estimate, 7.9; P = 0.004) and mebendazole (6.3; P = 0.03) (there were insufficient data for multivariate adjustment). Excess risks for the three drugs were in the range of 9 to 12 cases per million users. There was no significant association with chloramphenicol, although the multivariate relative-risk estimate was elevated (2.7; 0.7 to 10). Other drugs that have been reported to increase the risk of aplastic anemia, such as nonsteroidal anti-inflammatory drugs and anticonvulsants, were not commonly used. There were no associations with commonly used drugs, including benzodiazepines, antihistamines, oral contraceptives, and herbal preparations. For all associated drugs, the overall etiologic fraction (the proportion of cases attributable to an exposure) was 5%, compared with 25% in Europe and Israel. Drugs are uncommon causes of aplastic anemia in Thailand, and their use does not explain the relatively high incidence of the disease in that country.