Childhood leukemia and 50 Hz magnetic fields: findings from the Italian SETIL case-control study

Abstract

We report on an Italian case-control study on childhood leukemia and exposure to extremely low frequency magnetic fields (ELF-MF). Eligible for inclusion were 745 leukemia cases, aged 0-10 years at diagnosis in 1998-2001, and 1475 sex- and age-matched population controls. Parents of 683 cases and 1044 controls (92% vs. 71%) were interviewed. ELF-MF measurements (24-48 h), in the child's bedroom of the dwelling inhabited one year before diagnosis, were available for 412 cases and 587 controls included in the main conditional regression analyses. The magnetic field induction was 0.04 μT on average (geometric mean), with 0.6% of cases and 1.6% of controls exposed to >0.3 μT. The impact of changes in the statistical model, exposure metric, and data-set restriction criteria was explored via sensitivity analyses. No exposure-disease association was observed in analyses based on continuous exposure, while analyses based on categorical variables were characterized by incoherent exposure-outcome relationships. In conclusion, our results may be affected by several sources of bias and they are noninformative at exposure levels >0.3 μT. Nonetheless, the study may contribute to future meta- or pooled analyses. Furthermore, exposure levels among population controls are useful to estimate attributable risk.

Figure 1

Participation rates and inclusion in the datasets for the analyses. CLR = dataset of cases and controls strictly matched on age (difference in dates of birth not larger than ±15 days), with valid measurements, included in the main analyses based on conditional logistic regression models; ULR-1 = dataset of matched and unmatched cases and controls with valid measurements from sets originally strictly matched on age, included in a first series of unconditional logistic regression models; ULR-2 = dataset of matched and unmatched cases (with valid measurements but independent of compliance with the strict age-matching criterion) included in a second series of unconditional logistic regression models.