Recruitment bias in a population-based study of children with cerebral palsy

OBJECTIVE. The purpose of this analysis was to assess recruitment bias in a population-based study of locomotor ability in children with cerebral palsy. METHOD. A population-based case register was used as a sampling frame and was considered a highly ascertained record of children with the condition. A twin track approach to recruitment for the Locomotor Study was adopted through: (1) a specialist orthopedic service and (2) a community pediatric network on behalf of the case register. The subjects included children with cerebral palsy aged 4 to 16 years in 2003, able to walk >= 10 m, and a resident in Northern Ireland, as well as their parents. RESULTS. The Orthopaedic Service identified clinically distinct children with cerebral palsy in terms of type, severity, age, and geographic residence. More families responded to an invitation, and more were ultimately recruited into the study via the Orthopaedic Service compared with a case register using community pediatric contacts. Overall, 37.8% of the eligible cerebral palsy population participated in the Locomotor Study, but there was no evidence of any systematic biases in demographic or key clinical characteristics when compared with nonparticipants. One follow-up reminder led to an increase in recruitment of 10%. CONCLUSIONS. Care must be taken in the recruitment of children with cerebral palsy through clinic-based populations, although these routes may prove more successful in follow-up. Provided they are comprehensive, case registers have a valuable contribution to make to clinical research by providing a sampling frame including information on baseline characteristics of an affected population.