Estimating the incidence of hospitalized injurious falls: impact of varying case definitions

Aim: To assess the validity of widely used approaches to estimate the incidence of hospitalized falls. Methods: Internal probabilistic data linkage of the 2000-01 New South Wales Inpatient Statistics Collection was used to identify first admissions for injurious falls. Results: Using data linkage techniques, a total of 20 883 ( 93.9%, 95% CI 93.5 to 94.2) cases were identified as first admission for injurious falls corresponding to an incidence rate of 1161.4 per 100 000. The exclusion of non-acute admissions approach provided the best estimate of incidence ( 1185.4 per 100 000 people). When comparing the performance of different approaches to identifying first admissions to that of the data linkage '' gold standard '', the method based on the transfer variable performed best in terms of sensitivity and specificity. Conclusions: All the examined approaches have relatively low specificity raising questions about their use. The introduction of a unique patient identifier and the date of injury in hospital discharge datasets would facilitate the identification of incident cases of fall related hospitalizations.