Validation of the Updated "LIfestyle for BRAin health" (LIBRA) Index in the English Longitudinal Study of Ageing and Maastricht Aging Study

Background: The "LIfestyle for BRAin health" (LIBRA) index was recently updated with three new modifiable factors: hearing impairment, social contact, and sleep (LIBRA2), but has not yet been validated. Objective: Comparison of the performance of both LIBRA versions in predicting dementia risk. Methods: Longitudinal data from the English Longitudinal Study of Ageing (ELSA) and the Maastricht Aging Study (MAAS) were used. The weighted LIBRA (11/12 factors available) and LIBRA2 (14/15 factors available) scores were calculated, with higher scores representing an unhealthier lifestyle. Dementia diagnoses were based on self- or informant reported physician diagnosis, an informant-based cognitive screening tool, registry data or test data. Cox-proportional hazards regression was used to investigate the association between LIBRA(2) scores and dementia risk. Model fit and predictive accuracy were determined using the Akaike information criterion and Harrell's C index. Results: Over an average follow-up of 8.3 years in ELSA and 17.9 years in MAAS, 346 (4.6%) and 120 (8.5%) individuals developed dementia, respectively. In ELSA, a one-point increase in LIBRA2 was associated with an 8% (1.06-1.11) higher dementia risk (LIBRA: 13%, 1.09-1.16). In MAAS, a one-point increase in LIBRA2 was associated with a 6% (1.01-1.12) higher dementia risk (LIBRA: 8%, 0.99-1.16). In ELSA, LIBRA (Harrell's C = 0.68) and LIBRA2 (Harrell's C = 0.67) performed similarly. In MAAS, LIBRA2 (Harrell's C = 0.62) performed better compared to LIBRA (Harrell's C = 0.52) Conclusions: LIBRA2 is abetter model for identifying individuals at increased dementia risk and for public health initiatives aimed at dementia risk reduction.