Maust DT, et al. - Researchers sought to develop a risk prediction model that may assist in identifying older adults with dementia at high imminent risk of potentially preventable hospitalization (PPH). They used multivariable logistic regression to develop a 30-day risk prediction model. Participants were 1,793,783 community-dwelling older adults (≥ 65 years of age) with dementia who received care through the Veterans Health Administration. Hospitalization risk was correlated with following characteristics (1) age and other demographic factors; (2) outpatient, emergency department, and inpatient utilization; (3) medical and psychiatric diagnoses; and (4) prescribed medication use including changes to psychotropic medications (eg, initiation or dosage increase). The C statistic was used to determine model discrimination for each of the three cohorts. In the development cohort, PPH was reported for 0.6% of patients within 30 days. The C statistic was 0.83 for the development cohort as well as for the prediction cohort. Further, those predicted to be at high 30-day risk continued to be at higher risk throughout a year of follow-up. Findings support the possibility to distinguish older adults with dementia at high risk of imminent PPH, and their risk remains elevated for an entire year. As acute hospitalization is associated with the negative outcomes for those with dementia, healthcare systems and providers are suggested to engage the high-risk patients proactively to avoid unnecessary hospitalization.