Background: Effective training programs for primary care providers (PCPs) to support dementia detection are needed, especially in developing countries. This study aimed to investigate the effect of an enhanced training on the competency and service of PCPs for dementia detection.Methods: We conducted a cluster randomized trial in Beijing, China. Community healthcare centers (CHCs) located in Fengtai or Fangshan District were eligible. The enrolled CHCs in each district were randomly assigned to the standard or the enhanced training group at a 1:1 ratio. PCPs serving older adults in enrolled CHCs were eligible to participate. The standard training group received three-hour didactic lectures, three monthly supervisions, 3 months of online support and dementia screening packages. The enhanced training group additionally received three monthly face-to-face supervisions and 3 months of online support. The participants became aware of their group membership at the end of the standard training. The knowledge, attitudes, service, and skills regarding dementia detection were assessed using questionnaires and submitted dementia detection records, respectively.Results: A total of 23 and 21 CHCs were randomly assigned to the standard and the enhanced training group, respectively, and 58 participants from 20 CHCs assigned to the standard training group and 48 from 16 CHCs assigned to the enhanced training group were included in the final analysis (mean age 37.5 years, and 67.0% women). A significant increase in the knowledge score was found in both groups, but the increase was similar in the two groups (P = 0.262). The attitude score remained stable in both groups, and no between-group difference was found. Compared with the baseline, both groups reported an increase in dementia detection service, especially the enhanced training group (24.1% to 31.0% in the standard training group and 14.6% to 45.8% in the enhanced training group). The completion rate and accuracy of submitted dementia detection records in the enhanced training group were both significantly higher than those in the standard training group (both P < 0.001).Conclusion: The enhanced training had similar effect on the knowledge of PCPs comparing with the standard training, but was better on continuous service and skills of PCPs related to dementia detection.Trial registration:www.ClinicalTrials.gov, identifier: NCT02782000. Registration date: May 2016. The trial was completed in July 2017.