Introduction No study has investigated how exercise modifies the effect of fall-related drugs (FRDs) on falls among people with Alzheimer's disease (AD). Objective The aim of this study was to investigate how exercise intervention and FRDs interact with fall risk among patients with AD. Methods In the FINALEX trial, community-dwelling persons with AD received either home-based or group-based exercise twice weekly for 1 year (n =129); the control group received normal care (n =65). The number of falls was based on spouses' fall diaries. We examined the incidence rate ratios (IRRs) for falls among both non-users and users of various FRDs (antihypertensives, psychotropics, drugs with anticholinergic properties [DAPs]) in both control and combined intervention groups. Results Between the intervention and control groups, there was no difference in the number of falls among those without antihypertensives or psychotropics. In the intervention group taking antihypertensives, the IRR was 0.5 falls/person-year (95% confidence interval [CI] 0.4-0.6), while in the control group, the IRR was 1.5 falls/person-year (95% CI 1.2-1.8) [p < 0.001 for group, p = 0.067 for medication, p < 0.001 for interaction]. Among patients using psychotropics, the intervention group had an IRR of 0.7 falls/person-year (95% CI 0.6-0.9), while the control group had an IRR of 2.0 falls/person-year (95% CI 1.6-2.5) [p < 0.001 for group, p = 0.071 for medication, p < 0.001 for interaction]. There was a significant difference in falls between the intervention and control groups not using DAPs (0.6, 95% CI 0.5-0.7; 1.2, 95% CI 1.0-1.4), and between the intervention and control groups using DAPs (1.1, 95% CI 0.8-1.3; 1.5, 95% CI 1.0-2.1) [p < 0.001 for group, p = 0.014 for medication, p = 0.97 for interaction]. Conclusion Exercise has the potential to decrease the risk for falls among people with AD using antihypertensives and psychotropics. Trial Registration ACTRN12608000037303.