ACTIVExtend: 24 Months of Alendronate After 18 Months of Abaloparatide or Placebo for Postmenopausal Osteoporosis

Abstract

Purpose: In women with postmenopausal osteoporosis, we investigated the effects of 24 months of treatment with alendronate (ALN) following 18 months of treatment with abaloparatide (ABL) or placebo (PBO).

Methods: Women who completed ABL or PBO treatment in ACTIVE were eligible to receive up to 24 months of ALN. We evaluated the incidence of vertebral and nonvertebral fractures and changes in bone mineral density (BMD) during the entire 43-month period from ACTIVE baseline to the end of ACTIVExtend and for the 24-month extension only.

Results: Five hundred fifty-eight women from ACTIVE's ABL group and 581 from its PBO group (92% of ABL and PBO completers) were enrolled. During the full 43-month treatment period, 0.9% of evaluable women in the ABL/ALN group experienced a new radiographic vertebral fracture vs 5.6% of women in the PBO/ALN group, an 84% relative risk reduction (RRR, P < 0.001). Kaplan-Meier incidence rates for other reported fracture types were significantly lower for ABL/ALN vs PBO/ALN (all P < 0.05). Gains in BMD achieved during ACTIVE were further increased during ACTIVExtend. For ACTIVExtend only, RRR for vertebral fractures was 87% with ABL/ALN vs PBO/ALN (P = 0.001). Adverse events were similar between groups. A supplemental analysis for regulatory authorities found no hip fractures in the ABL/ALN group vs five in the PBO/ALN group.

Conclusions: Eighteen months of ABL followed by 24 months of ALN reduced the risk of vertebral, nonvertebral, clinical, and major osteoporotic fractures and increased BMD. Sequential ABL followed by ALN appears to be an effective treatment option for postmenopausal women at risk for osteoporosis-related fractures.

Trial registration: ClinicalTrials.gov NCT01657162.

Figure 1.

Study design and participant enrollment and disposition. (a) Study design. Participants were treated with ABL, teriparatide, or PBO for 18 mo in ACTIVE. Participants who received ABL or PBO during ACTIVE were eligible for enrollment in ACTIVExtend. A gap in treatment of up to 1 mo (from mo 18 to 19) was allowed for rollover and reconsenting from ACTIVE to ACTIVExtend. Former ABL and former PBO participants began monotherapy with ALN at cumulative mo 19 for up to 24 mo. (b) Participant enrollment and disposition. *As reported by Cosman et al. (10). ^†Baseline for the integrated 43-mo analysis was day 1 of ACTIVE. ^‡Baseline of the ACTIVExtend analysis was day 1 of ACTIVExtend (cumulative mo 19). ^§As reported by Miller et al. (9). ^¶A modified intent-to-treat (mITT) population, including those participants with an evaluable postbaseline spine radiograph assessment, was evaluated for incident new vertebral fractures. Fourteen ABL/ALN participants (one because she was not included in the mITT population for ACTIVE and 13 because they did not have a postbaseline spinal radiograph) were not included in the ACTIVExtend mITT, yielding an ABL/ALN mITT of n = 544; 13 PBO/ALN participants (two because they were not included in the ACTIVE mITT and 11 for no postbaseline spinal radiograph) were excluded from the mITT, yielding an mITT n = 568. BL, baseline.

Figure 2.

Incidence of new vertebral fractures in ACTIVE, ACTIVExtend only, and ACTIVE plus ACTIVExtend. mITT populations, representing those participants who had baseline and also postbaseline spinal x-rays at the specified time points, were evaluated for vertebral fracture rates. In ACTIVE, treatment with ABL was associated with an 86% RRR for new vertebral fractures compared with PBO. A gap in treatment of up to 1 mo (from mo 18 to 19) was allowed for rollover and reconsenting from ACTIVE to ACTIVExtend. During the ACTIVExtend period only (mo 19 to 43), prior treatment with ABL was associated with an RRR of 87% compared with prior treatment with PBO. For the full ACTIVE/ACTIVExtend study period (mo 0 to 43), treatment with ABL was associated with an 84% RRR compared with PBO. *P ≤ 0.001 for ABL vs PBO and for ABL/ALN vs PBO/ALN. ACTIVE findings were reported by Miller et al. (9).

Figure 3.

Time-to-event analyses of nonvertebral fractures, clinical fractures, and major osteoporotic fractures from ACTIVE baseline at mo 43. Curves indicate time to the first event. (a) Nonvertebral fractures were defined as fractures excluding those of the spine, sternum, patella, toes, fingers, skull, and face and those with high trauma. (b) Clinical fractures were defined as all fractures that would cause a patient to seek medical care, regardless of the level of trauma, including clinical spine. (c) Major osteoporotic fractures were defined as fractures of the wrist, upper arm, hip, and clinical spine. A gap in treatment of up to 1 mo (from mo 18 to 19) was allowed for rollover and reconsenting from ACTIVE to ACTIVExtend. Risk reduction = (1 − HR) × 100. Data for mo 0 to 18 originally appeared in Miller et al. (9).

Figure 4.

Percentage changes from ACTIVE baseline to end of ACTIVExtend in BMD and in bone turnover markers. (a–c) Mean percentage changes from baseline in BMD at: (a) LS, (b) TH, and (c) FN. Error bars represent 95% CIs. (d and e) Median percentage changes in s-PINP (d) and in s-CTX (e). Error bars represent interquartile ranges. A gap in treatment of up to 1 mo (from mo 18 to 19) was allowed for rollover and reconsenting from ACTIVE to ACTIVExtend. Former PBO and former ABL participants began monotherapy with ALN at mo 19. *P < 0.001 for ABL vs PBO and for ABL/ALN vs PBO/ALN; ^†P < 0.05 for ABL/ALN vs PBO/ALN. Data for mo 0 to 18 originally appeared in Miller et al. (9), and data for mo 25 originally appeared in Cosman et al. (10).