Postmenopausal Caucasian women aged less than 80 years (n = 99) with one or more atraumatic vertebral fracture and no hip fractures, were treated by cyclical administration of enteric coated sodium fluoride (NaF) or no NaF for 27 months, with precautions to prevent excessive stimulation of bone turnover. In the first study 65 women, unexposed to estrogen (-E study), age 70.8 +/- 0.8 years (mean +/- SEM) were all treated with calcium (Ca) 1.0-1.2 g daily and ergocalciferol (D) 0.25 mg per 25 kg once weekly and were randomly assigned to cyclical NaF (6 months on, 3 months off, initial dose 60 mg/day; group F CaD, n = 34) or no NaF (group CaD, n = 31). In the second study 34 patients, age 65.5 +/- 1.2 years, on hormone replacement therapy (E) at baseline, had this standardized, and were all treated with Ca and D and similarly randomized (FE CaD, n = 17; E CaD, n = 17) (+E study). The patients were stratified according to E status and subsequently assigned randomly to +/- NaF. Seventy-five patients completed the trial. Both groups treated with NaF showed an increase in lumbar spinal density (by DXA) above baseline by 27 months: FE CaD + 16.2% and F CaD +9.3% (both p = 0.0001). In neither group CaD nor E CaD did lumbar spinal density increase. Peripheral bone loss occurred at most sites in the F CaD group at 27 months: tibia/fibula shaft -7.3% (p = 0.005); femoral shaft -7.1% (p = 0.004); distal forearm -4.0% (p=0.004); total hip -4.1% (p = 0.003); and femoral neck -3.5% (p = 0.006). No significant loss occurred in group FE CaD. Differences between the two NaF groups were greatest at the total hip at 27 months but were not significant [p < 0.05; in view of the multiple bone mineral density (BMD) sites, an alpha of 0.01 was employed to denote significance in BMD changes throughout this paper]. Using Cox's proportional hazards model, in the -E study there were significantly more patients with first fresh vertebral fractures in those treated with NaF than in those not so treated (RR = 24.2, p = 0.008, 95% CI 2.3-255). Patients developing first fresh fractures in the first 9 months were markedly different between groups: -23% of F CaD, 0 of CaD, 29% of FE CaD and 0 of E CaD. The incidence of incomplete (stress) fractures was similar in the two NaF-treated groups. Complete nonvertebral fractures did not occur in the two +E groups; there were no differences between groups F CaD and CaD. Baseline BMD (spine and femoral neck) was related to incident vertebral fractures in the control groups (no NaF), but not in the two NaF groups. Our results and a literature review indicate that fluoride salts, if used, should be at low dosage, with pretreatment and co-treatment with a bone resorption inhibitor.