Improving results in rat fracture models: enhancing the efficacy of biomechanical testing by a modification of the experimental setup

Background: Animal fracture models, primarily performed in rats, are crucial to investigate normal and pathological bone healing. However, results of biomechanical testing representing a major outcome measure show high standard deviations often precluding statistical significance. Therefore, the aim of our study was a systematical examination of biomechanical characteristics of rat femurs during three-point bending. Furthermore, we tried to reduce variation of results by individually adapting the span of bearing and loading areas to the bone's length. Methods: We examined 40 paired femurs of male Wistar-rats by DXA (BMD and BMC of the whole femur) and pQCT-scans at the levels of bearing and loading areas of the subsequent biomechanical three-point bending test. Individual adjustment of bearing and loading bars was done respecting the length of each specimen. Subgroups of light (< 400 g, n = 22) and heavy (> 400 g, n = 18) animals were formed and analysed separately. We furthermore compared the results of the individualised bending-setting to 20 femurs tested with a fix span of 15 mm. Results: Femurs showed a length range of 34 to 46 mm. The failure loads ranged from 116 to 251 N (mean 175.4 +/- 45.2 N; heavy animals mean 221 +/- 18.9 N; light animals mean 138.1 +/- 16.4 N) and stiffness ranged from 185 N/mm to 426 N/mm (mean 315.6 +/- 63 N/mm; heavy animals mean 358.1 +/- 34.64 N/mm; light animals mean 280.8 +/- 59.85 N/mm). The correlation of densitometric techniques and failure loads was high (DXA R-2 = 0.89 and pQCT R-2 = 0.88). In comparison to femurs tested with a fix span, individual adaptation of biomechanical testing homogenized our data significantly. Most notably, the standard deviation of failure loads (221 +/- 18.95 N individualized setting vs. 205.5 +/- 30.36 N fixed) and stiffness (358.1 +/- 34.64 N/mm individualized setting vs. 498.5 +/- 104.8 N/mm fixed) was reduced by at least one third. Conclusions: Total variation observed in any trait reflects biological and methodological variation. Precision of the method hence affects the statistical power of the study. By simply adapting the setting of the biomechanical testing, interindividual variation could be reduced, which improves the precision of the method significantly.