Modification to Mirels scoring system location component improves fracture prediction for metastatic disease of the...

Correctly identifying patients at risk of femoral fracture due to metastatic bone disease remains a clinical challenge. Mirels criteria remains the most widely referenced method with the advantage of being easily calculated but it suffers from poor specificity. The purpose of this study was to develop and evaluate a modified Mirels scoring system through scoring modification of the original Mirels location component within the proximal femur.

Computational (finite element) experiments were performed to quantify strength reduction in the proximal femur caused by simulated lytic lesions at defined locations. Virtual spherical defects representing lytic lesions were placed at 32 defined locations based on axial (4 axial positions: neck, intertrochanteric, subtrochanteric or diaphyseal) and circumferential (8 circumferential: 45-degree intervals) positions. Finite element meshes were created, material property assignment was based on CT mineral density, and femoral head/greater trochanter loading consistent with stair ascent was applied. The strength of each femur with a simulated lesion divided by the strength of the intact femur was used to calculate the Location-Based Strength Fraction (LBSF). A modified Mirels location score was next defined for each of the 32 lesion locations with an assignment of 1 (LBSF > 75%), 2 (LBSF: 51-75%), and 3 (LBSF: 0-50%). To test the new scoring system, data from 48 patients with metastatic disease to the femur, previously enrolled in a Musculoskeletal Tumor Society (MSTS) cross-sectional study was used. The lesion location was identified for each case based on axial and circumferential location from the CT images and assigned an original (2 or 3) and modified (1,2, or 3) Mirels location score. The total score for each was then calculated. Eight patients had a fracture of the femur and 40 did not over a 4-month follow-up period. Logistic regression and decision curve analysis were used to explore relationships between clinical outcome (Fracture/No Fracture) and the two Mirels scoring methods.

The location-based strength fraction (LBSF) was lowest for lesions in the subtrochanteric and diaphyseal regions on the lateral side of the femur; lesions in these regions would be at greatest risk of fracture. Neck lesions located at the anterior and antero-medial positions were at the lowest risk of fracture. When grouped, neck lesions had the highest LBSF (83%), followed by intertrochanteric (72%), with subtrochanteric (50%) and diaphyseal lesions (49%) having the lowest LBSF. There was a significant difference (p < 0.0001) in LBSF between each axial location, except subtrochanteric and diaphyseal which were not different from each other (p = 0.96). The area under the receiver operator characteristic (ROC) curve using logistic regression was greatest for modified Mirels Score using site specific location of the lesion (Modified Mirels-ss, AUC = 0.950), followed by a modified Mirels Score using axial location of lesion (Modified Mirels-ax, AUC = 0.941). Both were an improvement over the original Mirels score (AUC = 0.853). Decision curve analysis was used to quantify the relative risks of identifying patients that would fracture (TP, true positives) and those erroneously predicted to fracture (FP, false positives) for the original and modified Mirels scoring systems. The net benefit of the scoring system weighed the benefits (TP) and harms (FP) on the same scale. At a threshold probability of fracture of 10%, use of the modified Mirels scoring reduced the number of false positives by 17-20% compared to Mirels scoring.

A modified Mirels scoring system, informed by detailed analysis of the influence of lesion location, improved the ability to predict impending pathological fractures of the proximal femur for patients with metastatic bone disease. Decision curve analysis is a useful tool to weigh costs and benefits concerning fracture risk and could be combined with other patient/clinical factors that contribute to clinical decision making.