Comorbidity and osteoporotic fracture: approach through predictive modeling techniques using the OSTEOMED registry

Abstract

Purpose: To examine the response to anti-osteoporotic treatment, considered as incident fragility fractures after a minimum follow-up of 1 year, according to sex, age, and number of comorbidities of the patients.

Methods: For this retrospective observational study, data from baseline and follow-up visits on the number of comorbidities, prescribed anti-osteoporotic treatment and vertebral, humerus or hip fractures in 993 patients from the OSTEOMED registry were analyzed using logistic regression and an artificial network model.

Results: Logistic regression showed that the probability of reducing fractures for each anti-osteoporotic treatment considered was independent of sex, age, and the number of comorbidities, increasing significantly only in males taking vitamin D (OR = 7.918), patients without comorbidities taking vitamin D (OR = 4.197) and patients with ≥ 3 comorbidities taking calcium (OR = 9.412). Logistic regression correctly classified 96% of patients (Hosmer-Lemeshow = 0.492) compared with the artificial neural network model, which correctly classified 95% of patients (AUC = 0.6).

Conclusion: In general, sex, age and the number of comorbidities did not influence the likelihood that a given anti-osteoporotic treatment improved the risk of incident fragility fractures after 1 year, but this appeared to increase when patients had been treated with risedronate, strontium or teriparatide. The two models used classified patients similarly, but predicted differently in terms of the probability of improvement, with logistic regression being the better fit.

Keywords: Anti-osteoporotic treatment; Artificial neural network; Comorbidities; Logistic regression; Osteoporosis; Osteoporotic fractures.