Prediction of mortality at one year after surgery for pertrochanteric fracture in the elderly via a Bayesian belief network.

Abstract

Pertrochanteric fractures in the elderly are common and associated with considerable mortality and disability. However, the predictors of the fracture mortality have been somewhat controversial. The aim of this study was to use univariate, multivariate analyses and a Bayesian belief network (BBN) model, which are graphic and intuitive to the clinician, to understand of the prognosis of pertrochanteric fractures. Records of patients undergoing surgery at our hospital between January 2013 and June 2018 were retrospectively reviewed. Univariate and multivariate regression as well as a machine-learned BBN model were used to estimate mortality at one year after surgery for pertrochanteric fracture in the elderly. Complete data were available for 448 surgically treated patients who were followed up for 12 months (age ≥60 years). Multivariate regression analysis revealed that hypertension, diabetes mellitus, chronic obstructive pulmonary disease, albumin, serum potassium, blood urea nitrogen and blood lactate were independent risk factors for death in surgical treatment patients (P < 0.05). First-degree predictors of mortality following surgery were established: the number of comorbid diseases, serum albumin, blood lactate and blood urea nitrogen. Following cross-validation, the area under the ROC curve was 0.85 (95% CI: 0.76-0.91) for the one-year probability of postoperative mortality. We believe cohesive models such as the Bayesian belief network can be useful as clinical decision-support tools and provide clinicians with information to the treatment of old pertrochanteric fracture. This method warrants further development and must be externally validated in other patient populations.