Development of a Mortality Risk Model in Elderly Hip Fracture Patients by Different Analytical Approaches
Hip fracture is a major health issue that accompanies community aging. The most critical time after a hip fracture should be the first year. Care systems and surgical techniques for hip fractures have improved, so the trend of mortality in elderly hip fracture could be changed with them. Therefore, we observed the changes in the trend and critical factors for first-year mortality for the hip fractures in an elderly population in Taiwan, and mortality of prognosis prediction model was developed
... odel was developed for the early diagnosis using a population-based database in Taiwan (National Health Insurance Research Database, NHIRD). A total of 166,274 elderly subjects with an age greater than 60-years-old from 2001 to 2010 were collected for this study. Cox proportional-hazards (PH) regression and logistic regression were calculated to odds ratio and hazard ratio for mortality of those patients and compared it. Data mining algorithms were also used to generate a risk stratification prediction model. The first-year mortality rate of the overall study group was 21.5% in 2001 and 15.0% in 2010 (p for trend < 0.001). In the male subgroup, the first-year mortality rate was 29.3% in 2001 and decreased to 17.3% in 2010; the trend of standardized mortality ratio was significantly decreased from 4.4 to 2.6 (p for trend < 0.001). By logistic regression, mortality significantly increased with age and male gender. Furthermore, gender, age, patients with diabetes mellitus (DM), cardiovascular (CV), and renal comorbidity, and surgical intervention can be variables for constructing the risk stratification model. The findings of the study will be used for helping related field physicians to predict the prognosis risk of hip fracture patients, and provide evidence-based tailored treatment recommendations for those patients. It may consider to build various models for predicting the prognosis of hip fracture or integrating prediction algorithms into the computerized physician order entry system, thus creating a practical clinical decision support system with warning functions.