To develop prediction models using machine-learning (ML) algorithms for 90-day and one-year mortality prediction in femoral neck fracture (FNF) patients aged 50 years or older based on the Hip fracture Evaluation with Alternatives of Total Hip arthroplasty versus Hemiarthroplasty (HEALTH) and Fixation using Alternative Implants for the Treatment of Hip fractures (FAITH) trials. This study included 2,388 patients from the HEALTH and FAITH trials, with 90-day and one-year mortality proportions of 3.0% (71/2,388) and 6.4% (153/2,388), respectively. The mean age was 75.9 years (SD 10.8) and 65.9% of patients (1,574/2,388) were female. The algorithms included patient and injury characteristics. Six algorithms were developed, internally validated and evaluated across discrimination (c-statistic; discriminative ability between those with risk of mortality and those without), calibration (observed outcome compared to the predicted probability), and the Brier score (composite of discrimination and calibration).Aims
Methods
Older patients with multiple medical co-morbidities
are increasingly being offered and undergoing total joint arthroplasty
(TJA). These patients are more likely to require intensive care
support, following surgery. We prospectively evaluated the need
for intensive care admission and intervention in a consecutive series
of 738 patients undergoing elective hip and knee arthroplasty procedures.
The mean age was 60.6 years (18 to 91; 440 women, 298 men. Risk
factors, correlating with the need for critical care intervention,
according to published guidelines, were analysed to identify high-risk
patients who would benefit from post-operative critical care monitoring.
A total of 50 patients (6.7%) in our series required critical care
level interventions during their hospital stay. Six independent
multivariate clinical predictors were identified (p <
0.001)
including a history of congestive heart failure (odds ratio (OR)
24.26, 95% confidence interval (CI) 9.51 to 61.91), estimated blood
loss >
1000 mL (OR 17.36, 95% CI 5.36 to 56.19), chronic obstructive
pulmonary disease (13.90, 95% CI 4.78 to 40.36), intra-operative
use of vasopressors (OR 8.10, 95% CI 3.23 to 20.27), revision hip
arthroplasty (OR 2.71, 95% CI 1.04 to 7.04) and body mass index
>
35 kg/m2 (OR 2.70, 95% CI 123 to 5.94). The model was
then validated against an independent, previously published data
set of 1594 consecutive patients. The use of this risk stratification
model can be helpful in predicting which high-risk patients would
benefit from a higher level of monitoring and care after elective
TJA and aid hospitals in allocating precious critical care resources. Cite this article:
