Machine Learning and Regression Analysis to Model the Length of Hospital Stay in Patients with Femur Fracture.

Fractures of the femur are a frequent problem in elderly people, and it has been demonstrated that treating them with a diagnostic-therapeutic-assistance path within 48 h of admission to the hospital reduces complications and shortens the length of the hospital stay (LOS). In this paper, the preoperative data of 1082 patients were used to further extend the previous research and to generate several models that are capable of predicting the overall LOS: First, the LOS, measured in days, was predicted through a regression analysis; then, it was grouped by weeks and was predicted with a classification analysis. The KNIME analytics platform was applied to divide the dataset for a hold-out cross-validation, perform a multiple linear regression and implement machine learning algorithms. The best coefficient of determination (R2) was achieved by the support vector machine (R2 = 0.617), while the mean absolute error was similar for all the algorithms, ranging between 2.00 and 2.11 days. With regard to the classification analysis, all the algorithms surpassed 80% accuracy, and the most accurate algorithm was the radial basis function network, at 83.5%. The use of these techniques could be a valuable support tool for doctors to better manage orthopaedic departments and all their resources, which would reduce both waste and costs in the context of healthcare.

Ambulatory Ability and Personal Independence After Hemiarthroplasty and Total Arthroplasty for Intracapsular Hip Fracture: A Prospective Comparative Study.

BACKGROUND: Total hip arthroplasty (THA) has not only been associated with best functional outcomes but also with higher dislocation risk when compared with bipolar hemiarthroplasty (HA). The functionality and activities of daily living (ADL) of patients treated with THA or HA for intracapsular hip fracture (IHF) have been scarcely investigated in comparison with the preoperative status. METHODS: Two comparable groups of 60 patients with an IHF who had undergone either THA or bipolar HA were created matching several preoperative characteristics. Matched variables included age, gender, body mass index, surgical delay, American Society of Anesthesiologists class, comorbidity, cognitive status, educational status, prefracture functional status, and radiographic fracture classification. Patients were prospectively followed up for 1 year using telephone interviews. RESULTS: The ambulatory ability (5-item scale) and ADL Index significantly decreased in both the groups in comparison with the prefracture status at the 4-month and 1-year follow-up. The need for walking aids (5-item scale) at 4 months was significantly higher among patients who had undergone HA. Lower scores on the ADL Index were recorded among patients with HA in comparison with those with THA at 4 months and 1 year. No significant differences in ambulatory ability, complication rate, and mortality were detected between the 2 groups although HA and THA were associated with a tendency to a higher prevalence of general and local complications, respectively. CONCLUSION: THA provides better short-term results in terms of ADLs and allows early discontinuation in the use of walking aids as compared with bipolar HA in elderly cognitively intact patients with IHF.

Factors Predicting Mobility and the Change in Activities of Daily Living After Hip Fracture: A 1-Year Prospective Cohort Study.

OBJECTIVES: To assess the change in ambulatory ability, need for walking aids, and activities of daily living (ADL) after femoral neck, intertrochanteric, or subtrochanteric fractures and to examine the determinants of these functional outcomes. DESIGN: A prospective observational cohort study. SETTING: A multicenter study involving 1 university hospital and 2 community hospitals. PATIENTS: A consecutive cohort of 552 patients (mean age, 78.3 years; range, 50-105) who underwent surgery for a hip fracture. MAIN OUTCOME MEASURES: Ambulatory ability, need for walking aids, and ADL index, 4 and 12 months after surgery. RESULTS: At both 4 months and 1-year follow-up time points, there was a significant decrease in ambulatory ability and the ADL index score and also an increase in the need for walking aids in comparison with the prefracture status. Ambulatory ability, but not ADL, significantly recovered between the 4-month and 1-year follow-up. One year after fracture, the prefracture functional status was regained by 57% of the patients, but approximately 13% of the formerly ambulating patients were unable to walk. The prefracture status was the most important determinant of ambulatory ability, need for walking aids, and ADL. Comorbidities, a poor cognitive status, and non-weight-bearing status after surgery were also negative predictors. Neither the fracture pattern nor its specific surgical treatment was predictive of any functional outcomes. CONCLUSIONS: Regardless of the type of fracture or surgical treatment used, 57% of the patients do not regain their prefracture ambulatory ability. Recovery of ambulatory ability can occur until 1 year postoperatively. The prefracture status and cognitive level are the most important determinant of all functional outcomes. LEVEL OF EVIDENCE: Prognostic Level I. See Instructions for Authors for a complete description of levels of evidence.