RESUMO
Background: Glenoid bone loss is a risk factor leading to the failure of arthroscopic Bankart repair. While 20-25% glenoid bone loss has long been considered the level to necessitate bony augmentation, recent studies indicate that 13.5% has a "subcritical" glenoid bone loss level, which is associated with decreased short- and medium-term functional scores. Few researchers worked on the long-term effect of "subcritical" or even less severe degrees of glenoid bone loss on redislocation rates and functional outcomes after arthroscopic Bankart repair. This study aimed to evaluate the effect of subcritical or less severe glenoid bone loss on redislocation rates and function after arthroscopic Bankart repair. Methods: A patient cohort who had undergone computed tomography (CT) of glenoid bone loss and arthroscopic Bankart repair over 15 years ago was reviewed. Western Ontario Shoulder Instability (WOSI) score, Single Assessment Numeric Evaluation (SANE) score, redislocation after operation, mechanism of recurrence, and revision details were reviewed. Results: Seventy-five patients were reassessed 17.6 ± 1.9 years following initial surgery. The age at enrolment was 26.8 ± 8.3 years. Twenty-two (29%) patients of the 75 patients had a redislocation on long-term follow-up, though this was not related to glenoid bone loss severity. The impaired functional score was found in patients with initial glenoid bone loss of 7% or more on long-term follow-up: WOSI (physical symptoms): 0.98 ± 2.00 vs 2.25 ± 4.01, p=0.04 and WOSI (total): 0.79 ± 1.43 vs 1.88 ± 3.56, p=0.04. Conclusions: At a mean of 17.5 years following arthroscopic Bankart repair, redislocation occurs in over a quarter of 75 patients, and they are not related to initial glenoid bone loss severity. Impaired functional outcome is apparent in patients with initial glenoid bone loss of >7%, though this impairment does not seem sufficiently severe to warrant an alternative treatment approach.
RESUMO
BACKGROUND: The rate of geriatric hip fracture in Hong Kong is increasing steadily and associated mortality in fragility fracture is high. Moreover, fragility fracture patients increase the pressure on hospital bed demand. Hence, this study aims to develop a predictive model on the length of hospital stay (LOS) of geriatric fragility fracture patients using machine learning (ML) techniques. METHODS: In this study, we use the basic information, such as gender, age, residence type, etc., and medical parameters of patients, such as the modified functional ambulation classification score (MFAC), elderly mobility scale (EMS), modified Barthel index (MBI) etc, to predict whether the length of stay would exceed 21 days or not. RESULTS: Our results are promising despite the relatively small sample size of 8000 data. We develop various models with three approaches, namely (1) regularizing gradient boosting frameworks, (2) custom-built artificial neural network and (3) Google's Wide & Deep Learning technique. Our best results resulted from our Wide & Deep model with an accuracy of 0.79, with a precision of 0.73, with an area under the receiver operating characteristic curve (AUC-ROC) of 0.84. Feature importance analysis indicates (1) the type of hospital the patient is admitted to, (2) the mental state of the patient and (3) the length of stay at the acute hospital all have a relatively strong impact on the length of stay at palliative care. CONCLUSIONS: Applying ML techniques to improve the quality and efficiency in the healthcare sector is becoming popular in Hong Kong and around the globe, but there has not yet been research related to fragility fracture. The integration of machine learning may be useful for health-care professionals to better identify fragility fracture patients at risk of prolonged hospital stays. These findings underline the usefulness of machine learning techniques in optimizing resource allocation by identifying high risk individuals and providing appropriate management to improve treatment outcome.