Objective:To compare the effectiveness of awake prone positioning (APP) care combined with standardized nursing and standardized nursing care in the prevention of early postoperative pulmonary complications (PPCs) in elderly patients with hip fracture.Methods:A retrospective cohort study was conducted to analyze the clinical data of 84 elderly patients with hip fracture Admitted to Zhongda Hospital Affiliated to Southeast University from February 2021 to August 2021. There were 31 males and 53 females, aged 67-96 years [(82.3±6.3)years]. Fracture types were femoral neck fracture ( n=45) and intertrochanteric fracture ( n=39). Surgical procedures included closed reduction internal fixation ( n=39), hip hemiarthroplasty ( n=35), and total hip arthroplasty ( n=10). Among them, 42 patients received standardized nursing care and APP intervention (APP combined with standardized nursing care group), while the remaining 42 patients received standardized nursing care only (standardized nursing care group). The incidence rate of PPCs (including pneumonia, respiratory failure, pleural effusion, atelectasis and pulmonary edema) within 30 postoperative days, arterial oxygen pressure (PaO 2), arterial carbon dioxide pressure (PaCO 2), arterial oxygen saturation (SaO 2) on the 4th postoperative day, difference in PaO 2 between the 4th postoperative day and emergency visit, clinical pulmonary infection score (CPIS) on the 4th postoperative day, and number of adverse events related to APP were compared between the two groups. Results:All the patients were followed up for 30-90 days [(86.1±16.5)days]. The incidence rates of PPCs and type 1 postoperative respiratory failure in the APP combined with standardized nursing care group were 16.7% (7/42) and 4.8% (2/42), and were 35.7% (15/42) and 21.4% (9/42) in the standardized nursing care group (all P<0.05). The PaO 2 and SaO 2 on the 4th postoperative day, and difference in PaO 2 between the 4th postoperative day and emergency visit were (82.0±8.8)mmHg, 0.96±0.01, and 3.2 (-1.9, 8.0)mmHg in the APP combined with standardized nursing care group, and were (74.3±12.1)mmHg, 0.94±0.03, and -7.6 (-17.2, 1.1)mmHg in the standardized nursing care group (all P<0.01). The CPIS on the 4th postoperative day was 2.0 (1.0, 3.0)points in the APP combined with standardized nursing care group and 4.0 (1.0, 7.0)points in the standardized nursing care group ( P<0.05). No statistically significant differences were observed in the incidence of pneumonia, type I respiratory failure, pleural effusion, atelectasis and pulmonary edema within 30 postoperative days, as well as PaCO 2 on the 4th postoperative day between the two groups (all P>0.05). None of the patients experienced adverse events related to APP. Conclusion:For elderly patients with hip fracture, compared with standardized nursing care, application of APP combined with standardized nursing care can significantly decrease the incidence rate of early PPCs, especially type I respiratory failure, and improve postoperative oxygenation.

Objective:To analyze the risk factors for postoperative one-year mortality in elderly patients with femoral intertrochanteric fracture following multidisciplinary treatment (MDT) by intramedullary nailing.Methods:The clinical data were retrospectively analyzed of the 158 elderly patients with femoral intertrochanteric fracture who had undergone MDT by proximal femoral intramedullary nailing between January 2018 and August 2020 at Department of Orthopedics, Trauma Center, Zhongda Hospital Affiliated to Southeast University. There were 41 males and 117 females with an average age of 82.5 years (from 65 to 95 years). By the modified Evans classification, there were 15 cases of type Ⅰ, 16 cases of type Ⅱ, 35 cases of type Ⅲ, 81 cases of type Ⅳ, and 11 cases of type Ⅴ. The one-year mortality was documented in the patients after surgery. To screen for risk factors, univariate analysis was conducted of gender, age, body mass index (BMI), modified Evans classification of fractures, time from injury to operation, American Society of Anesthesiologists (ASA) classification, Charlson comorbidity index (CCI) and comorbidities, as well as preoperative hemoglobin (Hb), serum albumin (ALB) and total lymphocyte count (TLC). The factors with P<0.05 were included in the multivariate logistic regression model analysis to determine the risk factors. Results:A total of 13 patients died within one year after surgery, yielding a mortality of 8.2% (13/158). Univariate analysis showed significant differences in age, body mass index, modified Evans classification of fractures, CCI and Hb between the surviving and dead patients ( P<0.05). Multivariate logistic regression analysis showed that age >85 years ( OR=0.122, 95% CI: 0.018 to 0.834, P=0.032), BMI>23.9 kg/m 2 ( OR=0.083, 95% CI: 0.013 to 0.510, P=0.007), CCI≥3 points ( OR=0.051, 95% CI: 0.090 to 0.275, P=0.001) and preoperative Hb<90 g/L ( OR=4.733, 95% CI: 1.036 to 21.624, P=0.045) were the independent risk factors for postoperative one-year mortality in the elderly patients with intertrochanteric fracture following MDT by proximal femoral intramedullary nailing. Conclusions:After MDT by proximal femoral intramedullary nailing of femoral intertrochanteric fractures, the geriatric patients with an age >85 years, BMI>23.9 kg/m 2, CCI≥3 points and Hb<90 g/L are likely to die. Therefore, special care should be taken for them.

Objective:To analyze the characteristics and risk factors of previous low-energy fractures in elderly patients with hip fractures admitted to our hospital.Methods:The data for this study was collected from 596 hip fracture patients admitted to Zhongda Hospital Affiliated to Southeast University between January 2018 and December 2021.Out of these patients, there were 404 females and 192 males.Based on the history of low-energy fracture before hip fracture, the patients were divided into two groups: a low-energy fracture group and a non-low-energy fracture group.A comparison was made between the two groups in terms of gender, age, fracture type, BMI, number of combined medical diseases, ASA score, and other characteristics.Results:The study included a total of 596 patients, with 368 patients having no history of low-energy fractures and 228 patients with low-energy fractures.Among the patients with low-energy fractures, there were 118 vertebral fractures, 69 hip fractures, 57 rib fractures, 19 radial fractures, 14 humerus fractures, and 12 patella fractures.Univariate analysis revealed significant differences in age, gender, fracture type, number of combined medical diseases, and ASA score between the two groups( P<0.05 for all). The results of multivariate Logistic analysis indicated that age( OR=1.046, 95% CI: 1.022-1.070), female sex( OR=1.474, 95% CI: 1.011-2.148), and the number of comorbid medical diseases( OR=1.211, 95% CI: 1.113-1.318)were independent risk factors for patients with a history of low-energy fractures. Conclusions:Our findings provide evidence that vertebral, hip, and rib fractures were the three most common previous low-energy fractures in elderly patients with hip fractures.We identified age, female gender, and number of medical diseases as independent risk factors for prior low-energy fractures in this population.

OBJECTIVE: To review the current applications of machine learning in orthopaedic trauma and anticipate its future role in clinical practice. METHODS: A comprehensive literature review was conducted to assess the status of machine learning algorithms in orthopaedic trauma research, both nationally and internationally. RESULTS: The rapid advancement of computer data processing and the growing convergence of medicine and industry have led to the widespread utilization of artificial intelligence in healthcare. Currently, machine learning plays a significant role in orthopaedic trauma, demonstrating high performance and accuracy in various areas including fracture image recognition, diagnosis stratification, clinical decision-making, evaluation, perioperative considerations, and prognostic risk prediction. Nevertheless, challenges persist in the development and clinical implementation of machine learning. These include limited database samples, model interpretation difficulties, and universality and individualisation variations. CONCLUSION The expansion of clinical sample sizes and enhancements in algorithm performance hold significant promise for the extensive application of machine learning in supporting orthopaedic trauma diagnosis, guiding decision-making, devising individualized medical strategies, and optimizing the allocation of clinical resources.
Artificial Intelligence ; Orthopedics ; Machine Learning ; Algorithms