Application and prospect of machine learning in orthopaedic trauma / 中国修复重建外科杂志

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.

Risk factors for one-year mortality in elderly patients with femoral intertrochanteric fracture following multidisciplinary treatment by intramedullary nailing / 中华创伤骨科杂志

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.