This paper systematically reviews the application progress of machine learning in perioperative transfusion medicine, focusing on its significant achievements in identifying transfusion risk factors, accurately predicting transfusion requirements, and enabling dynamic monitoring with real-time feedback. It also examines the methodologies, performance metrics, and clinical significance of constructing machine learning models across various surgical specialties, including orthopaedics, cardiac surgery, trauma, and obstetrics. The review further analyzes major challenges currently facing the field, including data bias, model overfitting and interpretability issues, alongside privacy and ethical concerns. Finally, it outlines future directions, highlighting how multimodal data fusion, deep learning applications, multicentre validation, and interdisciplinary collaboration are poised to significant potential for advancing the clinical translation of intelligent transfusion models, achieve personalized precision transfusion management, and enhance patient safety and therapeutic outcomes.

Type 2 diabetes mellitus(T2DM)is a metabolic disease characterized by insulin resistance,and is one of the most common chronic non-communicable diseases worldwide.In the field of traditional Chinese medicine(TCM),yang deficiency causing diabetes is one of the important pathogenetic mechanisms of T2DM and contributes to the core pathological basis of insulin resistance.Guided by the theory of yang deficiency causing diabetes,this paper reviewed the relevant domestic literature issued in recent years,sorted out western medical pathogenesis and treatment for insulin resistance in T2DM,TCM theory of yang deficiency causing diabetes and its clinical application,and the clinical efficacy of TCM for the treatment of insulin resistance,and then explored the applicability of theory of yang deficiency causing diabetes for TCM treatment of insulin resistance in T2DM.It is concluded that TCM treatment for insulin resistance in T2DM based on the theory of yang deficiency causing diabetes has significant efficacy and advantages,for it realizes the integration of advantages of TCM and western medicine and achieves the synergistic actions through keeping the scientific nature and standardization of western medicine and by maintaining the advantages of holism and individualization of TCM treatment.TCM treatment for insulin resistance is effective on improving insulin signal transduction,insulin secretion function and other related metabolic abnormalities indicators through multiple pathways and targets,thus to improve the health status of the body.TCM treatment for insulin resistance exerts good safety and tolerance,and can reduce the incidence of adverse reactions caused by western medicine.However,the research on TCM treatment for insulin resistance still has the insufficiencies such as low quality of clinical trials,unclear therapeutic mechanism,and lack of innovation and pioneering.Further relevant research needs to be carried out in-depth,so as to provide a scientific basis for TCM to play a greater role in preventing and treating metabolic diseases.

Objective:To investigate the risk factors for hemorrhagic transformation (HT) after intravenous thrombolysis (IVT) in patients with acute ischemic stroke (AIS), and the predictive value of Neutrophil to lymphocyte ratio (NLR).Methods:Consecutive patients with AIS received IVT in Zhengzhou People’s Hospital from January 2021 to December 2022 were retrospectively enrolled. HT was defined as no intracranial hemorrhage was found on the first imaging examination after admission, and new intracranial hemorrhage was found on the imaging examination 24 h after IVT or when symptoms worsened. sHT was defined as HT and the National Institutes of Health Stroke Scale (NIHSS) score increased by ≥4 compared to admission or required surgical treatment such as intubation and decompressive craniectomy. The baseline clinical and laboratory data of the patients were collected, and NLR, lymphocyte to monocyte ratio (LMR), and platelet to neutrophil ratio (PNR) were calculated. Multivariate logistic regression analysis was used to identify the independent predictors of HT and sHT, and receiver operating characteristic (ROC) curve was used to analyze the predictive value of NLR for HT and sHT after IVT. Results:A total of 196 patients were included (age 65.37±13.10 years, 124 males [63.3%]). The median baseline NIHSS score was 4 (interquartile range: 2-10). Twenty patients (10.2%) developed HT, and 12 (6.1%) developed sHT. Univariate analysis showed that there were statistically significant differences in age, baseline NIHSS score, creatinine, NLR, and stroke etiology type between the HT group and the non-HT group (all P<0.05); there were statistically significant differences in age, NLR, PNR, creatinine, baseline NIHSS score, and stroke etiological type between the sHT group and the non-sHT group (all P<0.05). Multivariate logistic regression analysis showed that NLR was an independent predictor of HT (odds ratio [ OR] 1.375, 95% confidence interval [ CI] 1.132-1.670; P=0.001) and sHT ( OR 1.647, 95% CI 1.177-2.304; P=0.004) after IVT. The ROC curve analysis showed that the area under the curve for predicting HT by NLR was 0.683 (95% CI 0.533-0.833; P=0.007), the optimal cutoff value was 5.78, the sensitivity and specificity were 55.0% and 84.1%, respectively. The area under the curve for predicting sHT by NLR was 0.784 (95% CI 0.720-0.839; P=0.001), the optimal cutoff value was 5.94, the sensitivity and specificity were 66.67% and 84.24%, respectively. Conclusions:A higher baseline NLR is associated with an increased risk of HT and sHT after IVT in patients with AIS, and can serve as a biomarker for predicting HT and sHT after IVT.

Objective:To investigate the characteristics and causes of endplate injury in the oblique lateral interbody fusion for the treatment of lumbar diseases, and summarize the precaution of endplate injury.Methods:Thirty-five cases of endplate injury were observed, which were originally treated with oblique lateral interbody fusion with or without pedicle screw fixation from October 2014 to December 2017. There were 7 males and 28 females, and the age ranged from 51 to 78 years old (averagely 62.8±8.13 years). There were 2 cases of lumbar disc degeneration, 10 cases of lumbar canal stenosis, 17 cases of lumbar degenerative spondylolisthesis, 2 cases of lumbar spondylolysis with or without spondylolisthesis, and 4 cases of lumbar degenerative scoliosis. Lesion sites contained L 3,4 in 2 cases, L 4,5 in 21 cases, L 2-4 in 3 cases, L 3-5 in 4 cases, L 2-5 in 3 cases and L 1-5 in 2 cases. Preoperative bone mineral density examination revealed there were 7 cases of T>-1 SD, 24 cases of -2.5 SD