BACKGROUND:Based on different algorithms of machine learning,how to carry out clinical research on lumbar disc herniation with the help of various algorithmic models has become a trend and hot spot in the development of intelligent medicine at present. OBJECTIVE:To review the characteristics of different algorithmic models of machine learning in the diagnosis and treatment of lumbar disc herniation,and summarize the respective advantages and application strategies of algorithmic models for the same purpose. METHODS:The computer searched PubMed,Web of Science,EMBASE,CNKI,WanFang,VIP and China Biomedical(CBM)databases to extract the relevant articles on machine learning in the diagnosis and treatment of lumbar disc herniation.Finally,96 articles were included for analysis. RESULTS AND CONCLUSION:(1)Different algorithm models of machine learning provide intelligent and accurate application strategies for clinical diagnosis and treatment of lumbar disc herniation.(2)Traditional statistical methods and decision trees in supervised learning are simple and efficient in exploring risk factors and establishing diagnostic and prognostic models.Support vector machine is suitable for small data sets with high-dimensional features.As a nonlinear classifier,it can be applied to the recognition,segmentation and classification of normal or degenerative intervertebral discs,and to establish diagnostic and prognostic models.Ensemble learning can make up for the shortcomings of a single model.It has the ability to deal with high-dimensional data and improve the precision and accuracy of clinical prediction models.Artificial neural network improves the learning ability of the model,and can be applied to intervertebral disc recognition,classification and making clinical prediction models.On the basis of the above uses,deep learning can also optimize images and assist surgical operations.It is the most widely used model with the best performance in the diagnosis and treatment of lumbar disc herniation.The clustering algorithm in unsupervised learning is mainly used for disc segmentation and classification of different herniated segments.However,the clinical application of semi-supervised learning is relatively less.(3)At present,machine learning has certain clinical advantages in the identification and segmentation of lumbar intervertebral discs,classification and grading of the degenerative intervertebral discs,automatic clinical diagnosis and classification,construction of the clinical predictive model and auxiliary operation.(4)In recent years,the research strategy of machine learning has changed to the neural network and deep learning,and the deep learning algorithm with stronger learning ability will be the key to realizing intelligent medical treatment in the future.

Objectives:To investigate the effect of inhibition of long non-coding RNA(lnc RNA)in human metastasis associated lung adenocarcinoma transcript 1(MALAT1)on glycolipitoxicity-induced human umbilical vein endothelial cell dysfunction. Methods:Human umbilical vein endothelial cells were treated with glucose and palmitic acid in vitro to establish the glycolipitoxic endothelial cell models.Following groups were examined:control group,high-glucose and high-fat group,high-glucose and high-fat + non-targeting RAN control group,high-glucose and high-lipid+MALAT1 siRNA group,and high-glucose and high-lipid+MAPK1 siRNA group.RT-qPCR was used to detect the mRNA expression of MALAT1 and MAPK1.Western blot was used to detect the expression levels of autophagy,mitochondrial fusion division,apoptosis,and pathway-related proteins.Immunofluorescence confocal localization was used to detect the fluorescence colocalization of autophagy and lysosome-related proteins.The number of autophagolysosomes in endothelial cells was observed by transmission electron microscopy.Mitochondrial probe staining was used to detect mitochondrial morphology,immunofluorescence was used to detect intracellular reactive oxygen species(ROS)production,flow cytometry was used to detect the apoptosis of cells in each group,cell proliferation and scratch assays were used to detect the proliferation and migration ability of cells in different groups at different time points.The angiogenesis was quantified by counting the number of new blood vessels in each group. Results:Compared with the control group,the expression of lncRNA MALAT1 mRNA and the expression of phosphorylated mito-activated protein kinase 1(p-MAPK1)were upregulated(both P＜0.05)and the expression of phosphorylated mammalian target protein(p-mTOR)was downregulated in the high-glucose and high-fat group and the high-sugar and high-fat control group(all P＜0.01).Compared with the high-glucose and high-fat non-targeting RNA control group,the expressions of microtubule-associated protein 1A/1B-light chain 3(LC3)and p62 were downregulated(P＜0.01,P＜0.05),LC3 and lysosome-associated membrane protein 2(LAMP2)protein co-localized positive fluorescence particles were increased(both P＜0.01),number of lysosomes were decreased,the expression of ROS was decreased(P＜0.01),the expression level of mitochondrial fusion protein optic nerve atrophin 1(OPA1)was increased(P＜0.05),the expressions of cleaved caspase-3 and BCL-2-related X protein(BAX)were decreased and BCL-2 was increased(all P＜0.05),cell proliferation,migration,and tube-forming ability were increased(all P＜0.01),and the expression of p-MAPK1 was decreased(P＜0.05)and p-mTOR expression was increased(both P＜0.05)in the high-glucose and high-lipid+si-MALAT1 group.Compared with the high-glucose and high-fat non-targeting RNA control group,the expression of p-MAPK1 in endothelial cells was decreased and the expression of p-mTOR was increased in the high-glucose and high-lipid+si-MAPK1 group(both P＜0.01). Conclusions:Inhibition of lncRNA MALAT1 expression can reduce the level of mitophagy in glycolipidotoxic environments,reduce apoptosis of endothelial cells and improve endothelial cell function,which may be related to the regulation of MAPK1/mTOR signaling pathway.

Objective:To investigate the application value of nectin-4 targeting radiotracer 68Ga-N188 in the diagnosis of pancreatic cancer. Methods:The prospective study was conducted. The clinicopathologic data of 16 patients diagnosed as pancreatic cancer on enhanced computed tomography (CT) who were admitted to the Peking University First Hospital from August to December 2022 were collected. There were 9 males and 7 females, aged (62±8)years. All patients underwent 18F-flurodeoxyglucose ( 18F-FDG) and 68Ga-N188 positron emission tomography (PET)/CT examination. Observation indicators: (1) distribution of 68Ga-N188 in different tissues and tumor primary lesion of patients; (2) expression of Nectin-4 and uptake of 68Ga-N188 in pancreatic cancer; (3) comparison of examination results between 68Ga-N188 and 18F-FDG PET/CT. Measurement data with normal distribution were represented as Mean± SD, and comparison between groups was conducted using the independent sample t test. Count data were described as absolute numbers or percentages. Results:(1) Distribution of 68Ga-N188 in different tissues and tumor primary lesion of patients. Results of PET/CT examination showed that in 1 hour after injection, the maximum standard uptake value (SUVmax) and mean standard uptake value (SUVmean) of 68Ga-N188 in fat, muscle, skin, and brain tissues of 16 patients were 0.40±0.16 and 0.25±0.09, 0.68±0.20 and 0.44±0.12, 0.39±0.14 and 0.28±0.11, 0.09±0.04 and 0.05±0.02, respectively. In the tissues of the esophagus, liver, spleen, and pancreas, the above indicators were 1.53±0.48 and 1.16±0.31, 1.49±0.45 and 0.91±0.30, 1.40±0.30 and 1.02±0.24, 1.24±0.31 and 0.96±0.25, respectively. In tumor primary lesion, the above indicators were 3.28±1.02 and 2.14±0.62, respectively, showing significant differences in SUVmax and SUVmean compared with pancreatic tissue ( t=8.03, 6.75, P<0.05). The tumor background ratio in tumor primary lesion based on SUVmax was 1.82±0.58. (2) Expression of Nectin-4 and uptake of 68Ga-N188 in pancreatic cancer. Results of immunohistochemical staining in 16 patients showed that there were 7 patients with high Nectin-4 expression and 9 patients with low Nectin-4 expression. Results of PET/CT examination showed that the SUVmax of 68Ga-N188 in tumor primary lesion of the 7 patients with high Nectin-4 expression and 9 patients with low Nectin-4 expression were 3.77±1.10 and 2.64±0.68, showing a significant difference between them ( t=2.64, P<0.05). The SUVmax of 18F-FDG in tumor primary lesion of the 7 patients with high Nectin-4 expression and 9 patients with low Nectin-4 expression were 6.73±3.24 and 6.43±3.45, showing no significant difference between them ( t=0.17, P>0.05). (3) Comparison of examination results between 68Ga-N188 and 18F-FDG PET/CT. Of the 16 patients, cases with positive results of tumor primary lesion on 68Ga-N188 and 18F-FDG PET/CT were 14 and 11, respectively, for the 14 pancreatic cancer patients diagnosed by postoperative histopathology. Among them, cases with positive results of tumor primary lesion on 68Ga-N188 and 18F-FDG PET/CT were 3 and 1 for the 3 pancreatic cancer patients receiving evaluation for chemotherapy. The SUVmax of 18F-FDG in tumor primary lesion of the 3 patients with chemotherapy and the 11 patients without chemotherapy were 2.80±0.69 and 6.97±2.11, showing a significant difference between them ( t=3.29, P<0.05). The SUVmax of 68Ga-N188 in tumor primary lesion of the 3 patients with chemotherapy and the 11 patients without chemotherapy were 3.38±1.12 and 2.93±0.50, showing no significant difference between them ( t=0.66, P>0.05). Cases with positive results of lymph node metastases in 68Ga-N188 and 18F-FDG PET/CT were 6 and 4, respectively, for the 6 pancreatic cancer patients diagnosed with lymph node metastases by postoperative histopathology, and the SUVmax of 68Ga-N188 and 18F-FDG in lymph node metastases were 2.25±1.12 and 4.02±1.27. Conclusion:68Ga-N188 PET/CT can be used for imaging diagnosis of tumor primary lesion and lymph node metastases of pancreatic cancer.

Background::Pulmonary embolism (PE) is a severe and acute cardiovascular syndrome with high mortality among patients with autoimmune inflammatory rheumatic diseases (AIIRDs). Accurate prediction and timely intervention play a pivotal role in enhancing survival rates. However, there is a notable scarcity of practical early prediction and risk assessment systems of PE in patients with AIIRD.Methods::In the training cohort, 60 AIIRD with PE cases and 180 age-, gender-, and disease-matched AIIRD non-PE cases were identified from 7254 AIIRD cases in Tongji Hospital from 2014 to 2022. Univariable logistic regression (LR) and least absolute shrinkage and selection operator (LASSO) were used to select the clinical features for further training with machine learning (ML) methods, including random forest (RF), support vector machines (SVM), neural network (NN), logistic regression (LR), gradient boosted decision tree (GBDT), classification and regression trees (CART), and C5.0 models. The performances of these models were subsequently validated using a multicenter validation cohort.Results::In the training cohort, 24 and 13 clinical features were selected by univariable LR and LASSO strategies, respectively. The five ML models (RF, SVM, NN, LR, and GBDT) showed promising performances, with an area under the receiver operating characteristic (ROC) curve (AUC) of 0.962-1.000 in the training cohort and 0.969-0.999 in the validation cohort. CART and C5.0 models achieved AUCs of 0.850 and 0.932, respectively, in the training cohort. Using D-dimer as a pre-screening index, the refined C5.0 model achieved an AUC exceeding 0.948 in the training cohort and an AUC above 0.925 in the validation cohort. These results markedly outperformed the use of D-dimer levels alone.Conclusion::ML-based models are proven to be precise for predicting the onset of PE in patients with AIIRD exhibiting clinical suspicion of PE.Trial Registration::Chictr.org.cn: ChiCTR2200059599.

Objective To compare the clinical efficacy of ankle arthroscopy combined with closed reduction guide and conventional surgical incision in the treatment of trimalleolar fracture.Methods A total of 60 patients with ankle fracture were divided into two groups according to different surgical plans:the ankle arthroscopy combined with closed reduction guide surgery group(arthroscopy group)and the conventional incision surgery group(incision group),with 30 cases in each group.The operative time,intraoperative blood loss and complications of the two groups were observed and compared.Pain and functional recovery of patients were evaluated by the American Orthopaedic Foot&Ankle Society(AOFAS)ankle and hind foot scores and Foot and Ankle Disability Index(FADI)scores.Results All 60 patients were followed up.Compared with the arthroscopy group,patients in the incision group had a longer surgical time,a shorter incision length in the medial malleolus,a reduced number of cases of skin numbness and reduced bleeding(P＜0.05).The AOFAS score and the FADI score at 12 months after surgery were higher in the arthroscopic group than those of the incision group(P＜0.05).After 12 months of surgery,the AOFAS score in patients without cartilage injury of the arthroscopic group were higher than those of patients with cartilage injury(P＜0.05),while there were no significant differences in pain and force line scores between patients with cartilage injury and patients without cartilage injury(P＞0.05).Conclusion The application of ankle arthroscopy combined with closed reduction guide in the treatment of trimalleolar fracture can achieve better postoperative results,but it has no obvious advantages in operation time and incision infection compared with the incision surgery.

Traumatic supraorbital fissure syndrome (TSOFS) is a symptom complex caused by nerve entrapment in the supraorbital fissure after skull base trauma. If the compressed cranial nerve in the supraorbital fissure is not decompressed surgically, ptosis, diplopia and eye movement disorder may exist for a long time and seriously affect the patients′ quality of life. Since its overall incidence is not high, it is not familiarized with the majority of neurosurgeons and some TSOFS may be complicated with skull base vascular injury. If the supraorbital fissure surgery is performed without treatment of vascular injury, it may cause massive hemorrhage, and disability and even life-threatening in severe cases. At present, there is no consensus or guideline on the diagnosis and treatment of TSOFS that can be referred to both domestically and internationally. To improve the understanding of TSOFS among clinical physicians and establish standardized diagnosis and treatment plans, the Skull Base Trauma Group of the Neurorepair Professional Committee of the Chinese Medical Doctor Association, Neurotrauma Group of the Neurosurgery Branch of the Chinese Medical Association, Neurotrauma Group of the Traumatology Branch of the Chinese Medical Association, and Editorial Committee of Chinese Journal of Trauma organized relevant experts to formulate Chinese expert consensus on the diagnosis and treatment of traumatic supraorbital fissure syndrome ( version 2024) based on evidence of evidence-based medicine and clinical experience of diagnosis and treatment. This consensus puts forward 12 recommendations on the diagnosis, classification, treatment, efficacy evaluation and follow-up of TSOFS, aiming to provide references for neurosurgeons from hospitals of all levels to standardize the diagnosis and treatment of TSOFS.

Objective:To explore the indications and effect of surgical treatment of autoimmune pancreatitis.Methods:Clinical data of these 15 patients with autoimmune pancreatitis diagnosed and treated at the Department of General Surgery, the First Hospital of Peking University from 2010 to 2021 were retrospectively analyzed.Results:The main clinical symptoms were obstructive jaundice, abdominal pain, distension and weight loss. The diagnosis of AIP was confirmed by EUS-FNA in 6 patients,among them, 4 did not relapse after oral hormone treatment, 2 did not receive relevant treatment, and 1 developed gastric cancer one year later. Under a suspicion of malignancy, 9 patients underwent surgical laparotomy ,and the diagnosis was established by pathology. There was no recurrence after oral hormone therapy in 1 patient who underwent laparotomy and pancreatic biopsy. One out of the 3 patients with choledochojejunostomy relapsed after 3 years. Of the 5 patients who underwent pancreatectomy, 4 had no obvious recurrence, and 1 had recurrence after 3 years.Conclusions:Untypical autoimmune pancreatitis is likely to be misdiagnosed as pancreatic cancer. For patients with suspicious malignancy, operational management and biopsy may benefit.

ObjectiveTo build an evaluation index system for traditional Chinese medicine （TCM） medicated diet， promoting the scientific and standardized development of medicated diet in TCM. MethodsThe framework of the evaluation index system was constructed through literature review and Delphi expert consultation method. The analytic hierarchy process was used to construct a hierarchical structure model. Pairwise comparisons between the indicators were conducted using the Saaty 1-9 scale method， and the weight of each indicator was calculated using Yaahp 10.3. ResultsThe response rates for the two rounds of expert consultation were 93.33% and 100%， respectively. The Kendall's W coefficients for the first-level and second-level indicators in the second round were 0.270 and 0.281， respectively （both P＜0.001）. Finally， an evaluation index system for TCM medicated diet therapy was constructed， consisting of 6 primary indicators and 27 secondary indicators. The weightings of the primary indicators were as follows： sensory appearance （0.1843）， health value （0.3569）， ingredient compatibility （0.1271）， packaging （0.0370）， production and preparation （0.1005）， and reliability （0.1940）. ConclusionA comprehensive and universally applicable evaluation index system for TCM medicated diet has been developed， taking into conside-rations of color， taste， appearance， efficacy， preparation， quality and others. This system can provide valuable reference for the evaluation of the value of medicated diet as well as its development.

Objective:To analyze the medication and compatibility law of TCM compound patents in the treatment of diabetic nephropathy (DN) based on data mining method; To provide basis for research and development of new drug in clinic.Methods:TCM compound patents for DN treatment were retrieved from national patent platform. Excel 2019 was used to conduct statistical analysis on drug frequency, property and taste and meridian. SPSS Modeler 18.0 and SPSS Statistic 26.0 were used for drug association rules and clustering analysis. The complex network of co-occurrence of core drugs was constructed with Cytoscape 3.9.0, and the potential of the correlation between new prescriptions and drugs was demonstrated.Results:A total of 261 TCM compound patents were included, including 438 kinds of Chinese materia medica. High-frequency drugs included Astragali Radix, Rehmanniae Radix, Salviae Miltiorrhizae Radix et Rhizoma, Lycii Fructus, etc. Drug categories were mainly deficiency tonic drugs. The properties and tastes were mainly cold and sweet, and the meridians were mainly liver and kidney meridians. The commonly used medicinal pair was Ganoderma-Rehmannine Radix. The commonly used triple medicinal combination was Notoginseng Radix et Rhizoma-Angelicae Sinensis Radix-Ganoderma. There were 7 groups of clustering medicines, including Notoginseng Radix et Rhizoma, Ganoderma, Angelicae Sinensis Radix, Euryales Semen, Rehmanniae Radix and Lycii Fructus. There were 5 groups of potential medicines, including Campsis Flos-Caulis Tinosporae Sinensis-Kalopanacis Radix-Fimbristylis Rigiduta Nees-Padicularisdis Dissectae Radix -Korshinsk Peashrub-Alismatis Fructus-Cynanchi Wallichii Radix. The core new prescriptions for treating DN were obtained through topological attribute analysis and screening.Conclusions:The national TCM compounds patents treatment for DN is based on the pathogenesis of this disease, which is characterized by deficiency in nature and excess in superficiality. It often uses methods such as tonifying qi and spleen, nourishing yin and tonifying kidney, promoting blood circulation and resolving blood stasis to improve clinical efficacy, providing ideas for the development of new drugs.

Traumatic cerebrospinal fluid leakage commonly presents in traumatic brain injury patients, and it may lead to complications such as meningitis, ventriculitis, brain abscess, subdural hematoma or tension pneumocephalus. When misdiagnosed or inappropriately treated, traumatic cerebrospinal fluid leakage may result in severe complications and may be life-threatening. Some traumatic cerebrospinal fluid leakage has concealed manifestations and is prone to misdiagnosis. Due to different sites and mechanisms of trauma and degree of cerebrospinal fluid leak, treatments for traumatic cerebrospinal fluid leakage varies greatly. Hence, the Craniocerebral Trauma Professional Group of Neurosurgery Branch of Chinese Medical Association and the Neurological Injury Professional Group of Trauma Branch of Chinese Medical Association organized relevant experts to formulate the " Chinese expert consensus on the diagnosis and treatment of traumatic cerebrospinal fluid leakage in adults ( version 2023)" based on existing clinical evidence and experience. The consensus consisted of 16 recommendations, covering the leakage diagnosis, localization, treatments, and intracranial infection prevention, so as to standardize the diagnosis and treatment of traumatic cerebrospinal fluid leakage and improve the overall prognosis of the patients.