OBJECTIVE: To construct machine learning prediction model for sepsis-associated encephalopathy (SAE), and analyze the application value of the model on early identification of SAE risk in elderly septic patients. METHODS: Patients aged over 60 years with a primary diagnosis of sepsis admitted to intensive care unit (ICU) from 2008 to 2023 were selected from Medical Information Mart for Intensive Care-IV 2.2 (MIMIC-IV 2.2). Demographic variables, disease severity scores, comorbidities, interventions, laboratory indicators, and hospitalization details were collected. Key factors associated with SAE were identified using univariate Logistic regression analysis. The data were randomly divided into training and validation sets in a 7 : 3 ratio. Multivariable Logistic regression analysis was conducted in the training set and visualized using a nomogram model for prediction of SAE. The discrimination of the model was evaluated in the validation set using the receiver operator characteristic curve (ROC curve), and its calibration was assessed using calibration curve. Furthermore, multiple machine learning algorithms, including multi-layer perceptron (MLP), support vector machine (SVM), naive bayes (NB), gradient boosting machine (GBM), random forest (RF), and extreme gradient boosting (XGB), were constructed in the training set. Their predictive performance was subsequently evaluated on the validation set. Taking the XGB model as an example, the interpretability of the model through the SHapley Additive exPlanations (SHAP) algorithm was enhanced to identify the key predictive factors and their contributions. RESULTS: A total of 2 204 septic patients were finally enrolled, of whom 840 developed SAE (38.1%). A total of 21 variables associated with SAE were screened through univariate Logistic regression analysis. Multivariable Logistic regression analysis showed that endotracheal intubation [odds ratio (OR) = 0.40, 95% confidence interval (95%CI) was 0.19-0.88, P < 0.001], oxygen therapy (OR = 0.76, 95%CI was 0.53-0.95, P = 0.023), tracheotomy (OR = 0.20, 95%CI was 0.07-0.53, P < 0.001), continuous renal replacement therapy (CRRT; OR = 0.32, 95%CI was 0.15-0.70, P < 0.001), cerebrovascular disease (OR = 0.31, 95%CI was 0.16-0.60, P < 0.001), rheumatic disease (OR = 0.44, 95%CI was 0.19-0.99, P < 0.001), male (OR = 0.68, 95%CI was 0.54-0.86, P = 0.001), and maximum anion gap (AG; OR = 0.95, 95%CI was 0.93-0.97, P < 0.001) were associated with an decreased probability of SAE, and age (OR = 1.05, 95%CI was 1.03-1.06, P < 0.001), acute physiology score III (APSIII; OR = 1.02, 95%CI was 1.01-1.02, P < 0.001), Oxford acute severity of illness score (OASIS; OR = 1.04, 95%CI was 1.03-1.06, P < 0.001), and length of hospital stay (OR = 1.01, 95%CI was 1.01-1.02, P < 0.001) were associated with an increased probability of SAE. A nomogram model was constructed based on these variables. In the validation set, ROC curve analysis showed that the model achieved an area under the ROC curve (AUC) of 0.723, and the calibration curve showed good consistency between the predicted probability of the model and the observed probability. Among the machine learning algorithms, including MLP, SVM, NB, GBM, RF, and XGB, the SVM model and RF model demonstrated relatively good predictive performance, with AUC of 0.748 and 0.739, respectively, and the sensitivity was both exceeding 85%. The predictive performance of the XGB model was explained through SHAP analysis, and the results indicated that APSIII score (SHAP value was 0.871), age (SHAP value was 0.521), and OASIS score (SHAP value was 0.443) were important factors affecting the predictive performance of the model. CONCLUSIONS The machine learning-based SAE prediction model exhibits good predictive capability and holds significant application value for the early identification of SAE risk in elderly septic patients.
Humans ; Machine Learning ; Aged ; Sepsis-Associated Encephalopathy ; Sepsis/complications* ; Intensive Care Units ; Logistic Models ; Middle Aged ; Male ; ROC Curve ; Female ; Bayes Theorem ; Nomograms ; Support Vector Machine ; Algorithms

Objective To investigate the expression of PLCD3 mRNA in the synovium of osteoarthritis(OA)and its relationship with immune cell infiltration.Methods Based on the differentially expressed genes of OA found in the previous study,the expression of phospholipase Cδ3(PLCD3)mRNA was detected by col-lecting synovial samples from OA group and control group.CIBERSORT algorithm was used to analyze the infiltration pattern of immune cells in OA group and control group,and the correlation between PLCD3 and infiltrating immune cells was further analyzed.Results Compared with the control group,the relative expres-sion level of PLCD3 mRNA was significantly increased in synovial samples of OA group(P<0.05).The pro-portions of B cells naive,NK cells activated,M2 macrophages and mast cells activated in synovial tissues of OA group were relatively high(P<0.05).PLCD3 was positively correlated with the proportion of these four immune cells(P<0.05).Conclusion PLCD3 may be a key biomarker for the diagnosis of OA,which may be involved in the pathogenesis of OA by interacting with infiltrating immune cells.

BACKGROUND:Molecular mechanisms targeting the miRNA/mRNA axis to regulate osteoarthritis disease process have been studied.We identified the mRNA:phospholipase C delta 3(PLCD3)and its target miRNA(miR-34a-5p)with clinical predictive value through previous bioinformatics studies,while experiments to verify their specific roles and mechanisms in regulating osteoarthritis are still lacking. OBJECTIVE:To investigate the regulatory role and mechanism of miR-34a-5p/PLCD3 axis on osteoarthritis progression. METHODS:The synovium of 15 patients with knee osteoarthritis was selected as the osteoarthritis group,and the synovium of 15 young patients with internal fixation of patellar fracture caused by trauma during the same period was selected as the control group.The expression of PLCD3 and miR-34a-5p in the synovium was detected by real-time PCR.Human fibroblast like synovial cells-osteoarthritis(HFLS-OA)cells were treated by cell transfection and divided into miR-34a-5p mimic group,pCDH-PLCD3 group,miR-34a-5p mimic+pCDH-PLCD3 group,miR-34a-5p inhibitor group,si-PLCD3 group,and miR-34a-5p inhibitor+si-PLCD3 group.The relationship between PLCD3 and miR-34a-5p expression was detected by real-time PCR.The effects of HFLS-OA cell viability and cell migration in each group were detected by CCK-8 assay and cell scratch test.Western blot assay was used to detect the expression level of apoptosis marker protein.The expression of inflammatory factors was detected by ELISA. RESULTS AND CONCLUSION:(1)PLCD3 was a direct target of miR-34a-5p,and the expression levels of PLCD3 and miR-34a-5p were negatively correlated.(2)Upregulation of PLCD3 promoted proliferation of HFLS-OA cells and inhibited cell migration.The up-regulation of miR-34a-5p significantly inhibited the activity of HFLS-OA cells and enhanced cell migration.Overexpression of miR-34a-5p significantly increased the levels of Casp3 and Casp9 proteins in HFLS-OA cells,while overexpression of PLCD3 showed the opposite trend.(3)PLCD3 overexpression significantly increased the expression of interleukin 6 and tumor necrosis factor alpha in HFLS-OA cells,while miR-34a-5p mimics showed protective activity.(4)The miR-34a-5p/PLCD3 axis may affect the progression of osteoarthritis by regulating the inflammatory process or apoptosis of synovial cells.

Based on the view of "spleen deficiency generating turbidity"， it is believed that the main pathology of irritable bowel syndrome diarrhea-predominant （IBS-D） is spleen deficiency and turbidity excess， with spleen deficiency as the root and turbidity stagnating intestines as the branch， and the treatment principle of draining turbidity and transporting the center was proposed. In the acute stage， turbidity excess is the main cause， the treatment should unblock the bowels and discharge turbidity， commonly with modified Zhishi Daozhi Decoction （枳实导滞汤）； in the remission stage， spleen deficiency is the main cause， the treatment should boost qi and fortify the spleen， commonly with modified Qiwei Baizhu Powder （七味白术散）. Treating the branch in acute conditions， and treating the root in moderate conditions， so as to help restore the conduction function of the intestines and bowels， the transportation and transformation function of the spleen and stomach， then the water and grains have their own way， clear and turbid each in its own way.

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 compare the safety of radial artery puncture in elderly patients aged 75 years and older who are undergoing neurointerventional procedures.Methods:A single-center retrospective study was conducted, involving 350 elderly patients aged 75 years and older who received neurointerventional treatment at Beijing Tiantan Hospital, Capital Medical University, from June to December 2022.The participants were divided into two groups based on the puncture site: femoral artery puncture and radial artery puncture.The safety indicators compared between the two groups included puncture failure, changes in puncture site, general puncture complications(such as subcutaneous bleeding, puncture site hematoma, and vasospasm), severe puncture complications(including distal limb ischemia and pseudoaneurysm), and lower limb venous thrombosis.Multivariate Logistic regression analysis was conducted to evaluate the impact of different puncture methods on the occurrence of complications.Results:Among the 350 patients, 280 underwent femoral artery puncture, while 70 underwent radial artery puncture.There were no statistically significant differences in baseline characteristics between the two groups(all P>0.05).The proportions of patients using antiplatelet drugs prior to surgery, puncture failure rates, rates of change in puncture sites, and the incidence of severe complications-including distal limb ischemia and pseudoaneurysm-were not significantly different between the two groups( χ2=2.051, 0.075, 0.588, 3.175; P=0.152, 0.784, 0.443, 0.075).In the femoral artery puncture group, 20.4%(57 cases)of patients experienced general puncture complications(including subcutaneous bleeding, puncture site hematoma, and vasospasm), whereas only 8.6%(6 cases)in the radial artery puncture group experienced such complications, revealing a statistically significant difference between the two groups( χ2=5.720, P=0.022).Multivariate Logistic regression analysis indicated that, compared to femoral artery puncture, radial artery puncture was associated with a reduced risk of all complications( OR=0.272, 95% CI: 0.139-0.532, P<0.001), general puncture complications( OR=0.375, 95% CI: 0.153-0.919, P=0.032)and lower limb venous thrombosis( OR=0.219, 95% CI: 0.050-0.954, P=0.043). Conclusions:In elderly patients aged 75 years and older who are undergoing neurointerventional procedures, radial artery puncture is associated with a reduced incidence of general puncture complications and lower limb venous thrombosis when compared to femoral artery puncture, indicating a superior safety profile.

Dysphagia is the main complication of chemoradiotherapy for head and neck cancer. Recently, the advancement of multidisciplinary treatment has achieved a higher tumor control rate, but also a higher incidence of late radiation-induced dysphagia in head and neck cancer. Radiation-induced dysphagia leads to prolonged unnatural feeding, nutritional deficiency, weight loss, and also has a major risk for silent aspiration and aspiration pneumonia, which significantly reduces the quality of life of patients. Besides, late radiation-induced dysphagia is the main reason for limiting the intensity of treatment. Therefore, it is of great significance to deeply understand the pathogenesis of radiation-induced dysphagia and actively explore effective prevention and treatment measures to improve the survival rate and quality of life in head and neck cancer. This paper summarizes the pathogenesis, occurrence, risk factors of radiation-induced dysphagia in head and neck cancer, as well as the progress in the measurement and reporting methods, prevention and treatment strategies.

Objective To study the effects of aneurysmal neck angle on stent displacement after endovascular repair of abdominal aortic aneurysm (AAA). Methods The CT images of 28 patients were selected to establish preoperative AAA model, postoperative AAA model and covered stent model respectively, and the models were divided into non-severe angulation group ( n = 14) and severe angulation group ( n = 14) according to the preoperative angle of tumor neck. The geometric shape of each model was measured, and the changes of AAA geometric parameters and postoperative stent displacements before and after surgery were analyzed. The displacement force of the model during the first follow-up was calculated by hemodynamic simulation. Results Significant differences were found in tumor length, maximum diameter, displacement force, tumor neck length and tumor volume between two groups of patients (P<0. 05), while there was no significant difference between COG (the center of gravity) displacement and proximal displacement (P> 0. 05). For the incidence of internal leakage, there were 2 cases in non-severe angulation group and 4 cases in severe angulation group (P>0. 05).Conclusions Severe neck angulation can lead to a significant increase in support displacement force and decrease in proximal anchorage zone, and thus increase the possibility of support displacement. It is suggested that doctors should strengthen postoperative follow-up for patients with severe neck angulation and be vigilant of the occurrence of long-term internal leakage in clinic.

Objective:To assess the predictive performance of the risk of cardiovascular diseases (CVD) derived from the China Kadoorie Biobank (CKB-CVD) model, prediction for atherosclerotic cardiovascular disease (ASCVD) risk in China (China-PAR) model, and the risk of fatal and nonfatal ischemic cardiovascular diseases derived from the USA-People′s Republic of China Collaborative Study (USA-PRC) model in Chinese Multi-provincial Cohort Study (CMCS).Methods:In this prospective cohort study, a total of 21 948 individuals aged ≥35 years without CVD were selected from 8 provinces and cities in China during the CMCS survey from 1992 to 2005 for 10-year follow-up. The occurrence of CVD or ASCVD events during the follow-up period was used as the gold standard. The CKB-CVD and China-PAR models were used to calculate the predicted risk of CVD events, while the USA-PRC model was used to calculate the predicted risk of ASCVD events. The discrimination of the models was evaluated using the C-statistic, and the calibration was assessed using the Hosmer-Lemeshow χ2 test and decile plot. Results:During the 10-year follow-up, a total of 955 (4.4%) CVD events, including 791 (3.6%) ASCVD events, were recorded among the study participants. The C-index for the CKB-CVD, China-PAR, and USA-PRC models were 0.775 (95% CI: 0.757-0.793), 0.781 (95% CI: 0.763-0.798), and 0.769 (95% CI: 0.750-0.789) for men, and 0.762 (95% CI: 0.737-0.788), 0.769 (95% CI: 0.745-0.794), and 0.767 (95% CI: 0.741-0.794) for women, respectively. China-PAR model showed good calibration for men ( χ2=2.20), however, both CKB-CVD and USA-PRC models demonstrated poor calibration in both men and women ( χ2>20). The results indicated that the CKB-CVD model overestimated the risk of CVD events in both males and females, while the China-PAR model underestimated the risk in females. Furthermore, the USA-PRC model underestimated the risk of ASCVD in both males and females in most decile groups, but overestimated the risk in the highest decile group. Conclusion:The CKB-CVD, China-PAR, and USA-PRC risk assessment models show some degree of deviation from the actual risk of events in the CMCS cohort, but all exhibit good discrimination.