Objective To evaluate the predictive ability and clinical application value of artificial intelligence (AI) systems in the benign and malignant differentiation and pathological type of pulmonary nodules, and to summarize clinical application experience. Methods A retrospective analysis was conducted on the clinical data of patients with pulmonary nodules admitted to the Department of Thoracic Surgery, Second Hospital of Lanzhou University, from February 2016 to February 2025. Firstly, pulmonary nodules were divided into benign and non-benign groups, and the discriminative abilities of AI systems and clinicians were compared. Subsequently, lung nodules reported as precursor glandular lesions (PGL), microinvasive adenocarcinoma (MIA), and invasive adenocarcinoma (IAC) in postoperative pathological results were analyzed, comparing the efficacy of AI systems and clinicians in predicting the pathological type of pulmonary nodules. Results In the analysis of benign/non-benign pulmonary nodules, clinical data from a total of 638 patients with pulmonary nodules were included, of which there were 257 males (10 patients and 1 patient of double and triple primary lesions, respectively) and 381 females (18 patients and 1 patient of double and triple primary lesions, respectively), with a median age of 55.0 (47.0, 61.0) years. Different lesions in the same patient were analyzed as independent samples. Univariate analysis of the two groups of variables showed that, except for nodule location, the differences in the remaining variables were statistically significant (P<0.05). Multivariate logistic regression analysis showed that age, nodule type (subsolid pulmonary nodule), average density, spicule sign, and vascular convergence sign were independent influencing factors for non-benign pulmonary nodules, among which age, nodule type (subsolid pulmonary nodule), spicule sign, and vascular convergence sign were positively correlated with non-benign pulmonary nodules, while average density was negatively correlated with the occurrence of non-benign pulmonary nodules. The area under the receiver operating characteristic curve (AUC) of the malignancy risk value given by the AI system in predicting non-benign pulmonary nodules was 0.811, slightly lower than the 0.898 predicted by clinicians. In the PGL/MIA/IAC analysis, clinical data from a total of 411 patients with pulmonary nodules were included, of which there were 149 males (8 patients of double primary lesions) and 262 females (17 patients of double primary lesions), with a median age of 56.0 (50.0, 61.0) years. Different lesions in the same patient were analyzed as independent samples. Univariate analysis results showed that, except for gender, nodule location, and vascular convergence sign, the differences in the remaining variables among the three groups of PGL, MIA, and IAC patients were statistically significant (P<0.05). Multinomial multivariate logistic regression analysis showed that the differences between the parameters in the PGL group and the MIA group were not statistically significant (P>0.05), and the maximum diameter and average density of the nodules were statistically different between the PGL and IAC groups (P<0.05), and were positively correlated with the occurrence of IAC as independent risk factors. The average AUC value, accuracy, recall rate, and F1 score of the AI system in predicting lung nodule pathological type were 0.807, 74.3%, 73.2%, and 68.5%, respectively, all better than the clinical physicians’ prediction of lung nodule pathological type indicators (0.782, 70.9%, 66.2%, and 63.7% respectively). The AUC value of the AI system in predicting IAC was 0.853, and the sensitivity, specificity, and optimal cutoff value were 0.643, 0.943, and 50.0%, respectively. Conclusion This AI system has demonstrated high clinical value in predicting the benign and malignant nature and pathological type of lung nodules, especially in predicting lung nodule pathological type, its ability has surpassed that of clinical physicians. With the optimization of algorithms and the adequate integration of multimodal data, it can better assist clinical physicians in formulating individualized diagnostic and treatment plans for patients with lung nodules.

BACKGROUND: Lung cancer is one of the most common malignant tumors worldwide and a major cause of cancer-related deaths. Early-stage lung cancer is often manifested as pulmonary nodules, and accurate assessment of the malignancy risk is crucial for prolonging survival and avoiding overtreatment. This study aims to construct a model based on image feature parameters automatically extracted by artificial intelligence (AI) to evaluate its effectiveness in predicting the malignancy of part-solid nodule (PSN). METHODS: This retrospective study analyzed 229 PSN from 222 patients who underwent pulmonary nodule resection at Lanzhou University Second Hospital between October 2020 and February 2025. According to pathological results, 45 cases of benign lesions and precursor glandular lesion were categorized into the non-malignant group, and 184 cases of pulmonary malignancies were categorized into the malignant group. All patients underwent preoperative chest computed tomography (CT), and AI software was used to extract imaging feature parameters. Univariate analysis was used to screen significant variables; variance inflation factor (VIF) was calculated to exclude highly collinear variables, and LASSO regression was further applied to identify key features. Multivariate Logistic regression was used to determine independent risk factors. Based on the selected variables, five models were constructed: Logistic regression, random forest, XGBoost, LightGBM, and support vector machine (SVM). Receiver operating characteristic (ROC) curves were used to assess the performance of the models. RESULTS: The independent risk factors for the malignancy of PSN include roughness (ngtdm), dependence variance (gldm), and short run low gray-level emphasis (glrlm). Logistic regression achieved area under the curves ( AUCs) of 0.86 and 0.89 in the training and testing sets, respectively, showing good performance. XGBoost had AUCs of 0.78 and 0.77, respectively, demonstrating relatively balanced performance, but with lower accuracy. SVM showed an AUC of 0.93 in the training set, which decreased to 0.80 in the testing set, indicating overfitting. LightGBM performed excellently in the training set with an AUC of 0.94, but its performance declined in the testing set, with an AUC of 0.88. In contrast, random forest demonstrated stable performance in both the training and testing sets, with AUCs of 0.89 and 0.91, respectively, exhibiting high stability and excellent generalizability. CONCLUSIONS The random forest model constructed based on independent risk factors demonstrated the best performance in predicting the malignancy of PSN and could provide effective auxiliary predictions for clinicians, supporting individualized treatment decisions.
.
Humans ; Male ; Female ; Lung Neoplasms/pathology* ; Middle Aged ; Retrospective Studies ; Artificial Intelligence ; Aged ; Tomography, X-Ray Computed ; Adult ; Solitary Pulmonary Nodule/diagnostic imaging* ; ROC Curve

Background and objective Lung cancer is the cancer with the highest incidence and mortality rates in China,and non-small cell lung cancer(NSCLC)accounts for 80％-85％of all malignant lung tumors.Currently,surgical treat-ment remains the primary treatment modality for lung cancer.In recent years,the effectiveness of immune checkpoint inhibi-tors for NSCLC has become a consensus,and neoadjuvant immunochemotherapy(nICT)has shown promising efficacy and safety in early to intermediate stage NSCLC.However,there are fewer studies related to nICT for locally advanced NSCLC.This study aims to evaluate the efficacy and safety of nICT therapy in locally advanced resectable NSCLC.Methods 85 con-firmed resectable stage ⅢA and ⅢB patients treated in the Department of Thoracic Surgery,Second Hospital of Lanzhou University,from January 2021 to April 2024,were divided into the nICT group(n=32)and the surgery alone group(n=53).Clinical baseline data,perioperative indicators,postoperative complications,imaging response rate,pathological response rate,incidence of adverse events,and quality of life were compared between the two groups.Results There were no statisti-cally significant differences in clinical baseline data between the two groups(P＞0.05).Incidence of choosing thoracotomy was higher in the nICT group than in the surgery alone group(P=0.002).There were no significant differences in surgical time,intraoperative blood loss,number of dissected lymph nodes,duration of chest tube placement,postoperative hospital stay,and R0 resection rate between the two groups(P＞0.05).The overall incidence of postoperative complications was 31.25％in the nICT group and 22.64％in the surgery alone group,with no statistically significant difference(P=0.380).In the nICT group,the objective response rate(ORR)was 84.38％,with 5 cases of complete response(CR)(15.63％),22 cases of partial response(PR)(68.75％),15 cases of pathological response rate(pCR)(46.88％),and 11 cases of major pathological reaponse(MPR)(34.38％).During nICT treatment,12 cases(37.50％)experienced grade 3 treatment-related adverse events,no death induced by adverse events or immune related adverse events.Moreover,the symptoms of the patients were improved after nICT treat-ment.Conclusion Neoadjuvant immunochemotherapy shows promising efficacy in locally advanced resectable NSCLC,with manageable treatment-related adverse events.It is a safe and feasible neoadjuvant treatment modality for locally advanced resectable NSCLC.

OBJECTIVE:To systematically review the clinical effect of blood flow restriction training on rehabilitation after anterior cruciate ligament reconstruction to provide a reference for clinical practice. METHODS:Databases including CNKI,WanFang,PubMed,Web of Science and EBSCO were searched to collect randomized controlled trials of blood flow restriction training in the intervention of anterior cruciate ligament reconstruction from inception to August 10,2022.Outcomes included knee muscle strength,knee muscle mass,and knee function evaluation,all of which were continuous variables.Two reviewers independently screened the literature and extracted data.Cochrane bias risk assessment tool and Physiotherapy Evidence Database Scale were used to evaluate the bias risk of the included articles.Meta-analysis was then performed using RevMan 5.4 software. RESULTS:A total of 9 publications were included,including 226 subjects,114 in the trial group and 112 in the control group.Meta-analysis results showed that compared with conventional resistance training,the blood flow restriction training group could significantly improve knee muscle strength[SMD=0.54,95%CI(0.29,0.79),P＜0.01],muscle mass[SMD=0.26,95%CI(0.06,0.46),P=0.01]and knee joint function[SMD=1.17,95%CI(0.53,1.80),P＜0.01].Subgroup analysis showed that only when the intervention time was more than 4 weeks,there were significant improvements in knee joint muscle strength[SMD=0.68,95%CI(0.38,0.97),P＜0.01]and muscle mass[SMD=0.38,95%CI(0.09,0.68),P=0.01]. CONCLUSION:Current evidence shows that blood flow restriction training can improve muscle strength and knee function in patients with anterior cruciate ligament reconstruction and reduce muscle atrophy.It is recommended that the postoperative intervention time should be more than 4 weeks to achieve better muscle strength and muscle mass improvement.

BACKGROUND: LY01005 (Goserelin acetate sustained-release microsphere injection) is a modified gonadotropin-releasing hormone (GnRH) agonist injected monthly. This phase III trial study aimed to evaluated the efficacy and safety of LY01005 in Chinese patients with prostate cancer. METHODS: We conducted a randomized controlled, open-label, non-inferiority trial across 49 sites in China. This study included 290 patients with prostate cancer who received either LY01005 or goserelin implants every 28 days for three injections. The primary efficacy endpoints were the percentage of patients with testosterone suppression ≤50 ng/dL at day 29 and the cumulative probability of testosterone ≤50 ng/dL from day 29 to 85. Non-inferiority was prespecified at a margin of -10%. Secondary endpoints included significant castration (≤20 ng/dL), testosterone surge within 72 h following repeated dosing, and changes in luteinizing hormone, follicle-stimulating hormone, and prostate specific antigen levels. RESULTS: On day 29, in the LY01005 and goserelin implant groups, testosterone concentrations fell below medical-castration levels in 99.3% (142/143) and 100% (140/140) of patients, respectively, with a difference of -0.7% (95% confidence interval [CI], -3.9% to 2.0%) between the two groups. The cumulative probabilities of maintaining castration from days 29 to 85 were 99.3% and 97.8%, respectively, with a between-group difference of 1.5% (95% CI, -1.3% to 4.4%). Both results met the criterion for non-inferiority. Secondary endpoints were similar between groups. Both treatments were well-tolerated. LY01005 was associated with fewer injection-site reactions than the goserelin implant (0% vs . 1.4% [2/145]). CONCLUSION: LY01005 is as effective as goserelin implants in reducing testosterone to castration levels, with a similar safety profile. TRIAL REGISTRATION ClinicalTrials.gov, NCT04563936.
Humans ; Male ; Antineoplastic Agents, Hormonal/therapeutic use* ; East Asian People ; Gonadotropin-Releasing Hormone/agonists* ; Goserelin/therapeutic use* ; Prostate-Specific Antigen ; Prostatic Neoplasms/drug therapy* ; Testosterone

Objective:To explore the cause of death of 2 suspected Yunnan sudden unexplained death (YNSUD) cases in Dayao County, Yunnan Province.Methods:The field epidemiological investigation and autopsy of 2 cases of YNSUD in Dayao County from June 15 to 20, 2020 were conducted; and blood and tissue samples were collected for qualitative analysis of common poisons and drugs.Results:The areas where the two cases were located were all seriously ill villages with a history of YNSUD, and the time of death occurred in the onset season of YNSUD. There was no blood relationship between the 2 cases, no obvious abnormal symptoms before death, no special diet, no history of exposure to pesticides and other toxic chemicals, and the test results of common poisons were all negative. Autopsy pathological examination results showed that case 1 died of acute cardiac dysfunction caused by sudden acute myocardial infarction of coronary heart disease, and case 2 died of central respiratory and circulatory failure caused by spontaneous subarachnoid hemorrhage.Conclusions:The two cases are excluded from YNSUD through autopsy, and the cause of death is determined. It is suggested that emergency response should be taken as soon as possible for YNSUD cases, and autopsy should be actively carried out to clarify the cause of death from a pathological point of view.

Objective To investigate the characteristics of knee kinematics and ground reaction force (GRF), as well as the stress state of cartilage and meniscus in the process of lateral incisions at different cutting angles under expected conditions. Methods Kinematics and GRF data of 14 subjects at 45°, 90° and 135° cutting angle respectively under expected conditions were collected. The knee joint reaction force was obtained through the inverse dynamics calculation of Visual 3D. Based on three-dimensional (3D) finite element model of the knee joint, the contact process at 3 lateral cutting angles was simulated. ResultsUnder expected conditions, there were significant differences in knee joint kinematics characteristics at 3 cutting angles during contact process(P＜0.001), and the knee flexion increased with the cutting angle increasing; the vertical GRF decreased significantly with the cutting angle increasing (P＜0.001), while the horizontal GRF showed the opposite trend; for 3 cutting angles, the peak contact stress of patellar cartilage and femoral cartilage was larger at 90° cutting angle, the peak principal stress at anterior cruciate ligament (ACL) contact point was also larger at 90° cutting angle, and the following was at 135° and 45° cutting angle, respectively; the peak contact stress of lateral femoral cartilage was larger than that of medial femoral cartilage at 3 cutting angles. Conclusions The risk of knee joint injury is higher at 90° cutting angle, and the stress state of knee joint at 135° cutting angles is better than that at 90° cutting angle, and the risk of knee joint injury does not increase with the increase of cutting angle under expected conditions.

[Abstract] Objective: To explore the role of adhesion molecule with Ig like domain 2 (AMIGO2) in the proliferation of nasopharyn‐ geal carcinoma (NPC) cells and its mechanisms. Methods: A total of 10 NPC tissue samples and 10 normal nasopharyngeal epithelial tissue samples collected at Fujian Cancer Hospital during September 2017 and November 2017 were used for this study; in addition, NPC cell lines (CNE-1, CNE-2, SUNE-1, 6-10B, C666-1) and human immobilized nasopharyngeal epithelial cell line NP69 were also collected. The relative expression of AMIGO2 mRNAin above mentioned tissues and cell lines was detected by qPCR. Lentivirus vectors were constructed to interfere AMIGO2 mRNA expression, and qPCR was used to verify its interference efficiency. CCK-8 method, Clonal formation and Flow cytometry were performed to evaluate the effect of AMIGO2 interference on proliferation, clone formation and apoptosis of NPC cells. The influence of AMIGO2 interference on PI3K/AKT/mTOR signaling pathway and proliferation related molecular markers in NPC cells was assessed by Western blotting. Results: The results of qPCR showed that AMIGO2 was highly expressed in NPC tissues, CNE-2, and SUNE-1 cells (all P<0.01). The interference efficiency of AMIGO2 in CNE-2 and SUNE-1 cells could reach over 50%. The interfering of AMIGO2 expression significantly inhibited the proliferation and clone formation of CNE-2 and SUNE-1 cells (all P<0.01), promoted cell apoptosis (all P<0.01), reduced the phosphorylated protein expression levels of PI3K, AKT and mTOR in SUNE-1 cells (all P<0.01), as well as down-regulated the protein expressions of survivin and PCNA (all P<0.01). Conclusion: AMIGO2 may promote the proliferation as well as inhibit apoptosis of NPC cells by activating the PI3K/AKT/mTOR signaling pathway, suggesting that AMIGO2 may be a potential target for NPC therapy.

OBJECTIVE： To study the effects of Tiaopi huxin prescription （TPHXP） on the atherosclerosis （AS） of ApoE－/－ mice， and to investigate its mechanism. METHODS： Forty male ApoE－/－ mice were divided into blank group， model group， simvastatin group （positive control， 5 mg/kg） and TPHXP low-dose and high-dose groups （50， 150 mg/kg）， with 8 mice in each group. Except that blank group was given common diet， other groups were given high-lipid diet to induce AS model. After modeling， administration groups were given relevant medicine intragastrically， and blank group and model group were given constant volume of normal saline intragastrically， once a day， for consecutive 12 weeks. After last medication， the serum levels of TC， TG， LDL-C and HDL-C were determined by spectrophotometry. The serum level of NO was detected by nitrate reduction method. The serum levels of IL-6 and VCAM-1 were determined by ELISA. After separating thoracic aorta， HE staining was used to observe the formation of plaque in the thoracic aorta of mice in each group， and the corrected plaque area was calculated. Western blotting was conducted to determine the expression of NF-κB p65， Cav-1 and eNOS. RESULTS： Compared with blank group， the serum levels of TC， TG， LDL-C， IL-6 and VCAM-1 were increased significantly in model group， while the levels of HDL-C and NO were decreased significantly （P＜0.01）. The plaque of thoracic aorta was obvious and the corrected plaque area were increased significantly （P＜0.01）. The relative expression of NF-κB p65 and Cav-1 were increased significantly， while the relative expression of eNOS was decreased significantly （P＜0.01）. Compared with model group， the serum levels of TC， TG and LDL-C in administration groups， the serum levels of IL-6 and VCAM-1 in simvastatin group and TPHXP high-dose group were decreased significantly， while the serum levels of HDL-C and NO were increased significantly in administration groups （P＜0.05 or P＜0.01）. In administration groups， the plaques of thoracic aorta were reduced and the corrected plaque area was decreased significantly （P＜0.05 or P＜0.01）； the relative expression of NF-κB p65 and Cav-1 were decreased significantly， while the relative expression of eNOS was increased significantly （P＜0.05 or P＜0.01）. CONCLUSIONS： TPHXP can regulate the level of blood lipid， decrease the level of inflammatory factors and inhibit the formation of AS plaque， the mechanism of which may be associated with inhibiting Cav-1/NF-κB pathway.

OBJECTIVE： To study the mechanism of Prunus persica-Carthamus tinctorius couplet medicine in the treatment of osteonecrosis of the femoral head （ONFH）. METHODS： The network pharmacology was adopted. The active components of P. persica -C. tinctorius couplet medicine and ONFH target were screened through TCM systematic pharmacological analysis platform target （TCMSP）， DRAR-CPI， hnuman gene database （GeneCards） and online medelian inheritance in man （OMIM） using oral availability of compounds （OB）＞30％ and drug like （DL）＞0.18 as standard. Network topology attribute analysis software Cytoscape 3.6.0 was utilized to construct the active components-ONFH targets network. Target protein interaction network was established on the basis of STRING database， and top 5 target proteins in the list of connectivity were screened， and molecular docking server was used to predict the combination activity of active components from P. persica -C. tinctorius couplet medicine. The biological processes of target gene ontology （GO） and metabolic pathways in Kyoto encyclopedia of genes and genomes （KEGG） were enriched and analyzed by DAVID. RESULTS： A total of 44 active components were screened from P. persica -C. tinctorius couplet medicine， including baicalin， quercetin， etc.， and 78 targets related to ONFH including VEGF， VEGI， CRP， etc. Through analysis of molecular docking server， binding activity of active components of P. persica -C. tinctorius couplet medicine to target protein was strong. GO and KEGG pathway enrichment analysis showed that biological process of P. persica -C. tinctorius couplet medicine for ONFH was related with negative regulation of apoptosis process and positive regulation of nuclear factor-κB transcription factor， mainly through regulating secretory glycoprotein signaling pathway， melanogenesis signaling pathway， VEGF signaling pathway， signaling pathway of basal cell carcinoma， adenosine-activated protein kinase signaling pathway. CONCLUSIONS： This study preliminarily validates the major targets and pathways of P. persica -C. tinctorius couplet medicine for ONFH， which lay a foundation for further study on their pharmacological action.