OBJECTIVE: To identify the optimal machine learning algorithm for predicting post-stroke epilepsy (PSE) within one year following acute stroke, establish a nomogram model based on this algorithm, and perform external validation to achieve accurate prediction of secondary epilepsy. METHODS: A total of 870 acute stroke patients admitted to the emergency department of Xiang'an Hospital of Xiamen University from June 2019 to June 2023 were enrolled for model development (model group). An external validation cohort of 435 acute stroke patients admitted to the Fifth Hospital of Xiamen during the same period was used to validate the machine learning algorithms and nomogram model. Patients were classified into control and epilepsy groups based on the development of PSE within one year. Clinical and laboratory data, including baseline characteristics, stroke location, vascular status, complications, hematologic parameters, and National Institutes of Health Stroke Scale (NIHSS) score, were collected for analysis. Nine machine learning algorithms such as logistic regression, CN2 rule induction, K-nearest neighbors, adaptive boosting, random forest, gradient boosting, support vector machine, naive Bayes, and neural network were applied to evaluate predictive performance. The area under the curve (AUC) of receiver operator characteristic curve (ROC curve) was used to identify the optimal algorithm. Logistic regression was used to screen risk factors for PSE, and the top 10 predictors were selected to construct the nomogram model. The predictive performance of the model was evaluated using the ROC curve in both the model and validation groups. RESULTS: Among the 870 patients in the model group, 29 developed PSE within one year. Among the nine algorithms tested, logistic regression demonstrated the best performance and generalizability, with an AUC of 0.923. Univariate logistic regression identified several risk factors for PSE, including platelet count, white blood cell count, red blood cell count, glycated hemoglobin (HbA1c), C-reactive protein (CRP), triglycerides, high-density lipoprotein (HDL), aspartate aminotransferase (AST), alanine aminotransferase (ALT), activated partial thromboplastin time (APTT), thrombin time, D-dimer, fibrinogen, creatine kinase (CK), creatine kinase-MB (CK-MB), lactate dehydrogenase (LDH), serum sodium, lactic acid, anion gap, NIHSS score, brain herniation, periventricular stroke, and carotid artery plaque. Further multivariate logistic regression analysis showed that white blood cell count, HDL, fibrinogen, lactic acid and brain herniation were independent risk factors [odds ratio (OR) were 1.837, 198.039, 47.025, 11.559, 70.722, respectively, all P < 0.05]. In the external validation group, univariate logistic regression analysis showed that platelet count, white blood cell count, CRP, triacylglycerol, APTT, D-dimer, fibrinogen, CK, CK-MB, LDH, NIHSS score, and cerebral herniation were risk factors for PSE one year after acute stroke. Further multiple logistic regression analysis showed that APTT and cerebral herniation were independent predictors (OR were 0.587 and 116.193, respectively, both P < 0.05). The nomogram model, constructed using 10 key variables-brain herniation, periventricular stroke, carotid artery plaque, white blood cell count, triglycerides, thrombin time, D-dimer, serum sodium, lactic acid, and NIHSS score-achieved an AUC of 0.908 in the model group and 0.864 in the external validation group. CONCLUSIONS The logistic regression-based prediction model for epilepsy one year after acute stroke, developed using machine learning algorithms, showed optimal predictive performance. The nomogram model based on the logistic regression-derived predictors showed strong discriminative power and was successfully validated externally, suggesting favorable clinical applicability and generalizability.
Humans ; Machine Learning ; Stroke/complications* ; Nomograms ; Epilepsy/etiology* ; Algorithms ; Male ; Female ; Logistic Models ; Middle Aged ; Aged ; Risk Factors ; Bayes Theorem

Objective To investigate the correlation between human leucocyte antigen-DQA1(HLA-DQA1)and clinical characteristics of patients with Sj?gren's syndrome(SS).Methods A total of 242 SS patients admitted to the First Affiliated Hospital of Baotou Medical College from August 2022 to August 2023 were selected as the study objects.According to the HLA-DQA1 test results,the patients were divided into HLA-DQA1 positive group(n=147)and HLA-DQA1 negative group(n=95).The clinical manifestations,laboratory indicators,labial gland biopsy and disease activity were compared between two groups.Receiver operating characteristic curve was used to analyze the diagnostic value of HLA-DQA1 for disease activity in SS patients.Results The proportion of dry mouth,dry eye and purpura,the proportion of anti-SSA antibodies,anti-SSB antibodies,antinuclear antibody(ANA)positive and the level of immunoglobulin G in HLA-DQA1 positive group were significantly higher than those in HLA-DQA1 negative group(P＜0.05),and the hemoglobin level was significantly lower than that in HLA-DQA1 negative group(P＜0.05).The disease activity of HLA-DQA1 positive group was significantly higher than that of HLA-DQA1 negative group(P＜0.05).The areas under the curve of HLA-DQA1,anti-SSA antibody and anti-SSB antibody to determine the disease activity of SS patients were 0.593,0.534 and 0.593,respectively.The area under the curve of disease activity of SS patients judged by the three indexes combined was 0.638.Conclusion HLA-DQA1 is correlated with the disease activity of SS patients.In HLA-DQA1 positive patients,dry mouth,dry eyes,hyperglobulinemia,anemia and purpura were more obvious.Meanwhile,the positive rates of anti-SSA/SSB antibodies and ANA were higher,suggesting that HLA-DQA1 expression is helpful in judging the disease of SS patients.

Objective: QL1604 is a highly selective, humanized monoclonal antibody against programmed death protein 1. We assessed the efficacy and safety of QL1604 plus chemotherapy as first-line treatment in patients with advanced cervical cancer. Methods: This was a multicenter, open-label, single-arm, phase II study. Patients with advanced cervical cancer and not previously treated with systemic chemotherapy were enrolled to receive QL1604 plus paclitaxel and cisplatin/carboplatin on day 1 of each 21-day cycle for up to 6 cycles, followed by QL1604 maintenance treatment. Results: Forty-six patients were enrolled and the median follow-up duration was 16.5 months. An 84.8% of patients had recurrent disease and 13.0% had stage IVB disease. The objective response rate (ORR) per Response Evaluation Criteria in Advanced Solid Tumors (RECIST) v1.1 was 58.7% (27/46). The immune ORR per immune RECIST was 60.9% (28/46).The median duration of response was 9.6 months (95% confidence interval [CI]=5.5–not estimable). The median progression-free survival was 8.1 months (95% CI=5.7–14.0). Fortyfive (97.8%) patients experienced treatment-related adverse events (TRAEs). The most common grade≥3 TRAEs (>30%) were neutrophil count decrease (50.0%), anemia (32.6%), and white blood cell count decrease (30.4%). Conclusion QL1604 plus paclitaxel-cisplatin/carboplatin showed promising antitumor activity and manageable safety profile as first-line treatment in patients with advanced cervical cancer. Programmed cell death protein 1 inhibitor plus chemotherapy may be a potential treatment option for the patient population who have contraindications or can’t tolerate bevacizumab, which needs to be further verified in phase III confirmatory study.

Objective To explore the application and effect of a pulmonary rehabilitation exercise program in patients with moderate to severe COPD based on the Information-Motivation-Behavior Skill(IMB)Model.Methods The convenience sampling method was adopted to select patients with moderate to severe COPD admitted to the department of respiratory and critical care medicine in a tertiary A hospital in Yantai City from October 2021 to February 2022.They were randomly divided into an intervention group(32 cases)and a control group(31 cases).The intervention group was treated with the pulmonary rehabilitation exercise program based on the IMB model on the basis of routine nursing,while the control group was treated with routine nursing.The degree of dyspnea,exercise endurance,quality of life,pulmonary rehabilitation exercise compliance,self-management ability and lung function were compared between the 2 groups before and 6 months after the intervention.Results After intervention,the degree of dyspnea,exercise endurance,quality of life,pulmonary rehabilitation exercise compliance and self-management ability were significantly different between the 2 groups(P＜0.05).There was no statistically significant difference in lung function between the 2 groups after intervention(P＞0.05).Conclusion The pulmonary rehabilitation program based on IMB model can effectively alleviate the symptoms of dyspnea in patients with moderate to severe COPD,improve exercise endurance,improve pulmonary rehabilitation exercise compliance and self-management ability,and improve the patients'quality of life.

Objective:To investigate the role of p-AKT-mTOR-P70S6K signaling pathway in radiation therapy for polyploid cervical cancer cells.Methods:Human cervical cancer HeLa cell lines were selected and HeLa cells were radiated under 7 Gy of 6 MV X-ray. The morphological changes of the cells were observed with an inverted microscope on day 5 after radiation induction. All cells were divided into the 7 Gy group (7 Gy X-ray radiation but not transfected polyploidy HeLa cells) and the control group (the non-radiation-induced and not transfected HeLa cells). In addition, the plasmid carrying pcDNA3 negative control sequence and the plasmid carrying pcDNA3-TT-AKT sequence were transfected into HeLa cells, respectively, which were induced by 7 Gy X-ray radiation after 48 h of transfection, and then they were recorded as the pcDNA3 + 7 Gy group and the pcDNA3-TT-AKT + 7 Gy group. Cell proliferation ability was detected by using CCK-8 assay, cell cycle was detected by using flow cytometry, cell apoptosis was detected by using mitochondrial membrane potential assay, the relative expression levels of cell proliferation, cell cycle, apoptosis and autophagy related proteins were tested by using Western blot.Results:Most of the normal HeLa cells in the 7 Gy group died on day 5 after radiation induction, and only a few surviving cells increased in size with multiple nuclei. The results of Western blot showed that the relative expression levels of p-AKT, p-mTOR and p-P70S6K in HeLa cells of the 7 Gy group were lower than those of the control group (all P < 0.05). CCK-8 assay showed that the absorbance ( A) values were 0.45±0.06, 0.65±0.06 after 48 h of culture and 0.75±0.05, 1.05±0.02 after 72 h of culture, respectively in the pcDNA3 + 7 Gy group and the pcDNA3-TT-AKT + 7 Gy group, and the differences were statistically significant (all P < 0.05), and the A values in the pcDNA3-TT-AKT + 7 Gy group were all higher than those in the pcDNA3 +7 Gy group. Flow cytometry results showed that the proportion of cells was (29.2±3.6)%, (26.7±1.7)% in G 0/G 1 phase and (29.6±1.6)%, (30.3±0.6)% in G 2/M phase, respectively in the pcDNA3 + 7 Gy group and the pcDNA3-TT-AKT + 7 Gy group, and the differences were not statistically significant (all P > 0.05); the proportion of cells in S phase was (10.2±0.9)% and (14.6±1.5)%, respectively in the pcDNA3 + 7 Gy group and the pcDNA3-TT-AKT + 7 Gy group, and the differences were statistically significant ( t = 2.86, P = 0.043). Mitochondrial membrane potential assay showed that the green fluorescence proportion was (23.1±2.5)% and (14.3±1.9)%, respectively in the pcDNA3 + 7 Gy group and the pcDNA3-TT-AKT + 7 Gy group, and the different was statistically significant ( t = 4.82, P = 0.009). Western blot results showed that the relative expression level of p-cdc25c (Ser216) in the pcDNA3-TT-AKT+7 Gy group was higher than that in the pcDNA3+7 Gy group ( P < 0.001); and the relative expression levels of Bak and LC3-Ⅱ/Ⅰ in the pcDNA3-TT-AKT+7Gy group were lower than those in the pcDNA3 +7 Gy group, respectively (all P < 0.05). Conclusions:The p-AKT-mTOR-P70S6K signaling pathway may be involved in the regulation of radiation-induced polyploidy HeLa cell proliferation, cell cycle and cell apoptosis.

Objective:To construct an evidence-based prediction model for early recurrence after surgery of hepatocellular carcinoma (HCC) based on Meta-analysis and to do external validation study.Methods:The literatures in Chinese National Knowledge Infrastructure, Wanfang, VIP, Chinese Science Citation Database (CSCD), Chinese Social Science Citation System (CCSCI), PubMed, Web of Science and IEEE databases between January 2019 and December 2023 were searched based on the subject words. According to the inclusion and exclusion criteria, 9 literatures were included to screen the risk factors affecting the early recurrence of HCC. When the same risk factor was found in ≥5 included literatures, Meta-analysis was performed by using Review Manager 5.4.1 software. External validation data were collected from 401 patients with primary HCC who underwent surgery in Liaoning Cancer Hospital between March 2014 and March 2017. The patients were divided into early recurrence group (176 cases) and early non-recurrence group (225 cases) according to whether they relapsed 2 years after surgery. The OR values of all risk factors obtained in the Meta-analysis were converted into modeling, and postoperative early recurrence rate of HCC in the Meta-analysis was used to calculate β 0, and finally the logistic model was obtained. The OR value was incorporated into the logit (P) model, and the morbidity (P) of the external validation data was calculated. Taking the recurrence 2 years after surgery or not as the dependent variable and P as the independent variable, the receiver operating characteristic (ROC) curve was drawn to calculate the area under the curve (AUC). Results:A total of 8 risk factors for early HCC recurrence were screened out from 9 literatures (x 1: alpha-fetoprotein ≥ 400 ng/ml; x 2: tumor number ≥ 2; x 3: the longest tumor diameter ≥ 5 cm; x 4: Barcelona staging B-C; x 5: microvascular invasion; x 6: moderate to low differentiation; x 7: incomplete capsule; x 8: nonanatomic hepatectomy). The Meta-analysis included 1 757 HCC cases, with 960 postoperative early recurrences and an early recurrence rate of 45.36%, finally the β 0 value was -0.201. The predictive model for 2-year recurrence of HCC was constructed and calculated as logit (P) = -0.201+0.835x 1+0.905x 2+0.783x 3+1.008x 4+0.765x 5+0.831x 6+1.533x 7+0.940x 8. Analysis of variance by external validation data showed that the differences in ascites, alpha-fetoprotein, tumor number, tumor diameter, Barcelona staging, microvascular invasion, tumor differentiation degree, capsule invasion, resection type, and systemic inflammation index were statistically significant between early recurrence group and early non-recurrence group (all P < 0.05). ROC curve analysis showed that AUC of postoperative early recurrence of HCC predicted by the model was 0.718, (95% CI: 0.689-0.753), the optimal cut-off value was 3.11, the Yoden index was 0.288, the sensitivity was 69.32%, and the specificity was 69.56%. Conclusions:The evidence-based prediction model constructed based on Meta-analysis for postoperative early recurrence of HCC has a high predictive value. However, further verification and optimization with big data is still needed.

Objective: QL1604 is a highly selective, humanized monoclonal antibody against programmed death protein 1. We assessed the efficacy and safety of QL1604 plus chemotherapy as first-line treatment in patients with advanced cervical cancer. Methods: This was a multicenter, open-label, single-arm, phase II study. Patients with advanced cervical cancer and not previously treated with systemic chemotherapy were enrolled to receive QL1604 plus paclitaxel and cisplatin/carboplatin on day 1 of each 21-day cycle for up to 6 cycles, followed by QL1604 maintenance treatment. Results: Forty-six patients were enrolled and the median follow-up duration was 16.5 months. An 84.8% of patients had recurrent disease and 13.0% had stage IVB disease. The objective response rate (ORR) per Response Evaluation Criteria in Advanced Solid Tumors (RECIST) v1.1 was 58.7% (27/46). The immune ORR per immune RECIST was 60.9% (28/46).The median duration of response was 9.6 months (95% confidence interval [CI]=5.5–not estimable). The median progression-free survival was 8.1 months (95% CI=5.7–14.0). Fortyfive (97.8%) patients experienced treatment-related adverse events (TRAEs). The most common grade≥3 TRAEs (>30%) were neutrophil count decrease (50.0%), anemia (32.6%), and white blood cell count decrease (30.4%). Conclusion QL1604 plus paclitaxel-cisplatin/carboplatin showed promising antitumor activity and manageable safety profile as first-line treatment in patients with advanced cervical cancer. Programmed cell death protein 1 inhibitor plus chemotherapy may be a potential treatment option for the patient population who have contraindications or can’t tolerate bevacizumab, which needs to be further verified in phase III confirmatory study.

Objective To explore the mechanism of Marsdenia tenacissima in the treatment of breast cancer through network pharmacology and experimental verification.Methods Literature retrieval was conducted to obtain the active components of Marsdenia tenacissima.The SwissTargetPrediction database was used to predict the potential targets of these active components.Targets of breast cancer were obtained from GeneCards,GEPIA2,OMIM,PharmGKB and TTD databases.The intersection targets were obtained,and a Marsdenia tenacissima-breast cancer-targets network was constructed using Cytoscape 3.9.0 software.The core targets were identified through protein-protein interaction(PPI)network analysis,followed by GO and KEGG pathway enrichment analysis to screen relevant signaling pathways.Molecular docking validation was performed for the top 10 key targets and major active components.The human breast cancer cell line MDA-MB-231 was treated with Marsdenia tenacissima injection in vitro.Cell proliferation ability was detected by CCK-8 assay and colony formation assay.Cell apoptosis was detected by Calcein-AM/PI staining and flow cytometry.Cell migration ability was detected by Transwell assay.Western blot experiment was used to validate the PI3K-AKT signaling pathway.Results Totally 37 active components and 276 potential targets against breast cancer were screened from Marsdenia tenacissima,including 11alpha-O-Benzoyl-12beta-O-acetyl tenacigenin B,Caffeic acid,Drevogenin A and Kaempferol.25 core targets were screened by PPI network such as AKT1,EGFR,TNF,CTNNB1 and IL-6,which mainly affected the estrogen signaling pathway,ErbB signaling pathway,HIF-1 signaling pathway and PI3K-AKT signaling pathway,etc.The molecular docking results showed that the main active components of Marsdenia tenacissima exhibited good binding activities with the core targets AKT1,ALB,CASP3,ESR1 and TNF.The results of in vitro experiments showed that Marsdenia tenacissima injection could inhibit the proliferation and migration ability of MDA-MB-231 cells(P<0.01,P<0.001)and induce apoptosis(P<0.001),as well as inhibit the activation of PI3K-AKT signaling pathway(P<0.05,P<0.01).Conclusion Marsdenia tenacissima may exert its anti-breast cancer effects through multiple targets and pathways,and the mechanism may be related to the inhibition of PI3K-AKT signaling pathway.

Objective: QL1604 is a highly selective, humanized monoclonal antibody against programmed death protein 1. We assessed the efficacy and safety of QL1604 plus chemotherapy as first-line treatment in patients with advanced cervical cancer. Methods: This was a multicenter, open-label, single-arm, phase II study. Patients with advanced cervical cancer and not previously treated with systemic chemotherapy were enrolled to receive QL1604 plus paclitaxel and cisplatin/carboplatin on day 1 of each 21-day cycle for up to 6 cycles, followed by QL1604 maintenance treatment. Results: Forty-six patients were enrolled and the median follow-up duration was 16.5 months. An 84.8% of patients had recurrent disease and 13.0% had stage IVB disease. The objective response rate (ORR) per Response Evaluation Criteria in Advanced Solid Tumors (RECIST) v1.1 was 58.7% (27/46). The immune ORR per immune RECIST was 60.9% (28/46).The median duration of response was 9.6 months (95% confidence interval [CI]=5.5–not estimable). The median progression-free survival was 8.1 months (95% CI=5.7–14.0). Fortyfive (97.8%) patients experienced treatment-related adverse events (TRAEs). The most common grade≥3 TRAEs (>30%) were neutrophil count decrease (50.0%), anemia (32.6%), and white blood cell count decrease (30.4%). Conclusion QL1604 plus paclitaxel-cisplatin/carboplatin showed promising antitumor activity and manageable safety profile as first-line treatment in patients with advanced cervical cancer. Programmed cell death protein 1 inhibitor plus chemotherapy may be a potential treatment option for the patient population who have contraindications or can’t tolerate bevacizumab, which needs to be further verified in phase III confirmatory study.

Objective:To explore the effect of personalized nutritional support based on nutritional risk screening on nutritional status and prognosis of patients with inflammatory bowel disease.Methods:A total of 100 patients with inflammatory bowel disease admitted to the Department of Gastroenterology, The First Affiliated Hospital of Wenzhou Medical University from January 2021 to September 2022 were selected as the study objects, and were divided into control group and observation group according to the random number method. NRS 2002 nutritional risk screening was performed on all patients. The control group was given routine nursing and nutritional support. On this basis, the observation group received patient-centered personalized nutrition support program shared by doctors and patients. The nutritional status, inflammatory indicators and prognosis of the two groups were compared and observed at admission, discharge, 1 month after discharge, and 3 months after discharge.Results:From admission to 3 months after discharge, albumin, prealbumin, nitrogen balance, triceps skinfold thickness in the two groups were significantly increased ( F = 8.43, 14.32, 10.27, 23.41, 7.66, 8.91, 6.84, 8.90, P < 0.05), while the malnutrition inflammation score was significantly decreased ( F = 4.84, 7.42, P < 0.05). Albumin, prealbumin, nitrogen balance, triceps skinfold thickness in the observation group were significantly higher than those in the control group at 3 months after discharge ( t = 7.95, 17.43, 6.55, 6.72, P < 0.001), and the malnutrition inflammation score was significantly lower than that of the control group ( t = 6.95, P < 0.001). As treatment progressed, the levels of C-reactive protein and fecal calprotectin gradually decreased and the erythrocyte sedimentation rate slowed down in both groups compared with the admission, with statistical significance ( F = 9.03, 11.28, 18.37, 19.20, 32.42, 28.88, P < 0.001). The levels of C-reactive protein and fecal calprotectin and erythrocyte sedimentation rate in the observation group were significantly lower than those in the control group 3 months after discharge ( t = 8.29, 7.99, 10.34, P < 0.001). Patients in the observation group had good compliance with the formulated diet plan, and no related rejection events occurred. The readmission rate of patients in the observation group was significantly lower than that of the control group ( χ2 = 10.18, P < 0.05). Conclusion:Individualized nutrition support programs based on nutritional risk screening can help improve the nutritional status and disease status of patients with inflammatory bowel disease.