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 analyze the clinical characteristics of patients undergoing extracorporeal cardiopulmonary resuscitation (ECPR), and to explore the risk factors leading to poor prognosis.Methods:The clinical data of 95 patients with ECPR admitted to the First Affiliated Hospital of Zhengzhou University from January 2020 to May 2023 were retrospectively analyzed. According to the survival status at the time of discharge, the patients were divided into the survival group and death group. The difference of clinical data between the two groups was compared to explore the risk factors related to death and poor prognosis. Risk factors associated with death were identified by Binary Logistic regression analysis. Results:A total of 95 patients with ECPR were included in this study, 62 (65.3%) died and 33 (34.7%) survived at discharge. Patients in the death group had longer low blood flow time [40 (30, 52.5) min vs. 30 (24.5, 40) min ] and total cardiac arrest time[40 (30, 52.5) min vs. 30(24.5, 40) min], shorter total hospital stay [3 (2, 7.25) d vs. 19 (13.5, 31) d] and extracorporeal membrane oxygenation (ECMO) assisted time [26.5 (17, 50) h vs. 62 (44, 80.5) h], and more IHCA patients (56.5% vs. 33.3%) and less had spontaneous rhythm recovery before ECMO (37.1% vs. 84.8%). Initial lactate value [(14.008 ± 5.188) mmol/L vs.(11.23 ± 4.718) mmol/L], APACHEⅡ score [(30.10 ± 7.45) vs. (25.88 ± 7.68)] and SOFA score [12 (10.75, 16) vs. 10 (9.5, 13)] were higher ( P< 0.05). Conclusions:No spontaneous rhythm recovery before ECMO, high initial lactic acid and high SOFA score are independent risk factors for poor prognosis in ECPR patients.

Objective To investigate the potential mechanism of Jianpi Shenshi Formula for the treatment of hyperuricemia(HUA)by using network pharmacology and molecular docking techniques.Methods The active ingredients of Jianpi Shenshi Formula were searched and screened by combining TCMSP,BATMAN,and TCM-ID database with literature,and then SwissTargetPrediction was used to obtain the corresponding targets of the ingredients.Cytoscape 3.8.0 was used to construct a"drug-ingredients"network to analyze and obtain the main active ingredients of Jianpi Shenshi Formula.The GeneCards,OMIM,and disgenet databases were used to obtain the relevant targets of hyperuricemia.The intersection targets of Jianpi Shenshi Formula and hyperuricemia were imported into the STRING database for protein-protein interaction(PPI)network analysis,and hub targets for network were screened by CytoHubba plug-in.Meanwhile,the GO function and KEGG pathway enrichment analysis of the intersection targets were carried out using R4.2.2 software.Molecular docking of hub targets and key ingredients was performed using CB-DOCK 2.Results A total of 90 active ingredients of Jianpi Shenshi Formula were screened,among which quercetin,kaempferol,luteolin,stigmasterol,and ethyl linoleate were the main active ingredients,and 837 targets corresponding to the ingredients were obtained,with a total of 64 intersecting targets.CASP3,IL1B,IL6,PPARG,SIRT1,MAPK3,TNF,STAT3,TGFβ1,PTGS2,and XDH were the hub targets.The potential targets of action are mainly enriched in signaling pathways such as inflammation,metabolism,environment,cellular processes,biological systems,and hyperuricemia-related pathways.Conclusion Jianpi Shenshi Formula may exert effects on inhibition of uric acid production,and/or enhancement of uric acid excretion,anti-inflammation,and amelioration of related complications through the modulation of hyperuricemia-related signaling pathways(including neoplastic,infectious,metabolic,and cardiovascular diseases),as well as metabolic,immune,inflammatory,and other biological pathways by a variety of active ingredients such as quercetin,kaempferol,luteolin,stigmasterol,and ethyl linoleate.

This study aimed to explore the value of magnetic resonance imaging (MRI) T 2 mapping in the assessment of dermatomyositis (DM) and polymyositis (PM). Thirty-three confirmed cases (myosin group) and eight healthy volunteers (healthy control group) at the Department of Rheumatology and Immunology, the First Affiliated Hospital of Kunming Medical University, from October 2016 to December 2017, were collected and analyzed. Multiple parameters of the myosin group were quantified, including creatine kinase (CK), erythrocyte sedimentation rate (ESR), C-reactive protein (CRP), complement C3, and complement C4. Disease status was evaluated using a panel of tools: myositis disease activity assessment tool-muscle (MDAAT-muscle), myositis disease activity assessment tool-whole (MDAAT-all), health assessment questionnaire (HAQ), medical outcomes study health survey short form-36 item (SF-36), hand muscle strength test (MMT-8) score, and MRI T 2 mapping of muscle (22 muscles in the pelvis and thighs) T 2 values. The results showed that in the myositis group, the measurements for CK, ESR, CRP, complement C3, and complement C4 were 457.2 (165.6, 1 229.2) IU/L, 20 (10, 42) mm/1h, 3.25 (2.38, 10.07) mg/L, 0.90 (0.83, 1.06) g/L, and 0.18 (0.14, 0.23) g/L, respectively. The scores for MMT-8, MDAAT-muscle, MDAAT-all, HAQ, and SF-36 were 57.12±16.23, 5.34 (4.00, 6.00), 34.63±12.62, 1.55 (0.66, 2.59), and 44.66±7.98, respectively. T 2 values were significantly higher in all 22 muscles of the pelvis and thighs of patients with DM or PM compared with the healthy controls [(54.99±11.60)ms vs. (36.62±1.66)ms, P<0.001], with the most severe lesions in the satrorius, iliopsoas, piriformis, gluteus minimus, and gluteus medius muscles. The total muscle T 2 value in the myositis group was positively correlated with CK, MDAAT-muscle, MDAAT-all, and HAQ ( r=0.461, 0.506, 0.347, and 0.510, respectively, all P<0.05). There was a negative correlation between complement C4, SF-36, and MMT-8 scores ( r=-0.424, -0.549, and -0.686, respectively, all P<0.05). Collectively, the findings from this study suggest that MRI T 2 mapping can objectively reflect the disease status of DM and PM.

Objective:To investigate the clinical application of continuous renal replacement therapy (CRRT) in infants with acute kidney injury (AKI) after liver transplantation.Methods:A retrospective study was conducted on infants with AKI after liver transplantation in Tianjin First Center Hospital from January 1, 2019 to June 1, 2021. Infants with AKI within 1 year after liver transplantation were divided into CRRT group and non-CRRT group according to whether CRRT was performed. The preoperative and intraoperative condition, the postoperative complications were compared, the risk factors of CRRT for AKI infants, the clinical characteristics of CRRT were analyzed, and the prognosis between CRRT group and non-CRRT group were compared.Results:① A total of 512 cases of pediatric liver transplantation were performed. A total of 189 cases (36.9%) developed AKI within 1 year after surgery, including 18 cases in CRRT group and 171 cases in non-CRRT group. ② There was no significant difference in preoperative conditions between the two groups. The duration of liver transplantation (hours: 8.8±1.5 vs. 7.5±1.3) and intraoperative blood loss [mL: 370 (220-800) vs. 310 (200-400)] in CRRT group were significantly higher than those in non-CRRT group. CRRT group had significantly higher incidence of postoperative complication [unplanned operation: 8 cases (44.4%) vs. 14 cases (8.2%), primary nonfunction: 1 case (5.6%) vs. 0 case (0%), retransplantation: 3 cases (16.7%) vs. 0 case (0%), hepatic artery thrombosis: 3 cases (16.7%) vs. 4 cases (2.3%), intestinal fistula: 2 cases (11.1%) vs. 2 cases (1.2%)] than non-CRRT group (all P < 0.05). ③ The average start time of CRRT was 10 (1-240) days. The per capita frequency of CRRT treatment was 3.3 (1.0-14.0) times. The average duration of each CRRT treatment was 10.1 (6.0-19.3) hours, the average reduction rate of serum creatinine (SCr) was 25.6% (13.5%-45.0%) after CRRT. ④ In CRRT group, 5 patients died, the 1-year and 2-year survival rates were both 72.22%. In non-CRRT group, 6 patients died, the 1-year and 2-year survival rates were 97.1% and 96.5%, respectively. There were significant differences in 1-year and 2-year survival rates between the two groups (both P < 0.01). Conclusions:The incidence of AKI after pediatric liver transplantation was high, and most infants treated with CRRT were associated with serious surgical complications. CRRT was a powerful means to remove inflammatory factors and maintain the stability of circulation and internal environment, which could improve the multi-organ dysfunction effectively.

Objective:To study the use of digital subtraction angiography (DSA) guided transnasal ileus tube placement in management of abdominal compartment syndrome (ACS) after liver transplantation.Methods:From January 2015 to December 2019, a total of 30 patients who developed ACS after liver transplantation who were admitted to the Transplantation Intensive Care Unit of Tianjin First Central Hospital were retrospectively studied. According to the way of decompression, these patients were divided into the study group and the control group. Patients in the control group were treated with conventional abdominal decompression, while patients in the study group were treated with DSA guided transnasal ileus tube placement based on management principles developed in conventional abdominal decompression. Changes in intra-abdominal pressure, treatment efficacy rates and liver functions were monitored in the two groups up to 7 days after abdominal decompression.Results:There were 23 males and 7 females, aged (53.4±11.6) years. After treatment, the IAP, portal venous blood flow velocity, bile drainage volume, ALT and AST in the study group were significantly better when compared with the findings before treatment: [IAP: (7.13±3.87) vs (22.73±2.09) mmHg, portal vein blood flow velocity: (34.76±10.31) vs (21.45±6.47) cm/s, bile drainage volume: (198.43±19.94) vs (80.72±9.52) ml/d, ALT: (158.92±67.56) vs (278.73±99.17) U/L, AST: (79.36±15.63) vs (196.71±89.05) U/L], ( P<0.05). After treatment, when compared with the control group, the IAP, portal vein blood flow velocity, bile drainage and TBil in the study group were significantly better [IAP: (7.13±3.87) vs (13.47±6.19) mmHg, portal vein blood flow velocity: (34.76±10.31) vs (24.98±8.54) cm/s, bile drainage: (198.43±19.94) vs (108.73±21.30) ml/d, TBil: (258.85±91.95) vs (343.69±89.45) μmol/L], ( P<0.05). In the control group, the IAP significantly decreased on the fourth day after treatment, ( P<0.05); compared with the significant difference in the study group on the second day after treatment ( P<0.05). After 7 days of treatment, the efficacy rate of the control group was 46.7% (7/15), compared to 86.7% (13/15) in the study group. The difference between the two groups was significant (χ 2=5.400, P<0.05). Conclusion:DSA guided transnasal ileus tube placement for treatment of abdominal compartment syndrome after liver transplantation resulted in a better treatment efficacy rate than conventional treatment.

Objective:To investigate a cluster epidemic of COVID-19 after a mass gathering activity in Ningbo of Zhejiang province and analyze the transmission chain and status of infection cases of different generations.Methods:The tracking of all the close contacts of the first COVID-19 case and epidemiological investigation were conducted on January 29, 2020 after a cluster epidemic of COVID-19 related with a Buddhism rally on January 19 (the 1.19 rally) in Ningbo occurred. The swabs of nose/throat of the cases and close contacts were collected and tested for nucleic acids by real-time fluorescence quantitative RT-PCR.Results:From January 26 to February 20, 2020, a total of 67 COVID-19 cases and 15 asymptomatic infection cases related with the 1.19 rally were reported in Ningbo. The initial case was the infection source who infected 29 second generation cases and 4 asymptomatic infection cases, in whom 23 second generation cases and 3 asymptomatic infection cases once took bus with the initial case, the attack rate was 33.82% (23/68) and the infection rate was 38.24% (26/68). The risks of suffering from COVID-19 and being infected were 28.91 times and 26.01 times higher in rally participants taking bus with initial case compared with those taking no bus with initial case. In this epidemic, 37 third+generation cases and 11 related asymptomatic infection cases occurred, the attack rate was 2.88% (37/1 283) and the infection rate was 4.76% (48/1 008). The main transmission routes included vehicle sharing and family transmission.Conclusion:It was a cluster epidemic of COVID-19 caused by a super spreader in a massive rally. The epidemic has been under effective control.

Objective:To describe the basic characteristics of clusters of coronavirus diseases 2019 (COVID-19) cases in Ningbo, Zhejiang province, and evaluate the generation time (Tg) and basic reproduction number ( R0) of COVID-19. Methods:The basic information and onset times of the clusters of COVID-19 cases in Ningbo were investigated, the inter-generational interval of the cases were fitted by using gamma distribution, and the R0 was calculated based on the SEIR model. Results:In the 15 clusters of COVID-19 cases, a total of 52 confirmed cases, 5 cases of nucleic acid-positive asymptomatic cases. The cases occurred from January 23 to February 4, the cases were mainly women. The incubation period was (6.11±3.38) days, and the median was 5 days. The Tg was (6.93±3.70) days. There were no significant differences in Tg between age group<60 years and age group 60 years and above, and between men and women ( P=0.551). According to the Tg calculated in this paper, the R0 of COVID-19 in Ningbo was 3.06 (95 %CI: 2.64- 3.51); according to the reported case transmission interval of 7.5 days in the literature, the R0 was 3.32 (95 %CI: 2.51-9.38). Conclusion:There is no age and gender specific differences in the Tg of clusters of COVID-19 cases in Ningbo, and COVID-19 has high infectivity and spreading power in early phase.

Objective To investigate the clinical efficacy and influencing factors in patients with acute-on-chronic liver failure grade 3 after liver transplantation.Methods 33 patients with acute-on-chronic grade 3 liver failure who were treated in Tianjin First Center Hospital from January 2015 to December 2017 was retrospectively analyzed,including 21 patients in liver transplantation group and 12 patients in control group.Among them,28 patients were males and 5 patients were females,aged (43.4± 12.3) years.The data and follow-up information of all patients were collected.The survival condition was analyzed by Kaplan-Meier.Univariate and multivariate Cox regression analysis was used to analyze the risk factors of death in patients after liver transplantation.Results There was no significant difference in Child-Pugh score,total bilirubin,creatinine and infection before operation between liver transplantation group and control group (P＞0.05).The age of patients in liver transplantation group was older than the control group,the difference was statistically significant (P＜0.05).The 1-year and 3-year cumulative survival rates in the liver transplantation group were 61.9％ and 61.9％ respectively and the rates in control group were 8.3％ and 8.3％ respectively by Kaplan-Meier survival analysis.There was significant difference between the two groups (P＜0.05).Twenty-one patients in the liver transplantation group were followed up for a long time,13 patients survived and followed up for 163～ 1 123 days.Except for renal insufficiency complicated with renal anemia in 1 case,the other 12 cases had normal liver function,and 8 cases died in 2～54 days after liver transplantation.Postoperative shock was an independent risk factor for death after liver transplantation by univariate and multivariate Cox regression analysis.Conclusion Acute-on-chronic grade 3 liver failure was indication for liver transplantation,postoperative shock was an independent risk factor for death after liver transplantation.

OBJECTIVE To investigate the efficacy of coblation for early glottic cancer. METHODS Twenty-two patients with early glottic carcinoma (Tis-T2) without lymph node metastasis accepted resection of laryngeal cancer lesions using transoral endoscopic coblation,without pre-operative or post-operative radiotherapy and chemotherapy. All the patients were followed up for 30 to 70 months. RESULTS No severe complications such as dyspnea and bleeding occurred in these cases.Only mild postoperative pain happened to the patients.All patients could swallow and speak after operation. No recurrence occurred in 21 cases till now. One case, with poorly differentiated squarnous cell lesion in the anterior commissure invading subglottic area, recurred 4 months after operation. Salvage partial laryngectomy was performed and no recurrence was found after salvage operation. CONCLUSION The result suggests that transoral endoscopic coblation is a good method for early glottic cancer. It is worth popularizing.