the aim of this study is to explore the feasibility of using machine learning (ML) technology to predict postoperative recurrence risk among stage iV colorectal cancer patients. four basic ML algorithms were used for prediction-logistic regression, decision tree, GradientBoosting and lightGBM. the research samples were randomly divided into a training group and a testing group at a ratio of 8:2. 999 patients with stage 4 colorectal cancer were included in this study. In the training group, the GradientBoosting model's AUC value was the highest, at 0.881. The Logistic model's AUC value was the lowest, at 0.734. The GradientBoosting model had the highest F1_score (0.912). In the test group, the AUC Logistic model had the lowest AUC value (0.692). The GradientBoosting model's AUC value was 0.734, which can still predict cancer progress. However, the gbm model had the highest AUC value (0.761), and the gbm model had the highest F1_score (0.974). The GradientBoosting model and the gbm model performed better than the other two algorithms. the weight matrix diagram of the GradientBoosting algorithm shows that chemotherapy, age, LogCEA, CEA and anesthesia time were the five most influential risk factors for tumor recurrence. the four machine learning algorithms can each predict the risk of tumor recurrence in patients with stage iV colorectal cancer after surgery. Among them, GradientBoosting and gbm performed best. Moreover, the GradientBoosting weight matrix shows that the five most influential variables accounting for postoperative tumor recurrence are chemotherapy, age, LogCEA, ceA and anesthesia time. Colorectal cancer is a common malignant tumor with high morbidity and mortality in clinical practice. It ranks third in mortality among all tumors 1. Approximately 1.4 million new cases are diagnosed every year, and about half of the new cases are in the progressive stage. The 5-year survival rate is 30% ~ 40%, due primarily to postoperative recurrence and metastasis, of which 10% ~ 30% have abdominal cavity metastasis, with a median survival of 7 months. In China, the incidence and mortality of colorectal cancer rank third and fifth, respectively, among systemic tumors. Currently, the main clinical approach is surgical treatment assisted with multidisciplinary methods such as radiotherapy, chemotherapy and targeted therapy. However, a meta-analysis of 18 clinical trials shows that patients have a recurrence rate of 80.00% within 3 years after surgery 2. With early diagnosis and treatment, the prognosis of early stage colorectal cancer patients is optimistic, and the middle and long-term survival rate is usually high. However, as early symptoms are not typical, they are easily ignored by patients, leading to progression to the middle and late stages when they are finally admitted to hospitals. This inhibits treatment and reduces long-term survival rates. Recent machine learning (ML) methods have shown accurate predictive ability, and have been increasingly used in the diagnosis and prognosis of various diseases and hea...

ObjectiveTo investigate the effect of dexmedetomidine in the prevention of etomidate-induced myoclonus.MethodsWe searched for randomized controlled trials (RCTs) regarding the use of dexmedetomidine in preventing etomidate-induced myoclonus in the databases PubMed, EMBASE, the Cochrane Library, and CNKI. We extracted data and assessed the quality of the literature and adopted RevMan 5.2 to conduct meta-analysis on each effective index and employed funnel plot to test publication bias.ResultsThe results showed that the incidence of etomidate-induced myoclonus in the dexmedetomidine treated groups was significantly lower than that of the control groups (risk ratio [RR]=0.27, 95% confidence interval [CI] [0.15, 0.47], P<0.00001). With regard to the severity of etomidate-induced myoclonus, incidences of etomidate-induced myoclonus in the dexmedetomidine treated groups resulting in mild myoclonus (RR=0.37, 95% CI [0.19, 0.75], P=0.006), moderate myoclonus (RR=0.21, 95% CI [0.12, 0.37], P<0.00001), or severe myoclonus (RR=0.18, 95% CI [0.08, 0.38], P<0.00001) were significantly lower than those of the control groups. No statistically significant difference was found (RR=0.70, 95% CI [0.47, 1.04], P=0.08) between etomidate-induced myoclonus in the dexmedetomidine treated groups and that of the midazolam treated groups.ConclusionDexmedetomidine can effectively prevent the incidence of etomidate-induced myoclonus and reduce the severity of etomidate-induced myoclonus. In addition, there were no significant differences between the effects of dexmedetomidine and midazolam in preventing etomidate-induced myoclonus.

ObjectiveWe undertook a meta-analysis to investigate the effect of dexmedetomidine on postoperative cognitive dysfunction (POCD).MethodsWe searched PubMed, EMBASE, the Cochrane Library, CNKI and Google Scholar to find randomized controlled trials (RCTs) of the influence of dexmedetomidine on POCD in elderly adults who had undergone general anaesthesia. Two researchers independently screened the literature, extracted data, and evaluated methodologic quality against inclusion and exclusion criteria. We used RevMan 5.2 to undertake our meta-analysis.ResultsThirteen RCTs were included. Compared with controls, dexmedetomidine: 1) significantly reduced the incidence of POCD (relative risk = 0.59, 95% confidence interval [CI] 0.45–2.95) and improved Mini-Mental State Examination (MMSE) score (mean difference, MD = 1.74, 95% CI 0.43–3.05) on the first postoperative day; and 2) reduced the incidence of POCD after the first postoperative day (MD = 2.73, 95% CI 1.33–4.12).ConclusionDexmedetomidine reduces the incidence of POCD and improves postoperative MMSE score.

ObjectiveTo investigate the effect of pretreatment with midazolam on myoclonus induced by etomidate injection.MethodsA meta-analysis was performed using Review Manager software, version 5.2. Two researchers independently searched PubMed, Cochrane Library, and Embase® databases for randomized controlled trials involving patients who underwent etomidate induced general anaesthesia with or without midazolam pretreatment, published between 1990 and 2016. Outcome measures comprised overall myoclonus incidence rate and incidence rate classified by degree of myoclonus following etomidate injection. Data were assessed using a fixed effects model.ResultsFive studies, comprising 302 patients, were included for analysis. Overall incidence rate of etomidate injection-induced myoclonus was significantly lower in the pooled midazolam group versus controls (relative risk [RR] 0.34, 95% confidence interval [CI] 0.26, 0.44); Results subgrouped by degree of myoclonus showed significantly lower incidence in midazolam groups versus control groups for mild myoclonus (RR 0.56, 95% CI 0.39, 0.80); moderate myoclonus (RR 0.20, 95% CI 0.10, 0.41); and severe myoclonus (RR 0.12, 95% CI 0.04, 0.39).ConclusionMidazolam can effectively prevent etomidate-induced myoclonus, and alleviate the degree of etomidate-induced myoclonus.

No abstract

ObjectiveThis study was designed to evaluate the efficacy and safety of preinjection of dezocine in preventing etomidate-induced myoclonus.MethodsPubMed, Embase, The Cochrane Library, and China National Knowledge Infrastructure (CNKI) were searched to collect relevant randomized controlled trials (RCTs) from inception to July 2016 on the preinjection of dezocine in preventing etomidate-induced myoclonus. Two researchers independently screened literature, extracted data, and evaluated bias risks in accordance with inclusion and exclusion criteria, and then used RevMan 5.2 to perform the meta-analysis.ResultsA total of six RCTs were included in this study. The meta-analysis showed that 1) the preinjection of dezocine can reduce the incidence of etomidate-induced myoclonus (relative risk [RR] =0.25, 95% CI [0.13, 0.50], P<0.0001), which is consistent with the result of subgroup analysis; 2) the preinjection of dezocine can reduce the incidence of mild, moderate, and severe myoclonus; 3) dezocine was not related to an increasing incidence of etomidate-induced dizziness and nausea (RR =2.83, 95% CI [0.66, 12.08], P=0.6); and 4) dezocine did not reduce heart rates after the administration of etomidate (mean difference =1.06, 95% CI [−4.08, 6.19], P=0.69).ConclusionThe preinjection of dezocine has the effect of both lowering the incidence of etomidate-induced myoclonus and easing the severity of myoclonus, but without increasing dizziness and nausea or affecting the heart rate.

The Platelet to lymphocyte ratio (PLR) has been reported to predict prognosis of patients with hepatocellular carcinoma (HCC). This study examined the prognostic potential of stratified PLR for HCC patients undergoing curative liver resection. Medical records were retrospectively analyzed for 778 HCC patients undergoing curative liver resection at the Affiliated Tumor Hospital of Guangxi Medical University and the First People's Hospital of Changde between April 2010 and October 2013. Patients were stratified based on quintile analysis of their preoperative PLR, and patients in different quintiles were analyzed for overall survival (OS) and disease-free survival (DFS) using Kaplan-Meier analysis. Independent predictors of death or recurrence were explored using multivariable Cox proportional hazard regression. Higher PLR quintiles were significantly associated with poorer overall survival (p < 0.001). Multivariate analysis showed PLR to be an independent risk factor for OS (p = 0.003). Patients in PLR quintile 5 had lower overall survival than in quintile 1 (hazard ratio (HR) = 2.780, 95% confidence interval (CI): 1.769-4.367, p < 0.001). Although patients in PLR quintile 5 had significantly lower disease-free survival (DFS) than in quintile 1 (HR = 1.534, 95% CI: 1.112-2.117, p = 0.009), this association was not significant after multivariable adjustment (p = 0.220). Subgroup analysis also showed that PLR quintiles were significantly associated with poor OS in patients positive for HBsAg or with cirrhosis (both p < 0.001). Similar results were obtained when PLR was analyzed as a dichotomous variable with cut-off values of 110 and 115. Elevated preoperative PLR may be independently associated with poor OS and DFS in HCC patients following curative resection.

Objective To evaluate the efficacy of pre-injection of butorphanol on etomidate-induced myoclonus during anesthesia induction. Methods Randomized controlled trials (RCTs) of the ability of butorphanol to prevent etomidate-induced myoclonus were collected by searching PubMed, Cochrane Library, CNKI, and WanFang databases, from the day of database establishment until May 2017. The literature was screened independently by two evaluators, and the data were then extracted and independently evaluated. Finally, meta-analysis was performed by using RevMan 5.2 software. Results Eight RCTs were analyzed. The results of meta-analysis showed that: 1. compared with the control group, butorphanol was effective in preventing etomidate-induced myoclonus [RR = 0.15, 95% CI: 0.11, 0.21]; 2. butorphanol was effective in preventing mild, moderate, and severe etomidate-induced myoclonus [RR = 0.40, 95% CI: 0.25, 0.63; RR = 0.15, 95% CI: 0.08, 0.27; and RR = 0.04, 95% CI: 0.01, 0.09]; 3. butorphanol did not increase the incidence of dizziness and nausea associated with etomidate. Conclusions Butorphanol could reduce the incidence and degree of etomidate-induced myoclonus. Notably, it did not increase the incidence of dizziness and nausea associated with etomidate.