ABSTRACT
Objective:To establish a long-term mortality rate prediction model for patients aged 60 years and over with atrial fibrillation and coronary heart disease using the machine learning method, and identify the corresponding risk factors of mortality.Methods:In this retrospective cohort study, a total of 329(11 cases lost of follow-up)patients with 183 males(55.6%)and 146 females(44.4%), aged(77.8±7.3)years, and 142 patients aged 80 years or older(43.2%)were selected in our hospitals from January 2013 to March 2015.And their clinical data on atrial fibrillation and coronary heart disease were analyzed.They were divided into the death group(151 cases)and the survival group(167 cases)according to the survival outcome.In addition, 60 patients aged 60 years and over admitted to our hospitals from April to July 2015 with atrial fibrillation and coronary heart disease were selected as external data validation set.The clinical data included age, gender, body mass index, diagnosis, co-morbidity, laboratory indicators, electrocardiogram, echocardiogram, treatment data.These patients were followed up for at least 6 years, and the main adverse cardiovascular and cerebrovascular events(MACCE), including death, were recorded.Finally, the data of the enrolled patients were randomly divided into the training set and the test set according to the ratio of 9∶1, Different models were established to predict the long-term mortality of patients with atrial fibrillation and coronary heart disease by machine learning algorithm.The optimal model was established by substituting external data(60 cases)into the model for verification and comparison.The top 20 risk factors for mortality were determined by Shapley additive explanation(SHAP)algorithm.Results:A total of 329 hospitalized patients were included in this study, the overall median follow-up time was 77.0 months(95% CI: 54.0~84.0), 11 cases lost during follow-up(3.3%), and 151 cases died(45.9%). The analysis found that the areas under the ROC curve for a support vector machine(SVM)model, k-Nearest Neighbor(KNN)model, decision tree model, random forest model, ADABoost model, XGBoost model and logistic regression model were 0.76, 0.75, 0.75, 0.91, 0.86, 0.85 and 0.81, respectively.The random forest model had the highest prediction efficiency, with the accuracy of 0.789 and F1 value of 0.806, which was better than the logistic regression model[the Area Under Receiver Operating Characteristic Curve(AUC): 0.91 vs.0.81, P<0.05]. D-dimer, age, number of MACCE, left ventricular ejection fraction, serum albumin level, anemia, New York Heart Association(NYHA)grade, history of old myocardial infarction, estimated glomerular filtration rate(eGFR)and resting heart rate were important risk factors for predicting long-term mortality. Conclusions:The random forest model based on machine learning method can predict the long-term mortality of patients with atrial fibrillation and coronary heart disease aged 60 years and over, have a good identification ability.Its accuracy is higher than that of the traditional Logistic regression model.Reducing the long-term mortality and improving the long-term outcomes can be achieved by intervening on D-dimer levels, correcting hypoproteinemia and anemia, improving cardiac function and controlling resting ventricular rates.
ABSTRACT
Objective To evaluate the effects of L-alanyl-L-glutamine (LALG) intensified parenteral nutrition support in advanced malignant carcinoma patients.Methods 68 patients were randomly divided into two groups,control group (n =34) received only parenteral nutrition,treatment group (n =34) received parenteral nutrition combined with a dose of 0.3 g ·(kg·d)-1 LALG.Nutrition status and immune functions were determined at pre-therapy and 15th days after therapy.Results After the therapy,the pALB and TRF of treatment group were significantly increased [(24.9±8.06) mg/dl vs (27.3±6.05) mg/dl; (1.62±0.43) g/L vs (2.06±0.32) g/L].Before therapy,no significant change in IgA,IgM and IgG was found in two groups (P ＞ 0.05).After the therapy,IgA and IgG of the treatment group after the therapy were significantly different from those before the therapy [(2.85±1.43) mg/L vs (3.63±5.36) mg/L; (0.95±0.43) mg/L vs (1.13±0.09) mg/L],IgA,IgM and IgG of the control group had no difference compared with those before the therapy (P ＞ 0.05),CD4+ of treatment group was significandy different compared with those of control group [(39.19±4.23) ％ vs (36.62±3.58) ％] (P ＜ 0.05).There is no significantly difference between CD:/ CD8+ CD8+ of treatment group and those of control therapy (P ＞ 0.05).After therapy,the score of quality of life in treatment group was higher than that in control group (P ＜ 0.05).Conclusion LALG intensified parenteral nutrition has better effects on improvement of the nutrition and immune functions.
ABSTRACT
Objective To investigate the detection of BJ-75A-9 mHNA, WNX and CK19 mRNA in peripheral blood cells of lung cancer patients and evaluate its diagnostic value. Methods The expression of BJ-TSA-9, LUNX and CK19 mRNA in peripheral blood cells was delected from 84 lung cancer patients, 32 benign lung lesions and 20 healthy volunteers by nested reverse transcription polymerase chain re-action (Nested-RT-PCR). Results The positive detection rates of BJ-75A-9,LUNX and CK19 mRNA in the peripheral blood of the pa-tients with lung cancer were 59.5%,40.4%and 22.6% respectively. In the 32 peripheral blood samples of the patients with benign lung le-sions,the positive detection rate of BJ-TSA-9,LUNX and CK19 mRNA were 9.3%, 12.5% and 6.3% respectively. No expression of BJ-TSA-9,LUNX and CK19 was detected in lhe samples of the healthy volunteers. The expression level of BJ-TSA-9, WNX and CKI9 mRNA in the peripheral blood of lung cancer stage IV patients was significantly higher than those of stages II and ID (P< 0.05). Conclusion RT-PCR amplification of BJ-TSA-9, LUNX and CK19 mRNA are an efficient way to detect early haematogenous dissemination of cancer cells for lung cancer patients. The detection of BJ-TSA-9 expression is sensitive and specific for lung cancer,and it is superior to both LUNX and CK19 mRNA. The expression of BJ-7SA-9 mRNA in peripheral blood might predict the hematogenous metastatic spreading of lung cancer cells.
ABSTRACT
<p><b>BACKGROUND</b>To observe the efficacy and safety of navelbine (NVB) combined with ifosfamide (IFO) and cisplatin (DDP) (NIP regimen) and IFO plus DDP (IP regimen) for advanced non-small cell lung cancer (NSCLC).</p><p><b>METHODS</b>One hundred and twenty patients with advanced NSCLC pathologically proved were randomly divided into group A (NIP regimen, n=60) and group B (IP regimen, n=60).</p><p><b>RESULTS</b>In group A, 58 patients were evaluable. The response rates were 58.62%(34/58), 65.58%(17/26) and 53.12% (17/32) in whole group, untreated patients, and retreated patients, respectively. The median duration of survival was 11.3 months. One-year survival rate was 40.0%. In group B, 59 patients could be evaluated. The response rates were 40.68%(24/59), 63.33%(19/30) and 17.24%(5/29) in whole group, untreated patients, and retreated patients, respectively. The median duration of survival was 9 months and 1-year survival rate was 36.7%. There was no significant difference in objective response rate among all the patients and the patients with no prior treatment between the two groups ( P > 0.05, P > 0.05). However, among retreated patients, the response rate in group A was remarkably higher than that in group B ( P < 0.05). The main dose limiting toxicity was myelosuppression. Leukopenia at grade III+IV was significantly higher in the NIP arm than in the IP arm ( P < 0.05).</p><p><b>CONCLUSIONS</b>NIP yields a higher response rate than IP does in retreated patients, with acceptable toxicity, which can be the first line regimen in the retreatment of advanced NSCLC. IP regimen showes a similar response rate and less toxicity in initial patients, compared with NIP regimen, so it might be considered a relevant regimen in initial patients with advanced NSCLC.</p>
ABSTRACT
To evaluate the effect of mobilization of peripheral blood stem cells (PBSC) with high dose cyclophosphamide combination chemotherapy and G-CSF in breast cancer patients, a new mobilization protocol was designed on the basis of standard combination chemotherapy regimen, in which the dose of cyclophosphamide was raised to 2 to 4 times, and G-CSF began to be used at the dose of 150 micro g twice everyday when white blood cell (WBC) decreased below 1.0 x 10(9)/L. PBSC collection was performed while WBC increased over 5.0 x 10(9)/L during bone marrow recovering. The PBSC mobilization protocol was completed in 10 patients, the median nadir of WBC was 0.8 (0.4 - 1.0) x 10(9)/L, the median time of PBSC collection was 2 (2 - 4), the median number of collected CD34(+) cells was 6.43 (1.99 - 8.75) x 10(6)/kg. The results showed that the protocol, high dose cyclophosphamide combination chemotherapy, was an optimal PBSC mobilization regimen in breast cancer patients.
ABSTRACT
OBJECTIVE:To evaluate the therapeutic efficacy and safety of MS Contin for patients with cancerous pain. METHODS:To control open clinical test was performed on 856 patients with terminal cancer,the analgesia effects,life quality and adverse reactions in these patients were compared before and after treatment with MS Contin.RESULTS:In the efficacy analysis,MS Contin lowered the pain degree(P