RESUMO
BACKGROUND: Dynamic prediction of patient mortality risk in the ICU with time series data is limited due to high dimensionality, uncertainty in sampling intervals, and other issues. A new deep learning method, temporal convolution network (TCN), makes it possible to deal with complex clinical time series data in ICU. We aimed to develop and validate it to predict mortality risk using time series data from MIMIC III dataset. METHODS: A total of 21,139 records of ICU stays were analysed and 17 physiological variables from the MIMIC III dataset were used to predict mortality risk. Then we compared the model performance of the attention-based TCN with that of traditional artificial intelligence (AI) methods. RESULTS: The area under receiver operating characteristic (AUCROC) and area under precision-recall curve (AUC-PR) of attention-based TCN for predicting the mortality risk 48 h after ICU admission were 0.837 (0.824 -0.850) and 0.454, respectively. The sensitivity and specificity of attention-based TCN were 67.1% and 82.6%, respectively, compared to the traditional AI method, which had a low sensitivity (< 50%). CONCLUSIONS: The attention-based TCN model achieved better performance in the prediction of mortality risk with time series data than traditional AI methods and conventional score-based models. The attention-based TCN mortality risk model has the potential for helping decision-making for critical patients. TRIAL REGISTRATION: Data used for the prediction of mortality risk were extracted from the freely accessible MIMIC III dataset. The project was approved by the Institutional Review Boards of Beth Israel Deaconess Medical Center (Boston, MA) and the Massachusetts Institute of Technology (Cambridge, MA). Requirement for individual patient consent was waived because the project did not impact clinical care and all protected health information was deidentified. The data were accessed via a data use agreement between PhysioNet, a National Institutes of Health-supported data repository (https://www.physionet.org/), and one of us (Yu-wen Chen, Certification Number: 28341490). All methods were carried out in accordance with the institutional guidelines and regulations.
Assuntos
Inteligência Artificial , Unidades de Terapia Intensiva , Mortalidade Hospitalar , Hospitalização , Humanos , Curva ROCRESUMO
BACKGROUND AND AIMS: Screening for hepatopulmonary syndrome in cirrhotic patients is limited due to the need to perform contrast enhanced echocardiography (CEE) and arterial blood gas (ABG) analysis. We aimed to develop a simple and quick method to screen for the presence of intrapulmonary vascular dilation (IPVD) using noninvasive and easily available variables with machine learning (ML) algorithms. METHODS: Cirrhotic patients were enrolled from our hospital. All eligible patients underwent CEE, ABG analysis and physical examination. We developed a two-step model based on three ML algorithms, namely, adaptive boosting (termed AdaBoost), gradient boosting decision tree (termed GBDT) and eXtreme gradient boosting (termed Xgboost). Noninvasive variables were input in the first step (the NI model), and for the second step (the NIBG model), a combination of noninvasive variables and ABG results were used. Model performance was determined by the area under the curve of receiver operating characteristics (AUCROCs), precision, recall, F1-score and accuracy. RESULTS: A total of 193 cirrhotic patients were ultimately analyzed. The AUCROCs of the NI and NIBG models were 0.850 (0.738-0.962) and 0.867 (0.760-0.973), respectively, and both had an accuracy of 87.2%. For both negative and positive cases, the recall values of the NI and NIBG models were both 0.867 (0.760-0.973) and 0.875 (0.771-0.979), respectively, and the precisions were 0.813 (0.690-0.935) and 0.913 (0.825-1.000), respectively. CONCLUSIONS: We developed a two-step model based on ML using noninvasive variables and ABG results to screen for the presence of IPVD in cirrhotic patients. This model may partly solve the problem of limited access to CEE and ABG by a large numbers of cirrhotic patients.
RESUMO
BACKGROUND: Dynamic and precise estimation of blood loss (EBL) is quite important for perioperative management. To date, the Triton System, based on feature extraction technology (FET), has been applied to estimate intra-operative haemoglobin (Hb) loss but is unable to directly assess the amount of blood loss. We aimed to develop a method for the dynamic and precise EBL and estimate Hb loss (EHL) based on artificial intelligence (AI). METHODS: We collected surgical patients' non-recycled blood to generate blood-soaked sponges at a set gradient of volume. After image acquisition and preprocessing, FET and densely connected convolutional networks (DenseNet) were applied for EBL and EHL. The accuracy was evaluated using R2, the mean absolute error (MAE), the mean square error (MSE), and the Bland-Altman analysis. RESULTS: For EBL, the R2, MAE and MSE for the method based on DenseNet were 0.966 (95% CI: 0.962-0.971), 0.186 (95% CI: 0.167-0.207) and 0.096 (95% CI: 0.084-0.109), respectively. For EHL, the R2, MAE and MSE for the method based on DenseNet were 0.941 (95% CI: 0.934-0.948), 0.325 (95% CI: 0.293-0.355) and 0.284 (95% CI: 0.251-0.317), respectively. The accuracies of EBL and EHL based on DenseNet were more satisfactory than that of FET. Bland-Altman analysis revealed a bias of 0.02 ml with narrow limits of agreement (LOA) (-0.47 to 0.52 mL) and of 0.05 g with narrow LOA (-0.87 to 0.97 g) between the methods based on DenseNet and actual blood loss and Hb loss. CONCLUSIONS: We developed a simpler and more accurate AI-based method for EBL and EHL, which may be more fit for surgeries primarily using sponges and with a small to medium amount of blood loss.
RESUMO
Objective To systematically evaluate the clinical effects of endobutton plate and clavicular hook plate in the treatment of ac-romioclavicular joint dislocation. Methods The clinical study on endobutton plate and clavicular hook plate in the treatment of acromiocla-vicular joint dislocation was subjected to computer search for CNKI,VIP,WangFang Data,PubMed,EMbase and The Cochrane Library input before July 2017. Two reviewers independently screened literature,extracted data and assessed the risk bias of included studies and then Rev-Man 5. 3 software was used to perform meta-analysis. A total of 10 studies were conducted with 725 patients. Results After operation of the patients who underwent endobutton plate,the Constant score was higher [MD=8. 55,95％CI (7. 82, 9. 29),P<0. 01] with shorter opera-tion time [MD=4. 94, 95％CI 4. 30 to 5. 59,P< 0. 01],less bleeding (MD= -1. 93,95％CI -2. 63 to -1. 22,P<0. 01],and shorter hospital stay [MD= -0. 39, 95％CI -0. 70 to -0. 09,P=0. 01],respectively. Conclusion The treatment of acromioclavicular joint dis-location with type III by endobutton plate has the advantages of shorter operation time,less intraoperative bleeding,quick recovery of shoulder function,and shorter hospital stay.
RESUMO
Objective To explore the effect of aerobic exercise training on artery elasticity among patients with essential hypertension.Methods A total of 155 cases of patients with essential hypertension (EH)were selected,and were divided into control group(76 cases)and aerobic exercise group(79 cases).Control group was follow routine drug therapy,and aerobic exercise group was follow aerobic exercise training besides the routine therapy for 12 weeks.CAVI,ABI values,limb blood pressure,TG,TC,LDL -C,HDL -C and U -MA were compared before and after the intervention.Results After the intervention,bilateral CAVI values of aerobic exercise group were 7.76 ±0.15,7.88 ±0.15,8.87 ±0.25 and 8.89 ± 0.22,and lower than those before the intervention(P <0.05).The decline range of bilateral CAVI value(the difference between the mean differences before and after the intervention)were 1.03 ±0.07 and 1.03 ±0.06,significantly wider than the control group of 0.33 ±1.97 and 0.15 ±0.08(P <0.05).After the intervention,limb systolic pressure,diastolic blood pressure and triglyceride,cholesterol decreased in the aerobic exercise group(P <0.05).The limb systolic blood pressure and left limb diastolic blood pressure decreased in the control group after intervention (P <0.05),but the decline range was smaller than the aerobic exercise group(P <0.05 ).Conclusion The aerobic exercise training could significantly improve arterial elasticity among patients with essential hypertension.
RESUMO
Asoprisnil, a member of the selective progesterone receptor modulators, exerts high progesterone receptor selectivity, endometrial targeted advantages and significant anti-implantation effect in rats. The purpose of this study was to confirm the anti-implantation effect of asoprisil, investigate the ultrastructural changes of the peri-implantation endometrium in mice and explore the effect of asoprisnil on endometrial receptivity and its targeted contraceptive proficiency. Post-coitus mice were administered with different dosages (0.2, 0.1, 0.05 mg·g(-1)·day(-1)) of asoprisnil from day 1 of pregnancy to day 3. Then 3 animals in each group were killed on day 5 of pregnancy, and uteri were collected to examine the ultrastructural changes of endometria under a transmission electron microscope (TEM). A total of 80 animals were sacrificed on day 8 of pregnancy, and the uterine horns were examined for the presence or absence of nidation sites and the number of implantation embryos. The results showed that the implantation rate and the average number of implantation embryos in asoprisnil groups were statistically significantly decreased as compared with the vehicle control group (P<0.05). The TEM results revealed that, in vehicle control group, the tight junction between the luminal epithelia cells was short and straight, the gap was wide; the luminal epithelia cells were covered with plenty of short, clavate and neatly arranged microvilli; the endometril stromal cells were large with plenty of cytoplasm, and showed significant decidual change; there was more than one nucleus in stromal cells, and the karyotheca was integrity. In low dosage and high dosage asoprisnil groups, the tight junction was longer and more curve than in the vehicle control group; microvilli were uneven and asymmetrically distributed in luminal epithelia; the stromal cells were small and the decidual change was not significant; there were karyopyknosis and karyolysis in stromal cells; there were abnormal thick-wall vessels in the endometrium. It was suggested that asoprisnil changed the ultrastructure of the endometrium in implantation window, disturbed the endometrial receptivity and finally resulted in embryo implantation failure.
Assuntos
Animais , Feminino , Camundongos , Gravidez , Anticoncepção Pós-Coito , Métodos , Implantação Tardia do Embrião , Fisiologia , Endométrio , Fisiologia , Estrenos , Oximas , Ocitócicos , Prenhez , Resultado do TratamentoRESUMO
Asoprisnil, a member of the selective progesterone receptor modulators, exerts high progesterone receptor selectivity, endometrial targeted advantages and significant anti-implantation effect in rats. The purpose of this study was to confirm the anti-implantation effect of asoprisil, investigate the ultrastructural changes of the peri-implantation endometrium in mice and explore the effect of asoprisnil on endometrial receptivity and its targeted contraceptive proficiency. Post-coitus mice were administered with different dosages (0.2, 0.1, 0.05 mg·g(-1)·day(-1)) of asoprisnil from day 1 of pregnancy to day 3. Then 3 animals in each group were killed on day 5 of pregnancy, and uteri were collected to examine the ultrastructural changes of endometria under a transmission electron microscope (TEM). A total of 80 animals were sacrificed on day 8 of pregnancy, and the uterine horns were examined for the presence or absence of nidation sites and the number of implantation embryos. The results showed that the implantation rate and the average number of implantation embryos in asoprisnil groups were statistically significantly decreased as compared with the vehicle control group (P<0.05). The TEM results revealed that, in vehicle control group, the tight junction between the luminal epithelia cells was short and straight, the gap was wide; the luminal epithelia cells were covered with plenty of short, clavate and neatly arranged microvilli; the endometril stromal cells were large with plenty of cytoplasm, and showed significant decidual change; there was more than one nucleus in stromal cells, and the karyotheca was integrity. In low dosage and high dosage asoprisnil groups, the tight junction was longer and more curve than in the vehicle control group; microvilli were uneven and asymmetrically distributed in luminal epithelia; the stromal cells were small and the decidual change was not significant; there were karyopyknosis and karyolysis in stromal cells; there were abnormal thick-wall vessels in the endometrium. It was suggested that asoprisnil changed the ultrastructure of the endometrium in implantation window, disturbed the endometrial receptivity and finally resulted in embryo implantation failure.
RESUMO
<p><b>OBJECTIVE</b>To investigate the apoptosis effect induced by D-limonene on BGC-823 gastric cancer cells.</p><p><b>METHODS</b>The expression of p53, bc1-2 in BGC-823 cells and qualitative, quantitative index of cell apoptosis were detected with MTT, electron microscopy, flow cytometry and immunohistochemical method.</p><p><b>RESULTS</b>D-limonene could induce the formation of apoptotic bodies in a dose- and time-dependent manner. The expression of bcl-2 protein decreased and p53 protein increased in BGC-823 cells treated with D-limonene, compared with the control cells.</p><p><b>CONCLUSION</b>D-limonene exerts its cytotoxic effect on BGC-823 gastric cancer cells by inducing apoptosis.</p>
