Background: Few studies of breast cancer surgery outcomes have used longitudinal data for more than 2 years. This study aimed to validate the use of the artificial neural network (ANN) model to predict the 5-year mortality of breast cancer patients after surgery and compare predictive accuracy between the ANN model, multiple logistic regression(MLR) model, and Cox regression model.Methods: This study compared the MLR, Cox, and ANN models based on clinical data of 3632 breast cancer patients who underwent surgery between 1996 and 2010. An estimation dataset was used to train the model, and a validation dataset was used to evaluate model performance. The sensitivity analysis was also used to assess the relative significance of input variables in the prediction model.Results: The ANN model significantly outperformed the MLR and Cox models in predicting 5-year mortality, with higher overall performance indices. The results indicated that the 5-year postoperative mortality of breast cancer patients was significantly associated with age, Charlson comorbidity index (CCI), chemotherapy, radiotherapy, hormone therapy, and breast cancer surgery volumes of hospital and surgeon (all P < 0.05). Breast cancer surgery volume of surgeon was the most influential (sensitive) variable affecting 5-year mortality, followed by breast cancer surgery volume of hospital, age, and CCI.Conclusions: Compared with the conventional MLR and Cox models, the ANN model was more accurate in predicting 5-year mortality of breast cancer patients who underwent surgery. The mortality predictors identified in this study can also be used to educate candidates for breast cancer surgery with respect to the course of recovery and health outcomes.

OBJECTIVE: We wanted to evaluate the impact of two reconstruction algorithms (halfscan and multisector) on the image quality and the accuracy of measuring the severity of coronary stenoses by using a pulsating cardiac phantom with different heart rates (HRs). MATERIALS AND METHODS: Simulated coronary arteries with different stenotic severities (25, 50, 75%) and different luminal diameters (3, 4, 5 mm) were scanned with a fixed pitch of 0.16 and a 0.35 second gantry rotation time on a 64-slice multidetector CT. Both reconstruction algorithms (halfscan and multisector) were applied to HRs of 40-120 beats per minute (bpm) at 10 bpm intervals. Three experienced radiologists visually assessed the image quality and they manually measured the stenotic severity. RESULTS: Fewer measurement errors occurred with multisector reconstruction (p = 0.05), a slower HR (p < 0.001) and a larger luminal diameter (p = 0.014); measurement errors were not related with the observers or the stenotic severity. There was no significant difference in measurements as for the reconstruction algorithms below an HR of 70 bpm. More nonassessable segments were visualized with halfscan reconstruction (p = 0.004) and higher HRs (p < 0.001). Halfscan reconstruction had better quality scores when the HR was below 60 bpm, while multisector reconstruction had better quality scores when the HR was above 90 bpm. For the HRs between 60 and 90 bpm, both reconstruction modes had similar quality scores. With excluding the nonassessable segments, both reconstruction algorithms achieved a similar mean measured stenotic severity and similar standard deviations. CONCLUSION: At a higher HR (above 90 bpm), multisector reconstruction had better temporal resolution, fewer nonassessable segments, better quality scores and better accuracy of measuring the stenotic severity in this phantom study.
*Algorithms ; Artifacts ; Computer Simulation ; Coronary Angiography/*methods ; Coronary Stenosis/*radiography ; Electrocardiography ; *Heart Rate ; Image Processing, Computer-Assisted/*methods ; Models, Cardiovascular ; Observer Variation ; Phantoms, Imaging ; Reproducibility of Results ; Severity of Illness Index ; Tomography, Spiral Computed/*methods

To establish method suitable to assay HCMVpp65 of the blood donors in blood bank and to supply safe blood to the patients, the immunocytochemical techniques were used, (6 - 8) x 10(6)/ml cells were counted, 50 x 10(3) cells were detected by light microscope, The results showed that 10 positive samples in 103 samples were found, positive rate was 9.71%, among 10 positive samples, 2 samples were still positive in the second detecting. In conclusion, this method is simple, quick and effective, suitable to detect HCMVpp65 of the blood donors in the blood bank.
Blood Banks ; Blood Donors ; Female ; Humans ; Immunohistochemistry ; Male ; Phosphoproteins ; blood ; Viral Matrix Proteins ; blood

INTRODUCTION: Bystander cardiopulmonary resuscitation (B-CPR) is associated with improved out-of hospital cardiac arrest survival. Community-level interventions including dispatcher-assisted CPR (DA-CPR) and myResponder were implemented to increase B-CPR. We sought to assess whether these interventions increased B-CPR. METHODS: The Singapore out-of-hospital cardiac arrest registry captured cases that occurred between 2010 and 2017. Outcomes occurring in 3 time periods (Baseline, DA-CPR, and DA-CPR plus myResponder) were compared. Segmented regression of time-series data was conducted to investigate our intervention impact on the temporal changes in B-CPR. RESULTS: A total of 13,829 out-of-hospital cardiac arrest cases were included from April 2010 to December 2017. Higher B-CPR rates (24.8% versus 50.8% vs 64.4%) were observed across the 3 time periods. B-CPR rates showed an increasing but plateauing trend. DA-CPR implementation was significantly associated with an increased B-CPR (level odds ratio [OR] 2.26, 95% confidence interval [CI] 1.79-2.88; trend OR 1.03, 95% CI 1.01-1.04), while no positive change was detected with myResponder (level OR 0.95, 95% CI 0.82-1.11; trend OR 0.99, 95% CI 0.98-1.00). CONCLUSION B-CPR rates in Singapore have been increasing alongside the implementation of community-level interventions such as DA-CPR and myResponder. DA-CPR was associated with improved odds of receiving B-CPR over time while the impact of myResponder was less clear.