ABSTRACT
Objective:To investigate a time series deep learning model for respiratory motion prediction.Methods:Eighty pieces of respiratory motion data from lung cancer patients were used in this study. They were divided into a training set and a test set at a ratio of 8∶2. The Informer deep learning network was employed to predict the respiratory motions with a latency of about 600 ms. The model performance was evaluated based on normalized root mean square errors (nRMSEs) and relative root mean square errors (rRMSEs).Results:The Informer model outperformed the conventional multilayer perceptron (MLP) and long short-term memory (LSTM) models. The Informer model yielded an average nRMSE and rRMSE of 0.270 and 0.365, respectively, at a prediction time of 423 ms, and 0.380 and 0.379, respectively, at a prediction time of 615 ms.Conclusions:The Informer model performs well in the case of a longer prediction time and has potential application value for improving the effects of the real-time tracking technology.
ABSTRACT
Objective To evaluate the influence of the placement of instant hand disinfectant in compliance and qualified rate of hand hygiene of clinicians.Methods Hand hygiene compliance of clinicians in departments of gyne-cology,obstetrics,and general surgery were observed after the placement of instant hand disinfectant at the door-way of wards,hand specimens were taken to check hand hygiene effectiveness.Results Before and after placement of instant hand disinfectant at the doorway of wards of above departments,hand hygiene behaviors of 300 person-times were observed.Hand hygiene compliance rate among clinicians in department of gynecology,obstetrics,and general surgery increased from 32.33% to 74.33%,33.67% to 85.67%,and 26.33% to 64.00%,respectively(all P <0.001).Each department selected 98 hand hygiene specimens,the qualified rate was 98.98%,100.00% and 94.90% respectively.Conclusion The placement of instant hand disinfectant at the doorway of each ward can effec-tively improve clinicians’hand hygiene compliance and hand hygiene effectiveness.
ABSTRACT
Objecflve To determine the prevalences of nutritional risk,undemutrition,overweight,and obesity as well as nutritional support and the changes of nutritional risks from admission to discharge or over a two-week period.Methods A consecutive sampling was performed.Dam were collected from general surgical depart-ments in three Beijing teaching hospitals from March to July in 2007.Patients were screened using Nutritional Risk Screening 2002(NRS2002)on admission and two weeks after admission(or discharge).The nutritional supper apphcation during hospital stay was recorded.NRS2002 score≥3 was classified as nutritional risk.BMI<1 8.5kg/m2 with impaired genend condition was defined as undemutrition.Results Among 300 enrolled patients,the NRS2002 WaS completed by 99.0%(297/300)of all patients.The nutritional risk and the prevalence of under_nutrition,overweight,and obesity was 30.0%,8.1%,38.3%,and 9.4%,respectively at admission.Fifty of 90(62.2%)patients who were at nutritional risk received nutritional support while 40 of 210(19.O%)non-risk patients received nutritional support.Especially among major abdominal surgery patients,56 of 90(71.6%)pa-tients who were at nutritional risk received nutritional supper while 35 of 81(43.2%)non-risk pafients received nutritional support.The prevalence of nutritional risk changed from 30.0%to 35.8%(X2=2.271,P=0.132).Conclusions NRS2002 is a feasible nutritional risk screening tool among general surgical pafienm in selected Bei-jing teaching hospitals.Nutritional support is somehow inappropriately apphed in general surgical hospitalized pa-tients.The prevalence of nutritional risk remains unchanged in general surgical patients during hospitalization.