ABSTRACT
Acute respiratory distress syndrome (ARDS) is a serious threat to human life and health disease, with acute onset and high mortality. The current diagnosis of the disease depends on blood gas analysis results, while calculating the oxygenation index. However, blood gas analysis is an invasive operation, and can't continuously monitor the development of the disease. In response to the above problems, in this study, we proposed a new algorithm for identifying the severity of ARDS disease. Based on a variety of non-invasive physiological parameters of patients, combined with feature selection techniques, this paper sorts the importance of various physiological parameters. The cross-validation technique was used to evaluate the identification performance. The classification results of four supervised learning algorithms using neural network, logistic regression, AdaBoost and Bagging were compared under different feature subsets. The optimal feature subset and classification algorithm are comprehensively selected by the sensitivity, specificity, accuracy and area under curve (AUC) of different algorithms under different feature subsets. We use four supervised learning algorithms to distinguish the severity of ARDS (P/F ≤ 300). The performance of the algorithm is evaluated according to AUC. When AdaBoost uses 20 features, AUC = 0.832 1, the accuracy is 74.82%, and the optimal AUC is obtained. The performance of the algorithm is evaluated according to the number of features. When using 2 features, Bagging has AUC = 0.819 4 and the accuracy is 73.01%. Compared with traditional methods, this method has the advantage of continuously monitoring the development of patients with ARDS and providing medical staff with auxiliary diagnosis suggestions.
Subject(s)
Humans , Algorithms , Area Under Curve , Blood Gas Analysis , Machine Learning , Monitoring, Physiologic , Methods , ROC Curve , Respiratory Distress Syndrome , Diagnosis , Sensitivity and SpecificityABSTRACT
<p><b>OBJECTIVE</b>To evaluate the differences in the therapeutic effects on relapsing-remitting multiple sclerosis (RRMS) at remission stage between acupuncture at acupoints and shallow needling therapy at the nearby points.</p><p><b>METHODS</b>Forty-two patients of RRMS were randomized into an observation group and a control group, 21 cases in each one. In the observation group, besides the basic treatment, acupuncture was applied according to's empirical prescriptions as "the empirical ten needles" "thirteen needles of the governor vessel" "twelve needles of hand and foot" as well as the symptomatic points. In the control group, the basic treatment was given. Additionally, the shallow needling therapy was given at the sites 0.2 to 0.3lateral to the acupoints, and the arrival ofwas not required. In the two groups, acupuncture was given once a day for 5 days a week, continuously for 2 weeks. At the intervals of 2 weeks, totally the treatment of 3 months was required. The follow-up visit was conducted for 2 years. Separately, the scores of the expanded disability status scale (EDSS) before and in follow-up after treatment, the annual recurrent rate before and after treatment and recurrent interval after treatment were observed in the patients of the two groups.</p><p><b>RESULTS</b>In the observation group, EDSS scores in 3-month and 6-month follow-up were reduced as compared with those before treatment (both<0.05) and those in the 12-month and 24-month follow-up were increased (both<0.05). In the control group, EDSS scores were increased in tendency continuously in 3-month, 6-month, 12-month and 24-month follow-up (all<0.05). In each time point of follow-up, the different value of EDSS scores in the observation group was lower than that in the control group (<0.05,<0.01). The annual recurrent rates after treatment were reduced as compared with those before treatment in the two groups (both<0.01) and the value in the observation group was lower than that in the control group (<0.01). The recurrent interval in the observation group was longer than that in the control group[(441.56±65.37) d vs (382.78±59.33) d,<0.01].</p><p><b>CONCLUSIONS</b>Acupuncture achieves the significant therapeutic effects on RRMS at the remission stage. This therapy relieves the symptoms of neural functional deficits, delays the time of occurrence and reduces the annual recurrent rate.</p>
ABSTRACT
Objective To design a temperature control strategy for riptide bioreactor to eliminate integral saturation by conventional proportion integration differentiation (PID) control.Methods According to the requirement of the riptide bioreactor for the temperature control,the temperature control system model determined by experiment was got,then the effectiveness of the integral limiter PID control method was verified,and finally the integral limiter PID control method wasimproved further using the integral separation combined with the actual experimental results and its effectiveness was tested.Results The simulation results showed that the control effects of the integral limiter PID was good.However,the actual tests proved that there was still deficiencies in large overshoot and long stable time,and good experimental results were obtainedafter improving the integral limiter PID by the integral separation method.Conclusion The improved integral limiter PID control method effectively avoids the overshoot of the system caused by the integral saturation,achieves high control precision,has a very good control performance for the temperature control of riptide bioreactor,and well meets the requirements of mammalian cell culture.
ABSTRACT
Objective To develop a BP neural network to differentiate between ventricular fibrillation( VF) and non-VF rhythms.Methods Eighteen metrics were extracted from the ECG signals.Each of these metrics respectively characterized each aspect of the signals, such as morphology, gaussianity, spectra, variability, and complexity.These metrics were regarded as the input vector of the BP neural network.After training, a classifier used for VF and non-VF rhythm classification was obtained.Results and Conclusion The constructed BP neural network was tested with the databases of VFDB and CUDB, and the accuracy was 98.61%and 95.37%, respectively.
ABSTRACT
Objective To design a temperature control strategy for wave bioreactors.Methods According to the requirements of temperature control precision and response speed of wave bioreactors,the traditional PID control method was combined with fuzzy control method which was used to adjust the parameters of the PID control in real time online in order to strengthen the ability of the temperature control strategy to regulate temperature.Results A fuzzy PID controller was completed and simulation results were compared with the traditional PID controller.Conclusion The fuzzy PID control method has a smaller overshoot and shorter stability than the traditional one, so it has a higher temperature control performance.
ABSTRACT
Objective To investigate the effect of early acupuncture at Huatuo jiaji points on striatalβ-endorphin and dynorphin levels in rats with post-stroke limb spasm.Methods Seventy SD rats were randomized into group A (normal) of 9 rats and group B (sham operation) of 10 rats. After a model of post-stroke limb spasm was made in the remaining rats, they were randomized into groups C (model), D (acupuncture at Huatuo jiaji points) and E (baclofen). Group D received acupuncture at Huatuo jiaji points and group E, an oral gavage of baclofen tablets. After seven days of treatment, striatalβ-endorphin and dynorphin levels were neasured by radioimmunoassay.Resultsβ-endorphin levels increased significantly in groups C, D and E compared with groups A and B (P0.05). Dynorphin levels increased significantly in groups C, D and E compared with groups A and B (P0.05).Conclusions Acupuncture at Huatuo jiaji points can increase striatalβ-endorphin levels but not change striatal dynorphin levels, which conforms to the relationship between enkephalin and spasm, and improve the animal’s spasticity.
ABSTRACT
This paper introduces the development and animal tests of a miniaturized electrical chest compression device. Based on pulse width modulation technology produced by micro control unit, the device can control the frequency and depth of the compression accurately, as well as perform real-time adjustment. Therefore, it can perform continuous and stable chest compression for long time, which may increase the successful rate of cardiopulmonary resuscitation (CPR). Besides, the device can also produce different types of compression waveforms, including trapezoidal and triangular waveforms. Then, the performance and efficacy of the device was assessed with a rat model of asphyxial cardiac arrest (CA).