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
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 explore the relationship between the spot size and the result of ploidy analysis in the detection technology based on single-particles, and to fix the scope of spot thickness on the basis of the experimental result.Methods The influence of spot thickness on voltage signals produced by single cells was analyzed.The parameters of the beam shap system in the incident field were designed and optimized on ZEMAX.Finally, according to the cells′diameter, the target size of spots was set.A set of spots of different thickness and of Gaussian distribution obtained from the optical experimental platform was used to conduct ploidy detection experiments.Results Target spots were both obtained from ZEMAX simulation and the optical platform.When the spot thickness was larger than both monocytes and coenocytes, the mean fluorescence intensity ratio was 2.03,which met the demand of the index.Conclusion When the height of the pulse is used to represent the fluorescence density, the relative size of spots and cells will affect the result of ploidy detection.Only when spot thickness is larger than cells is the ploidy ratio accurate.
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 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 real-time oxygen generation and supply device for ambulances and to carry out finite element simulated analysis and performance evaluation .Methods Based on the working principles of pressure swing adsorption (PSA) and oxygen pneumatic compression technology ,the structural components and technological processes of an oxygen generation and compression unit as well as an oxygen filling and supply unit were built .The integrated structure of the device was designed by Solidworks .The static structure of the oxygen generation and compression unit was analyzed by ANSYS.Modal analysis of the circuit board was also conducted .The performance of the prototype was evaluated .Results Wtih a stable structure and reliable circuitry , the device could produce and fill oxygen automatically at the flow of 5.0 L/min, concentration of 94.0%, and pressure of 13.0 MPa.Conclusion This device can produce , fill and supply oxygen automatically,and the goal of design is achieved .
ABSTRACT
Objective To design and develop an air purification system for intensive care ambulances,which can effectively purify the air in the compartment and sterilize the microbes in the air.Methods By integrating titanium dioxide photocatalysts with air filtration materials,an air purification system was designed that was capable of effective sterilization of microbes in the air via photocatalytic oxidation and decomposition,and of effective filtration of particles in the air through HEPA filters.The protection effect was evaluated by air filtration and sterilization tests in accordance with the related national standards.Results The air cleanliness could reach the 100 000 level with bacteria counts no more than 1 CFU per pan for 15 minutes in the ambulance compartment when the air purification system worked normally,which could meet the demands of environmental hygienic standards for intensive care units.Conclusion The air purification system can effectively purify and sterilize the air in the compartment of an intensive care ambulance.The effects of air purification meet the requirements of related hygienic standards,which can satisfy the demands of treatment and intensive care for the victims in the ambulance.
ABSTRACT
Objective To develop a portable end-tidal carbon dioxide monitor for the patient's physiological monitoring during the process of the first aid and transport.Methods MCU was used as the core of the control system to communicate with the ETCO2 detection module and the SD memory module. The power supply module and software system were realized for the monitor.Results The monitor had high stability, reliability and performances.Conclusion The monitor meets the desired requirements, and can be used for the monitoring of the patients during first aid or transportation.
ABSTRACT
Objective To present a miniaturized nucleic acid amplification system for spot rapid detection .Methods A miniaturized nucleic acid amplification system with structured packed porous media of particles to uniform the air temperature was designed according to the working principle and heat transfer characteristics of an air -heated nucleic acid amplification system.Thermodynamic simulation and temperature cycling test were carried on to verify the feasibility of the system.Results The structured packed porous media of particles worked well in uniforming the air temperature of the system and the temperature uniformity could reach 0.8℃.The miniaturized nucleic acid amplification system with a volume parameter of 80 mm ×40 mm ×20 mm(length ×height ×width)was portable.The average rate of heating was 10℃/s while the average rate of cooling was 5℃/s.Compared with standard PCR instrument , the miniaturized nucleic acid amplification system performed well in the process of amplification and met the requirements of preliminary design .Conclusion The miniaturized nucleic acid amplification system with a rapid reaction velocity and portable volume could be applied to nucleic acid detection of unknown samples on the spot .
ABSTRACT
Objective A major component of flow cytometry data analysis involves gating , which is the process of identifying homogeneous groups of cells .As manual gating is error-prone, non-reproducible, nonstandardized, and time-consuming , we propose a time-efficient and accurate approach to automated analysis of flow cytometry data .Methods Unlike manual analysis that successively gates the data projected onto a two-dimensional filed, this approach, using the K-means clustering results , directly analyzed multidimensional flow cytometry data via a similar subpopulations-merged algorithm.In order to apply the K-means to analysis of flow cytometric data , kernel density estimation for selecting the initial number of clustering and k-d tree for optimizing efficiency were proposed .After K-means clustering , results closest to the true populations could be achieved via a two-segment line regression algorithm .Results The misclassification rate (MR) was 0.0736 and time was 2 s in Experiment One, but was 0.0805 and 1 s respectively in Experiment Two. Conclusion The approach we proposed is capable of a rapid and direct analysis of the multidimensional flow cytometry data with a lower misclassification rate compared to both nonprobabilistic and probabilistic clustering methods .
ABSTRACT
Objective To develop an intelligent system which is able to offer an optimized emergency treatment recommendation for fast triage automatically.Methods An algorithm and intelligent platform for grading injury were developed based on physiological signal collecting technology, intelligent grading algorithm and integration technology.A comparison between this system and traditional methods was made.Results This intelligent system was able to increase accuracy by 21%and took only 48%of the time taken by traditional methods.There was significant difference between the two groups(P=0.038<0.05).Conclusion The accuracy of the triage is improved by this intelligent system that is less time-consuming.With this device, the injury statement can be identified quickly and the targeted medical treatment can be performed accurately.The efficiency of emergency treatment in case of disaster will thus be dramatically increased.
ABSTRACT
Objective There are three categories of bioaerosol laser telemetry systems according to the light source configuration parameters:namely traditional lidar(light datection and ranging,laser radar), micro-pulse lidar and pseudo-random modulation(lidar).The system source parameters,which impact the degree of danger and detection sensitivity of the system, need to be optimized.Methods With reference to the USA laser product safety standards and by establishing the corresponding mathematical model of a lidar, the three categories of lidar source configuration were compared according to signal to noise ratio(SNR) and security before the repetition rate, pulse energy, divergence angle, distance and other dangerous impact factors were calculated.Results The results showed that to ensure eyesafety, the use of the pulse frequency should be set at 55 kHz for the highest SNR under the micro-pulse lidar excitation mode.Conclusion The eyesafety requirements impact the excitation of light source of a bioaerosol telemetry system.
ABSTRACT
Objective To present a new algorithm of real-time peak detection for pulse signals based on FPGA , which is known as the dynamic threshold with half peak detection method ( DT-HP ) .Methods With Gaussian-shaped pulse signals as the target , the method was improved from conventional methods .The FPGA detection process of the algorithm required no more than three detection parameters: the starting point , the maximum value and the pulse width .Results The algorithm solved the floating baseline and repeating detection that occur in traditional methods .Compared with the results of polynomial fitting method and flow cytometry , the difference was only 3.2% and 9.3%.Conclusion The algorithm takes less time ,RAM, and cache while allowing floating baseline detection , which can be used as an effective method for rapid detection in FPGA .
ABSTRACT
Technology for rapid detection of trace microbes combined with flow cytometry and image cytometry is used for rapid detection of cells and microorganisms, quantification of fluorescent signals, and visualization of cells and mi-crobes.Its fast and accurate count of microorganisms plays an important role in detection of the quantity of food and water, and can help to improve residents′quality of life and health.This article describes several common methods for detecting microorganisms with emphasis on their advantages and disadvantages.Current applications and future developlments are also discussed.
ABSTRACT
Objective To study and design a fluid resuscitation control system which is suitable for the treatment of hemorrhagic shock in the battlefield and prehospital settings. Methods The physiological parameters of the wounded were set as the system input and fuzzy control technology was used to identify the hemorrhagic shock (HS) severity and made a decision. At last, fluid resuscitation was finished with the use of the efficient blood transfusion and infusion pump. Results High-speed resuscitation could be carried out when the wounded was in severe condition, while low-speed resuscitation could be conducted when the wound was in mild condition. Conclusions Compared with the traditional resuscitation method, the designed fluid resuscitation control system can improve the efficiency of fluid resuscitation and the treatment success rate.
ABSTRACT
Objective To develop a multi-channel dry type biochemistry sensor with a compact structure and high measurement accuracy.Methods The principle of double beam compensation based on reference LED was applied to improve the measurement accuracy.The complex splitting system was replaced by MXN fiber bundle and free-form surface lens to make the instrument more compact and lightweight.Use of the adaptive amplification photoelectric detection improved the measurement accuracy while simplifying the process.Results and Conclusion It has been proved by experiments that this sensor has the advantages of high measurement accuracy, little interference and compact construction. This sensor may well meet the requirements of dry type biochemistry analysis.
ABSTRACT
The inspiratory impedance threshold device (ITD) was put forward by Lurie in 1995, and was assigned as a class II a recommendation by the International Liaison Committee on Resuscitation (ILCOR) resuscitation guidelines in 2005. The ITD is used to augment negative intrathoracic pressure during recoil of the chest so as to enhance venous return and cardiac output, and to decrease intracranial pressure. In the recent years many researches on the ITD have been1 carried out, but all the researches can not take out a clear evidence to support or refute the use of the ITD. This paper introduces the structure and working principle of the ITD in detail, the research results and the debates about the use of the ITD for the past years.
Subject(s)
Humans , Cardiopulmonary Resuscitation , Electric Impedance , PressureABSTRACT
To realize the measurement of the chest compression depth during the administration of manual cardiopulmonary resuscitation, two 3-axis digital accelerometers were applied for chest compression acceleration and environment acceleration acquisition, with one placed in the chest compression sensor pad, and the other placed in the back sensor pad. Then double integration was made for the acceleration-to-depth conversion with both of the accelerations after preprocessing. The method further included integration reset mechanism based on compression force, with the force point of a pre-determined threshold and the maximum force point as the starting point and the ending point of the integration, respectively. Moreover, a software compensation algorithm was implemented to further increase the accuracy of the depth estimation and reliability of the acceleration. The final performance of the compression depth estimation is within +/- 0.6 cm with 95% confidence of a total of 283 compressions. Accurate and real-time estimation of chest compression depth greatly facilitates the control of compression depth for the lifesaver during manual cardiopulmonary resuscitation.
Subject(s)
Humans , Acceleration , Cardiopulmonary Resuscitation , Methods , Heart Arrest , Therapeutics , Heart Massage , Methods , Reference Standards , Pressure , ThoraxABSTRACT
Objective A comparability analysis was performed between the various parameters of the self-developed dry-type blood cell analyzer with the reference instrument (Sysmex XT-1800i).Methods In line with the evaluation program of blood cells issued by ICSH,the detection results,six parameters as HCT,Hb,GRAN (granulocytes),LM (lymphatic and monocytes),WBC and PLT,were compared between the two instruments.Some indexes of the subject instrument such as precision,comparability,outlier points,bias,etc.were analyzed and compared so as to calculate the equation of linear regression and the expected bias intervals.Results The intra and inter CV of the subject instrument about six parameters were respectively less than 5％ and 6％,so it showed that the instrument had good precision.Correlation analysis showed that the classification results of HCT,Hb,GRAN and WBC had a good correlation (r =0.991,0.972,0.986,0.975,P ＜0.01),while that of LM and PLT were slightly lower (r =0.952,0.942,P ＜0.01) ; As to the medical decision level,HCT values were 14％ and 70％,WBC 0.5 × 109/L and 3 ×109/L,and PLT 10 × 109/L,50 × 109/L and 100 × 109/L,and the acceptable bias of these values all fell in the confidence intervals; the values of the rest items were slightly higher than the high value of the confidence interval of expected bias.Conclusions The subject instrument produces the same results in the test of its parameters as the reference instrument Sysmex XT-1800i and therefore the two instruments are comparable.The subject instrument is particularly suitable for field rapid detection.
ABSTRACT
The paper designed the portable free hemoglobin detector using spectrophotometry, which determines the concentration of free hemoglobin. The device has features of portability, compact and precise. It can evaluate the quality of blood products instantly and effectively.