Machine Learning Methods to Investigate Drug Delivery in Infusion Pump

In the current scenario, usage of the smart medical pump is predominant in the medical field. The precise drug dosage, flow accuracy should be maintained to increase the performance of an infusion pump. In this work, an attempt has been made to predict and control the speed of the infusion pump for suitable infusion flowrate using machine learning technique and Linear Quadratic Gaussian (LQG) controller. The data for this study is considered from the publicly available online database, electronic Medicines Compendium (eMC). The speed of the infusion pump has been calculated using the drug dosage and flow rate for two different drugs. The prediction of infusion pump speed is achieved using Linear regression with Principal Component analysis (PCR) and Support Vector Machine Regression (SVR). The performance of the prediction schemes is evaluated using standard metrics. To validate the optimal control of the predicted speed, two different medical graded motors are considered. Further, the optimal control of the pump speed is investigated using Proportional–Integral–Derivative (PID), Linear Quadratic Regulator (LQR), and LQG controllers for its stability criteria. The prediction of the pump speed using regression models PCR, SVR has been verified and then the transient response analysis with rise time, settling time for both the motors have been examined. Results demonstrate that the LQG optimal control strategy achieves fast rise time, settling time of motor1 with 0.653s, 1.15s, and 0.22, 0.392s for motor2 respectively.

Sensitivity analysis of environmental impact of milk powder spray drying system based on intelligent algorithm

The increasing market demand for milk powder has not only promoted the production capacity of milk powder, but also increased the impact on the environment. Therefore, it is very important to study the relationship between the environmental impact of milk powder spray drying (MPSD) system and system-related parameters and identify the key parameters to improve the efficiency of the sustainable improvement of the system. Treed Gaussian Process (TGP) and Standardized Regression Coefficients (SRC)methods are used to analyze the sensitivity of the system to environmental impacts. The results show that the inlet air temperature of the drying tower has the greatest impact on the environment of the system, accounting for about 82%, followed by the atomization pressure and the feed pump speed, accounting for about 9% and 8% respectively. Moreover, not only the environmental performance of the system should be improved, but also the quality of milk powder should be guaranteed when optimizing the parameters such as the inlet air temperature of drying tower. This study can help the manufacturers of milk powder and related equipment to determine the priority of improving the system from the perspective of environmental protection.

Effects of Acute Pump Speed Changes on Cerebral Hemodynamics in Patients With an Implantable Continuous-Flow Left Ventricular Assist Devices

Mechanical circulatory support (MCS) with an implantable left ventricular assist device (LVAD) is an established therapeutic option for advanced heart failure. Most of the currently used LVADs generate a continuous stream of blood that decreases arterial pulse pressure. This study investigated whether a change of the pulse pressure during different pump speed settings would affect cerebral autoregulation and thereby affect cerebral blood flow (CBF). The study included 21 haemodynamically stable outpatients with a continuous-flow LVAD (HeartMate II, Abbott, USA) implanted a median of 6 months before the study (interquartile range 3 to 14 months). Arterial blood pressure (measured by finger plethysmography) was recorded simultaneously with CBF (measured by transcranial Doppler ultrasound) during baseline pump speed (8900 rpm [IQR 8800; 9200]) and during minimum and maximum tolerated pump speeds (8000 rpm [IQR 8000; 8200] and 9800 rpm [IQR 9800; 10 000]). An increase in LVAD pump speed by 800 rpm [IQR 800; 1000] from the baseline lead to a significant decrease in arterial pulse pressure and cerebral blood flow pulsatility (relative change −24 % and −32 %, both p < 0.01), but it did not affect mean arterial pressure and mean CBF velocity (relative change 1 % and −1.7 %, p=0.1 and 0.7). In stable patients with a continuous-flow LVAD, changes of pump speed settings within a clinically used range did not impair static cerebral autoregulation and cerebral blood flow.

Housingless ESPs for Slim Completion Wells

This paper describes a new electrical submersible pump (ESP) design concept to overcome the challenges of applications in slim well completions or thru-tubing deployment. The housing of the conventional pump is removed, allowing the pump impellers to have a larger diameter. The impact of this design change on pump hydraulic performance is assessed in this paper. Downhole ESPs operate in environments where space is limited radially. This is especially the case for slim completions or for thru-tubing rigless deployment. To provide the required rate and total dynamic head, the current approach is to use permanent magnetic motors and operate the slim systems at rotational speed over the conventional speed of 3500-4000 RPM. High-speed operations require new pump stage designs to minimize erosion and vibration. This paper provides an alternative pump design, which removes the pump housing with the benefit of increasing the impeller tip diameter, and hence potentially reducing pump length and operational speed. To ensure the pump retains the well fluids, the diffusers are designed to be externally threaded with an O-ring feature. The centrifugal pump affinity laws are applied to evaluate the impact of removing the pump housing and increasing the impeller outside diameter. A typical ESP housing wall thickness is about 0.18-0.25 inch. With the housing removed, the incremental space available for the impeller tip to occupy is increased by 0.36-0.5 inch. Analysis shows that, for the same pump speed as a conventional pump with a housing, a housingless pump will increase the head generated by 23-32%, and the rate capacity about 36-51%, depending on the pump series. In general, the smaller the pump outer diameter, the greater the flow and head capacity increase. This is because the available space due to removing the housing becomes a considerable size of the impeller tip diameter for the smaller series pumps. The elimination of pump housing enables impellers with a larger diameter to be used to generate more head per stage. In comparison to a conventional pump of the same outside diameter, and providing the same amount of total dynamic head, the housingless pump can have fewer stages and a shorter length or operate at a reduced speed. The reduced length can help mitigating pump-bending stress for installation in deviated or horizontal wells. The reduction in required operating speeds will reduce pump wears, heat generation and vibration. The housingless ESPs have applications for slim well completions or thru-tubing deployments.

Optimisation of a Pump-Controlled Hydraulic System using Digital Displacement Pumps

When electrifying working machines, energy-efficient operation is key to maximise the use of the limited capacity of on-board batteries. Previous research indicate high energy savings by means of component and system design. In contrast, this paper focuses on how to maximise energy efficiency by means of both design and control optimisation. Simulation-based optimisation and dynamic programming are used to find the optimal electric motor speed trajectory and component sizes for a scooptram machine equipped with pump control, enabled by digital displacement pumps with dynamic flow sharing. The results show that a hardware configuration and control strategy that enable low pump speed minimise drag losses from parasitic components, partly facilitated by the relatively high and operation point-independent efficiencies of the pumps and electric motor. 5–10% cycle energy reductions are indicated, where the higher figure was obtained for simultaneous design and control optimisation. For other, more hydraulic-intense applications, such as excavators, greater reductions could be expected.

Abstract 11597: Characterization of Epinephrine Use During Extracorporeal Cardiopulmonary Resuscitation

Introduction: Guidelines recommend dosing Epinephrine (Epi) at regular intervals during pediatric cardiac arrest, including patients requiring extracorporeal membrane oxygenation (ECMO). The impact of Epi-induced vasoconstriction on systemic afterload and veno-arterial ECMO support is poorly understood. Hypothesis: Higher total dose of Epi and shorter interval between Epi dose and ECMO flow during cardiac arrest will increase systemic afterload and interfere with ECMO support. Methods: This is an ancillary study to a single-center, retrospective observational study of patients 0-18 years old who required ECMO cannulation during resuscitation over a six-year period. Patients were excluded if ECMO was initiated prior to arrest or if the resuscitation record was incomplete. The primary exposure was time from last dose of Epi to initiation of ECMO flows; secondary exposures included cumulative Epi dose delivered and indexed to arrest time. Mean arterial pressure (MAP) and systemic vasodilator therapy were used as surrogates for systemic afterload; ECMO pump speed and vasoactive-inotrope score (VIS) were used as measures of ECMO support. Results: A total 92 events in 87 patients analyzed. The patient cohort was 53% female with median (IQR) age of 122 (30-478) days, weight 4.4 (3.3 - 8.7) kg, and 43% single ventricle physiology. On average, Epi was given 7 (4 - 10) times during a 35 (27 - 44) min arrest, for a total dose of 65 (37 - 101) mcg/kg; the last dose was given 6 (2 -16) min prior to the initiation of ECMO flows. In the 6 hours following initiation of ECMO, MAP increased from 42 (36 - 56) mmHg to 57 (47 - 70) mmHg, (p<0.0001). Shorter interval between last Epi dose and ECMO initiation trended with higher MAP after 1 hour of support (estimate -0.43, p=0.06) and associated with increased of vasodilators within 6 hours of ECMO (vasodilators used (1 - 6) vs not used 9 (3 - 16) min, p=0.05). No other associations were found between Epi delivery, MAP, vasodilator use, pump speed or VIS. Conclusion: There is limited evidence to support that regular dosing of Epi throughout a cardiac arrest is associated with clinically significant increases in afterload after ECMO cannulation. Additional studies are needed to validate findings against ECMO flows and clinically relevant outcomes.

Experimental Research on the Measurement of High-Pressure Microflow Based on Momentum Principle

The fuel injector is an important component of the diesel engine. It has a great influence on the atomization of diesel fuel injection, the formation of mixed gas, and combustion emissions. Due to the current nozzle structure, processing level, and the internal hydraulic conditions of each nozzle, there are certain differences between the injection rules of each hole, and there are few methods to quantify the quality of the injector using mathematical methods in engineering. Based on the principle of spray momentum, this paper measures the injection characteristics of each hole of four five-hole pressureless chamber injectors of the same model and analyzes the circulating fuel injection volume and flow coefficient of each injector and each hole under different working conditions. It is proposed to evaluate the quality of the injector with the average circulating fuel injection volume, average flow coefficient, and nonuniformity as indicators. The test results are as follows: there are differences in the circulating fuel injection volume and flow coefficient between each hole of the same fuel injector. With the increase of the fuel injection pump speed, the average circulating fuel injection volume of each hole differs by 2.8%–47.5%, and the average flow coefficient differs by 3.7%–30%; as the fuel injection volume increases, the average circulating fuel injection volume of each injector differs 1.8%–36%, and the average flow coefficient difference is 2.5%–28.7%. The circulating fuel injection volume and flow coefficient of different fuel injectors of the same model are different. With the increase of the fuel injection pump speed, the average circulating fuel injection volume of each injector differs by 3.5%–9.6%, and the average flow coefficient differs by 1.4%–5.7%; as the fuel injection volume increases, the average circulating fuel injection volume of each injector differs 0.3%–5.5%, and the average flow coefficient difference is 2.8–4.2%. The relative flow coefficient of each hole differs from 0 to 0.02, and the nonuniformity differs from 1.8% to 16.9%. The relative circulating fuel injection amount of each hole differs from 0.02 to 0.1, and the nonuniformity differs from 1.1% to 6.9%. The relative flow coefficient of each hole and its nonuniformity is smaller than the relative circulating fuel injection volume of each hole and its nonuniformity.

Evaluation of the efficiency of a new pulsatile flow‑generating circulatory-assist system in rotary blood pumps. Research on a mathematical model

Objective: to study the effect of a pulsatile flow-generation (PFG) device on the basic hemodynamic parameters of the circulatory system using a mathematical model.Results. Modelling and simulation showed that the use of PFG significantly (76%) increases aortic pulse pressure. The proposed mathematical model adequately describes the dynamics of the circulatory system and metabolism (oxygen debt) on physical activity in normal conditions and heart failure, and the use of non-pulsatile and pulsatile circulatory-assist systems. The mathematical model also shows that the use of PFG device blocks the development of rarefaction in the left ventricular cavity associated with a mismatch of blood inflow and outflow in diastolic phase when there is need to increase systemic blood flow by increasing the rotary pump speed.

Echo-guided LVAD speed optimization for exercise maximization

Background Continuous-flow left ventricular assist devices (LVAD) are becoming a destination therapy in patients with end-stage left ventricular dysfunction and a competitive method for heart transplantation. Current generation pumps operate with a fixed rotation speed and do not have the automatic speed adjustment capability. However, it was shown that acceleration of the pump speed during stress test increases the maximum exercise tolerance. Purpose The study aimed to evaluate the concept of dynamic pump speed optimization based on the echocardiographic assessment of aortic valve opening (AVO) during the cardiopulmonary exercise test (CPET). Methods Patients with implanted third-generation centrifugal continuous-flow LVAD's with hydrodynamic bearing were prospectively included. Two CPET's were performed after resting speed optimization. The first one with maintained baseline pump speed settings, and the second one with gradually increased speed depending on live echocardiographic imaging. The sequence of tests was random. Results Exercise AVO was apparent in all 22 included patients. The resting pump speed was 2691 RPM and incremented on average by 566 RPM (20%). Pump power and flow raised from 5.6 to 9.8 Watts (p&lt;0.0001) and from 5.8 to 7.3 l/min (p&lt;0.0001), respectively. Peak VO2 increased from 11.1 to 12.8 ml/kg/min (p=0.0003) and maximum workload from 1.1 to 1.2 W/kg (p=0.03). The Borg scale exertion level decreased from 15.2 to 13.5 (p=0.0049). There was a visible trend towards longer exercise time (36s) but no statistical significance was achieved (p=0.1). Conclusion Ultrasonographic AVO analysis is possible during CPET's in patients supported with LVAD. Dynamic echo-guided pump speed adjustment based on the AVO improves exercise tolerance, augments peak VO2 consumption and maximal workload. An automatic speed adjustment in the next generations of LVAD controllers might improve functional capacity and requires further basic, technological and clinical research. FUNDunding Acknowledgement Type of funding sources: Other. Main funding source(s): 1. Cor Aegrum Foundation of Cardiac Surgery Development in Cracow2. Medtronic Poland Sp. z o.o.

An Intra-Cycle Optimal Control Framework for Ventricular Assist Devices Based on Atrioventricular Plane Displacement Modeling

A promising treatment for congestive heart failure is the implementation of a left ventricular assist device (LVAD) that works as a mechanical pump. Modern LVADs work with adjustable constant rotor speed and provide therefore continuous blood flow; however, recently undertaken efforts try to mimic pulsatile blood flow by oscillating the pump speed. This work proposes an algorithmic framework to construct and evaluate optimal pump speed policies with respect to generic objectives. We use a model that captures the atrioventricular plane displacement, which is a physiological indicator for heart failure. We employ mathematical optimization to adapt this model to patient specific data and to find optimal pump speed policies with respect to ventricular unloading and aortic valve opening. To this end, we reformulate the cardiovascular dynamics into a switched system and thereby reduce nonlinearities. We consider system switches that stem from varying the constant pump speed and that are state dependent such as valve opening or closing. As a proof of concept study, we personalize the model to a selected patient with respect to ventricular pressure. The model fitting results in a root-mean-square deviation of about 6 mmHg. The optimization that considers aortic valve opening and ventricular unloading results in speed modulation akin to counterpulsation. These in silico findings demonstrate the potential of personalized hemodynamical optimization for the LVAD therapy.