Multiple drug hemodynamic control by means of a supervisory-fuzzy rule-based adaptive control system: validation on a model.

A control device that uses an expert system approach for a two input-two output system has been developed and evaluated using a mathematical model of the hemodynamic response of a dog. The two inputs are the infusion rates of two drugs: sodium nitroprusside (SNP) and dopamine (DPM). The two controlled variables are the mean arterial pressure and the cardiac output. The control structure is dual mode, i.e., it has two levels: a critical conditions (coarse) control mode and a noncritical conditions (fine) control mode. The system switches from one to the other when threshold conditions are met. Different "controller parameters sets"-including the values for the threshold conditions-can be given to the system which will lead to different controller outputs. Both control modes are rule-based, and supervisory capabilities are added to ensure adequate drug delivery. The noncritical control mode is a fuzzy logic controller. The system includes heuristic features typically considered by anesthesiologists, like waiting periods and the observance of a "forbidden dosage range" for DPM infusion when used as an inotrope. An adaptation algorithm copes with the wide range of sensitivities to SNP found among different individuals, as well as the time varying sensitivity frequently observed in a single patient. The control device is eventually tested on a nonlinear model, designed to mimic the conditions of congestive heart failure in a dog. The test runs show a highest overshoot of 3 mmHg with nominal SNP sensitivity. When tested with different simulated SNP sensitivities, the controller adaptation produces a faster response to lower sensitivities, and reduced oscillations to higher sensitivities. The simulations seem to show that the system is able to drive and adequately keep the two hemodynamic variables within prescribed limits.

Hemodynamic management of congestive heart failure by means of a multiple mode rule-based control system using fuzzy logic.

A rule-based system was designed to control the mean arterial pressure (MAP) and the cardiac output (CO) of a patient with congestive heart failure (CHF), using two vasoactive drugs: sodium nitroprusside (SNP) and dopamine (DPM). The controller has three different modes, that engage according to the hemodynamic state. The critical conditions control mode (CCC) determines the initial infusion rates, and continues active if the MAP or the CO fall outside of the defined criticality thresholds: an upper and a lower boundary for the MAP and a lower boundary for the CO. Inside the boundaries the control is performed by noncritical conditions control modes (NCC's), which are fuzzy logic controllers. If the CO is within normal range and the MAP is close to the goal range, then the MAP is driven using only SNP, in a single-input-single-output mode (NCC-SISO). Otherwise the NCC multiple-input-multiple-output is active (NCC-MIMO). The goal values for the controlled variables are defined as a band of 5 mmHg for the MAP and 5 mL/kg/min for the CO, but there is little concern for this application if the CO is too high (i.e., in practical terms the CO only needs to achieve a necessary minimum rate). The NCC-MIMO includes a gain adaptation algorithm to cope with the wide variety in sensitivities to SNP. Supervisory capabilities to ensure adequate drug delivery complete the controller scheme. After extensive testing and tuning on a CHF-hemodynamics nonlinear model, the control system was applied in dog experiments, which led to further enhancements. The results show an adequate control, presenting a fast response to setpoint changes with an acceptable overshoot.

Power requirements for vibrotactile piezo-electric and electromechanical transducers.

Human-machine information transfer through tactile excitation has addressed new applications in virtual reality, robotics, telesurgery, sensory substitution and rehabilitation for the handicapped in the past few years. Power consumption is an important factor in the design of vibrotactile displays, because it affects energy needs and the size, weight, heat dissipation and cost of the associated electronics. An experimental study is presented on the power required to reach tactile thresholds in electromechanical and piezo-electric transducers. Three different waveforms are considered, with an excitatory period formed by a burst of rectangular 50% duty cycle pulses (R50), rectangular low duty cycle pulses (RLO) and sinusoidal pulses (SIN). Ten different pulse repetition periods (RPs) were considered in the range 1/550-1/25 s. The voltage and current waveforms applied to the transducers at sensation thresholds in a group of 12 healthy subjects were sampled and stored in a digital oscilloscope. The average power was determined for each subject, and differences of two orders of magnitude were measured between the electromechanical and the piezo-electric transducer power consumption. Results show that, for the electromechanical transducer, a smaller power consumption of 25 microW was determined for RP = 1/25 s and the RLO waveform. In the case of the piezo-electric transducer, power of 0.21 microW was determined for SIN excitation and RP = 1/250 s. These results show the advantages of reducing power requirements for vibrotactile displays, which can be optimised by the choice of appropriate types of transducer, excitatory waveforms and pulse repetition periods.

Expert-system classification of sleep/waking states in infants.

This work is part of a project to develop an expert system for automated classification of the sleep/waking states in human infants; i.e. active or rapid-eye-movement sleep (REM), quiet or non-REM sleep (NREM), including its four stages, indeterminate sleep (IS) and wakefulness (WA). A model to identify these states, introducing an objective formalisation in terms of the state variables characterising the recorded patterns, is presented. The following digitally recorded physiological events are taken into account to classify the sleep/waking states: predominant background activity and the existence of sleep spindles in the electro-encephalogram; existence of rapid eye movements in the electro-oculogram; and chin muscle tone in the electromyogram. Methods to detect several of these parameters are described. An expert system based on artificial ganglionar lattices is used to classify the sleep/waking states, on an off-line minute-by-minute basis. Algorithms to detect patterns automatically and an expert system to recognise sleep/waking states are introduced, and several adjustments and tests using various real patients are carried out. Results show an overall performance of 96.4% agreement with the expert on validation data without artefacts, and 84.9% agreement on validation data with artefacts. Moreover, results show a significant improvement in the classification agreement due to the application of the expert system, and a discussion is carried out to justify the difficulties of matching the expert's criteria for the interpretation of characterising patterns.

Polysomnographic pattern recognition for automated classification of sleep-waking states in infants.

A robust, automated pattern recognition system for polysomnography data targeted to the sleep-waking state and stage identification is presented. Five patterns were searched for: slow-delta and theta wave predominance in the background electro-encephalogram (EEG) activity; presence of sleep spindles in the EEG; presence of rapid eye movements in an electro-oculogram; and presence of muscle tone in an electromyogram. The performance of the automated system was measured indirectly by evaluating sleep staging, based on the experts' accepted methodology, to relate the detected patterns in infants over four months of post-term age. The set of sleep-waking classes included wakefulness, REM sleep and non-REM sleep stages I, II, and III-IV. Several noise and artifact rejection methods were implemented, including filters, fuzzy quality indices, windows of variable sizes and detectors of limb movements and wakefulness. Eleven polysomnographic recordings of healthy infants were studied. The ages of the subjects ranged from 6 to 13 months old. Six recordings counting 2665 epochs were included in the training set. Results on a test set (2,369 epochs from five recordings) show an overall agreement of 87.7% (kappa 0.840) between the automated system and the human expert. These results show significant improvements compared with previous work.

Single trial P300 detection in children using expert knowledge and SOM.

Preliminary results of an automatic system for single trial P300 visual evoked potential events detection are presented. For each single trial P300, several candidate events were generated, and then filtered, using 3 wave features. The surviving candidate events were fed into a SOM-based classifier. A context filter was applied before the final output. No stationary condition of the P300 is involved in the algorithms. Recordings of 27 assessment sessions, each with 120 trials, were visually inspected by experts to identify and mark the P300 events, which was accomplished in about one third of the trials. The dataset was divided in training (18) and testing (9) subsets. The system identifies the initial and end times of the P300; it obtained a sensitivity of 53.9%, a specificity of 64.0% and an accuracy of 61.2% in the testing dataset.

A balanced sleep/wakefulness classification method based on actigraphic data in adolescents.

Several research groups have developed automated sleep-wakefulness classifiers for night wrist actigraphic (ACT) data. These classifiers tend to be unbalanced, with a tendency to overestimate the detection of sleep, at the expense of poorer detection of wakefulness. The reason for this is that the measure of success in previous works was the maximization of the overall accuracy, disregarding the balance between sensitivity and specificity. The databases were usually sleep recordings, hence the over-representation of sleep samples. In this work an Artificial Neural Network (ANN), sleep-wakefulness classifier is presented. ACT data was collected every minute. An 11-min moving window was used as observing frame for data analysis, as applied in previous sleep ACT studies. However, our feature set adds new variables such as the time of the day, the median and the median absolute deviation. Sleep and Wakefulness data were balanced to improve the system training. A comparison with previous studies can still be done, by choosing the point in the ROC curve associated with the corresponding data balance. Our results are compared with a polysomnogram-based hypnogram as golden standard, rendering an accuracy of 92.8%, a sensitivity of 97.6% and a specificity of 73.4%. Geometric mean between sensitivity and specificity is 84.9%.