Detection of Needle Dislodgement Using Extracorporeal Pressure Signals: A Feasibility Study.

Venous needle dislodgement (VND) during dialysis is a rarely occurring adverse event, which becomes life-threatening if not handled promptly. Because the standard venous pressure alarm, implemented in most dialysis machines, has low sensitivity, a novel approach using extracted cardiac information to detect needle dislodgement is proposed. Four features are extracted from the arterial and venous pressure signals of the dialysis machine, characterizing the mean venous pressure, the venous cardiac pulse pressure, the time delay, and the correlation between the two pressure signals. The features serve as input to a support vector machine (SVM), which determines whether dislodgement has occurred. The SVM is first trained on a set of laboratory data, and then tested on another set of laboratory data as well as on a small data set from clinical hemodialysis sessions. The results show that dislodgement can be detected after 12-17 s, corresponding to 24-143 ml blood loss. The standard venous pressure alarm used in clinical routine only detects 50% of the VNDs, whereas the novel method detects all VNDs and has a false alarm rate of 0.12 per hour, provided that the amplitude of the extracted cardiac pressure signal exceeds 1 mmHg. The results are promising; however, the method needs to be tested on a larger set of clinical data to better establish its performance.

Monitoring respiration using the pressure sensors in a dialysis machine.

OBJECTIVE: Although respiratory problems are common among patients with end-stage renal disease, respiration is not continuously monitored during dialysis. The purpose of the present study is to investigate the feasibility of monitoring respiration using the pressure sensors of the dialysis machine. APPROACH: Respiration induces variations in the blood pressure that propagates to the extracorporeal circuit of the dialysis machine. However, the magnitude of these variations are very small compared to pressure variations induced by the dialysis machine. We propose a new method, which involves adaptive template subtraction and peak conditioned spectral averaging, to estimate respiration rate from the pressure sensor signals. Using this method, an estimate of the respiration rate is obtained every 5th second provided that the signal quality is sufficient. The method is evaluated for continuous monitoring of respiration rate in nine dialysis treatment sessions. MAIN RESULTS: The median absolute deviation between the estimated respiration rate from the pressure sensor signals and a reference capnography recording was 0.02 Hz (1.3 breaths per min). SIGNIFICANCE: Our results suggest that continuous monitoring of respiration using the pressure sensors of the dialysis machine is feasible. The main advantage with such monitoring is that no additional sensors are required which may cause patient discomfort.

Central venous oxygen saturation and thoracic admittance during dialysis: new approaches to hemodynamic monitoring.

Intradialytic hypotension (IDH) is one of the most important short-term complications to hemodialysis (HD). Inadequate cardiac filling due to a reduction in the central blood volume is believed to be a major etiological factor. The aim of this study was to evaluate whether these pathophysiologic events are reflected in the central venous oxygen saturation (ScO(2)) and thoracic admittance (TA) during dialysis. Twenty ambulatory HD patients, 11 hypotension prone (HP) and 9 hypotension resistant, with central vascular access, were monitored during 3 HD sessions each. ScO(2), TA, finger blood pressure (BP), and relative change in blood volume (DeltaBV) were measured and sampled continuously. The relative TA decrease and DeltaBV were both largest in the HP group (p<0.05 for both), whereas ScO(2) decreased only in HP patients (p<0.001). Baseline TA was lower in the HP group (p<0.01). Changes in ScO(2) and TA correlated much closer than did changes in ScO(2) and DeltaBV (r=0.43 and 0.18, respectively). Our results suggest that an intradialytic decrease in cardiac output, as reflected by a fall in ScO(2), is a common feature to HD patients prone to IDH. In patients using a central vascular access, ScO(2) and TA measurements may be more specific to the pathophysiologic events preceding IDH than DeltaBV-the current standard monitoring method.

Detection of ventricular premature beats based on the pressure signals of a hemodialysis machine.

Monitoring of ventricular premature beats (VPBs), being abundant in hemodialysis patients, can provide information on cardiovascular instability and electrolyte imbalance. In this paper, we describe a method for VPB detection which explores the signals acquired from the arterial and the venous pressure sensors, located in the extracorporeal blood circuit of a hemodialysis machine. The pressure signals are mainly composed of a pump component and a cardiac component. The cardiac component, severely overshadowed by the pump component, is estimated from the pressure signals using an earlier described iterative method. A set of simple features is extracted, and linear discriminant analysis is performed to classify beats as either normal or ventricular premature. Performance is evaluated on signals from nine hemodialysis treatments, using leave-one-out crossvalidation. The simultaneously recorded and annotated photoplethysmographic signal serves as the reference signal, with a total of 149,686 normal beats and 3574 VPBs. The results show that VPBs can be reliably detected, quantified by a Youden's J statistic of 0.9, for average cardiac pulse pressures exceeding 1 mmHg; for lower pressures, the J statistic drops to 0.55. It is concluded that the cardiac pressure signal is suitable for VPB detection, provided that the average cardiac pulse pressure exceeds 1 mmHg.

Extracting a cardiac signal from the extracorporeal pressure sensors of a hemodialysis machine.

Although patients undergoing hemodialysis treatment often suffer from cardiovascular disease, monitoring of cardiac rhythm is not performed on a routine basis. Without requiring any extra sensor, this study proposes a method for extracting a cardiac signal from the built-in extracorporeal venous pressure sensor of the hemodialysis machine. The extraction is challenged by the fact that the cardiac component is much weaker than the pressure component caused by the peristaltic blood pump. To further complicate the extraction problem, the cardiac component is difficult to separate when the pump and heart rates coincide. The proposed method estimates a cardiac signal by subtracting an iteratively refined blood pump model signal from the signal measured at the extracorporeal venous pressure sensor. The method was developed based on simulated pressure signals, and evaluated on clinical pressure signals acquired during hemodialysis treatment. The heart rate estimated from the clinical pressure signal was compared to that derived from a photoplethysmographic reference signal, resulting in a difference of 0.07 ± 0.84 beats/min. The accuracy of the heartbeat occurrence times was studied for different strengths of the cardiac component, using both clinical and simulated signals. The results suggest that the accuracy is sufficient for analysis of heart rate and certain arrhythmias.

Prediction of intradialytic hypotension using photoplethysmography.

Intradialytic hypotension is the most common acute complication during conventional hemodialysis treatment. Prediction of such events is highly desirable in clinical routine for prevention. This paper presents a novel prediction method of acute symptomatic hypotension in which the photoplethysmographic signal is analyzed with respect to changes in amplitude, reflecting vasoconstriction, and cardiac output. The method is based on a statistical model in which the noise is assumed to have Laplacian amplitude distribution. The performance is evaluated on 11 hypotension-prone patients who underwent hemodialysis treatment, resulting in seven events with acute symptomatic hypotension and 17 without. The photoplethysmographic signal was continuously acquired during treatment as was information on blood pressure and oxygen saturation. Using leave-one-out cross validation, the proposed method predicted six out of seven hypotensive events, while producing 1 false prediction out of 17 possible. The performance was achieved when the prediction threshold was chosen to be in the range 57%-65% of the photoplethysmographic envelope at treatment onset.

Hemodialysis blood access flow rates can be estimated accurately from on-line dialysate urea measurements and the knowledge of effective dialyzer urea clearance.

Measurement of blood flow rate (Qa) is used to monitor arteriovenous fistulas and grafts that are used for hemodialysis blood access. Most Qa measurements use indicator dilution techniques to measure the recirculation that is induced by the reversal of hemodialysis blood lines. R plus the dialysis circuit flow (Qb) allows the calculation of Qa. The principle of needle reversal also can be used with a dialysate urea monitor (e.g., DQM 200 [Gambro]) without injection of diluent; the effect of the reversal on urea concentration is observed. Access blood water flow rate (Qaw) in relation to the effective clearance (K) is found from the urea concentrations in the dialysate with needles in the normal (Cn) and reverse (Cr) positions: K/Qaw = (Cn - Cr)/Cr. Qa is calculated by adjusting Qaw for hematocrit and protein. For testing of this theoretical relationship, 20 patients who were dialyzed on Integra (Hospal) and Centrysystem 3 (Cobe) machines that were fitted with DQM 200 were studied. During each treatment, lines were reversed and Qa was measured by ultrasound velocity dilution (Transonic HD01 monitor); at the same time, Cn and Cr were measured by DQM 200 and K was calculated. K1 was determined from a predialysis blood urea concentration (Cb), initial dialysate urea concentration (Cd), dialysate flow rate (Qd), and the relationship K x Cb = Qd x Cd (K1). K was determined separately from a conductivity step method using Diascan (Hospal) attached to Integra machines only (K2). With the use of K1, 127 comparisons were made; a correlation existed (r = 0.916), although Bland-Altman analysis showed that the dialysate urea method gave a mean value 5.3% +/- 15.3 (+/-SD) higher than that of Transonic (P < 0.001). With the use of K2, there also was a correlation of (r = 0.944; n = 63), and Bland-Altman testing showed an NS difference of +3.5% between the dialysate urea and Transonic methods. Qa can be estimated from on-line dialysate urea measurements that are taken before and after line reversal together with knowledge of K.