Rodolfo Valtuille

Using artificial intelligence to predict the equilibrated postdialysis blood urea concentration.

Total dialysis dose (Kt/V) is considered to be a major determinant of morbidity and mortality in hemodialyzed patients. The continuous growth of the blood urea concentration over the 30- to 60-min period following dialysis, a phenomenon known as urea rebound, is a critical factor in determining the true dose of hemodialysis. The misestimation of the equilibrated (true) postdialysis blood urea or equilibrated Kt/V results in an inadequate hemodialysis prescription, with predictably poor clinical outcomes for the patients. The estimation of the equilibrated postdialysis blood urea (eqU) is therefore crucial in order to estimate the equilibrated (true) Kt/V. In this work we propose a supervised neural network to predict the eqU at 60 min after the end of hemodialysis. The use of this model is new in this field and is shown to be better than the currently accepted methods (Smye for eqU and Daugirdas for eqKt/V). With this approach we achieve a mean difference error of 0.22 ± 7.71 mg/ml (mean % error: 1.88 ± 13.46) on the eqU prediction and a mean difference error for eqKt/V of –0.01 ± 0.15 (mean % error: –0.95 ± 14.73). The equilibrated Kt/V estimated with the eqU calculated using the Smye formula is not appropriate because it showed a great dispersion. The Daugirdas double-pool Kt/V estimation formula appeared to be accurate and in agreement with the results of the HEMO study.

Vascular Accesses for Haemodialysis in the Upper Arm Cause Greater Reduction in the Carotid-Brachial Stiffness than Those in the Forearm: Study of Gender Differences

Purpose. To evaluate in chronically haemodialysed patients (CHPs), if: (1) the vascular access (VA) position (upper arm or forearm) is associated with differential changes in upper limb arterial stiffness; (2) differences in arterial stiffness exist between genders associated with the VA; (3) the vascular substitute (VS) of choice, in biomechanical terms, depends on the previous VA location and CHP gender. Methods. 38 CHPs (18 males; VA in upper arm: 18) were studied. Left and right carotid-brachial pulse wave velocity (PWVc-b) was measured. In in vitro studies, PWV was obtained in ePTFE prostheses and in several arterial and venous homografts obtained from donors. The biomechanical mismatch (BM) between CHP native vessel (NV) and VS was calculated. Results/Conclusions. PWVc-b in upper limbs with VA was lower than in the intact contralateral limbs (P < 0.05), and differences were higher (P < 0.05) when the VA was performed in the upper arm. Differences between PWVc-b in upper limbs with VA (in the upper arm) with respect to intact upper limbs were higher (P < 0.05) in males. Independently of the region in which the VA was performed, the homograft that ensured the minimal BM was the brachial artery. The BM was highly dependent on gender and the location in the upper limb in which the VA was performed.

Dialysate-side urea kinetics. Neural network predicts dialysis dose during dialysis

Determination of the adequacy of dialysis is a routine but crucial procedure in patient evaluation. The total dialysis dose, expressed as Kt/V, has been widely recognised to be a major determinant of morbidity and mortality in haemodialysed patients. Many different factors influence the correct determination of Kt/V, such as urea sequestration in different body compartments, access and cardiopulmonary recirculation. These factors are responsible for urea rebound after the end of the haemodialysis session, causing poor Kt/V estimation. There are many techniques that try to overcome this problem. Some of them use analysis of blood-side urea samples, and in recent years, on-line urea monitors have become available to calculate haemodialysis dose from dialysate-side urea kinetics. All these methods require waiting until the end of the session to calculate the Kt/V dose. In this work, a neural network (NN) method is presented for early prediction of the Kt/V dose. Two different portions of the dialysate urea concentration-time profile (provided by an on-line urea minitor) were analysed: the entire curve A and the first half B, using an NN to predict the Kt/V and compare this with that provided by the monitor. The NN was able to predict Kt/V is the middle of the 4h session (B data) without a significant increase in the percentage error (B data: 6.69%±2.46%; A data: 5.58%±8.77%, mean±SD) compared with the monitor Kt/V.

Hydration Status Is Associated with Aortic Stiffness, but Not with Peripheral Arterial Stiffness, in Chronically Hemodialysed Patients

Background. Adequate fluid management could be essential to minimize high arterial stiffness observed in chronically hemodialyzed patients (CHP). Aim. To determine the association between body fluid status and central and peripheral arterial stiffness levels. Methods. Arterial stiffness was assessed in 65 CHP by measuring the pulse wave velocity (PWV) in a central arterial pathway (carotid-femoral) and in a peripheral pathway (carotid-brachial). A blood pressure-independent regional arterial stiffness index was calculated using PWV. Volume status was assessed by whole-body multiple-frequency bioimpedance. Patients were first observed as an entire group and then divided into three different fluid status-related groups: normal, overhydration, and dehydration groups. Results. Only carotid-femoral stiffness was positively associated (P < 0.05) with the hydration status evaluated through extracellular/intracellular fluid, extracellular/Total Body Fluid, and absolute and relative overhydration. Conclusion. Volume status and overload are associated with central, but not peripheral, arterial stiffness levels with independence of the blood pressure level, in CHP.

Hemodialysis Decreases the Etiologically-Related Early Vascular Aging Observed in End-Stage Renal Disease: A 5-Year Follow-Up Study

Aims: To analyze the early vascular aging (EVA) in end-stage renal disease (ESRD) patients, attempting to determine a potential association between EVA and the etiology of ESRD, and to investigate the association of hemodialysis and EVA in ESRD patients during a 5-year follow-up period. Methods: Carotid-femoral pulse wave velocity (cfPWV) was obtained in 151 chronically hemodialyzed patients (CHP) and 283 control subjects, and in 25 CHP, who were followed-up after a 5-year lapse. Results: cfPWV increased in ESRD patients compared to control subjects. The cfPWV-age relationship was found to have a steeper increase in ESRD patients. The highest cfPWV and EVA values were observed in patients with diabetic nephropathy. Regression analysis demonstrated a significant reduction of the EVA in HD patients on a 5-year follow-up. Conclusion: Patients in ESRD showed higher levels of EVA. cfPWV and EVA differed in ESRD patients depending on their renal failure etiology. CHP showed an EVA reduction after a 5-year follow-up period.

Artificial Neural Networks Applications in Dialysis

Artificial Neural Networks are mathematical models resembling the brain behavior. They have the ability to “learn” from the “environment” and produce responses as a consequence of this learning process. They were broadly used in medicine both as a classification model as well as a prediction tool. In hemodialysis they were used for molecular modeling in the estimation of equilibrated urea concentration, as a monitoring strategy for online treatment analysis and also for bed side models for hemodialysis adequacy evaluation. In this chapter the basic concepts of artificial neural models are introduced and a complete application in equilibrated urea estimation in hemodialized patients is presented.

Molecular Kinetics Modeling in Hemodialysis: On-Line Molecular Monitoring and Spectral Analysis

The knowledge of the underlying molecular kinetics is a key point for the development of a dialysis treatment as well as for patient monitoring. In this work, we propose a kinetic inference method that is general enough to be used on different molecular types measured in the spent dialysate. It estimates the number and significance of the compartments involved in the overall process of dialysis by means of a spectral deconvolution technique, characterizing therefore the kinetic behavior of the patient. The method was applied to 52 patients to reveal the underlying kinetics from dialysate time-concentration profiles of urea, which has a well-known molecular kinetic. Three types of behaviors were found: one-compartmental (exponential decay Tau = 180 ± 61.64 minutes), bicompartmental (Tau1 = 24.96 ± 19.33 minutes, Tau2 = 222.32 ± 76.59 minutes), and tricompartmental (Tau1 = 23.03 ± 14.21 minutes; Tau2 = 85.75 ± 27.48 minutes; and Tau3 = 337 ± 85.52 minutes). In patients with bicompartmental kinetics, the Tau2 was related to the level of dialysis dose. The study concluded that spectral deconvolution technique can be considered a powerful tool for molecular kinetics inference that could be integrated in on-line molecular analysis devices. Furthermore, the method could be used in the analysis of poorly understood molecules as well as in new hemodialysis target biomarkers.

Nutritional Markers and Body Composition in Hemodialysis Patients

The aims of this study were to analyse body composition, to detect the presence of undernutrition, and to establish a relationship between undernutrition and the biological markers routinely used as indicators of nutritional status in hemodialysis (HD) patients (pts). We used a body composition monitor (BCM) that expresses body weight in terms of lean tissue mass (LTM) and fat tissue mass (FTM) independent of hydration status. From nine HD units, 934 pts were included. Undernutrition was defined as having a lean tissue index (LTI = LTM/height2) below the 10th percentile of a reference population. Biochemical markers and parameters delivered by BCM were used to compare low LTI and normal LTI groups. Undernutrition prevalence was 58.8% of the population studied. Low LTI pts were older, were significantly more frequently overhydrated, and had been on HD for a longer period of time than the normal LTI group. FTI (FTI = FTM/ height2) was significantly higher in low LTI pts and increased according to BMI. LTI was not influenced by different BMI levels. Albumin and C-reactive protein correlated inversely (r = −0.28). However neither of them was statistically different when considering undernourished and normal LTI pts. Our BCM study was able to show a high prevalence of undernutrition, as expressed by low LTI. In our study, BMI and other common markers, such as albumin, failed to predict malnutrition as determined by BCM.

Hemodialysis decreases carotid-brachial and carotid-femoral pulse wave velocities: A 5-year follow-up study

Aortic stiffness is a prognostic parameter associated with patient mortality. Vascular access creation has been shown to have effects on arterial stiffness both in the aorta and in the upper limb arteries in chronically hemodialyzed patients (CHPs). However, no longitudinal studies have been conducted in order to characterize the evolution of arterial stiffness in CHPs. The aims of this work were (a) to measure baseline pulse wave velocity (PWV) in the carotid‐femoral and in right and left carotid‐brachial pathways in a cohort of CHP and (b) to conduct a 5‐year prospective study on the same cohort to determine possible time‐related differences. Pulse wave velocity was measured both in the carotid‐femoral and in the carotid‐brachial pathways, and clinical and biochemical parameters were collected in 25 CHPs, which were followed up after a 5‐year lapse. Right and left carotid‐brachial pathway PWV values showed significant decreases after the 5‐year follow‐up, independently of the presence of the vascular access (P < 0.001). Additionally, baseline carotid‐brachial PWV was significantly higher (P < 0.001) than values measured 5 years later for upper limbs with vascular access (11.97 ± 2.97 m/sec vs. 6.76 ± 1.48 m/sec, respectively) and without vascular access (12.25 ± 2.38 m/sec vs. 7.18 ± 1.88 m/sec, respectively). Similarly, PWV values in the carotid‐femoral pathway decreased significantly (P < 0.001) over the same period (13.27 ± 2.96 m/sec vs. 9.75 ± 2.99 m/sec, respectively). The 5‐year follow‐up of PWV showed significant decreases in both carotid‐brachial and carotid‐femoral pathways. The general changes in arterial stiffness could be related to the vascular access creation, hemodialysis therapy, and to the improvement of arterial pressure management.

Central-To-Peripheral Arterial Stiffness Gradient in Hemodialyzed Patients Depends on the Location of the Upper-limb Vascular Access

BACKGROUND Pulse wave velocity ratio (PWV-ratio), a measure of central-to-peripheral arterial stiffness gradient, is calculated as a quotient between carotid-femoral and carotid-radial PWV (cf-PWV/cr-PWV). This new index has been reported to be significantly associated with increased mortality in hemodialyzed patients. Since several reports showed differences in arterial stiffness regarding the pathway where the vascular access (VA) is, the purpose of this research was: a) to compare arterial stiffness values obtained in the left and right sides of the body in hemodialyzed and non-hemodialyzed patients, and b) to analyze PWV-ratio values obtained on the side of the body where the VA was placed and compare them to its contralateral intact side. Since it is difficult to adequately measure cr-PWV in patients with a VA in the forearm, we measured the carotid- brachial PWV (cb-PWV) and used it to calculate PWV-ratio (cf-PWV/cb-PWV). METHODS A Pearsons correlation and Bland & Altman analysis were performed in hemodialyzed (n=135) and non-hemodialyzed (n=77) patients, to quantify the equivalence between arterial stiffness parameters (cf-PWV, cb-PWV, PWV-ratio) obtained on each side of the body with respect to its contralateral side. RESULTS We conclude that PWV-ratio values measured on the side where the VA is placed were significantly higher than those obtained in its contralateral side, in hemodialyzed patients included in this research. Moreover, cf-PWV, cb-PWV and PWV-ratio values obtained on one side of the body were always highly correlated with its contralateral side. CONCLUSION According to this research, any research involving PWV-ratio should always consider the observed territory.