Artificial neural network modeling for drug dialyzability prediction.

PURPOSE: The purpose of this study was to develop an artificial neural network (ANN) model to predict drug removal during dialysis based on drug properties and dialysis conditions. Nine antihypertensive drugs were chosen as model for this study. METHODS: Drugs were dissolved in a physiologic buffer and dialysed in vitro in different dialysis conditions (UFRmin/UFRmax, with/without BSA). Samples were taken at regular intervals and frozen at -20ºC until analysis. Extraction methods were developed for drugs that were dialysed with BSA in the buffer. Drug concentrations were quantified by high performance liquid chromatography (HPLC) or mass spectrometry (LC/MS/MS). Dialysis clearances (CLDs) were calculated using the obtained drug concentrations. An ANOVA with Scheffe's pairwise adjustments was performed on the collected data in order to investigate the impact of drug plasma protein binding and ultrafiltration rate (UFR) on CLD. The software Neurosolutions was used to build ANNs that would be able to predict drug CLD (output). The inputs consisted of dialysis UFR and the herein drug properties: molecular weight (MW), logD and plasma protein binding. RESULTS: Observed CLDs were very high for the majority of the drugs studied. The addition of BSA in the physiologic buffer statistically significantly decreased CLD for carvedilol (p= 0.002) and labetalol (p<0.001), but made no significant difference for atenolol (p= 0.100). In contrast, varying UFR does not significantly affect CLD (p>0.025). Multiple ANNs were built and compared, the best model was a Jordan and Elman network which showed learning stability and good predictive results (MSEtesting = 129). CONCLUSION: In this study, we have developed an ANN-model which is able to predict drug removal during dialysis. Since experimental determination of all existing drug CLDs is not realistic, ANNs represent a promising tool for the prediction of drug CLD using drug properties and dialysis conditions.

Prediction of in vivo atenolol removal by high-permeability hemodialysis based on an in vitro model.

PURPOSE: In order to update our data on drug dialyzability using the high-permeability dialysis membranes, atenolol elimination by an in vitro dialysis model was compared to that observed in six patients during high-permeability hemodialysis (HD), and the predictive value of the model was evaluated. METHODS: Atenolol clearance was evaluated in six patients undergoing chronic HD. They were considered as eligible candidates if they were between 18 and 80 years of age, had a body mass index between 19 and 30 kg/m2, underwent HD and were taking atenolol on a regular basis in oral tablet form for at least 1 month before the study started. Atenolol clearance was also evaluated in three in vitro dialysis sessions with high-permeability polysulfone membrane. Atenolol was dissolved in 6 L of Krebs-Henseleit buffer with bovine serum albumin. Dialysis parameters were set to mirror as much as possible the patients' parameters (flow rate: 300 mL/min, dialyzate flow: 500 mL/min). After sample collection, drug concentrations were measured with high performance liquid chromatography. The comparison between in vivo and in vitro atenolol elimination kinetics was performed by drawing the curve fittings of concentrations vs. time on SigmaPlot 12, and adding a 95% prediction interval to each elimination curve fitting. RESULTS: Mean dialysis clearance of atenolol in vitro and in vivo was 198 ± 4 and 235 ± 53 mL/min, respectively. Atenolol was significantly removed within the study time period in both in vitro and in vivo experiments. By the end of in vitro dialysis, atenolol remaining in the drug reservoir was less than 2% of initial arterial concentration. CONCLUSION: Our study has indicated that atenolol is almost entirely cleared during high-permeability hemodialysis. Furthermore, the in vitro prediction interval of the drug elimination curve fitting could forecast its in vivo elimination especially at the end of dialysis.