Application of Counter-propagation Artificial Neural Networks in Prediction of Topiramate Concentration in Patients with Epilepsy
2015
Authors
Jovanović, MarijaSokić, Dragoslav
Grabnar, Iztok
Vovk, Tomaz
Prostran, Milica
Erić, Slavica
Kuzmanovski, Igor
Vučićević, Katarina
Miljković, Branislava
Article (Published version)
Metadata
Show full item recordAbstract
Purpose: The application of artificial neural networks in the pharmaceutical sciences is broad, ranging from drug discovery to clinical pharmacy. In this study, we explored the applicability of counter-propagation artificial neural networks (CPANNs), combined with genetic algorithm (GA) for prediction of topiramate (TPM) serum levels based on identified factors important for its prediction. Methods: The study was performed on 118 TPM measurements obtained from 78 adult epileptic patients. Patients were on stable TPM dosing regimen for at least 7 days; therefore, steady-state was assumed. TPM serum concentration was determined by high performance liquid chromatography with fluorescence detection. The influence of demographic, biochemical parameters and therapy characteristics of the patients on TPM levels were tested. Data analysis was performed by CPANNs. GA was used for optimal CPANN parameters, variable selection and adjustment of relative importance. Results: Data for training inclu...ded 88 measured TPM concentrations, while remaining were used for validation. Among all factors tested, TPM dose, renal function (eGFR) and carbamazepine dose significantly influenced TPM level and their relative importance were 0.7500, 0.2813, 0.0625, respectively. Relative error and root mean squared relative error (%) and their corresponding 95% confidence intervals for training set were 2.14 [(-2.41) - 6.70] and 21.5 [18.5 - 24.1]; and for test set were 6.21 [(-21.2) - 8.77] and 39.9 [31.7 - 46.7], respectively. Conclusions: Statistical parameters showed acceptable predictive performance. Results indicate the feasibility of CPANNs combined with GA to predict TPM concentrations and to adjust relative importance of identified variability factors in population of adult epileptic patients.
Source:
Journal of Pharmacy and Pharmaceutical Sciences, 2015, 18, 5, 856-862Publisher:
- Canadian Soc Pharmaceutical Sciences, Edmonton
Funding / projects:
- Basic and Clinical Pharmacological research of mechanisms of action and drug interactions in nervous and cardiovascular system (RS-MESTD-Basic Research (BR or ON)-175023)
DOI: 10.18433/J33031
ISSN: 1482-1826
PubMed: 26670371
WoS: 000369002800009
Scopus: 2-s2.0-84949767013
Collections
Institution/Community
PharmacyTY - JOUR AU - Jovanović, Marija AU - Sokić, Dragoslav AU - Grabnar, Iztok AU - Vovk, Tomaz AU - Prostran, Milica AU - Erić, Slavica AU - Kuzmanovski, Igor AU - Vučićević, Katarina AU - Miljković, Branislava PY - 2015 UR - https://farfar.pharmacy.bg.ac.rs/handle/123456789/2366 AB - Purpose: The application of artificial neural networks in the pharmaceutical sciences is broad, ranging from drug discovery to clinical pharmacy. In this study, we explored the applicability of counter-propagation artificial neural networks (CPANNs), combined with genetic algorithm (GA) for prediction of topiramate (TPM) serum levels based on identified factors important for its prediction. Methods: The study was performed on 118 TPM measurements obtained from 78 adult epileptic patients. Patients were on stable TPM dosing regimen for at least 7 days; therefore, steady-state was assumed. TPM serum concentration was determined by high performance liquid chromatography with fluorescence detection. The influence of demographic, biochemical parameters and therapy characteristics of the patients on TPM levels were tested. Data analysis was performed by CPANNs. GA was used for optimal CPANN parameters, variable selection and adjustment of relative importance. Results: Data for training included 88 measured TPM concentrations, while remaining were used for validation. Among all factors tested, TPM dose, renal function (eGFR) and carbamazepine dose significantly influenced TPM level and their relative importance were 0.7500, 0.2813, 0.0625, respectively. Relative error and root mean squared relative error (%) and their corresponding 95% confidence intervals for training set were 2.14 [(-2.41) - 6.70] and 21.5 [18.5 - 24.1]; and for test set were 6.21 [(-21.2) - 8.77] and 39.9 [31.7 - 46.7], respectively. Conclusions: Statistical parameters showed acceptable predictive performance. Results indicate the feasibility of CPANNs combined with GA to predict TPM concentrations and to adjust relative importance of identified variability factors in population of adult epileptic patients. PB - Canadian Soc Pharmaceutical Sciences, Edmonton T2 - Journal of Pharmacy and Pharmaceutical Sciences T1 - Application of Counter-propagation Artificial Neural Networks in Prediction of Topiramate Concentration in Patients with Epilepsy VL - 18 IS - 5 SP - 856 EP - 862 DO - 10.18433/J33031 ER -
@article{ author = "Jovanović, Marija and Sokić, Dragoslav and Grabnar, Iztok and Vovk, Tomaz and Prostran, Milica and Erić, Slavica and Kuzmanovski, Igor and Vučićević, Katarina and Miljković, Branislava", year = "2015", abstract = "Purpose: The application of artificial neural networks in the pharmaceutical sciences is broad, ranging from drug discovery to clinical pharmacy. In this study, we explored the applicability of counter-propagation artificial neural networks (CPANNs), combined with genetic algorithm (GA) for prediction of topiramate (TPM) serum levels based on identified factors important for its prediction. Methods: The study was performed on 118 TPM measurements obtained from 78 adult epileptic patients. Patients were on stable TPM dosing regimen for at least 7 days; therefore, steady-state was assumed. TPM serum concentration was determined by high performance liquid chromatography with fluorescence detection. The influence of demographic, biochemical parameters and therapy characteristics of the patients on TPM levels were tested. Data analysis was performed by CPANNs. GA was used for optimal CPANN parameters, variable selection and adjustment of relative importance. Results: Data for training included 88 measured TPM concentrations, while remaining were used for validation. Among all factors tested, TPM dose, renal function (eGFR) and carbamazepine dose significantly influenced TPM level and their relative importance were 0.7500, 0.2813, 0.0625, respectively. Relative error and root mean squared relative error (%) and their corresponding 95% confidence intervals for training set were 2.14 [(-2.41) - 6.70] and 21.5 [18.5 - 24.1]; and for test set were 6.21 [(-21.2) - 8.77] and 39.9 [31.7 - 46.7], respectively. Conclusions: Statistical parameters showed acceptable predictive performance. Results indicate the feasibility of CPANNs combined with GA to predict TPM concentrations and to adjust relative importance of identified variability factors in population of adult epileptic patients.", publisher = "Canadian Soc Pharmaceutical Sciences, Edmonton", journal = "Journal of Pharmacy and Pharmaceutical Sciences", title = "Application of Counter-propagation Artificial Neural Networks in Prediction of Topiramate Concentration in Patients with Epilepsy", volume = "18", number = "5", pages = "856-862", doi = "10.18433/J33031" }
Jovanović, M., Sokić, D., Grabnar, I., Vovk, T., Prostran, M., Erić, S., Kuzmanovski, I., Vučićević, K.,& Miljković, B.. (2015). Application of Counter-propagation Artificial Neural Networks in Prediction of Topiramate Concentration in Patients with Epilepsy. in Journal of Pharmacy and Pharmaceutical Sciences Canadian Soc Pharmaceutical Sciences, Edmonton., 18(5), 856-862. https://doi.org/10.18433/J33031
Jovanović M, Sokić D, Grabnar I, Vovk T, Prostran M, Erić S, Kuzmanovski I, Vučićević K, Miljković B. Application of Counter-propagation Artificial Neural Networks in Prediction of Topiramate Concentration in Patients with Epilepsy. in Journal of Pharmacy and Pharmaceutical Sciences. 2015;18(5):856-862. doi:10.18433/J33031 .
Jovanović, Marija, Sokić, Dragoslav, Grabnar, Iztok, Vovk, Tomaz, Prostran, Milica, Erić, Slavica, Kuzmanovski, Igor, Vučićević, Katarina, Miljković, Branislava, "Application of Counter-propagation Artificial Neural Networks in Prediction of Topiramate Concentration in Patients with Epilepsy" in Journal of Pharmacy and Pharmaceutical Sciences, 18, no. 5 (2015):856-862, https://doi.org/10.18433/J33031 . .