Application of Neural Networks to Population Pharmacokinetic Data Analysis

Persistent Link:
http://hdl.handle.net/10150/105273
Title:
Application of Neural Networks to Population Pharmacokinetic Data Analysis
Author:
Chow, Hsiao-Hui; Tolle, Kristin M.; Roe, Denise J.; Elsberry, Victor; Chen, Hsinchun
Citation:
Application of Neural Networks to Population Pharmacokinetic Data Analysis 1997-07, 86(7):840-845 Journal of Pharmaceutical Sciences
Publisher:
American Chemical Society and American Pharmaceutical Association
Journal:
Journal of Pharmaceutical Sciences
Issue Date:
Jul-1997
Description:
Artificial Intelligence Lab, Department of MIS, University of Arizona
URI:
http://hdl.handle.net/10150/105273
Submitted date:
2004-08-20
Abstract:
This research examined the applicability of using a neural network approach to analyze population pharmacokinetic data. Such data were collected retrospectively from pediatric patients who had received tobramycin for the treatment of bacterial infection. The information collected included patient-related demographic variables (age, weight, gender, and other underlying illness), the individualâ s dosing regimens (dose and dosing interval), time of blood drawn, and the resulting tobramycin concentration. Neural networks were trained with this information to capture the relationships between the plasma tobramycin levels and the following factors: patient-related demographic factors, dosing regimens, and time of blood drawn. The data were also analyzed using a standard population pharmacokinetic modeling program, NONMEM. The observed vs predicted concentration relationships obtained from the neural network approach were similar to those from NONMEM. The residuals of the predictions from neural network analyses showed a positive correlation with that from NONMEM. Average absolute errors were 33.9 and 37.3% for neural networks and 39.9% for NONMEM. Average prediction errors were found to be 2.59 and -5.01% for neural networks and 17.7% for NONMEM. We concluded that neural networks were capable of capturing the relationships between plasma drug levels and patient-related prognostic factors from routinely collected sparse withinpatient pharmacokinetic data. Neural networks can therefore be considered to have potential to become a useful analytical tool for population pharmacokinetic data analysis.
Type:
Journal Article (Paginated)
Language:
en
Keywords:
Data Mining; Medical Libraries
Local subject classification:
National Science Digital Library; NSDL; Artificial Intelligence lab; AI lab; Neural network approach

Full metadata record

DC FieldValue Language
dc.contributor.authorChow, Hsiao-Huien_US
dc.contributor.authorTolle, Kristin M.en_US
dc.contributor.authorRoe, Denise J.en_US
dc.contributor.authorElsberry, Victoren_US
dc.contributor.authorChen, Hsinchunen_US
dc.date.accessioned2004-08-20T00:00:01Z-
dc.date.available2010-06-18T23:22:49Z-
dc.date.issued1997-07en_US
dc.date.submitted2004-08-20en_US
dc.identifier.citationApplication of Neural Networks to Population Pharmacokinetic Data Analysis 1997-07, 86(7):840-845 Journal of Pharmaceutical Sciencesen_US
dc.identifier.urihttp://hdl.handle.net/10150/105273-
dc.descriptionArtificial Intelligence Lab, Department of MIS, University of Arizonaen_US
dc.description.abstractThis research examined the applicability of using a neural network approach to analyze population pharmacokinetic data. Such data were collected retrospectively from pediatric patients who had received tobramycin for the treatment of bacterial infection. The information collected included patient-related demographic variables (age, weight, gender, and other underlying illness), the individualâ s dosing regimens (dose and dosing interval), time of blood drawn, and the resulting tobramycin concentration. Neural networks were trained with this information to capture the relationships between the plasma tobramycin levels and the following factors: patient-related demographic factors, dosing regimens, and time of blood drawn. The data were also analyzed using a standard population pharmacokinetic modeling program, NONMEM. The observed vs predicted concentration relationships obtained from the neural network approach were similar to those from NONMEM. The residuals of the predictions from neural network analyses showed a positive correlation with that from NONMEM. Average absolute errors were 33.9 and 37.3% for neural networks and 39.9% for NONMEM. Average prediction errors were found to be 2.59 and -5.01% for neural networks and 17.7% for NONMEM. We concluded that neural networks were capable of capturing the relationships between plasma drug levels and patient-related prognostic factors from routinely collected sparse withinpatient pharmacokinetic data. Neural networks can therefore be considered to have potential to become a useful analytical tool for population pharmacokinetic data analysis.en_US
dc.format.mimetypeapplication/pdfen_US
dc.language.isoenen_US
dc.publisherAmerican Chemical Society and American Pharmaceutical Associationen_US
dc.subjectData Miningen_US
dc.subjectMedical Librariesen_US
dc.subject.otherNational Science Digital Libraryen_US
dc.subject.otherNSDLen_US
dc.subject.otherArtificial Intelligence laben_US
dc.subject.otherAI laben_US
dc.subject.otherNeural network approachen_US
dc.titleApplication of Neural Networks to Population Pharmacokinetic Data Analysisen_US
dc.typeJournal Article (Paginated)en_US
dc.identifier.journalJournal of Pharmaceutical Sciencesen_US
All Items in UA Campus Repository are protected by copyright, with all rights reserved, unless otherwise indicated.