Document Detail

Prediction of aminoglycoside response against methicillin-resistant Staphylococcus aureus infection in burn patients by artificial neural network modeling.
MedLine Citation:
PMID:  18083323     Owner:  NLM     Status:  MEDLINE    
OBJECTIVE: To predict the response of aminoglycoside antibiotics (arbekacin: ABK) against methicillin-resistant Staphylococcus aureus (MRSA) infection in burn patients after considering the severity of the burn injury by using artificial neural network (ANN). Predictive performance was compared with logistic regression modeling. METHODOLOGY: The physiologic data and some indicators of the severity of the burn injury were collected from 25 burn patients who received ABK against MRSA infection. A three-layered ANN architecture with six neurons in the hidden layer was used to predict the ABK response. The response was monitored using three clinical criteria: number of bacteria, white blood cell count, and C-reactive protein level. Robustness of models was investigated by the leave-one-out cross-validation. RESULTS: The peak plasma level, serum creatinine level, duration of ABK administration, and serum blood sugar level were selected as the linear input parameters to predict the ABK response. The area of the burn after skin grafting was the best parameter for assessing the severity of the burn injury in patients to predict the ABK response in the ANN model. The ANN model with the severity of the burn injury was superior to the logistic regression model in terms of predicting the performance of the ABK response. CONCLUSION: Based on the patients' physiologic data, ANN modeling would be useful for the prediction of the ABK response in burn patients with MRSA infection. Severity of the burn injury was a parameter that was necessary for better prediction.
Shigeo Yamamura; Keiko Kawada; Rieko Takehira; Kenji Nishizawa; Shirou Katayama; Masaaki Hirano; Yasunori Momose
Related Documents :
18969153 - Classification of venezuelan spirituous beverages by means of discriminant analysis and...
15066233 - Artificial neural networks for predictive modeling in prostate cancer.
22254573 - Tissue-based optimization of a sino-atrial node disc model.
Publication Detail:
Type:  Comparative Study; Journal Article     Date:  2007-12-03
Journal Detail:
Title:  Biomedicine & pharmacotherapy = Biomédecine & pharmacothérapie     Volume:  62     ISSN:  0753-3322     ISO Abbreviation:  Biomed. Pharmacother.     Publication Date:  2008 Jan 
Date Detail:
Created Date:  2008-01-15     Completed Date:  2008-04-22     Revised Date:  -    
Medline Journal Info:
Nlm Unique ID:  8213295     Medline TA:  Biomed Pharmacother     Country:  France    
Other Details:
Languages:  eng     Pagination:  53-8     Citation Subset:  IM    
School of Pharmaceutical Sciences, Toho University, Miyama 2-2-1, Funabashi, Chiba, Japan.
Export Citation:
APA/MLA Format     Download EndNote     Download BibTex
MeSH Terms
Aged, 80 and over
Aminoglycosides / administration & dosage,  pharmacokinetics,  therapeutic use*
Anti-Bacterial Agents / administration & dosage,  pharmacokinetics,  therapeutic use*
Blood Glucose
Burns / complications*,  microbiology
Creatinine / blood
Dibekacin / administration & dosage,  analogs & derivatives*,  pharmacokinetics,  therapeutic use
Logistic Models
Methicillin Resistance
Middle Aged
Neural Networks (Computer)*
Retrospective Studies
Severity of Illness Index
Skin Transplantation
Staphylococcal Infections / drug therapy*,  etiology
Staphylococcus aureus / drug effects
Treatment Outcome
Reg. No./Substance:
0/Aminoglycosides; 0/Anti-Bacterial Agents; 0/Blood Glucose; 34493-98-6/Dibekacin; 51025-85-5/habekacin; 60-27-5/Creatinine

From MEDLINE®/PubMed®, a database of the U.S. National Library of Medicine

Previous Document:  Motivational enhancement therapy to improve treatment utilization and outcome in pregnant substance ...
Next Document:  Paracoccidioides brasiliensis conidia recognize fibronectin and fibrinogen which subsequently partic...