Abciximab pharmacodynamic model with neural networks used to integrate sources of patient variability

Our objective was to develop a computational model for predicting abciximab-induced inhibition of ex vivo platelet aggregation from the administered dose and readily available patient clinical characteristics by use of a neural network approach.

A back-propagation neural network was designed to establish the relationship between abciximab dosing, patient clinical history, and effect (inhibition of 20 micromol/L adenosine diphosphate-induced ex vivo platelet aggregation). The neural network was trained by use of data from 8 (out of 47) patients undergoing coronary angioplasty and 30 healthy individuals. Final neuron connection weights were used to evaluate significant patient covariates. The final neural network was validated via (1) predicting the effects of the validation database (remaining 39 patients) and (2) predicting the individual patient doses to achieve 20% of baseline platelet aggregation.

The trained neural network successfully captured the complex pharmacodynamic profiles of abciximab without specifying a structural model and identified several patient covariates that significantly contribute to establishing the abciximab dose-effect relationship, including stable angina with nitrate treatment, previous myocardial infarction, and smoking. A wide distribution of individual bolus doses of abciximab was predicted, suggesting the potential for dosing individualization while improving the risk of adverse drug events. The mean predicted dose (16.9 mg) was in agreement with the results from a previously published concentration-effect relationship for abciximab (18.9 +/- 2.0 mg).

These findings suggest the usefulness of neural network methods to individualize dosing for drugs with a narrow therapeutic index when real-time measures of drug concentration and effect are unavailable, but future clinical studies are required for prospective validation.