Analysis of clinical data using neural nets

Clinical studies investigate the interdependence of dosing regimen, efficacy, and side effects. These relationships often involve complex dynamical functions. The study of phenomena intermediate between dosing and efficacy, e.g., pharmacokinetics (PK), helps one identify and understand these interdependences. However, efficacy still tends to be a complicated function of PK parameters, and indeed these parameters are becoming more complex as a function of dosing regimen, viz., studies involving immunosuppressants, biotechnology drugs, sophisticated delivery systems, and dosing strategies. Stationary and time-dependent neural nets can help one identify and model such unknown complex dynamical functions with few assumptions and limited data (1-7). Neural nets can relate dosing directly to efficacy, dosing to PK, PK to efficacy, or any component in the complex associations among treatments, pharmacodynamics, efficacy, and side effects. Neural nets can also assist one in the design of clinical trials involving complex and sophisticated procedures, e.g., randomized controlled clinical trials.