An Autoencoder for Clinical and Regulatory Data Processing

Abstract

A computer-driven terminology processing system, referred to as an “autoencoder,” is being developed at Merck Research Laboratories to aid in the management of clinical and regulatory data. The components of the autoencoder are: a large dictionary of clinical and therapy terms, a learning database to provide feedback, a thesaurus or word-substitution file, a modified Soundex algorithm, and an outcome report with a level of confidence indicator. The autoencoder operates in conjunction with the dictionary system to conduct comparisons of selected terms taken from input documents against dictionary terms. Algorithms evaluate these comparisons and assist users of the system in selecting dictionary terms to encode input documents. The use of the autoencoder to process clinical trial data and adverse experience reports is described and experience in autoencoding is discussed.