Medical applications of adaptive learning systems and diagnostic kits

摘要

A neural network system comprises: a processor, a memory device and an input layer comprising one or more input nodes configured to receive a first set of gene expression data categorized into one or more conditions from groups of subjects having the one or more conditions and to store the data in the memory device. The input layer further comprises input nodes configured to receive a second set of gene expression data from a biological sample from a patient. The neural network system further comprises: a rule base layer comprising one or more rule nodes, an adaptive component and an output layer comprising one or more output nodes. The memory device has an evolving connectionist systems (ECOS) program embodied on a computer-readable medium containing a set of instructions for execution by the processor. The adaptive component is configured to extract one or more first rules from the rule base layer. The one or more first rules represent relationships between the first set of gene expression data and the one or more conditions. Each of the rule nodes in the rule base layer has a minimum activation threshold; and each of the rule nodes is adapted to become activated when the data satisfies the minimum activation threshold of the rule node. The one or more first rules is a criterion for diagnosis or prognosis of a disease condition in a patient; and the program contains instructions to compare the one or more first rules and a second rule obtained from the second set of gene expression data from the patient to determine whether the patient has a disease condition. The ECOS program is an evolving fuzzy neural network (EFuNN) program.