ABSTRACT
This chapter focuses on the two major clinical applications of pattern recognition in medicine, namely, the automation of the analysis of the electrocardiogram and the automation of the analysis of images of the human white blood cell. Computerized taxonomy as related to medical data is, of course, pattern classification rather than pattern recognition. With the advent of general purpose electronic computers in the 20th century, a revolution has taken place in the methodology applied to medical data classification. Now that medical data is being systematically catalogued and stored in such a manner that it is retrievable by computer, there is a great temptation to pursue the possibility of automating medical data analysis for the purpose of automating medical diagnoses. This may be approached in two ways: automatic generation of the logical treatment given the disease state as an input or generating the likely disease state from an input of the patient’s symptoms.
