Expert systems for the interpretation of serum proteins

The ready availability of inexpensive desk-top computers with enormous disk storage has made the practicality of computer assisted medical interpretive software a reality. There seems little question that these programs could be of enormous help to physicians. However, there are daunting problems to their creation, including the lack of standards for clinical diagnostic precision or accuracy and paucity of helpful literature. As a result, the final products may be quite different. Little effort has been devoted in the laboratory to produce programs which could have great benefit in bridging the gap between laboratorians and clinicians. In a few circumscribed areas where the interpretation of laboratory measurements have been well studied in relation to patient demographics and to the final outcome, the impact has been enormous. The prime example is prenatal diagnosis of neural tube defects, and certain chromosomal and developmental abnormalities. Viewed as an obstacle by most people able and willing to attempt to create such programs is the omnipresence of necessary regulation. A brief overview of the general structure of a program to assist with the interpretation of serum proteins is given as a model in the perspective of current knowledge and state of the relevant literature.