Conclusions

Summary

In developing the prototype Roundsman system described in the previous chapters, we are exploring the proposition that the clinical literature can, and should, play a central role in computer-based decision support. Specifically, as discussed in the introduction to this book, the motivation underlying this research includes the following propositions:

• Reasoning from experimental evidence contained in the clinical literature is central to the decisions a physician makes in many areas of patient care. Medical artificial intelligence, heavily oriented toward causal modeling, has not adequately recognized this facet of medical reasoning.

• A computational model, based upon a declarative representation for published reports of clinical studies, can drive a computer program that selectively tailors knowledge of the clinical literature as it applies to a particular case.

• The development of such a computational model is an important first step toward filling a void in computer-based decision support systems. Furthermore, the model may help us better understand the general principles of reasoning from experimental evidence both in medicine and in other appropriate domains. This research therefore provides a base for further explicit analysis of these principles.

The Roundsman project delineates an explicit, computational model of medical decision-making which uses a structured representation of the clinical literature, together with a distance metric, to dynamically assess the “distance” between studies and a particular patient and treatment plan. Roundsman’s knowledge representation derives from informal protocol analysis of experienced clinicians. The prose output generated by the model’s computer implementation approximates target “scripts” of clinical reasoning developed in collaboration with an expert oncologist.