A new hybrid case-based architecture for medical diagnosis

This paper proposes a new hybrid case-based architecture that facilitates multiple diseases diagnosis and can learn new adaptation knowledge. The architecture hybridizes case-based reasoning (CBR), neural network, fuzzy theory, induction, utility theory, and knowledge-based planning technology to facilitate medical diagnosis. The basic mechanism is CBR that accumulates experiences as cases in the case library and diagnoses new patients by adapting the old cases that have successfully diagnosed previous similar diseases. A distributed fuzzy neural network performs approximate matching to tolerate potential noise in case retrieval. The induction technology along with utility theory is used in case selection, adaptation and learning, which helps a lot in selecting valuable features for the target case from existent ones and in pruning unnecessary search space. Knowledge-based planning is used as a general mechanism for case adaptation. It creates an adaptation plan from an adaptation tree that covers all the relevant problem features, satisfies all the relevant constraints, and contains all cases whose expected utilities are over a threshold. Execution of the case adaptation plan can diagnose multiple-diseases. Moreover, the adaptation tree can support case reuse and learning of various knowledge, including relationships between disease types and features, case-specific verification knowledge, and differential diagnosis rules, to enhance subsequent case-based reasoning. Hybridizing these techniques in the CBR paradigm can effectively produce a high quality diagnosis for a given medical consultation.