Medical diagnosis as pattern recognition in a framework of information compression by multiple alignment, unification and search

TL;DR

This paper introduces a novel AI-based framework for medical diagnosis that uses pattern recognition and information compression, effectively handling uncertainties and enabling probabilistic evaluation of diagnostic hypotheses.

Contribution

It presents a new approach based on the SP theory that simplifies disease representation, manages errors, and integrates learning and AI applications in medicine.

Findings

Effective handling of errors and uncertainties in diagnosis

Probabilistic evaluation of diagnostic hypotheses

Simplified and intuitive disease representation

Abstract

This paper describes a novel approach to medical diagnosis based on the SP theory of computing and cognition. The main attractions of this approach are: a format for representing diseases that is simple and intuitive; an ability to cope with errors and uncertainties in diagnostic information; the simplicity of storing statistical information as frequencies of occurrence of diseases; a method for evaluating alternative diagnostic hypotheses that yields true probabilities; and a framework that should facilitate unsupervised learning of medical knowledge and the integration of medical diagnosis with other AI applications.