Case-based medical informatics

Abstract

Background: The "applied" nature distinguishes applied sciences from theoretical sciences. To emphasize this distinction, we begin with a general, meta-level overview of the scientific endeavor. We introduce the knowledge spectrum and four interconnected modalities of knowledge. In addition to the traditional differentiation between implicit and explicit knowledge we outline the concepts of general and individual knowledge. We connect general knowledge with the "frame problem," a fundamental issue of artificial intelligence, and individual knowledge with another important paradigm of artificial intelligence, case-based reasoning, a method of individual knowledge processing that aims at solving new problems based on the solutions to similar past problems. We outline the fundamental differences between Medical Informatics and theoretical sciences and propose that Medical Informatics research should advance individual knowledge processing (case-based reasoning) and that natural language processing research is an important step towards this goal that may have ethical implications for patient-centered health medicine.

Discussion: We focus on fundamental aspects of decision-making, which connect human expertise with individual knowledge processing. We continue with a knowledge spectrum perspective on biomedical knowledge and conclude that case-based reasoning is the paradigm that can advance towards personalized healthcare and that can enable the education of patients and providers. We center the discussion on formal methods of knowledge representation around the frame problem. We propose a context-dependent view on the notion of "meaning" and advocate the need for case-based reasoning research and natural language processing. In the context of memory based knowledge processing, pattern recognition, comparison and analogy-making, we conclude that while humans seem to naturally support the case-based reasoning paradigm (memory of past experiences of problem-solving and powerful case matching mechanisms), technical solutions are challenging.Finally, we discuss the major challenges for a technical solution: case record comprehensiveness, organization of information on similarity principles, development of pattern recognition and solving ethical issues.

Summary: Medical Informatics is an applied science that should be committed to advancing patient-centered medicine through individual knowledge processing. Case-based reasoning is the technical solution that enables a continuous individual knowledge processing and could be applied providing that challenges and ethical issues arising are addressed appropriately.

Figure 1

The knowledge spectrum.

Figure 2

A blocks world example. In this particular example expressions such as: on(a, c), on(c, table), on(b, table), pyramid(a), brick(b), brick(c), ¬same-as(a, c), same-as(b, c), etc., are true.

Figure 3

The relationships between the knowledge modalities.

Figure 4

Knowledge representation media on the knowledge spectrum. The storage and transmission of knowledge are more advanced compared to the knowledge acquisition, retrieval and use capability of current technology.

Figure 5

Knowledge representation and processing in novices and experts.

Figure 6

Biomedical knowledge on the knowledge spectrum.

Figure 7

Representations of "brick" on the knowledge spectrum. Such representations range from rich (e.g., images, mental models) to less complex (sketches and diagrams) and to symbolic descriptions (textual, formal and conceptual).

Figure 8

A blocks world example. In this particular example brick(b), brick(c), pyramid(a), on(c, b), on(c, a) are true and therefore not rejected by definition (3): the condition that "c" MUST sit on something that is not a pyramid in order to be a brick is met by on(c, b).

Figure 9

Example of self organizing map (associative memory). Each one of the 9-dimensional, 683 individual cases is associated with a region on the 2-dimensional map and highlighted using a 3rd dimension (an "activation bubble" with elevation and colour). The organization of individual descriptions of cases obeys similarity principles: similar cases are closely mapped and very similar cases form clusters (e.g., the green area contains most of the benign cases).

Figure 10

Example of similarity based retrieval and knowledge induction. Ayercillin, a relatively new drug unknown to the system, is likely to be a penicillin because of its high contextual similarities with known penicillines.