Data-mining to build a knowledge representation store for clinical decision support. Studies on curation and validation based on machine performance in multiple choice medical licensing examinations

Abstract

Extracting medical knowledge by structured data mining of many medical records and from unstructured data mining of natural language source text on the Internet will become increasingly important for clinical decision support. Output from these sources can be transformed into large numbers of elements of knowledge in a Knowledge Representation Store (KRS), here using the notation and to some extent the algebraic principles of the Q-UEL Web-based universal exchange and inference language described previously, rooted in Dirac notation from quantum mechanics and linguistic theory. In a KRS, semantic structures or statements about the world of interest to medicine are analogous to natural language sentences seen as formed from noun phrases separated by verbs, prepositions and other descriptions of relationships. A convenient method of testing and better curating these elements of knowledge is by having the computer use them to take the test of a multiple choice medical licensing examination. It is a venture which perhaps tells us almost as much about the reasoning of students and examiners as it does about the requirements for Artificial Intelligence as employed in clinical decision making. It emphasizes the role of context and of contextual probabilities as opposed to the more familiar intrinsic probabilities, and of a preliminary form of logic that we call presyllogistic reasoning.

Computers and viral diseases. Preliminary bioinformatics studies on the design of a synthetic vaccine and a preventative peptidomimetic antagonist against the SARS-CoV-2 (2019-nCoV, COVID-19) coronavirus

“…The theory behind Q-UEL has been described and developed in several essentially mathematical papers. Refs [28][29][30][31][32][33][34][35][36] provide a more relevant and applied mathematical account, in conjunction with algorithm and software development. Ref [28] provided the first detailed description of the Q-UEL language as a means of interacting with the World Wide Web and potentially proving the basis of a "Thinking Web" for medicine, primarily by rendering the emerging Semantic Web as more fundamentally probabilistic [28].…”

“…difference from previous genomics use cases for Q-UEL [36] is that the notion of types of coronavirus and strain replaced the notion of human patient. The specific software of the decision support system interacting with the Internet was the more recent BioIngine implementation of Q-UEL and associated software applications [29][30][31][32][33][34][35]. These applications generate and use Q-UEL tags to extract, communicate knowledge and draw conclusions from it by automated inference.…”

“…[28] was generated by interacting with the HTML on the webpage for Google queries and the resulting list of hits. In the present paper, extensive use was made of MARPLE/HDNstudent with XTRACTOR [30,31]. This provides convenient ways of making search queries for initiating "autosurfing" of the Internet.…”

Item Analysis of Multiple Choice Questions in Medical Licensing Examination

“…This study has laid the foundation for medical licensing examination validation in Mongolia. However, more modern approaches that implement sophisticated data mining and artificial intelligence technologies in item analysis that are time-saving and more efficient are being used in the developed world, particularly in the United States 23 . Using in-depth, content analysis of professional criteria and the item analysis; officials in the United States have analyzed over 550000 exam materials to align exam questions with workforce tasks 24 .…”

A Novel Fuzzy Algorithm to Introduce New Variables in the Drug Supply Decision‐Making Process in Medicine

“…It includes the capability of learning automatically from data to control the health management systems, including an active guidance of clinicians in their treatment decisions. For clinical decision support, the key idea of the training process is extracting the expert knowledge from the information concerning medical records and the unstructured data including natural language [7]. E-health systems have become popular as they automatically evaluate the situation of patients without involvement from a physician [8].…”