End-User Construction of Influence Diagrams for Bayesian Statistics

TL;DR

This paper introduces a user-centered system called THOMAS that enables end users, such as physicians, to construct and manipulate influence diagrams for Bayesian models through domain-specific interfaces, improving interpretability.

Contribution

It presents a novel architecture and system that allow end users to create and manipulate influence diagrams using semantic interfaces and metadata-state diagrams, tailored for medical trial interpretation.

Findings

System enables physicians to interpret clinical trial data effectively.

Influence diagrams are made accessible to end users through domain-specific interfaces.

The architecture maintains semantic integrity during model transformations.

Abstract

Influence diagrams are ideal knowledge representations for Bayesian statistical models. However, these diagrams are difficult for end users to interpret and to manipulate. We present a user-based architecture that enables end users to create and to manipulate the knowledge representation. We use the problem of physicians' interpretation of two-arm parallel randomized clinical trials (TAPRCT) to illustrate the architecture and its use. There are three primary data structures. Elements of statistical models are encoded as subgraphs of a restricted class of influence diagram. The interpretations of those elements are mapped into users' language in a domain-specific, user-based semantic interface, called a patient-flow diagram, in the TAPRCT problem. Pennitted transformations of the statistical model that maintain the semantic relationships of the model are encoded in a metadata-state diagram, called the cohort-state diagram, in the TAPRCT problem. The algorithm that runs the system uses modular actions called construction steps. This framework has been implemented in a system called THOMAS, that allows physicians to interpret the data reported from a TAPRCT.