A community-of-practice-based evaluation methodology for knowledge intensive computational methods and its application to multimorbidity decision support.

OBJECTIVE: The study has dual objectives. Our first objective (1) is to develop a community-of-practice-based evaluation methodology for knowledge-intensive computational methods. We target a whitebox analysis of the computational methods to gain insight on their functional features and inner workings. In more detail, we aim to answer evaluation questions on (i) support offered by computational methods for functional features within the application domain; and (ii) in-depth characterizations of the underlying computational processes, models, data and knowledge of the computational methods. Our second objective (2) involves applying the evaluation methodology to answer questions (i) and (ii) for knowledge-intensive clinical decision support (CDS) methods, which operationalize clinical knowledge as computer interpretable guidelines (CIG); we focus on multimorbidity CIG-based clinical decision support (MGCDS) methods that target multimorbidity treatment plans. MATERIALS AND METHODS: Our methodology directly involves the research community of practice in (a) identifying functional features within the application domain; (b) defining exemplar case studies covering these features; and (c) solving the case studies using their developed computational methods-research groups detail their solutions and functional feature support in solution reports. Next, the study authors (d) perform a qualitative analysis of the solution reports, identifying and characterizing common themes (or dimensions) among the computational methods. This methodology is well suited to perform whitebox analysis, as it directly involves the respective developers in studying inner workings and feature support of computational methods. Moreover, the established evaluation parameters (e.g., features, case studies, themes) constitute a re-usable benchmark framework, which can be used to evaluate new computational methods as they are developed. We applied our community-of-practice-based evaluation methodology on MGCDS methods. RESULTS: Six research groups submitted comprehensive solution reports for the exemplar case studies. Solutions for two of these case studies were reported by all groups. We identified four evaluation dimensions: detection of adverse interactions, management strategy representation, implementation paradigms, and human-in-the-loop support. Based on our whitebox analysis, we present answers to the evaluation questions (i) and (ii) for MGCDS methods. DISCUSSION: The proposed evaluation methodology includes features of illuminative and comparison-based approaches; focusing on understanding rather than judging/scoring or identifying gaps in current methods. It involves answering evaluation questions with direct involvement of the research community of practice, who participate in setting up evaluation parameters and solving exemplar case studies. Our methodology was successfully applied to evaluate six MGCDS knowledge-intensive computational methods. We established that, while the evaluated methods provide a multifaceted set of solutions with different benefits and drawbacks, no single MGCDS method currently provides a comprehensive solution for MGCDS. CONCLUSION: We posit that our evaluation methodology, applied here to gain new insights into MGCDS, can be used to assess other types of knowledge-intensive computational methods and answer other types of evaluation questions. Our case studies can be accessed at our GitHub repository (https://github.com/william-vw/MGCDS).

Semantic knowledge modeling and evaluation of argument Theory to develop dialogue based patient education systems for chronic disease Self-Management.

BACKGROUND: To improve understanding as well as uptake of health educational material, it should be tailored to informational needs, offer intuitive modes of interaction, and present credible evidence for health claims. Dialogue systems go some way in meeting these requirements, as they emulate interactive and intuitive person-to-person communication. However, most works do not offer a formal model nor modelling process to structure dialogue content, and do not focus on ensuring credibility. METHODS: We propose an Extended Model of Argument (EMA) dialogue model and modelling process to support educational dialogue systems. In this dialogue model, computerized arguments directly offer evidence for health claims. EMA further offers "dialogue by design", where argument structures and interrelations are dynamically leveraged to offer dialogues, instead of relying on predefining discourse flows. We implemented an EMA-based dialogue education system for Juvenile Idiopathic Arthritis (JIA). We performed a qualitative evaluation with JIA health experts involving a Cognitive Walkthrough and Semi-Structured Interview. We applied Directed Content Analysis using categories from the O'Grady framework, and coded sub-themes within those categories using Grounded Theory. RESULTS: We identified 6 sub-themes within the participant feedback pertaining to Quality, Credibility, and Utility. Participants attached strong importance to credibility and found the dialogue system to be a flexible educational tool. Some participants suggested sorting educational items by importance, and presenting only salient knowledge associations to reduce dialogue complexity. CONCLUSION: Overall, our qualitative evaluation confirmed the following: the ability of EMA to offer credible and appropriate dialogues; and, in general, the utility of dialogue systems to educate JIA patients and their families. In future work, we will revise the system based on evaluation feedback, and perform a more extensive evaluation with patients and caregivers.