In clinical decision support, argumentation plays a key role while alternative reasons may be available to explain a given set of signs and symptoms, or alternative plans to treat a diagnosed disease. In literature, this key notion usually has closed boundary across approaches and lacks of openness and interoperability in Clinical Decision Support Systems (CDSSs) been built. In this paper, we propose a systematic approach for the representation of argumentation, their interpretation towards recommendation, and finally explanation in clinical decision support. A generic argumentation and recommendation scheme lays the foundation of the approach. On the basis of this, argumentation rules are represented using Resource Description Framework (RDF) for clinical guidelines, a rule engine developed for their interpretation, and recommendation rules represented using Semantic Web Rule Language (SWRL). A pair of proof knowledge graphs are made available in an integrated clinical decision environment to explain the argumentation and recommendation rationale, so that decision makers are informed of not just what are recommended but also why. A case study of triple assessment, a common procedure in the National Health Service of UK for women suspected of breast cancer, is used to demonstrate the feasibility of the approach. In conducting hypothesis testing, we evaluate the metrics of accuracy, variation, adherence, time, satisfaction, confidence, learning, and integration of the prototype CDSS developed for the case study in comparison with a conventional CDSS and also human clinicians without CDSS. The results are presented and discussed.

Background: Effective shared decision-making between patients and physicians is crucial for enhancing health care quality and reducing medical errors. The literature shows that the absence of effective methods to facilitate shared decision-making can result in poor patient engagement and unfavorable decision outcomes. Objective: In this paper, we propose a Collaborative Decision Description Language (CoDeL) to model shared decision-making between patients and physicians, offering a theoretical foundation for studying various shared decision scenarios. Methods: CoDeL is based on an extension of the interaction protocol language of Lightweight Social Calculus. The language utilizes speech acts to represent the attitudes of shared decision-makers toward decision propositions, as well as their semantic relationships within dialogues. It supports interactive argumentation among decision makers by embedding clinical evidence into each segment of decision protocols. Furthermore, CoDeL enables personalized decision-making, allowing for the demonstration of characteristics such as persistence, critical thinking, and openness. Results: The feasibility of the approach is demonstrated through a case study of shared decision-making in the disease domain of atrial fibrillation. Our experimental results show that integrating the proposed language with GPT can further enhance its capabilities in interactive decision-making, improving interpretability. Conclusions: The proposed novel CoDeL can enhance doctor-patient shared decision-making in a rational, personalized, and interpretable manner.

With the expansion of the scale and complexity of modern software systems, the failure rate of software projects remains high. One of the main reasons for the failure of software projects is the defects in processing software requirements. This paper proposes a software requirements engineers ability assessment method based on empirical software engineering to measure the matching degree between the software requirements engineers ability and industry expectations. First, collect the recruitment information of software requirements engineers from mainstream recruitment websites. Through natural language processing, the words related to the abilities of the software requirements engineer are counted. These words are summarized in the requirements acquisition, requirements analysis, and other SRE activities, then the industry expectations for various abilities are obtained. Later on, the authors collect the teaching settings of representative SRE courses, reflecting the software requirements engineers ability to learn the course. After that, this article defines the ratio of the industry expectation weight to the weight of each SRE activity in teaching as the software requirements engineers ability coefficient, which can intuitively reflect the matching degree between the software requirements engineers ability and industry expectations. Finally, take the national first-class undergraduate course SRE of Jinling Institute of Technology as an example to verify the methods practicality to a certain extent.