In this paper, an agent framework for solving multidisciplinary decisions is proposed, including a conceptual decision model coupled with an agent scheme, and a set of functional signatures that drive the inference. The framework is specially designed to support decision-making in organisational structuring among care specialists towards complex problems, individual planning and argumentation, and computing service binding. A case study of the triple assessment of breast cancer is used for illustration.

MOTIVATION: The output of a bioinformatic tool such as BLAST must usually be interpreted by an expert before reliable conclusions can be drawn. This may be based upon the expert's experience, additional data and statistical analysis. Often the process is laborious, goes unrecorded and may be biased. Argumentation is an established technique for reasoning about situations where absolute truth or precise probability is impossible to determine. RESULTS: We demonstrate the application of argumentation to 3D-PSSM, a protein structure prediction tool. The expert's interpretation of results is represented as an argumentation framework. Given a 3D-PSSM result, an automated procedure constructs arguments for and against the conclusion that the result is a good predictor of protein structure. In addition to capturing the unique expertise of the author of 3D-PSSM for distribution to users, an improvement in recall of 5-10 percentage points is achieved. This technique can be applied to a wide range of bioinformatic tools. AVAILABILITY: Example public server and benchmarking data are available at http://www.sbg.bio.ic.ac.uk/~brj03/argumentation/paper/. Source code available on request.

OBJECTIVES: Many groups are developing computer-interpretable clinical guidelines (CIGs) for use during clinical encounters. CIGs use "Task-Network Models" for representation but differ in their approaches to addressing particular modeling challenges. We have studied similarities and differences between CIGs in order to identify issues that must be resolved before a consensus on a set of common components can be developed. DESIGN: We compared six models: Asbru, EON, GLIF, GUIDE, PRODIGY, and PROforma. Collaborators from groups that created these models represented, in their own formalisms, portions of two guidelines: American College of Chest Physicians cough guidelines [correction] and the Sixth Report of the Joint National Committee on Prevention, Detection, Evaluation, and Treatment of High Blood Pressure. MEASUREMENTS: We compared the models according to eight components that capture the structure of CIGs. The components enable modelers to encode guidelines as plans that organize decision and action tasks in networks. They also enable the encoded guidelines to be linked with patient data-a key requirement for enabling patient-specific decision support. RESULTS: We found consensus on many components, including plan organization, expression language, conceptual medical record model, medical concept model, and data abstractions. Differences were most apparent in underlying decision models, goal representation, use of scenarios, and structured medical actions. CONCLUSION: We identified guideline components that the CIG community could adopt as standards. Some of the participants are pursuing standardization of these components under the auspices of HL7.

PROforma is an executable process modeling language that has been used successfully to build and deploy a range of decision support systems, guidelines, and other clinical applications. It is one of a number of recent proposals for representing clinical protocols and guidelines in a machine-executable format (see ). In this report, the authors outline the task model for the language and provide an operational semantics for process enactment together with a semantics for expressions, which may be used to query the state of a task during enactment. The operational semantics includes a number of public operations that may be performed on an application by an external agent, including operations that change the values of data items, recommend or make decisions, manage tasks that have been performed, and perform any task state changes that are implied by the current state of the application. Disclosure: PROforma has been used as the basis of a commercial decision support and guideline technology Arezzo (Infermed, London, UK; details in text).

This paper describes the development and application of PROforma, a unified technology for clinical decision support and disease management. Work leading to the implementation of PROforma has been carried out in a series of projects funded by European agencies over the past 13 years. The work has been based on logic engineering, a distinct design and development methodology that combines concepts from knowledge engineering, logic programming, and software engineering. Several of the projects have used the approach to demonstrate a wide range of applications in primary and specialist care and clinical research. Concurrent academic research projects have provided a sound theoretical basis for the safety-critical elements of the methodology. The principal technical results of the work are the PROforma logic language for defining clinical processes and an associated suite of software tools for delivering applications, such as decision support and disease management procedures. The language supports four standard objects (decisions, plans, actions, and enquiries), each of which has an intuitive meaning with well-understood logical semantics. The development toolset includes a powerful visual programming environment for composing applications from these standard components, for verifying consistency and completeness of the resulting specification and for delivering stand-alone or embeddable applications. Tools and applications that have resulted from the work are described and illustrated, with examples from specialist cancer care and primary care. The results of a number of evaluation activities are included to illustrate the utility of the technology.

A generic architecture for autonomous agents is presented. In common with other current proposals the agent is capable of reacting to and reasoning about events which occur in its environment, executing actions and plans in order to achieve goals in its environment, and communicating with other agents. The work described here proposes certain advances on other systems, notably the ability to reason about and make decisions under uncertainty, including decisions about competing beliefs and alternative actions. The framework is grounded in a non-classical decision model, the ‘domino’ model. This is formalized to ensure continuity with classical decision theory and avoid ad hoc features. The domino model is embodied in a well-defined knowledge representation language, R2L, which explicitly supports the central concepts of decisions and plans, and associated constructs of goals, arguments, commitments, obligations and constraints. The availability of such a language provides a sound basis for building knowledge-based agents for practical applications. A major issue for such applications, however, is how to ensure their safe operation. This is a central issue whether the agents are used in an advisory role (e.g. decision support systems) or an autonomous one (e.g. in a robot). Techniques for explicit management of safety are described and some broader theoretical implications are discussed.

We present the syntax and proof theory of a logic of argumentation, LA. We also outline the development of a category theoretic semantics for LA. LA is the core of a proof theoretic model for reasoning under uncertainty. In this logic, propositions are labeled with a representation of the arguments which support their validity. Arguments may then be aggregated to collect more information about the potential validity of the propositions of interest. We make the notion of aggregation primitive to the logic, and then define strength mappings from sets of arguments to one of a number of possible dictionaries. This provides a uniform framework which incorporates a number of numerical and symbolic techniques for assigning subjective confidences to propositions on the basis of their supporting arguments. These aggregation techniques are also described with examples.

An approach that accommodates classical decision theory within a framework of first-order logic with nonmonotonic extensions is described. Among the benefits offered by the approach are the potential: to express qualitative arguments about the desirability of decision options in the absence of probability or utility parameters; to automate techniques for generating decision options; and to initiate, control, and terminate a decision process autonomously. The rationality of a logical decision framework is discussed. A particular benefit of implementing decision procedures in a nonmonotonic logic is that decision systems can adapt automatically as beliefs change, contradictions are encountered, or new knowledge is acquired. A general conclusion is that metaknowledge and metalevel reasoning must be integral elements of a decision theory because of the versatility and operating flexibility they offer.>