John Fox

Probability, logic and the cognitive foundations of rational belief

n Abstractn n Since Pascal introduced the idea of mathematical probability in the 17th century discussions of uncertainty and “rational” belief have been dogged by philosophical and technical disputes. Furthermore, the last quarter century has seen an explosion of new questions and ideas, stimulated by developments in the computer and cognitive sciences. Competing ideas about probability are often driven by different intuitions about the nature of belief that arise from the needs of different domains (e.g., economics, management theory, engineering, medicine, the life sciences etc). Taking medicine as our focus we develop three lines of argument (historical, practical and cognitive) that suggest that traditional views of probability cannot accommodate all the competing demands and diverse constraints that arise in complex real-world domains. A model of uncertain reasoning based on a form of logical argumentation appears to unify many diverse ideas. The model has precursors in informal discussions of argumentation due to Toulmin, and the notion of logical probability advocated by Keynes, but recent developments in artificial intelligence and cognitive science suggest ways of resolving epistemological and technical issues that they could not address.n n

Interactive Decision Support for Medical Planning

We describe a decision support system for treatment planning which provides immediate feedback of constraints, interactions and dependencies on and between treatment actions, and the possible outcomes of proposed plans.

From Arguments to Decisions: Extending the Toulmin View

In his 1958 essays Toulmin criticises “scientific” views of logic and probability, suggesting that these philosophical and theoretical frameworks have failed to accommodate features of everyday dispute and debate. He offers an alternative perspective, summarised by his famous argumentation schema. He draws primarily on legal and regulatory examples, but we have found that medicine and science also provide rich sources of argumentation examples and many of these fit the Toulmin schema. However the decision-making elements of clinical judgement suggest the need for extensions to the standard layout. This paper presents a view of argumentation based decision making that preserves the essence of the Toulmin model but in an extended form.

Computerised Advice on Drug Dosage Decisions in Childhood Leukaemia: A Method and a Safety Strategy

Currently over 95% of children who are diagnosed with Acute Lymphoblastic Leukaemia in the UK are enrolled into Medical Research Council trials. The trial protocol specifies that following initial treatment there is a 2-3 year maintenance period during which drug dosage decisions are made weekly according to a set of pre-defined rules. These rules are complex, and there is a significant frequency of error in clinical practice, which can lead to patient harm. We have built a web-based decision support system (called LISA) to address this problem. The dose alteration rules from the MRC protocol were formalised in the PROforma guideline modeling language as a state transition problem, and dose adjustment recommendations are provided into the clinical setting by a PROforma enactment engine. The design and implementation of the decision support module, the safety issues raised and the strategy adopted for resolving them are discussed. System safety is very likely to become a major professional challenge for the medical AI community and it can be addressed, in this case, with relatively straightforward techniques.

7 Knowledge, arguments, and intentions in clinical decision-making

Publisher Summary The most influential theories of reasoning and decision making were developed by mathematicians and logicians, often informed by problems in some practical domain such as medicine or economics. Their work led to theoretical concepts with great intellectual depth and formal rigor, such as statistical decision theory (SDT). There are difficulties with expected utility and other mathematical techniques for practical decision making. Any quantitative decision procedure depends upon the ability to estimate the required parameters. This can be problematic in real-world applications. Classical decision theory focuses on only a small part of the decision process—making the choice. There are deep issues about the adequacy of quantitative formalisms to represent the kinds of knowledge and forms of reasoning that are routinely employed in medical thinking. This chapter presents an alternative framework that is formally sound but avoids the shortcomings of standard quantitative decision procedures.

Speech Interfaces for Point-of-Care Guideline Systems

A major limiting factor in the acceptability of interactive guideline and decision support systems is the ease of use of the system in the clinic. A way to reduce demands upon users and increase flexibility of the interface is to use natural language dialogues and speech based interfaces. This paper describes a voice-based data capture and decision support system in which knowledge of underlying task structure (a medical guideline) and domain knowledge (disease ontologies and semantic dictionaries) are integrated with dialogue models based on conversational game theory resulting in a flexible and configurable interface.

Introduction: Agents in Health Care

Agent technology has become a leading area of research in AI and computer science and the focus of a number of major initiatives. One of these is the AgentCities project funded by the European Union 5thFramework research programme(http://www.agentcities.org). AgentCities is a federation of specialist communities with a common interest in agents, one of which is concerned with health care. In this book, John Nealon and Toni Moreno have brought together an interesting set of papers that discuss the many practical issues that arise in trying to build agent applications in medicine. The papers are not simply focused on the health care domain however: they also succeed in raising a number of theoretical issues of wide relevance to the general field of agent research