NewsFinder automates the steps involved in finding, select- ing and publishing news stories that meet subjective judgments of relevance and interest to the Artificial Intelligence community. NewsFinder combines a broad search with AI-specific filters and incorporates a learning program whose judgment of interestingness of stories can be trained by feedback from readers. Since August, 2010, the program has been used to operate the AI in the News service that is part of the AAAI AI Topics site.

The American College of Medical Informatics is an honorary society established to recognize those who have made sustained contributions to the field.Its highest award, for lifetime achievement and contributions to the discipline now known more inclusively as biomedical informatics, is the Morris F. Collen Award.Dr. Collen's own efforts as a pioneer in the field stand as the embodiment of creativity, intellectual rigor, perseverance, and personal integrity.At most once a year, the College gives its highest recognition to an individual whose attainments have, throughout a career, substantially advanced the science and art of biomedical informatics.In 2006, the College was proud to present the Collen Award to Edward Hance Shortliffe, M.D., Ph.D. (Figure 1).As a physician, computer scientist, researcher, educator, and eloquent spokesperson for the field, Dr. Shortliffe's career contributions make him most deserving of the recognition embodied in the Collen Award. BeginningsEdward "Ted" Shortliffe was born on August 28th, 1947, in Edmonton, Alberta, Canada (see Figure 2).Ted's father was a physician and hospital administrator and his mother was a high school English teacher.The family moved to Con-necticut while Ted was a youngster (1954), and in 1962 he became a U.S. citizen.After graduating from high school and spending a year as an exchange student in Great Britain, Ted entered Harvard in the fall of 1966.As an undergraduate, he sought a research project in applied mathematics, which was the concentration at Harvard at the time that included computer science.An advisor steered Ted to the

BACKGROUND: Conserved protein sequence motifs are short stretches of amino acid sequence patterns that potentially encode the function of proteins. Several sequence pattern searching algorithms and programs exist foridentifying candidate protein motifs at the whole genome level. However, a much needed and important task is to determine the functions of the newly identified protein motifs. The Gene Ontology (GO) project is an endeavor to annotate the function of genes or protein sequences with terms from a dynamic, controlled vocabulary and these annotations serve well as a knowledge base. RESULTS: This paper presents methods to mine the GO knowledge base and use the association between the GO terms assigned to a sequence and the motifs matched by the same sequence as evidence for predicting the functions of novel protein motifs automatically. The task of assigning GO terms to protein motifs is viewed as both a binary classification and information retrieval problem, where PROSITE motifs are used as samples for mode training and functional prediction. The mutual information of a motif and aGO term association is found to be a very useful feature. We take advantage of the known motifs to train a logistic regression classifier, which allows us to combine mutual information with other frequency-based features and obtain a probability of correct association. The trained logistic regression model has intuitively meaningful and logically plausible parameter values, and performs very well empirically according to our evaluation criteria. CONCLUSIONS: In this research, different methods for automatic annotation of protein motifs have been investigated. Empirical result demonstrated that the methods have a great potential for detecting and augmenting information about the functions of newly discovered candidate protein motifs.

We propose and evaluate an agenda- and justification-based architecture for discovery systems that selects the next tasks to perform. This framework has many desirable properties: (1) it facilitates the encoding of general discovery strategies using a variety of background knowledge, (2) it reasons about the appropriateness of the tasks being considered, and (3) it tailors its behavior toward a user's interests. A prototype discovery program called HAMB demonstrates that both reasons and estimates of interestingness contribute to performance in the domains of protein crystallization and patient rehabilitation.

Autonomous discovery systems will be able to peruse very large databases more thoroughly than people can. In a companion paper by G.R. Livingston et al. (see ibid., p.385-92, 2001), we describe a general framework for autonomous systems. We present and evaluate heuristics for use in this framework. Although these heuristics were designed for a prototype system, we believe they provide good initial solutions to problems encountered when implementing fully autonomous discovery systems. As such, these heuristics may be used as the starting point for future research into fully autonomous discovery systems.

We present work in progress on a new methodology for leveraging the semantic content of ontologies to guide knowledge discovery in databases. Our system scans new databases to obtain type and constraint information, which users verify. Our system then uses this information in the context of a shared ontology to intelligently guide the potentially combinatorial process of feature construction. Further, our system learns each time it is applied, easing the user's verification task on subsequent runs..

One of the challenges of knowledge discovery is identifying patterns that are interesting, with novelty an important component of interestingness. Another important aspect of knowledge discovery is making efficient use of background knowledge. This paper develops a definition of novelty relative to a prior model of the domain. The definition of novelty is tested using pneumonia outcome data and a prior model of pneumonia severity.

No abstract available.

OBJECTIVE: To understand better the trade-offs of not incorporating explicit time in Quick Medical Reference (QMR), a diagnostic system in the domain of general internal medicine, along the dimensions of expressive power and diagnostic accuracy. DESIGN: The study was conducted in two phases. Phase I was a descriptive analysis of the temporal abstractions incorporated in QMR's terms. Phase II was a pseudo-prospective controlled experiment, measuring the effect of history and physical examination temporal content on the diagnostic accuracy of QMR. MEASUREMENTS: For each QMR finding that would fit our operational definition of temporal finding, several parameters describing the temporal nature of the finding were assessed, the most important ones being: temporal primitives, time units, temporal uncertainty, processes, and patterns. The history, physical examination, and initial laboratory results of 105 consecutive patients admitted to the Pittsburgh University Presbyterian Hospital were analyzed for temporal content and factors that could potentially influence diagnostic accuracy (these included: rareness of primary diagnosis, case length, uncertainty, spatial/causal information, and multiple diseases). RESULTS: 776 findings were identified as temporal. The authors developed an ontology describing the terms utilized by QMR developers to express temporal knowledge. The authors classified the temporal abstractions found in QMR in 116 temporal types, 11 temporal templates, and a temporal hierarchy. The odds of QMR's making a correct diagnosis in high temporal complexity cases is 0.7 the odds when the temporal complexity is lower, but this result is not statistically significant (95% confidence interval = 0.27-1.83). CONCLUSIONS: QMR contains extensive implicit time modeling. These results support the conclusion that the abstracted encoding of time in the medical knowledge of QMR does not induce a diagnostic performance penalty.

Bruce G. Buchanan, PhD; Leveraging a Fellowship in Medical Informatics: Focus on Software, Journal of the American Medical Informatics Association, Volume 2, Is

Careful study of medical informatics research and library-resource projects is necessary to increase the productivity of the research and development enterprise. Medical informatics research projects can present unique problems with respect to evaluation. It is not always possible to adapt directly the evaluation methods that are commonly employed in the natural and social sciences. Problems in evaluating medical informatics projects may be overcome by formulating system development work in terms of a testable hypothesis; subdividing complex projects into modules, each of which can be developed, tested and evaluated rigorously; and utilizing qualitative studies in situations where more definitive quantitative studies are impractical.

During AI's first decade (1956-1966), the task environments in which AI scientists investigated their basic science issues were generally idealized clean task environments, such as propositional calculus theorem proving and puzzle solving. After the mid-1960s, a bolder and more applied inclination to choose complex real-world problems as task environments became evident. These efforts were both successful and exciting, in two ways. First, the AI programs were achieving high levels of competence at solving certain problems that human specialists found challenging (the excitement was that our AI techniques were indeed powerful and that we were taking the first steps toward the dream of the very smart machine). Second, these complex real-world task environments were proving to be excellent at stimulating basic science questions for the AI science, in knowledge representation, problem solving, and machine learning. To recognize and illuminate this trend, the Artificial Intelligence Journal in 1978 sponsored a special issue on applications of artificial intelligence.

Induction programs make several assumptions that limit their practical utility. Research to overcome the limitation of working within a fixed vocabulary is reported. A recently reported phenomenon in machine learning is that there is a tradeoff between the simplicity of concept descriptions and coverage of training instances, and a learning system cannot have both. It is argued that if a learning system can generate new terms, it can achieve both simplicity and coverage. A method for generating one new kind of terms, comparative terms, is given. The experimental results on a mushroom classification task show that a single comparative term can achieve 90% predictive accuracy.>

The interdisciplinary anthropological study of knowledge elicitation (ASKE) project is introduced. The choice of anthropological methodology for the project is discussed, and the relevance of anthropology to knowledge engineering in general is pointed out. Examples are given of pitfalls observed in the knowledge elicitation process, including problems related to both interviewing technique and conceptual approach. Some preliminary conclusions are drawn based on work to date.>

The authors propose a model for an intelligent assistant to aid in building knowledge-based systems (KBSs) and discuss a preliminary implementation. The assistant participates in KBS construction, including acquisition of an initial model of a problem domain, acquisition of control and task-specific inference knowledge, testing and validation, and long-term maintenance of encoded knowledge. The authors present a hypothetical scenario in which the assistant and a KBS designer cooperate to create an initial domain model and then discuss five categories of knowledge the assistant requires to offer such help. They discuss two software technologies on which the assistant is based: an object-oriented programming language, and a user-interface framework.>

Abstract An explicit representation of the problem solving method of an expert system shell as abstract control knowledge provides a powerful foundation for learning. This paper describes the abstract control knowledge of the HERACLES expert system shell for heuristic classification problems, and describes how the ODYSSEUS apprenticeship learning program uses this representation to semi-automate “endgame” knowledge acquisition. The problem solving method of HERACLES is represented explicitly as domain-independent tasks and metarules. Metarules locate and apply domain knowledge to achieve problem solving subgoals, such as testing, refining, or differentiating between hypothesis; and asking general or clarifying questions. We show how monitoring abstract control knowledge for metarule premise failures provides a means of detecting gaps in the knowledge base. A knowledge base gap will almost always cause a metarule premise failure. We also show how abstract control knowledge plays a crucial role in using underlying domain theories for learning, especially weak domain theories. The construction of abstract control knowledge requires that the different types of knowledge that enter into problem solving be represented in different knowledge relations. This provides a foundation for the integration of underlying domain theories into a learning system, because justification of different types of new knowledge usually requires different ways of using an underlying domain theory. We advocate the construction of a definitional constraint for each knowledge relation that specifies how the relation is defined and justified in terms of underlying domain theories.

The most important development in expert systems is the introduction and proliferation of frameworks, or shells, that allow rapid prototyping, easy expansion, and continued maintenance. Several shells are now in commercial use and have been used to build expert systems of recognized value. The state of the art and several new lines of development will be discussed. Some of the developments involve fundamental research in AI on knowledge representation and inference; others involve making the shell environments themselves more intelligent.