Conversational case-based reasoning in medical decision making

OBJECTIVES Balancing the trade-offs between solution quality, problem-solving efficiency, and transparency is an important challenge in medical applications of conversational case-based reasoning (CCBR). For example, test selection in CCBR is often based on strategies in which the absence of a specific hypothesis (e.g., diagnosis) to be confirmed makes it difficult to explain the relevance of test results that users are asked to provide. In this paper, we present an approach to CCBR in medical classification and diagnosis that aims to increase transparency while also providing high levels of accuracy and efficiency. METHODS We present an algorithm for CCBR called iNN(k) in which feature selection is driven by the goal of confirming a target class and informed by a measure of a feature's discriminating power in favor of the target class. As we demonstrate in a CCBR system called CBR-Confirm, this enables a CCBR system to explain the relevance of any question it asks the user. We evaluate the algorithm's accuracy and efficiency on a selection of datasets related to medicine and health care. RESULTS The performance of iNN(k) on a given dataset is shown to depend on the value of k and on whether local or global feature selection is used in the algorithm. The combination of these parameters for which iNN(k) is most effective in addressing the trade-off between accuracy and efficiency is identified for each of the selected datasets. For example, only 42% and 51% on average of features in a complete problem description were needed by iNN(k) to provide accuracy levels of 86.5% and 84.3% respectively on the lymphography and SPECT heart datasets from the UCI machine learning repository. CONCLUSION Our results demonstrate the ability of iNN(k) to provide high levels of accuracy on most of the selected datasets, while often requiring the user to provide only a small subset of the features in a complete problem description, and enabling a CCBR system to explain the relevance of any question it asks the user.

[1]  Jadzia Cendrowska,et al.  PRISM: An Algorithm for Inducing Modular Rules , 1987, Int. J. Man Mach. Stud..

[2]  David W. Aha,et al.  Advances in conversational case-based reasoning , 2005, Knowl. Eng. Rev..

[3]  Thomas Roth-Berghofer,et al.  Explanations and Case-Based Reasoning: Foundational Issues , 2004, ECCBR.

[4]  Peter E. Hart,et al.  Nearest neighbor pattern classification , 1967, IEEE Trans. Inf. Theory.

[5]  David McSherry,et al.  Interactive Case-Based Reasoning in Sequential Diagnosis , 2001, Applied Intelligence.

[6]  David McSherry.  Minimizing Dialog Length in Interactive Case-Based Reasoning , 2001, IJCAI.

[7]  Hideo Shimazu,et al.  ExpertClerk: A Conversational Case-Based Reasoning Tool forDeveloping Salesclerk Agents in E-Commerce Webshops , 2002, Artificial Intelligence Review.

[8]  Ralph Bergmann,et al.  A Similarity-Based Approach to Attribute Selection in User-Adaptive Sales Dialogs , 2001, ICCBR.

[9]  David McSherry,et al.  Conversational Case-Based Reasoning in Medical Classification and Diagnosis , 2009, AIME.

[10]  Stewart Massie,et al.  A Visualisation Tool to Explain Case-Base Reasoning Solutions for Tablet Formulation , 2004, SGAI Conf..

[11]  K. Holyoak,et al.  The Cambridge handbook of thinking and reasoning , 2005 .

[12]  David McSherry.  Increasing Dialogue Efficiency in Case-Based Reasoning Without Loss of Solution Quality , 2003, IJCAI.

[13]  A. Elstein,et al.  Clinical problem solving and diagnostic decision making: selective review of the cognitive literature , 2002, BMJ : British Medical Journal.

[14]  Agnar Aamodt,et al.  Case-Based Reasoning: Foundational Issues, Methodological Variations, and System Approaches , 1994, AI Commun..

[15]  L. Shulman,et al.  Medical Problem Solving: An Analysis of Clinical Reasoning , 1978 .

[16]  Padraig Cunningham,et al.  An Evaluation of the Usefulness of Case-Based Explanation , 2003, ICCBR.

[17]  R. A. M. O N L O P E Z D E M A N T A R A S,et al.  Retrieval, reuse, revision and retention in case-based reasoning , 2006 .

[18]  Steven Bogaerts,et al.  What Evaluation Criteria Are Right for CCBR? Considering Rank Quality , 2006, ECCBR.

[19]  Ron Kohavi,et al.  A Study of Cross-Validation and Bootstrap for Accuracy Estimation and Model Selection , 1995, IJCAI.

[20]  James C. Lester,et al.  Dialogue Management for Conversational Case-Based Reasoning , 2004, ECCBR.

[21]  Isabelle Bichindaritz,et al.  Medical applications in case-based reasoning , 2005, The Knowledge Engineering Review.

[22]  Isabelle Bichindaritz,et al.  Case-based reasoning in the health sciences , 2006, Artif. Intell. Medicine.

[23]  Cynthia A. Thompson,et al.  Personalized Conversational Case-Based Recommendation , 2000, EWCBR.

[24]  Kalyan Moy Gupta.  Taxonomic Conversational Case-Based Reasoning , 2001, ICCBR.

[25]  Mu Zhu,et al.  The K-nearest neighbor algorithm predicted rehabilitation potential better than current Clinical Assessment Protocol. , 2007, Journal of clinical epidemiology.

[26]  Agnar Aamodt,et al.  A Knowledge-Intensive Method for Conversational CBR , 2005, ICCBR.

[27]  Hideo Shimazu,et al.  ExpertGuide: A Conversational Case-Based Reasoning Tool for Developing Mentors in Knowledge Spaces , 2001, Applied Intelligence.

[28]  Sa'adah Hassan,et al.  Conversational Case-Based Reasoning in Self-healing and Recovery , 2008, ECCBR.

[29]  Pedro A. González-Calero,et al.  Ontology-Driven Development of Conversational CBR Systems , 2006, ECCBR.

[30]  Agnar Aamodt,et al.  Explanation in Case-Based Reasoning–Perspectives and Goals , 2005, Artificial Intelligence Review.

[31]  Lukasz A. Kurgan,et al.  Knowledge discovery approach to automated cardiac SPECT diagnosis , 2001, Artif. Intell. Medicine.

[32]  Jim Hunter,et al.  Proceedings of the 11th conference on Artificial Intelligence in Medicine , 2005 .

[33]  David Leake,et al.  Case-Based Reasoning: Experiences, Lessons and Future Directions , 1996 .

[34]  David W. Aha,et al.  Conversational Case-Based Reasoning , 2001, Applied Intelligence.

[35]  Padraig Cunningham,et al.  A Dynamic Approach to Reducing Dialog in On-Line Decision Guides , 2000, EWCBR.

[36]  David McSherry,et al.  Explaining the Pros and Cons of Conclusions in CBR , 2004, ECCBR.

[37]  G A Gorry,et al.  Toward a theory of clinical expertise. , 1982, The American journal of medicine.

[38]  D. A V I,et al.  Advances in conversational case-based reasoning , 2006 .

[39]  Rainer Maximini,et al.  Explanation Service for Complex CBR Applications , 2004, ECCBR.

[40]  Padraig Cunningham,et al.  Explanation Oriented Retrieval , 2004, ECCBR.

[41]  Edwina L. Rissland,et al.  The Fun Begins with Retrieval: Explanation and CBR , 2006, ECCBR.

[42]  David McSherry,et al.  Introduction to the Special Issue on Explanation in Case-Based Reasoning , 2005, Artificial Intelligence Review.