A probabilistic and decision-theoretic approach to the management of infectious disease at the ICU

The medical community is presently in a state of transition from a situation dominated by the paper medical record to a future situation where all patient data will be available on-line by an electronic clinical information system. In data-intensive clinical environments, such as intensive care units (ICUs), clinical patient data are already fully managed by such systems in a number of hospitals. However, providing facilities for storing and retrieving patient data to clinicians is not enough; clinical information systems should also offer facilities to assist clinicians in dealing with hard clinical problems. Extending an information system's capabilities by integrating it with a decision-support system may be a solution. In this paper, we describe the development of a probabilistic and decision-theoretic system that aims to assist clinicians in diagnosing and treating patients with pneumonia in the intensive-care unit. Its underlying probabilistic-network model includes temporal knowledge to diagnose pneumonia on the basis of the likelihood of laryngotracheobronchial-tree colonisation by pathogens, and symptoms and signs actually present in the patient. Optimal antimicrobial therapy is selected by balancing the expected efficacy of treatment, which is related to the likelihood of particular pathogens causing the infection, against the spectrum of antimicrobial treatment. The models were built on the basis of expert knowledge. The patient data that were available were of limited value in the initial construction of the models because of problems of incompleteness. In particular, detailed temporal information was missing. By means of a number of different techniques, among others from the theory of linear programming, these data have been used to check the probabilistic information elicited from infectious-disease experts. The results of an evaluation of a number of slightly different models using retrospective patient data are discussed as well.

[1]  David Heckerman,et al.  Causal independence for probability assessment and inference using Bayesian networks , 1996, IEEE Trans. Syst. Man Cybern. Part A.

[2]  H. Brachinger,et al.  Decision analysis , 1997 .

[3]  Peter J. F. Lucas,et al.  Principles of expert systems , 1991, International computer science series.

[4]  Edward H. Shortliffe,et al.  Rule Based Expert Systems: The Mycin Experiments of the Stanford Heuristic Programming Project (The Addison-Wesley series in artificial intelligence) , 1984 .

[5]  Steen Andreassen,et al.  MUNIN - A Causal Probabilistic Network for Interpretation of Electromyographic Findings , 1987, IJCAI.

[6]  Peter J. F. Lucas,et al.  A decision-theoretic network approach to treatment management and prognosis , 1998, Knowl. Based Syst..

[7]  T. Clemmer,et al.  A computer-assisted management program for antibiotics and other antiinfective agents. , 1998, The New England journal of medicine.

[8]  Steen Andreassen,et al.  Using probabilistic and decision-theoretic methods in treatment and prognosis modeling , 1999, Artif. Intell. Medicine.

[9]  D. Heckerman,et al.  Toward Normative Expert Systems: Part I The Pathfinder Project , 1992, Methods of Information in Medicine.

[10]  R M Gardner,et al.  Computer surveillance of hospital-acquired infections and antibiotic use. , 1986, JAMA.

[11]  Steen Andreassen,et al.  A Decision Theoretic Approach to Empirical Treatment of Bacteraemia Originating from the Urinary Tract , 1999, AIMDM.

[12]  Gregory F. Cooper,et al.  A Method for Using Belief Networks as Influence Diagrams , 2013, UAI 1988.

[13]  Linda C. van der Gaag,et al.  Bayesian Belief Networks: Odds and Ends , 1996, Comput. J..

[14]  Edward H. Shortliffe,et al.  Computer-based medical consultations, MYCIN , 1976 .

[15]  Roe Goodman,et al.  Introduction to stochastic models , 1987 .

[16]  M. Kollef,et al.  Prevention of Ventilator-Associated Pneumonia , 2002 .

[17]  Martin L. Puterman,et al.  Markov Decision Processes: Discrete Stochastic Dynamic Programming , 1994 .

[18]  P. Ein-Dor,et al.  Improving empirical antibiotic treatment: prospective, nonintervention testing of a decision support system , 1997, Journal of internal medicine.

[19]  P. Lucas,et al.  Second evaluation of HEPAR, an expert system for the diagnosis of disorders of the liver and biliary tract. , 1991, Liver.

[20]  Craig Boutilier,et al.  Decision-Theoretic Planning: Structural Assumptions and Computational Leverage , 1999, J. Artif. Intell. Res..

[21]  Alfredo Pagoraro,et al.  Harrison's principles of internal medicine, 13th edition , 1995 .

[22]  John G. Bartlett.  Management of respiratory tract infections , 1997 .

[23]  F Gouin,et al.  Bronchoscopic or Blind Sampling Techniques for Diagnosis of Ventilator‐Associated Pneumonia , 1996, American journal of respiratory and critical care medicine.

[24]  R W Segaar,et al.  HEPAR: an expert system for the diagnosis of disorders of the liver and biliary tract. , 1989, Liver.

[25]  D. Heckerman,et al.  Probabilistic diagnosis using a reformulation of the INTERNIST-1/QMR knowledge base. II. Evaluation of diagnostic performance. , 1991, Methods of information in medicine.

[26]  Judea Pearl,et al.  Probabilistic reasoning in intelligent systems , 1988 .

[27]  E. Shortliffe.  Computer-based medical consultations: mycin (elsevier north holland , 1976 .

[28]  H J Norris,et al.  Robbins Pathologic Basis of Disease, 4th edition , 1990 .

[29]  D E Heckerman,et al.  Toward Normative Expert Systems: Part II Probability-Based Representations for Efficient Knowledge Acquisition and Inference , 1992, Methods of Information in Medicine.

[30]  P. Anthony.  Robbins' Pathologic Basis of Disease , 1990 .

[31]  P L Miller,et al.  Evaluation of Artificial Intelligence Systems in Medicine , 1988 .

[32]  Peter J. F. Lucas,et al.  Certainty-Factor-Like Structures in Bayesian Networks , 1999, AI*IA.

[33]  E. Gabrieli,et al.  Aspects of a computer-based patient record. , 1993, Journal of AHIMA.

[34]  A. Ambergen,et al.  Risk factors for pneumonia, and colonization of respiratory tract and stomach in mechanically ventilated ICU patients. , 1996, American journal of respiratory and critical care medicine.

[35]  Peter J. F. Lucas,et al.  Knowledge acquisition for decision-theoretic expert systems , 1996 .

[36]  D. Spiegelhalter,et al.  Evaluating medical expert systems: what to test and how? , 1990, Medical informatics = Medecine et informatique.

[37]  P J Lucas,et al.  Converting a rule-based expert system into a belief network. , 1993, Medical informatics = Medecine et informatique.

[38]  K. Adlassnig,et al.  Performance evaluation of medical expert systems using ROC curves. , 1989, Computers and biomedical research, an international journal.

[39]  Lawrence M. Fagan,et al.  Antimicrobial selection by a computer. A blinded evaluation by infectious diseases experts. , 1979, JAMA.

[40]  G. Chapman,et al.  [Medical decision making]. , 1976, Lakartidningen.

[41]  W. McIsaac,et al.  Effect of an Explicit Decision-Support Tool on Decisions to Prescribe Antibiotics for Sore Throat , 1998, Medical decision making : an international journal of the Society for Medical Decision Making.

[42]  Ross D. Shachter.  Evaluating Influence Diagrams , 1986, Oper. Res..

[43]  L. Li,et al.  New computer-based tools for empiric antibiotic decision support , 1997, AMIA.

[44]  David J. Spiegelhalter,et al.  Local computations with probabilities on graphical structures and their application to expert systems , 1990 .

[45]  Jacques Demongeot,et al.  MENINGE: A medical consulting system for child's meningitis. Study on a series of consecutive cases , 1992, Artif. Intell. Medicine.

[46]  S. Robbins,et al.  Pathologic basis of disease , 1974 .

[47]  P. Lucas,et al.  Computer-based Decision Support in the Management of Primary Gastric non-Hodgkin Lymphoma , 1998, Methods of Information in Medicine.