Download PDF
Methods Inf Med 1991; 30(03): 167-178
DOI: 10.1055/s-0038-1634833
Clinical Application
Schattauer GmbH

Combining Physiologic Models and Symbolic Methods to Interpret Time-Varying Patient Data*

M. G. Kahn
1   Department of Internal Medicine, Washington University School of Medicine, St. Louis MO, USA
,
L. M. Fagan
2   Medical Computer Science Group, Stanford University Medical Center, Stanford CA, USA
,
L. B. Sheiner
3   Department of Laboratory Medicine, University of California, San Francisco, CA, USA
› Author AffiliationsThis work was supported in part by grants NLM T15 LM07047 and LM04136 from the National Library of Medicine and the SUMEX Computer Resource, RR-00785, from the Division of Research Resources. We thank all the members of the ONCOCIN project, especially David Combs, Christopher Lane, Mark Musen, Janice Rohn, Samson Tu, and Cliff Wulfman, for making this project possible.
Further Information

Publication History

Publication Date:
08 February 2018 (online)

    Permissions and Reprints

Abstract

This paper describes a methodology for representing and using medical knowledge about temporal relationships to infer the presence of clinical events that evolve over time. The methodology consists of three steps: (1) the incorporation of patient observations into a generic physiologic model, (2) the conversion of model states and predictions into domain-specific temporal abstractions, and (3) the transformation of temporal abstractions into clinically meaningful descriptive text. The first step converts raw observations to underlying model concepts, the second step identifies temporal features of the fitted model that have clinical interest, and the third step replaces features represented by model parameters and predictions into concepts expressed in clinical language. We describe a program, called TOPAZ, that uses this three-step methodology. TOPAZ generates a narrative summary of the temporal events found in the electronic medical record of patients receiving cancer chemotherapy. A unique feature of TOPAZ is its use of numeric and symbolic techniques to perform different temporal reasoning tasks. Time is represented both as a continuous process and as a set of temporal intervals. These two temporal models differ in the temporal ontology they assume and in the temporal concepts they encode. Without multiple temporal models, this diversity of temporal knowledge could not be represented.

Key-Words

Symbolic Data Interpretation - Physiological Models and Simulation - Computer-Based Problem Solving - Temporal Reasoning and Representation

* Portions of this paper appeared in the Proceedings of the Symposium on Computer Applications in Medical Care, IEEE Computer Society Press, November 1989.


 

  • REFERENCES

  • 1 Blum BI. Clinical Information Systems. New York NY: Springer-Verlag; 1986
    Google Scholar
  • 2 McDonald CJ, Blevins L, Tierney WM, Martin DK. The Regenstrief medical records. M. D. Computing 1988; 05: 34-47.
    PubMedGoogle Scholar
  • 3 Pryor TA. The HELP medical record system. M. D. Computing 1988; 05: 22-33.
    PubMedGoogle Scholar
  • 4 Whiting-O’Keefe QE, Whiting A, Henke J. The STOR clinical information system. M. D. Computing 1988; 05: 8-21.
    PubMedGoogle Scholar
  • 5 Stead WW, Hammond WE. Computer-based medical records; The centerpiece of TMR. M. D. Computing 1988; 05: 48-62.
    PubMedGoogle Scholar
  • 6 Tu SW, Kahn MG, Musen MA, Ferguson JC, Shortliffe EH, Fagan LM. Episodic skeletal-plan refinement based on temporal data. Comm ACM 1989; 32: 1439-55.
    CrossrefPubMedGoogle Scholar
  • 7 Langlotz CP, Fagan LM, Tu SW, Sikic BI, Shortliffe EH. A therapy planning architecture that combines decision theory and artificial intelligence techniques. Comp Biomed Res 1987; 20: 279-303.
    CrossrefPubMedGoogle Scholar
  • 8 Kahn MG. Model-Based Interpretation of Time-Ordered Medical Data [Ph. D. Dissertation]. Section on Medical Information Sciences. San Francisco CA: University of California - San Francisco; 1988
    Google Scholar
  • 9 McKeown KR. Text Generation: Using Discourse Strategies and Focus Contraints to Generate Natural Language Text. Cambridge, England: Cambridge University Press; 1985
    Google Scholar
  • 10 Sheiner LB, Halkin H, Peck C, Rosenberg B, Melmon KL. Improved computer-assisted digoxin therapy. A method using feedback of measured serum digoxin concentrations. Ann Intern Med 1975; 82: 619-27.
    PubMedGoogle Scholar
  • 11 Sheiner LB, Beal SL. Bayesian individualization of pharmacokinetics: Simple implementation and comparison with non-Bayesian methods. J Pharma Sciences 1982; 71: 1344-8.
    PubMedGoogle Scholar
  • 12 Press WH, Flannery BP, Teukolsly SA, Vetterling WT. Numerical Recipes: the Art of magazine Computing. Cambridge, England: Cambridge University Press; 1986
    Google Scholar
  • 13 Kahn MG, Fagan LM, Tu S. Extensions of the time-oriented database model to support temporal reasoning in medical expert systems. Meth Inform Med 1991; 30: 4-14.
    PubMedGoogle Scholar
  • 14 Miller PL. A Critiquing Approach to Expert Computer Advice: ATTENDING. Boston MA: Pitman; 1984
    Google Scholar
  • 15 Miller PL, Rennels GD. Prose generation for expert systems: An applied computational linguistics approach. AI Magazine 1988; 09: 37-44.
    PubMedGoogle Scholar
  • 16 Rennels GD. A Computational Model of Reasoning From the Clinical Literature [Ph. D. Dissertation]. Medical Computer Meth. Inform. Med., Vol. 30, No. 3,1991 Science Group. Stanford CA: Stanford University; 1986
    Google Scholar
  • 17 Musen MA, Fagan LM, Shortliffe EH. Graphical specification of procedural knowledge for an expert system. In: Proceedings IEEE Computer Society Workshop on Visual Language. New York NY: IEEE Computer Society Press; 1986: 167-78 (Reprinted in: Expert Systems: The User Interface. J Hendler, ed, Norwood NJ: Ablex, 1988.)
    Google Scholar
  • 18 Musen MA. Generation of Model-based Knowledge-acquisition Tools for Clinicaltrial Advice Systems [Ph. D. Dissertation]. Medical Computer Science Group. Stanford CA: Stanford University; 1988
    Google Scholar
  • 19 Fangan LM. VM: Representing Time-Dependent Relations in a Medical Setting [Ph. D. Dissertation]. Department of Computer Science. Stanford CA: Stanford University; 1980
    Google Scholar
  • 20 Fangan LM, Kunz JC, Feigenbaum EA, Osborn JJ. Extensions to the rule-based formalism for a monitoring task. In: Buchanan BG, Shortliffe EH. eds. Rule-Based Expert Systems: the MYCIN Experiments of the Stanford Heuristic Programming Project. Reading MA: Addison-Wesley, Chapter; 1984. 22: 397-723.
    Google Scholar
  • 21 Blum RL. Discovery and representation of causal relationships from a large time-oriented clinical database: the RX project. In: Lindberg DAB, Reichertz PL, eds. Lecture Notes in Medical Informatics. New York NY: Springer-Verlag, 1982.;
    Google Scholar
  • 22 Blum RL. Discovery, confirmation and incorporation of causal relationships from a large time-oriented clinical data base: the RX project. In: Clancey WJ, Shortliffe EH. eds. Readings in Medical Artificial Intelligence: the First Decade. Reading MA: Addison-Wesley, Chapter; 1984. 17: 399-425.
    Google Scholar
  • 23 Downs SM. A Program for Automated Summarization of On-Line Medical Records [Dissertation]. Medical Computer Science. Stanford CA: Stanford University; 1986
    Google Scholar
  • 24 Downs SM, Walker MG, Blum RL. Automated summarization of on-line medical records. In: Salamon R, Blum B, Jørgensen M. eds. MEDINFO 86. Amsterdam: North-Holland Publ Comp; 1986: 800-4.
    Google Scholar
  • 25 Kahn KM, Gorry GA. Mechanizing temporal knowledge. Artif Intell 1977; 09: 87-108.
    CrossrefPubMedGoogle Scholar
  • 26 Mittal S, Chandraskaran B, Sticklen J. Pat-rec: A knowledge-directed database for a diagnostic expert system. Computer 1984; 17: 51-8.
    CrossrefPubMedGoogle Scholar
  • 27 Silverman H. A Digitalis Therapy Advisor [Dissertation]. Project MAC. Cambridge MA: Massachusetts Institute of Technology; 1975
    Google Scholar
  • 28 Long WJ. Reasoning about the state from causation and time in the medical domain. In: Proceedings American Association for Artificial Intelligence. Los Altos CA: Morgan Kaufmann Publ Inc; 1983: 251-4.
    Google Scholar
  • 29 Weiss SM, Kulikowski CA, Amarel S, Safir A. A model-based method for computer-aided medical decision making. Artif Intell. 1978. 11: 145-72.
    Google Scholar