Download PDF
CC BY-NC-ND 4.0 · Yearb Med Inform 2019; 28(01): 249-256
DOI: 10.1055/s-0039-1677895
History of Medical Informatics
Georg Thieme Verlag KG Stuttgart

Beginnings of Artificial Intelligence in Medicine (AIM): Computational Artifice Assisting Scientific Inquiry and Clinical Art – with Reflections on Present AIM Challenges

Casimir A. Kulikowski
1   Department of Computer Science, Rutgers University, USA
› Author Affiliations
Further Information

Publication History

Publication Date:
25 April 2019 (online)

   Permissions and Reprints

Summary

Background: The rise of biomedical expert heuristic knowledge-based approaches for computational modeling and problem solving, for scientific inquiry and medical decision-making, and for consultation in the 1970’s led to a major change in the paradigm that affected all of artificial intelligence (AI) research. Since then, AI has evolved, surviving several “winters”, as it has oscillated between relying on expensive and hard-to-validate knowledge-based approaches, and the alternative of using machine learning methods for inferring classification rules from labelled datasets. In the past couple of decades, we are seeing a gradual but progressive intertwining of the two.

Objectives: To give an overview of early directions in AI in medicine and threads of some subsequent developments motivated by the very different goals of scientific inquiry for biomedical research, and for computational modeling of clinical reasoning and more general healthcare problem solving from the perspective of today’s “AI-Deep Learning Boom”. To show how, from the beginning, AI was central to Biomedical and Health Informatics (BMHI), as a field investigating how to understand intelligent thinking in dealing professionally with the practice for healthcare, developing mathematical models, technology, and software tools to aid human experts in biomedicine, despite many previous bouts of “exuberant optimism” about the methodologies deployed.

Methods: An overview and commentary on some of the early research and publications in AI in biomedicine, emphasizing the different approaches to the modeling of problems involved in clinical practice in contrast to those of biomedical science. A concluding reflection of a few current challenges and pitfalls of AI in some biomedical applications.

Conclusion: While biomedical knowledge-based systems played a critical role in influencing AI in its early days, 50 years later they have taken a back seat behind “Deep Learning” which promises to discover knowledge structures for inference and prediction, both in science and for clinical decision-support. Early work on AI for medical consultation turned out to be more useful for explanation and teaching than for clinical practice, as had been originally intended. Today, despite the many reported successes of deep learning, fundamental scientific challenges arise in drawing on models of brain science, cognition, and language, if AI is to augment and complement rather than replace human judgment and expertise in biomedicine while also incorporating these advances for translational medicine. Understanding clinical phenotypes and how they relate to precision and personalization of care requires not only scientific inquiry, but also humanistic models of treatment that respond to patient and practitioner narrative exchanges, since it is the stories and insights of human experts which encourage what Norbert Weiner termed the ethical “human use of human beings”, so central to adherence to the Hippocratic Oath

Keywords

Artificial Intelligence in medicine - medical decision-making - clinical knowledge representation - expert systems - knowledge engineering - scientific inquiry - cognitive and brain science
 

  • References

  • 1 November J. Biomedical Computing: Digitizing Life in the United States. Baltimore: The Johns Hopkins University Press; 2012
    Google Scholar
  • 2 Buchanan BG, Sutherland G, Feigenbaum EA. Rediscovering some problems of artificial intelligence in the context of organic chemistry. In: Meltzer B, Michie D. editors. Machine Intelligence. Edinburgh: Edinburgh University Press; 1970
    Google Scholar
  • 3 Nash FA. Differential Diagnosis, an apparatus to assist the logical faculties. Lancet 1954; 266: 874-5
    PubMedGoogle Scholar
  • 4 Ledley RS, Lusted LB. Reasoning Foundations of Medical Diagnosis. Science 1959; 130: 9-21
    CrossrefPubMedGoogle Scholar
  • 5 Warner HR, Toronto AF, Veasy LG, Stephenson R. A mathematical approach to medical diagnosis. Application to congenital heart disease. JAMA 1961; 177: 177-83
    CrossrefPubMedGoogle Scholar
  • 6 Overall JE, Williams CM. Models for medical diagnosis. Behav Sci 1961; 6: 134-41
    PubMedGoogle Scholar
  • 7 Oberhoffer G. Report on an international seminar for medical documentation and statistics. Methods Inf Med 1962; 1: 27-31
    PubMedGoogle Scholar
  • 8 Waxman BD. Public Health Service support of biomedical computing. Proceedings 3rd IBM Medical Symposium Endicott, NY: IBM; 1961; 199-202
    PubMedGoogle Scholar
  • 9 Engle RL, Davis BJ. Medical Diagnosis: Past, Present and Future: III: Diagnosis in the future, including a critique on the use of electronic computers as diagnostic aids to the clinician. Arch Int Med 1963; 112: 530-43
    CrossrefPubMedGoogle Scholar
  • 10 Jacquez JA. The Diagnostic Process: Proceedings of a Conference at the University of Michigan. 1963
    PubMedGoogle Scholar
  • 11 Feinstein AR. Boolean algebra and clinical taxonomy I. Analytical synthesis of the general spectrum of a human disease. New Eng J Med 1963; 269: 929-38
    CrossrefPubMedGoogle Scholar
  • 12 Collen MF, Rubin L, Neyman J, Dantzig GB, Baer RM, Siegelauf AB. Automated multiphasic screening and diagnosis. Am J Public Health 1964; 54: 741-50
    PubMedGoogle Scholar
  • 13 Enslein K. editor. Data Acquisition and Processing in Biology and Medicine. New York: Pergamon; 1964
    Google Scholar
  • 14 Ledley RS. Use of Computers in Biology and Medicine. New York: McGraw Hill; 1965
    Google Scholar
  • 15 Collen M. Automated multiphasic screening as a diagnostic method for preventive medicine. Methods Inf Med 1965; 4: 71-4
    Article in Thieme ConnectPubMedGoogle Scholar
  • 16 Stacy RW, Waxman BD. editors. Computers in Biomedical Research. New York: Academic Press; 1965
    Google Scholar
  • 17 Baruch JJ, Barnett GO. Real-time shared on-line digital computer operations. J Chron Dis 1966; 19: 377-86
    CrossrefPubMedGoogle Scholar
  • 18 Gremy F, Joly Pages JC. Application des machines à traiter l’information au diagnostic médical, in Medicine Cybernetique: Actes du IV Congrès International de Médecine Cybernétique. Nice 1966; 289-97
    PubMedGoogle Scholar
  • 19 Lusted LB. Introduction to Medical Decision Making. Springfield, IL: Charles C. Thomas; 1968
    Google Scholar
  • 20 Gorry GA, Barnett GO. Experience with a model of medical diagnosis. Comp Biomed Res 1968; 1 (05) 490-507
    CrossrefPubMedGoogle Scholar
  • 21 Lindberg DAB. The Computer and Medical Care. Springfield, IL: Charles C. Thomas; 1968
    Google Scholar
  • 22 Kulikowski CA. A pattern recognition approach to medical diagnosis. IEEE Trans Syst Science & Cybernetics 1970; SSC-6 (03) 173-8
    PubMedGoogle Scholar
  • 23 Freiherr G. The seeds of Artificial Intelligence - SUMEX-AIM, NIH Division of Research Resources Report, Bethesda, MD; 1980
    PubMed
  • 24 Kulikowski CA. Opening Chapter of the First Generation of Artificial Intelligence in Medicine: The First Rutgers AIM Workshop, June 1975. Yearb Med Inform 2015; 10: 227-33
    Article in Thieme ConnectPubMedGoogle Scholar
  • 25 Feigenbaum EA. Knowledge Engineering: The Applied Side of Artificial Intelligence. Ann N Y Acad Sci 1984; 426: 91-107
    CrossrefPubMedGoogle Scholar
  • 26 Clancey WJ, Shortliffe EH. editors. Readings in Medical Artificial Intelligence: The First Decade. Reading, MA: Addision-Wesley; 1984
    Google Scholar
  • 27 Weiss SM, Kulikowski CA. A Practical Guide to Designing Expert Systems. Totowa, NJ: Rowman and Allanheld; 1984
    Google Scholar
  • 28 Feigenbaum EA, McCorduck P. The Fifth Generation: Artificial Intelligence and Japan’s Computer Challenge to the World. Reading, MA: Addison-Wesley; 1983
    Google Scholar
  • 29 Wikipedia entry for AI Winter: https://en.wikipedia.org/wiki/AI_winter
    PubMed
  • 30 Minsky M. Perceptrons. MIT Press 1968
    PubMed
  • 31 Lighthill J. Artificial Intelligence: A General Survey, Science Research Council (UK). 1972 https://en.wikipedia.org/wiki/Lighthill_repor
    PubMedGoogle Scholar
  • 32 Clancey WJ. The epistemology of a rule-based expert system —a framework for explanation. Artificial Intelligence 1983; 20 (03) 215-51
    CrossrefPubMedGoogle Scholar
  • 33 Blois M. Information and Medicine: The Nature of Medical Descriptions. CA: University of California Press; 1984
    Google Scholar
  • 34 Weiss S, Kulikowski CA. Computer Systems that Learn: Classification and Prediction Methods from Statistics, Neural Nets, Machine Learning, and Expert Systems. CA: Morgan Kaufmann; 1991
    Google Scholar
  • 35 Russell S, Norvig P. Artificial Intelligence: A Modern Approach, 3rd Edition. Pearson 2010
    PubMedGoogle Scholar
  • 36 Sejnowski TJ. The Deep Learning Revolution: artificial intelligence meets human intelligence. Cambridge, MA: MIT Press; 2018
    Google Scholar
  • 37 Rosse C, Mejino JL. A reference ontology for biomedical informatics: the Foundational Model of Anatomy. J Biomed Inform 2003; 36 (06) 478-500
    CrossrefPubMedGoogle Scholar
  • 38 Ochs C, Geller G, Perl Y, Musen MA. A unified software framework for deriving, visualizing, and exploring abstraction networks for ontologies. J Biomed Inform 2016; 62: 90-105
    CrossrefPubMedGoogle Scholar
  • 39 Rector AL, Nowlan WA. The GALEN project. Comput Methods Programs Biomed 1994; 45 (1-2) 75-8
    CrossrefPubMedGoogle Scholar
  • 40 Rector AL, Zanstra PE, Solomon WD, Rogers JE, Baud R, Ceusters W. et al. Reconciling users’ needs and formal requirements: issues in developing a reusable ontology for medicine. IEEE Trans Inf Technol Biomed 1998; Dec 2 (04) 229-42
    CrossrefPubMedGoogle Scholar
  • 41 Taine SI. The Medical Literature Analysis and Retrieval System (MEDLARS) of the U. S. National Library of Medicine. Methods Inf Med 1963; 2 (02) 65-9
    Article in Thieme ConnectPubMedGoogle Scholar
  • 42 Lindberg DA. Internet access to the National Library of Medicine. Eff Clin Pract 2000; 3 (05) 256-60
    PubMedGoogle Scholar
  • 43 Lindberg DA, Humphreys BL, McCray AT. The Unified Medical Language System. Methods Inf Med 1993; 32 (04) 281-91
    Article in Thieme ConnectPubMedGoogle Scholar
  • 44 Pearl J. The Book of Why: The New Science of Cause and Effect. New York: Basic Books; 2018
    Google Scholar
  • 45 Soo V-W, Kulikowski CA, Garfinkel D, Garfinkel L. Theory formation in postulating enzyme kinetic mechanisms: Reasoning with constraints. Comput Biomed Res 1988; 21 (04) 381-403
    CrossrefPubMedGoogle Scholar
  • 46 Butte AJ, Kohane I. Mutual information relevance networks: functional genomic clustering using pairwise entropy measurements. Biocomputing 2000; 418-29
    PubMedGoogle Scholar
  • 47 Cancer Genome Atlas Research Network. Comprehensive genomic characterization defines human glioblastoma genes and core pathways. Nature 2008; 455 (2216) 1061-8
    PubMedGoogle Scholar
  • 48 Murphy SG, Weber G, Mendis M, Gainer V, Chueh HC, Churchill S. et al. Serving the enterprise and beyond with informatics for integrating biology and the bedside (i2b2). J Am Med Inform Assoc 17 (02) 124-30
    PubMedGoogle Scholar
  • 49 Lederberg J. How Dendral Was Conceived and Born. ACM Symposium on the History of Medical Informatics, 5 November 1987. National Library of Medicine 1987
    PubMed
  • 50 Weiner N. Cybernetics or Control and Communication in the Animal and the Machine. New York: MIT Press and J Wiley; 1948
    Google Scholar
  • 51 McCulloch W, Pitts W. A logical calculus of the ideas immanent in nervous activity. Bull Math Biophys 1943; 5: 115-16
    CrossrefPubMedGoogle Scholar
  • 52 Masturzo A. Cybernetic Medicine. Springfield, IL: Charles C Thomas; 1965
    Google Scholar
  • 53 Hansen T. Proceedings of the First International Hospital Data Processing Conference, Elsinore. 1966
    PubMedGoogle Scholar
  • 54 Newell A, Shaw JC, Simon HA. Report on a General Problem Solving Program. Proc Int Conf Information Processing 1959; 256-64
    PubMedGoogle Scholar
  • 55 Samuel AL. Some Studies in Machine Learning Using the Game of Checkers. IBM J Res Dev 1959; 3: 210-29
    CrossrefPubMedGoogle Scholar
  • 56 Simon H. The Sciences of the Artificial. MIT Press 1969
    PubMedGoogle Scholar
  • 57 Newell A, Simon H. Computer Science as Empirical Inquiry: Symbols and Search. Communications ACM 1976; 19 (03) 113-26
    CrossrefPubMedGoogle Scholar
  • 58 Feigenbaum EA, Feldman AJ. Computers and Thought. New York: Mc-Graw Hill; 1963
    Google Scholar
  • 59 Amarel S. On the Representation of Problems and Goal-Directed Procedures for Computers. In: Theoretical Approaches to Non-Numerical Problem Solving 1969: 179-244
    PubMedGoogle Scholar
  • 60 Amarel S. Computer-based modeling and interpretation in medicine and psychology; the Rutgers Research Resource. In: Siler W, Lindberg DAB. editors. Computers in Life Science Research. FASEB Monographs, vol 2. Springer, Boston, MA: Springer; 1974
    Google Scholar
  • 61 Feigenbaum EA. SUMEX: Stanford Medical Experimental Computer Resource, Annual Report Year 6, May 1979 https://profiles.nlm.nih.gov/ps/access/BBGHML.pdf
    PubMed
  • 62 Rindfleisch TC. SUMEX-AIM Resource (1973 – 1992), https://www.tcracs.org/tcrwp/biosketch/sumex-aim/
    PubMed
  • 63 Szolovits P. editor. Artificial Intelligence in Medicine, AAAS Selected Symposium. Westview Press; 1982
    PubMedGoogle Scholar
  • 64 Schwartz WB. Medicine and the Computer - The problems and promise of change. N Engl J Med 1970; 283: 1257-64
    CrossrefPubMedGoogle Scholar
  • 65 Greenes RA, Buchanan BG, Ellison D. Presentation of the 2006 Morris F. Collen Award to Edward H. (Ted) Shortliffe. J Am Med Infor Assoc 2007; May-Jun; 14 (03) 376-85
    PubMedGoogle Scholar
  • 66 Cohen SN, Armstrong MF, Briggs RL, Chavez-Pardo R, Feinberg LS, Hannigan JF. et al. Computer-based monitoring and reporting of drug interactions. Proc Medinfo 1974; 74: 889-94
    PubMedGoogle Scholar
  • 67 Shortliffe EH, Axline SG, Buchanan BG, Merigan TC, Cohen SN. An artificial intelligence program to advise physicians regarding antimicrobial therapy. Comput Biomed Res 1973; 6: 544-60
    CrossrefPubMedGoogle Scholar
  • 68 Shortliffe EH. Computer-Based Medical Consultation. Mycin: New York: Elsevier; 1976
    Google Scholar
  • 69 Shortliffe EH, Buchanan BG. A model of inexact reasoning in medicine. Math Biosci 1975; 23 (3-4) 351-79
    CrossrefPubMedGoogle Scholar
  • 70 Safir A, Kulikowski CA, Crocetti AF, Kuo MI, Deuschle K. A New Method of Vision Care Delivery: A Pilot Study. Health Services Reports 1973; 88 (05) 405-15
    CrossrefPubMedGoogle Scholar
  • 71 Kulikowski CA, Weiss SM. Strategies of data base utilization in sequential pattern recognition. Proc IEEE Conf Decision and Control 1972: 103
    PubMedGoogle Scholar
  • 72 Weiss SM. A system for model-based computer-aided diagnosis and therapy. Thesis, Rutgers University 1974
    PubMedGoogle Scholar
  • 73 Weiss SM, Kulikowski CA, Amarel S, Safir A. A model-based method for computer-aided medical decision-making. Artif Intell 1978; 11: 145-72
    CrossrefPubMedGoogle Scholar
  • 74 Weiss SM, Kulikowski CA, Safir A. Glaucoma consultation by computer. Comput Biol Med 1978; 8: 25-40
    CrossrefPubMedGoogle Scholar
  • 75 Weiss SM, Kulikowski CA, Safir A. model-based consultation system for the long-term management of glaucoma. Proc Int Joint Conf AI (IJCAI) 1977; 826-31
    PubMedGoogle Scholar
  • 76 Pople H. On the mechanization of abductive logic. Proc IJCAI 1973: 146 62
    PubMedGoogle Scholar
  • 77 Miller RA, Pople HE, Myers JD. INTERNIST-1, An Experimental Computer-Based Diagnostic Consultant for General Internal Medicine. N Eng J Med 1982; 307: 478-86
    PubMedGoogle Scholar
  • 78 Myers JD. The Background of INTERNIST-I and QMR. In: Blum B, Duncan K. editors A History of Medical Informatics. New York: ACM Press; 1990. p. 427-33
    CrossrefGoogle Scholar
  • 79 Szolovits P, Pauker SG. Categorical and probabilistic reasoning in medical diagnosis. Artif Intell 1978; 11: 115-44
    CrossrefPubMedGoogle Scholar
  • 80 Patil RS, Szolovits P, Schwartz WB. Causal Understanding of patient illness in medical diagnosis. Proc 7th Int Joint Conf Artif Intell 1981; 893-9
    PubMedGoogle Scholar
  • 81 Clancey WJ. Tutoring rules for guiding a case method dialogue. Int J Man-Machine Studies 1979; 11: 25
    CrossrefPubMedGoogle Scholar
  • 82 Kuhn T. The Structure of Scientific Revolutions. Chicago, IL: Univ of Chicago Press; 1962
    Google Scholar
  • 83 Sharp B, Sedes F, Lubaszewski W. Cognitive Approach to Natural Language Processing. Elsevier 2017
    PubMedGoogle Scholar
  • 84 Sharp B. Towards a Cognitive Natural Language Processing Perspective. In: Gala N, Rapp R, Bel-Enguix G. editors. Language Production, Cognition, and the Lexicon. Text, Speech and Language Technology, vol 48. Cham: Springer; 2015
    PubMedGoogle Scholar
  • 85 Slotnick SD. Cognitive Neuroscience of Memory. Cambridge Univ Press; 2017
    PubMedGoogle Scholar
  • 86 Jackendoff R. Language, Consciousness, Culture: Essays on Mental Structure. MIT Press; 2007
    PubMedGoogle Scholar
  • 87 Polycretis I, Ivanov V, Michimizos KP. A Neural-Astrocytic Network Architecture: Astrocytic calcium waves modulate synchronous neuronal activity. Proc Int Conf Neuromorphic Syst, Knoxville, TN; 2018
    PubMedGoogle Scholar
  • 88 Smith TL. Making Truth: Metaphor in Science. Urbana & Chicago: Univ Illinois Press; 2003
    Google Scholar
  • 89 Lakoff G, Nunez RE. Where Mathematics Comes From: How the Embodied Mind Brings Mathematics into Being. Basic Books; 2000
    PubMedGoogle Scholar
  • 90 Kovecses Z. Language, Mind, and Culture. Oxford Univ Press; 2006
    PubMedGoogle Scholar
  • 91 Kandel E. Reductionism in Art and Brain Science. Columbia Univ Press; 2016
    PubMedGoogle Scholar
  • 92 Kulikowski CA. Narrative, Memory, Clinical Cognition, and Scientific Evidence: Just how data – driven can AI and Clinical Decision Support Be?. Presentation at the American College of Medical Informatics (ACMI) Winter Symposium, Fort Pierce, FL ; January 2019
    PubMedGoogle Scholar
  • 93 Maojo V, Kulikowski CA. Bioinformatics and Medical Informatics: Collaborations on the Road to Genomic Medicine?. J Am Med Inform Assoc 2003; 10 (06) 515-22
    CrossrefPubMedGoogle Scholar
  • 94 Charon R. Narrative Medicine: Honoring the Stories of Illness. Oxford University Press; 2006
    PubMedGoogle Scholar
  • 95 Charon R. Principles and Practice of Narrative Medicine. Oxford Univ Press; 2017
    PubMedGoogle Scholar
  • 96 Tountas Y. The historical origins of the basic concepts of health promotion and education: the role of ancient Greek philosophy and medicine. Health Promot Int 2009; 24 (02) 185-92
    CrossrefPubMedGoogle Scholar
  • 97 Hippocrates. Of the Epidemics (Adams F, Translation) Online Version: http://classics.mit.edu/Hippocrates/epidemics.1.i.html
    PubMed
  • 98 Shmerling RH. First Do No Harm, Harvard Health Blog, October 14, 2015, online: https://www.health.harvard.edu/blog/first-do-no-harm-201510138421
    PubMed
  • 99 Jotterand F. The Hippocratic Oath and Contemporary Medicine: Dialectic Between Past Ideals and Present Reality?. J Med Philos 2005; 30 (01) 107-28
    CrossrefPubMedGoogle Scholar
  • 100 Rosenbaum L. Transitional chaos or enduring harm? The EHR and the disruption of medicine. N Engl J Med 2015; 373: 1585-8
    CrossrefPubMedGoogle Scholar
  • 101 Sittig DF, Singh H. A new sociotechnical model for studying health information technology in complex adaptive healthcare systems. Qual Saf Health Care 2010; 19 (Suppl 3) i68-i74
    CrossrefPubMedGoogle Scholar
  • 102 Coeira E, Aarts J, Kulikowski CA. The dangerous decade. J Am Med Inform Assoc 2012; 19 (01) 2-5
    CrossrefPubMedGoogle Scholar
  • 103 Coeira E, Baker M, Magrabi F. First Compute No Harm. The British Medical Journal Opinion; Online: https://blogs.bmj.com/bmj/2017/07/19/enrico-coiera-et-al-first-compute-no-harm/
    PubMedGoogle Scholar
  • 104 Davies M, Srinivas N, Lin T-H, Chinya G, Cao Y, Choday SH. et al Loihi: A neuromorphic manycore processor with on-chip learning. IEEE Micro 2018; 38 (01) 82-99
    CrossrefPubMedGoogle Scholar
  • 105 Weiner N. The Human Use of Human Beings: Cybernetics and Society. Boston: Houghton-Mifflin; 1954. Unabridged authorized republication by DaCapo Press Series in Science; 1988
    PubMedGoogle Scholar