Interaction model

From Clinfowiki
Jump to: navigation, search

Clinical decision support (CDS) are rules in user interaction model for making clinical decisions. The rules are based on a large collection of medical knowledge and an accurate computer representation scheme.

Informaticians have been developing knowledge-based clinical decision support systems for over 30 years with many notable successes [1]

Nature of the medical decision

The key item that must be considered is the nature of the medical decision being made. Many medical decisions are based on numerous simple and widely agreed upon, rules that all clinicians know but have difficulty bringing to bear with 100% accuracy.

Examples of such decisions might include

  • Does this infant need an MMR vaccination today?
  • Do these particular arterial blood gas values represent a metabolic or respiratory acidosis?
  • Has the patient's sodium value fallen more than 25% over the last 12 hours?

These determinations are best implemented as interpretation or monitoring systems.

no clear cut solutions

Other decisions are fraught with complicated risk assessments and competing alternatives; they have no clear-cut "best" solutions. Such decisions are best implemented as critiquing systems. The consultation mode, on the other hand, has not met with much success in the clinical realm for the simple reason that clinicians are reluctant to spend extended periods of time entering data into a computer in order to receive advice. Finding the appropriate user interaction model is one of the most important, but often overlooked, tasks.

Teaching models

Any of the above mentioned interaction models can be enhanced by offering a "teaching mode" to the user. Such a mode would allow the system to "explain" its reasoning to the clinician. In a landmark article, Teach and Shortliffe stated that the ability of a system to "explain" its reasoning was one of the key factors in clinician acceptance of decision support systems [Teach, 1981]. Since that time many systems have been successfully deployed without this capability, although system developers are still encouraged to provide it when possible. Many developers skirt this issue by citing a scientific journal article or displaying the actual rules (along with the patient's data values) the system used to reach the conclusion.


Interpretation systems present information to clinicians passively. These systems can create relatively simple, yet nicely formatted clinical laboratory reports and graphs, or sophisticated interpretations of such things as electrocardiograms (EKGs) [Klingeman, 1967]. Interpretation systems work best when interfaced directly to the data generated by laboratory instruments that produce numeric data. In addition, there should be a well understood physiologic model in existence which unambiguously interprets the data. These systems have found their greatest clinical utility in areas such as arterial blood gas interpretation [Gardner, 1975], spirometry [Ostler, 1984], and automated PAP smear analysis [Wilbur, 1998], to name just a few.

  1. Klingeman J, Pipberger HV. Computer classifications of electrocardiograms. Comput Biomed Res 1967 Mar;1(1):1-17
  2. Gardner RM, Cannon GH, Morris AH, Olsen KR, Price WG: Computerized blood gas interpretation and reporting system. IEEE Computer 1975; 8:39-45.
  3. Ostler DV, Gardner RM, Crapo RO A computer system for analysis and transmission of spirometry waveforms using volume sampling. Comput Biomed Res 1984 Jun;17(3):229-40.
  4. Wilbur DC, Prey MU, Miller WM, Pawlick GF, Colgan TJ. The AutoPap system for primary screening in cervical cytology. Comparing the results of a prospective, intended-use study with routine manual practice. Acta Cytol 1998 Jan-Feb;42(1):214-20


Consultation systems carry on an interactive dialogue with clinicians in an attempt to help them arrive at a correct diagnoses or therapeutic decisions. These systems can be used by physicians to determine the test or procedure that will be most likely to help them confirm or rule out a specific diagnosis. One of the earliest consultation systems, MYCIN, was developed by Shortliffe in the early 1970s [Shortliffe, 1975]. Clinicians interacted with MYCIN through a long series of questions designed to elicit the patient's clinical state and then help the clinician select the appropriate antibiotic. More recently informaticians have utilized the consultation model for the implementation of clinical practice guidelines. Very few of these systems have met with extensive or even continued use in real-life clinical situations.

  1. Shortliffe EH, Davis R, Axline SG, Buchanan BG, Green CC, Cohen SN. Computer-based consultations in clinical therapeutics: explanation and rule acquisition capabilities of the MYCIN system. Comput Biomed Res 1975 Aug;8(4):303-20
  2. Reisman Y. [2] Computer-based clinical decision aids]. A review of methods and assessment of systems. Med Inf (Lond) 1996 Jul-Sep;21(3):179-97
  3. Teach RL, Shortliffe EH. An analysis of physician attitudes regarding computer-based clinical consultation systems. Comput Biomed Res 1981 Dec;14(6):542-58


Monitoring systems watch the clinical database for the storage of particular data items or the passage of a predetermined amount of time. Once such an item is stored in the database, a program is called which "decides" whether the particular data value (or combination of data values) warrants notifying a clinician.

Monitoring systems work best on problem areas in which the medical knowledge can be represented in one or more if-then-else type constructs. These systems have met with considerable success in areas as simple as the detection of abnormal laboratory results [Bradshaw, 1989] and adverse drug events [Classen, 1992] or as complicated as ventilator monitoring in ICU patients [Sittig, 1989]. Most clinicians find the "safety net" effect of such systems reassuring and more often than not are happy to comply with the computer's suggestion.

  1. Bradshaw KE, Gardner RM, Pryor TA. Development of a computerized laboratory alerting system. Comput Biomed Res 1989 Dec;22(6):575-87
  2. Classen DC, Pestotnik SL, Evans RS, Burke JP. Computerized surveillance of adverse drug events in hospital patients. JAMA 1991 Nov 27;266(20):2847-51 Published erratum appears in JAMA 1992 Apr 8;267(14):1922
  3. Sittig DF, Pace NL, Gardner RM, Beck E, Morris AH. Implementation of a computerized patient advice system using the HELP clinical information system. Comput Biomed Res 1989 Oct;22(5):474-87

Critiquing systems

Critiquing systems require that all the patient's clinical data, as well as the clinician's anticipated action be available in the computer. The critiquing system then generates a review of this decision based on its "understanding" of the patient's underlying patho-physiological condition and the risks associated with the planned therapeutic alternative chosen [Miller, 1983]. Such systems have met with their greatest success when incorporated into physician order entry systems. In such cases they can inform physicians of potential drug-drug, drug-lab, or drug-allergy interactions, as well as suggest less expensive alternatives. Given the diagnosis the physician is attempting to confirm or rule-out, a critiquing system might mention a more appropriate radiological exam [Harpole, 1997]. The management of a patient's hypertension [Miller, 1984] is another excellent example of a medical decision which begs for a critiquing system.

  1. Miller PL. Critiquing anesthetic management: the "ATTENDING" computer system. Anesthesiology. 1983 Apr;58(4):362-9.
  2. Miller PL, Black HR. Medical plan-analysis by computer: critiquing the pharmacologic management of essential hypertension. Comput Biomed Res. 1984 Feb;17(1):38-54.
  3. Harpole LH, Khorasani R, Fiskio J, Kuperman GJ, Bates DW. Automated evidence-based critiquing of orders for abdominal radiographs: impact on utilization and appropriateness. J Am Med Inform As# soc 1997 Nov-Dec;4(6):511-21

Clinical practice guidelines

Clinical practice guidelines aim to reduce the number of medical errors and practice variation. Guidelines with a national scope concerning important medical issues or disease domains represent one of the highest forms of practice policies. In traditional form, guidelines have been narrative / textual in composition, and have typically been created under the control of medical specialty organizations. Narrative guidelines are time- and resource-intensive in their creation and maintenance, and are limited in value by failing to provide specific recommendations in a given clinical scenario.(1) On the other hand, computer-interpretable guidelines (CIGs) can produce personalized recommendations during patient encounters, which render them more likely to affect provider behavior than standard narrative guidelines.(2)

Representing guidelines

The process of formally representing knowledge in CIGs is required to render the information computable.(3) Formal representation removes ambiguities that are present in the 'relaxed language' of narrative guidelines, and permit identification of for which information is lacking or missing. The formalization process that converts narrative guidelines to CIGs involves 'marking-up' narrative text and indicating relationships with certain structural components of the guideline, according to markup ontologies.(4) CIGs can also be created de novo using one of several modeling methods (ex. Asbru, EON, PRODIGY, GLIF, SAGE, PROforma, Arden Syntax, GLARE, GASTON, OncoDoc).(4) A review by Peleg and colleagues identified eight components that define the architecture of CIGs.(5) These components can be divided into two groups - those functioning to create decisions and actions, and those linking the guideline to clinical data and medical concepts.(4)


However, CIGs, like traditional narrative guidelines, are subject to some limitations. Unlike the concept of standards, where recommendations are so well-founded that the vast majority of clinicians would be expected to agree and adhere to them, guidelines allow a greater degree of allowance for interpretation and acceptance.(1) Consequently, guidelines are rendered less powerful in the mission to improve care through reducing practice variation. Other challenges include the debate over whether a standards-based approach might be helpful in the development of guidelines and their components. Another need exists for the development of workflow solutions to allow for guideline use within clinical information systems.(4)

Although guideline recommendations and algorithms are based on evidence, they may not integrate well with the provider's cognitive processes or clinical flow characteristics during a patient encounter. Progress will need to be made in the challenge to encode complex medical thinking. Chris Tessier MBI 512 Fall 2008

  1. Emberton M. Clinical practice guidelines for the surgeon-how should they be understood and applied? BJU International 2001; 88(6):485-492.
  2. Peleg M., Patel V.L., Tu S. et al. Support for guideline development through error classification and constraint checking. Proc AMIA Symp 2002:607-611.
  3. Kaiser K., Akkaya C., and Miksch S. How can information extraction ease formalizing treatment processes in clinical practice guidelines? A method and its execution. Artificial Intelligence in Medicine 2007; 39:151-163.
  4. Peleg M.(2007) Guidelines and Workflow Models. In R.A. Greenes (Ed.), Clinical Decision Support - The Road Ahead (p 282-303). Boston, MA: Elsevier.
  5. Peleg M., Tu S., Bury J., et a. Comparing computer-interpretable guideline models: A case-study approach. JAMIA 2003; 10(1): 52-68.


Artificial intelligence

Artificial intelligence is a system that was developed by a team of system engineers and clinicians. The system would take some of the workload from medical teams by assisting the physicians with tasks like diagnosis & Therapy recommendations.

An AI system could be running within electronic medical record system, and alert a clinician when it detects a contraindication to a planned treatment. It could also alert the clinician when it detected patterns in clinical data that suggested significant changes in a patient’s condition. The definition of artificial intelligence has changed over the years, since 1956 till now. It is mostly found in data rich areas like intensive care settings There are many different types of clinical task to which Artificial intelligence can be applied.

  1. Monitoring patients vital signs and then evaluating and administering the right amounts of different drugs needed
  2. Planning an adequate nutritional support for maintaining the metabolic needs of newborn infants. Control of the level of pressure support ventilation.
  3. Reading of the electrocardiogram (ECG).

There are numerous reasons why more expert systems are not in routine use. Some require the existence of an electronic medical record system to supply their data and most institutions do not yet have all their working data available electronically. Much of the difficulty has been the poor way in which they have fitted into clinical practice, which required additional effort from already busy individuals.

Examples of AI that are still in practice samrtcare/pc ventilator manager, 2004. VIE-PNN Neo-natal parentral nutrition 1993. Examples of decommissioned AI are: N‘eoGaneshVentilator manager, 1992. ACORN Coronary care admission ,1987. By Bassima Hammoud

See also Artificial intelligence in healthcare- IBM Watson