Clinical decision support system

Clinical (or Diagnostic) Decision Support Systems (CDSS) are interactive computer programs that directly assist physicians and other health professionals with decision making tasks. These fall under the class of Decision support systems.

For medical diagnosis, there are scopes for ambiguities in inputs, such as history (patient’s description of the diseased condition), physical examinations (especially in cases of uncooperative or less intelligent patients), and laboratory tests (faulty methods or equipment). Moreover, for treatment, there are chances of drug reactions and specific allergies, and patients' non-compliance of the therapy due to cost or time or adverse reactions.

In all these areas, computers can help the clinician to reach an accurate diagnosis faster. Another new branch of medicine pharmacogenomics is the product of breeding between information technology and biology, leading to individualized treatment.

The basic components of a CDSS include a dynamic (medical) knowledge base and an inferencing mechanism (usually a set of rules derived from the experts and evidence-based medicine). It could be based on Expert systems or artificial neural networks or both (Connectionist expert systems).

CDSS may be linked to Electronic medical records, for decision making and also they could be used for practicing Evidence-based medicine in an automated way. However they are not meant to replace doctors, rather empower them to make better and more rational decisions.

The role of an apparently simple search by Google in pointing towards a better diagnosis has been emphasized by a recent publication [1].

Other uses

CDSS offer a powerful medical informatics tool that can be usefully applied to EBM practice. Other applications of informatics that are in ubiquitous in clinical practice nowadays are the use of resources like the Internet and PubMed to look up published medical information, journals and even patient related informational sites or support groups.

Methods of Decision Support

1. Rule-based expert systems, where predefined rules in the form of {if-else if-then}guide the decision making. Rules may also be obtained by various forms of decision trees (e.g., Iterative Dichotomizer or ID variants) or Bayesian networks. The early models for building a Knowledge Base and utilizing it for decision-making, were: (a) Logical / deductive: branching logic (e.g., ID3 or iterative dichotomizer 3); e.g., MYCIN, NEOMYCIN [Sotos 1990] (b) Probabilistic: Bayesian e.g., de Dombal [1995] and (c) Hybrid: heuristic reasoning e.g., QMR (Quick Medical Reference), DXplain, ILIAD

2. Artificial neural networks or ANNs (also referred to as connectionist architectures, parallel distributed processing, and neuromorphic systems), are information-processing paradigm inspired by the way the densely interconnected, massively parallel structure of the mammalian brain processes information. ANNs are collections of mathematical models that emulate some of the observed properties of biological nervous systems and draw on the analogies of adaptive biological learning. It behaves more or less like a black box where the reasoning for the correct classification is not known.

3. Connectionist expert systems, where the "inferencing" methods of the ANNs can be backtracked and "rules generation" is possible. This might actually lead to the enhancement and enrichment of the medical knowledge base itself.

4. Rule-based CDSS are the ones that are mostly found in the commercially available clinical informatics applications. Alerts for allergies and possible drug interactions, prompts for drug doses corrected for weight, height, sex, age and underlying clinical condition are the ones that are most commonly touted as CDSS. Arden Syntax was designed and developed for this very purpose. However, due to some issues related to its acceptance and standardization, it has not really been able to deliver on its immense promise. However, use of Evidence-based medicine (EBM) and Outcomes Analysis (OA) coupled with Bayesian Belief Networks (BBN) can allow for a highly accurate diagnostic tool and treatment planner to be made available in the hands of the healthcare providers.

5. BBN is a mathematical model for using AI (probabilistic) networks for predictive purposes. It is used in the CDSS module as an AI engine to help make probabilistic predictions based upon the observations made by the clinician. These could be used for diagnostics, treatment planning, and even predicting outcomes.

Further reading

1. Bergman LG, Fors UG, Computer-aided DSM-IV-diagnostics – acceptance, use and perceived usefulness in relation to users’ learning styles. BMC Med Inform Decis Mak. 2005; 5:1 2. Berner ES, et al, Performance of four computer-based diagnostic systems, N Engl J Med. 1994, 330: 1792-1796 3. de Dombal FT, Computer-aided diagnosis and medical decision support are not synonymous. Methods Inf Med. 1995; 34: 369-370 4. de Lusignan S, Lakhani M, Chan T, The role of informatics in continuing professional development quality improvement in primary care, J Postgrad Med, 2003, 49: 163 – 165. 5. Garg AX, et al, Effects of computerized clinical decision support systems on practitioner performance and patient outcomes: a systematic review. JAMA. 2005 293:1223-38. 6. Haynes RB, Of studies, syntheses, synopses, and systems: the “4S” evolution of services for finding current best evidence, Evidence-Based Medicine 2001; 6:36-38 http://ebm.bmjjournals.com/cgi/reprint/6/2/36 7. Hersh W, Medical informatics education: an alternative pathway for training informationists, J Med Libr Assoc, 2002, 90(1): 76 – 79. 8. Kavitha S, Sarbadhikari SN, Rao Ananth N, Implementation of Decision Tree Classifier Using Classification Algorithm for Some Inborn Errors of Metabolism, Proc. Global Convention and Exposition on Telemedicine and eHealth, New Delhi 17-22 August, 2006. 9. Kunnamo I, et al, 2005, National Decision support database based on computer-readable guidelines and using structured data from electronic patient records http://www.terveysportti.fi/pls/kotisivut/docs/f1917377807/ gin_poster_decision_support_v2.pdf (Accessed July 2006) 10. Lemaire JB, et al, Effectiveness of the Quick Medical Reference as a diagnostic tool, CMAJ • September 21, 1999; 161 (6) http://www.cmaj.ca/cgi/content/full/161/6/725 11. Master-Hunter T, Heiman DL, Amenorrhea: Evaluation and Treatment, American Family Physician, 2006, 73: 1374 – 1382 http://www.aafp.org/afp/20060415/1374.html 12. Mendelson D, Carino TV, Evidence-Based Medicine In The United States—De Rigueur Or Dream Deferred? Health Affairs, 2005, 24: 133 – 136. doi: 10.1377/hlthaff.24.1.133 13. Pradhan M, The Crystal Ball - The Future of Informatics and Decision Making, http://www.informatics.adelaide.edu.au/topics/DS/MP-CrystalBallTalk.html 2001 (Accessed July 2006) 14. Sackett DL, Straus SE, Richardson WS, Rosenberg W, Haynes RB. Evidence-based medicine: how to practice and teach EBM. 2nd ed. New York, NY: Churchhill Livingstone, 2000. 15. Sarbadhikari SN, “Medical Informatics — Are the Doctors Ready?” (Guest Editorial) J. Indian Med. Assoc. 1995, 93: 165 – 166. 16. Sarbadhikari SN, A CDSS for diagnosing amenorrhea www.geocities.com/drsupten 2006 17. Sarbadhikari SN, Basic Medical Education must include Medical Informatics, Indian J Physiol. Pharamcol., 2004a, 48(4): 395-408. 18. Sarbadhikari SN, The State of Medical Informatics in India: A Roadmap for optimal organization, J. Medical Systems, 2005, 29: 125-141. 19. Sarbadhikari, SN Automated diagnostic systems. Indian Journal of Medical Informatics, 2004b, 1: 25-28. [Also accessible at http://openmed.nic.in/218/] 20. Schwartz A, Millam G; A web-based library consult service for evidence-based medicine: Technical development, BMC Medical Informatics and Decision Making 2006, 6:16 doi: 10.1186/1472-6947-6-16 http://www.biomedcentral.com/1472-6947/6/16 21. Shearer BS, Seymour A, Capitani C. Bringing the best of medical librarianship to the patient team, J Med Libr Assoc 2001; 90: 22–31. 22. Sim I, Gorman P, Greenes RA, Haynes RB, Kaplan B, Lehmann H, Tang PC; Clinical decision support systems for the practice of evidence-based medicine, J Am Med Inform Assoc. 2001; 8:527-534. 23. Smith S, The Classification Algorithm http://www.cs.mdx.ac.uk/ staffpages/serengul/The.Classification.algorithm.htm (Accessed July 2006). 24. Sotos G, MYCIN and NEOMYCIN: two approaches to generating explanations in rule-based expert systems. Aviat Space Environ Med. 1990; 61: 950-954. 25. Steinberg EP, Luce BR, Evidence Based? Caveat Emptor! Health Affairs, 2005, 24: 80-92. doi: 10.1377/hlthaff.24.1.80 26. Tan K, Dear PR, Newell SJ, Clinical decision support systems for neonatal care. Cochrane Database Syst Rev. 2005 2: CD004211.

External links

• OpenClinical maintains an extensive archive of Artificial Intelligence systems in routine clinical use.
• Some useful links
• Prerequisites
• A chapter of a book
• Another book chapter
• A slide show
• A systematic review
• A white paper on the use of CDSS for the practice of EBM
• A recent paper showing that the computerized clinical decision support systems can improve existing antimicrobial management programs
• Improving Outcomes with Clinical Decision Support: An Implementer’s Guide is a new resource designed to help healthcare organizations use clinical decision support (CDS) to measurably improve key healthcare outcomes such as the quality, safety, and cost-effectiveness of care delivery.