Abstract
This chapter describes the aspects of clinical medicine as representing decision-making under uncertainty. It covers basic concepts relevant to medical decision-making such as probability, heuristics, and biases. It explains operating characteristics of diagnostic tests such as sensitivity, specificity, and receiver-operating characteristic curves, and describes their application to clinical practice and clinical research. It integrates these concepts into a discussion of Bayes’ theorem, and provides a background for understanding the quantitative basis of the field of biomedical informat ics.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Notes
- 1.
The test sensitivity and specificity used in 7 Example 3.1 are consistent with the reported values of the sensitivity and specificity of the PCR test for diagnosis of HIV early in its development (Owens et al. 1996b); the test now has higher sensitivity and specificity.
- 2.
In medicine, a sign is an objective physical finding (something observed by the clinician) such as a temperature of 101.2 °F. A symptom is a subjective experience of the patient, such as feeling hot or feverish. The distinction may be blurred if the patient’s experience also can be observed by the clinician.
- 3.
Note that pretest and post-test probabilities correspond to the concepts of prevalence and predictive value. The latter terms were used in 7 Chap. 2 because the discussion was about the use of tests for screening populations of patients; in a population, the pretest probability of disease is simply that disease’s prevalence in that population.
- 4.
We assume a Bayesian interpretation of probability; there are other statistical interpretations of probability.
- 5.
This example assumes that we have a perfect method (different from EIA) for determining the presence or absence of antibody. We discuss the idea of gold-standard tests in 7 Sect. 3.3.4. We have chosen the numbers in the example to simplify the calculations. In practice, the sensitivity and specificity of the HIV EIAs are greater than 99%.
- 6.
Volunteers are often healthy, whereas patients in the clinically relevant population often have several diseases in addition to the disease for which a test is designed. These other diseases may cause FP test results. For example, patients with benign (rather than malignant) enlargement of their prostate glands are more likely than are healthy volunteers to have FP elevations of prostate-specific antigen (Meigs et al. 1996), a substance in the blood that is elevated in men who have prostate cancer. Measurement of prostate-specific antigen is often used to detect prostate cancer.
- 7.
Some authors refer to this expression as the odds-likelihood form of Bayes’ theorem.
- 8.
In medicine, to rule in a disease is to confirm that the patient does have the disease; to rule out a disease is to confirm that the patient does not have the disease. A doctor who strongly suspects that his or her patient has a bacterial infection orders a culture to rule in his or her diagnosis. Another doctor is almost certain that his or her patient has a simple sore throat but orders a culture to rule out streptococcal infection (strep throat). This terminology oversimplifies a diagnostic process that is probabilistic. Diagnostic tests rarely, if ever, rule in or rule out a disease; rather, the tests raise or lower the probability of disease.
- 9.
Expected-value decision making had been used in many fields before it was first applied to medicine.
- 10.
A more general term for expected-value decision making is expected utility decision making. Because a full treatment of utility is beyond the scope of this chapter, we have chosen to use the term expected value.
- 11.
For this simple example, death during an interval is assumed to occur at the end of the year.
- 12.
QALYs commonly are used as measures of utility (value) in medical decision analysis and in health policy analysis.
- 13.
In a more sophisticated decision analysis, the clinician also would adjust the utility values of outcomes that require surgery to account for the pain and inconvenience associated with surgery and rehabilitation. Other approaches to assessing utility are available and may be preferable in some circumstances.
- 14.
An operative mortality rate of 25% may seem high; however, this value is correct when we use QALYs as the basis for choosing treatment. A decision maker performing a more sophisticated analysis could use a utility function that reflects the patient’s aversion to risking death.
References
Beck, J. R., & Pauker, S. G. (1983). The Markov process in medical prognosis. Medical Decision Making, 3(4), 419–458.
Eddy, D. M. (1992). A manual for assessing health practices and designing practice policies: The explicit approach. Philadelphia: American College of Physicians.
Habbema, J. D. F., Wilt, T. J., Etzioni, R., Nelson, H. D., Schechter, C. B., Lawrence, W. F., Melnikow, J., Kuntz, K. M., Owens, D. K., & Feuer, E. J. (2014). Models in the development of clinical practice guidelines. Annals of Internal Medicine, 161, 812–818.
Hellmich, M., Abrams, K. R., & Sutton, A. J. (1999). Bayesian approaches to meta-analysis of ROC curves. Medical Decision Making, 19, 252–264.
Joyce, V. R., Barnett, P. G., Bayoumi, A. M., Griffin, S. C., Kyriakides, T. C., Yu, W., Sundaram, V., Holodniy, M., Brown, S. T., Cameron, W., Youle, M., Sculpher, M., Anis, A. H., & Owens, D. K. (2009). Health-related quality of life in a randomized trial of antiretroviral therapy for advanced HIV disease. Journal of the Acquired Immunodeficiency Syndrome, 50, 27–36.
Joyce, V. R., Barnett, P. G., Chow, A., Bayoumi, A. M., Griffin, S. C., Sun, H., Holodniy, M., Brown, S. T., Cameron, D. W., Youle, M., Sculpher, M., Anis, A. H., & Owens, D. K. (2012). Effect of treatment interruption and intensification of antiretroviral therapy on health-related quality of life in patients with advanced HIV: A randomized controlled trial. Medical Decision Making, 32, 70–82.
Leeflang, M. (2014). Systematic reviews and meta-analysis of diagnostic test accuracy. Clinical Microbiology and Infection, 20, 105–113.
Leeflang, M. M. G., Deeks, J. J., Gatsonis, C., Bossuyt, P. M., & on behalf of the Cochrane diagnostic test accuracy working group. (2008). Systematic reviews of diagnostic tests. Annals of Internal Medicine, 149, 889–897.
Lenert, L. A., Michelson, D., Flowers, C., & Bergen, M. R. (1995). IMPACT: An object-oriented graphical environment for construction of multimedia patient interviewing software (pp. 319–323). Washington, D.C.: Proceedings of the Annual Symposium of Computer Applications in Medical Care.
Lin, J. K., Lerman, B. J., Barnes, J. I., Bourisquot, B. C., Tan, Y. J., Robinson, A. Q. L., Davis, K. L., Owens, D. K., & Goldhaber-Fiebert, J. D. (2018). Cost effectiveness of chimeric antigen receptor T-cell therapy in relapsed or refractory pediatric B-cell acute lymphoblastic leukemia. Journal of Clinical Oncology, 36, 3192–3202.
Meigs, J., Barry, M., Oesterling, J., & Jacobsen, S. (1996). Interpreting results of prostate-specific antigen testing for early detection of prostate cancer. Journal of General Internal Medicine, 11(9), 505–512.
Moses, L. E., Littenberg, B., & Shapiro, D. (1993). Combining independent studies of a diagnostic test into a summary ROC curve: Data-analytic approaches and some additional considerations. Statistics in Medicine, 12(4), 1293–1316.
Musen, M. A., Tu, S. W., Das, A. K., & Shahar, Y. (1996). EON: A component-based approach to automation of protocol-directed therapy. Journal of the American Medical Informatics Association: JAMIA, 3(6), 367–388.
Nease, R. F., Jr., & Owens, D. K. (1994). A method for estimating the cost-effectiveness of incorporating patient preferences into practice guidelines. Medical Decision Making, 14(4), 382–392.
Nease, R. F., Jr., & Owens, D. K. (1997a). Use of influence diagrams to structure medical decisions. Medical Decision Making, 17(13), 263–275.
Nease, R. F., Jr., Kneeland, T., O’Connor, G. T., Sumner, W., Lumpkins, C., Shaw, L., Pryor, D., & Sox, H. C. (1995). Variation in patient utilities for the outcomes of the management of chronic stable angina. Implications for clinical practice guidelines. Journal of the American Medical Association, 273(15), 1185–1190.
Neumann, P. J., Sanders, G. D., Russell, L. B., Siegel, J. E., & Ganiats, T. G. (Eds.). (2017a). Cost-effectiveness in health and medicine (2nd ed.). New York: Oxford University Press.
Owens, D. K. (1998). Patient preferences and the development of practice guidelines. Spine, 23(9), 1073–1079.
Owens, D. K., & Nease, R. F., Jr. (1993). Development of outcome-based practice guidelines: A method for structuring problems and synthesizing evidence. The Joint Commission Journal on Quality Improvement, 19(7), 248–263.
Owens, D. K., & Nease, R. F., Jr. (1997). A normative analytic framework for development of practice guidelines for specific clinical populations. Medical Decision Making, 17(4), 409–426.
Owens, D., Harris, R., Scott, P., & Nease, R. F., Jr. (1995). Screening surgeons for HIV infection: A cost-effectiveness analysis. Annals of Internal Medicine, 122(9), 641–652.
Owens, D. K., Holodniy, M., Garber, A. M., Scott, J., Sonnad, S., Moses, L., Kinosian, B., & Schwartz, J. S. (1996a). The polymerase chain reaction for the diagnosis of HIV infection in adults: A meta-analysis with recommendations for clinical practice and study design. Annals of Internal Medicine, 124(9), 803–815.
Owens, D. K., Holodniy, M., McDonald, T. W., Scott, J., & Sonnad, S. (1996b). A meta-analytic evaluation of the polymerase chain reaction (PCR) for diagnosis of human immunodeficiency virus (HIV) infection in infants. Journal of the American Medical Association, 275(17), 1342–1348.
Owens, D. K., Shachter, R. D., & Nease, R. F., Jr. (1997a). Representation and analysis of medical decision problems with influence diagrams. Medical Decision Making, 17(3), 241–262.
Owens, D. K., Whitlock, E. P., Henderson, J., Pignone, M. P., Krist, A. H., Bibbins-Domingo, K., Curry, S. J., Davidson, K. W., Ebell, M., Gilman, M. W., Grossman, D. C., Kemper, A. R., Kurth, A. E., Maciosek, M., Siu, A. L., LeFevre, M. L., & for the U.S. Preventive Services Task Force. (2016). Use of decision models in the development of evidence-based clinical preventive services recommendations: Methods of the U.S. Preventive Services Task Force. Annals of Internal Medicine, 165, 501–508.
Palda, V. A., & Detsky, A. S. (1997). Perioperative assessment and management of risk from coronary artery disease. Annals of Internal Medicine, 127(4), 313–328.
Pauker, S. G., & Kassirer, J. P. (1980). The threshold approach to clinical decision making. The New England Journal of Medicine, 34(5 Pt 2), 1189–1208.
Peabody, G. (1922). The physician and the laboratory. Boston Medical Surgery Journal, 187, 324.
Peterson, W., & Birdsall, T. (1953). The theory of signal detectability. (Technical Report No. 13.): Electronic Defense Group, University of Michigan, Ann Arbor.
Ransohoff, D. F., & Feinstein, A. R. (1978). Problems of spectrum and bias in evaluating the efficacy of diagnostic tests. The New England Journal of Medicine, 299(17), 926–930.
Salpeter, S. R., Sanders, G. D., Salpeter, E. E., & Owens, D. K. (1997). Monitored isoniazid prophylaxis for low-risk tuberculin reactors older than 35 years of age: A risk-benefit and cost-effectiveness analysis. Annals of Internal Medicine, 127(12), 1051–1061.
Sanders, G. D., Hagerty, C. G., Sonnenberg, F. A., Hlatky, M. A., & Owens, D. K. (1999). Distributed dynamic decision support using a web-based interface for prevention of sudden cardiac death. Medical Decision Making, 19(2), 157–166.
Sanders, G. D., Hlatky, M. A., & Owens, D. K. (2005). Cost effectiveness of the implantable cardioverter defibrillator (ICD) in primary prevention of sudden death. The New England Journal of Medicine, 353, 1471–1478.
Siebert, U., Alagoz, O., Bayoumi, A. M., Jahn, B., Owens, D. K., Cohen, D., et al. (2012). State-transition modeling: A report of the ISPOR-SMDM modeling good research practices task force-3. Medical Decision Making, 32, 690–700.
Smith, L. (1985). Medicine as an art. In J. Wyngaarden & L. Smith (Eds.), Cecil textbook of medicine. Philadelphia: W. B. Saunders.
Sonnenberg, F. A., & Beck, J. R. (1993). Markov models in medical decision making: A practical guide. Medical Decision Making, 13(4), 322–338.
Sox, H. C. (1987). Probability theory in the use of diagnostic tests: Application to critical study of the literature. In H. C. Sox (Ed.), Common diagnostic tests: Use and interpretation (pp. 1–17). Philadelphia: American College of Physicians.
Sox, H. C., Blatt, M. A., Higgins, M. C., & Marton, K. I. (1988). Medical decision making. Boston: Butterworth Publisher.
Stein, P. D., Fowler, S. E., Goodman, L. R., Gottschalk, A., Hales, C. A., et al. (2006). Multidetector computed tomography for acute pulmonary embolism. The New England Journal of Medicine, 354, 2317–2327.
Sumner, W., Nease, R. F., Jr., & Littenberg, B. (1991). U-titer: A utility assessment tool. In Proceedings of the 15th annual symposium on computer applications in medical care (pp. 701–705). Washington, DC.
Swets, J. A. (1973). The relative operating characteristic in psychology. Science, 182, 990.
Torrance, G. W., & Feeny, D. (1989). Utilities and quality-adjusted life years. International Journal of Technology Assessment in Health Care, 5(4), 559–575.
Tversky, A., & Kahneman, D. (1974a). Judgment under uncertainty: Heuristics and biases. Science, 185, 1124–1131.
Disclaimer
The views presented are solely the responsibility of the authors and do not necessarily represent the views of the Patient-Centered Outcomes Research Institute (PCORI), its Board of Governors, or its Methodology Committee.
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2021 Springer Nature Switzerland AG
About this chapter
Cite this chapter
Owens, D.K., Goldhaber-Fiebert, J.D., Sox, H.C. (2021). Biomedical Decision Making: Probabilistic Clinical Reasoning. In: Shortliffe, E.H., Cimino, J.J. (eds) Biomedical Informatics. Springer, Cham. https://doi.org/10.1007/978-3-030-58721-5_3
Download citation
DOI: https://doi.org/10.1007/978-3-030-58721-5_3
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-030-58720-8
Online ISBN: 978-3-030-58721-5
eBook Packages: MedicineMedicine (R0)