Reply to Student #1

I agree with your statement that diagnosis is a process, not a destination. Too often diagnosis is regarded as giving the clinician a definite ‘end point,’ which means that although the initial diagnosis might be faulty and based upon incomplete data, there is always a temptation to subsume all information under the initial diagnostic label. Clinical Decision Support Systems CDSS may be based upon scientifically and mathematically reputable tools such as Bayes’ Theorem. But this does not mean that such systems are error-free when interacting with ‘real world’ complaints.

Bayes’ Theorem is used when “several alternative hypotheses are competing” and then the clinician conducts experimental tests to observe whether or not those consequences can or are likely to actually occur in the specific situation at hand (Pezzullo 2010). The tools of observation and experimentation must be accurately deployed by the observer, in this case the medical practitioner. Clinicians must use CDSS responsibility, in the context of ever-changing information and also their own instincts regarding the patient. While a database’s computation of probabilities may contain thousands of potential symptoms, causes, and diagnoses, ultimately the observer makes the decision as to how to test and interpret the data.

The American College of Medical Informants states: “CDS has been effective in improving outcomes at some health care institutions and practice sites by making needed medical knowledge readily available to knowledge users. Yet at many other sites, CDS has been problematic, stalled in the planning stages, or never even attempted.” Knowledge within medical databases such as CDSS must be useful, pertinent, easily searchable, and continuously updated. There is always a danger that with the increasingly pressed time constraints for doctors and nurses, the use of the tool will come to subsume the need for human efforts, input, and on-the-ground knowledge.

References

CDS Roadmap. (2006). American College of Medical Informants. Retrieved May 19, 2010 at https://www.amia.org/files/cdsroadmap_exec_summary.pdf

Pezzullo, John C. (2010, May 15). Bayes Theorem calculator. Interactive statistics.

Retrieved May 19, 2010 at http://statpages.org/bayes.html

Reply student #2

I think that your post highlights something very common amongst both practitioners and patients: the desire for diagnosis to be as an exact a science as physics or astronomy. It would be so nice to be able to discover the cause of a patient’s illness as easily as figuring out a scientific equation. However, while the diagnostic process invariably involves scientific facts and figures, diagnosis is just as much an art as a science. Past experience and gut instincts also play a role, and every clinician has his or her own methodology. Even the context of where the patient is seen may impact the assessment: a patient who is treated in the ER will receive less personalized care than someone seen by a specialist for the same complaint.

Are Diagnostic Decision Support Systems (DDSS) the solution? They can make medical treatment more standardized, by using data-driven analysis based upon a wealth of experience much greater than one clinician can possess. However, not all DDSS systems may be equally effective. According to Bravata (et al. 2004): “Systems specifically designed to support the diagnosis of bioterrorism-relevant diseases or syndrome” were deemed “critically deficient,” and as “false-positive and false-negative rates are unknown for most systems, decision making on the basis of these systems is seriously compromised.” Not all DDSS systems are created equal, especially systems designed to give advice in extraordinary circumstances: the information sources within the DDSS database may be more limited.

For any illness, being too focused on common probabilities of causation can cause clinicians to overlook data that does not fit in with their original interpretation of the patient’s illness. Using DDSS before getting to know the patient can cause significant ‘eccentric’ symptoms to be overlooked, as DDSS may bias the practitioner in favor of diagnosing common illnesses. “With all the tools available to modern medicine — the blood tests and M.R.I.’s and endoscopes — you might think that misdiagnosis has become a rare thing. But you would be wrong. Studies of autopsies have shown that doctors seriously misdiagnose fatal illnesses about 20% of the time. So millions of patients are being treated for the wrong disease” (Leonhardt 2006). Technology is never a substitute; it is merely a complement for the human side of medicine.

References

Bravata, Sundaram V., K.M. McDonald, W.M. Smith, H. Szeto, M.D. Schleinitz, et al.

(2004, January). Detection and diagnostic decision support systems for bioterrorism response. Emergency Infectious Diseases. [serial online]. Retrieved May 19, 2010. Available from: URL: http://www.cdc.gov/ncidod/EID/vol10no1/03-0243.htm

Leonhardt, David. (2006, February 22).Why doctors so often get it wrong. The New York Times.

Retrieved May 19, 2010 at http://www.nytimes.com/2006/02/22/business/22leonhardt.html