Reply to Student #1 I

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.