Diagnostic Test Accuracy Reasoning Chain

validated scientific chain v1.0.0 cc-by-sa

Block ID: fd0e956f-b568-4ea9-b5f7-cbc76be2ba46

Community-contributed block. PromptDNA makes no guarantee of output quality or fitness for purpose. User assumes all responsibility for use.

Template

Reason through what the test result in {test_scenario} actually tells you, avoiding the base-rate error that trips up experts. (1) Lay out the four quantities the problem needs: the test's sensitivity, its specificity, and the prevalence (prior probability) of the condition in the population being tested — the prevalence is the term most often ignored and the one that dominates the answer for rare conditions. (2) State the question precisely: after a positive (or negative) result, what is the probability the condition is truly present (or absent)? This is the predictive value, not the sensitivity, and confusing the two is the core mistake. (3) Work a concrete frequency example: imagine a natural population (say 10,000 people at the given prevalence), tabulate true positives, false positives, true negatives, false negatives from sensitivity and specificity, and read the predictive value directly from the table — frequencies make the base-rate effect visible where probabilities hide it. (4) Interpret: for a rare condition, even an accurate test yields many false positives, so a positive result may still mean the condition is unlikely. (5) Consider whether pre-test probability should be adjusted for this individual's specifics. (6) State the post-test probability and what a confirmatory test would add. This is analytical reasoning, not a substitute for clinical judgment.

Reason through what the test result in {test_scenario} actually tells you, avoiding the base-rate error that trips up experts. (1) Lay out the four quantities the problem needs: the test's sensitivity, its specificity, and the prevalence (prior probability) of the condition in the population being tested — the prevalence is the term most often ignored and the one that dominates the answer for rare conditions. (2) State the question precisely: after a positive (or negative) result, what is the probability the condition is truly present (or absent)? This is the predictive value, not the sensitivity, and confusing the two is the core mistake. (3) Work a concrete frequency example: imagine a natural population (say 10,000 people at the given prevalence), tabulate true positives, false positives, true negatives, false negatives from sensitivity and specificity, and read the predictive value directly from the table — frequencies make the base-rate effect visible where probabilities hide it. (4) Interpret: for a rare condition, even an accurate test yields many false positives, so a positive result may still mean the condition is unlikely. (5) Consider whether pre-test probability should be adjusted for this individual's specifics. (6) State the post-test probability and what a confirmatory test would add. This is analytical reasoning, not a substitute for clinical judgment.

Variables

Name	Type	Required	Trust level
test_scenario		yes

diagnostic-testingsensitivity-specificitybase-rateschain-of-thought

Ratings

0.0

Overall (0)

0.0

Accuracy

0.0

Consistency

0.0

Clarity

0.0

Efficiency

Benchmarks

Not yet self-validated against any benchmark. Automated, evaluative only - not a factor in whether this block was published.

Submitted by James P FounderMod via mcp · 2026-07-18