Professional Practice, Research, and Evidence
Hierarchy and appraisal
Rank evidence roughly as systematic reviews and meta-analyses of randomized trials, then individual randomized controlled trials, cohort studies, case-control studies, case series, and expert opinion. Appraise for randomization, blinding, allocation concealment, completeness of follow-up, and sample size. A p value tells you how unlikely the result is under the null; it does not tell you whether the change matters. Effect size, confidence intervals, minimal clinically important difference (MCID), and minimal detectable change (MDC) answer the clinical question.
Diagnostic statistics
Sensitivity is the proportion of people with the condition who test positive; specificity is the proportion without it who test negative. Positive and negative predictive values depend on prevalence, so they shift with setting; sensitivity and specificity (and likelihood ratios) are more stable. Reliability is reported with ICC or kappa, and you should know that a test can be reliable yet invalid.
Professional and ethical practice
Informed consent, confidentiality, documentation (SOAP format), billing accuracy, supervision and delegation limits, scope of practice, and continuing competence all appear in this domain. Document objective findings, the clinical reasoning behind the plan, and patient response - not just the treatment delivered.
Traps
Equating statistical significance with clinical importance; quoting predictive values as if they were fixed properties of a test; calling a measure valid merely because it is reliable; assuming higher-level evidence always transfers to your patient.
Rule of thumb
SnNout and SpPin - a highly sensitive test that is negative helps rule out; a highly specific test that is positive helps rule in.