Anaes · Measurement & monitoring physics

Bias and confounding in clinical research

Also known as Bias · Confounding · Selection bias · Performance bias · Detection bias · Attrition bias · Reporting bias · Effect modification · Propensity scoring

Every anaesthetic reads the literature, and every paper is threatened by two families of error that can make a useless intervention look effective or a harmful one look safe — bias and confounding. The model rests on eleven exam-critical ideas. First, BIAS is a SYSTEMATIC error that distorts the study findings in a particular direction, unlike RANDOM error (chance) which is unsystematic and handled by p-values and confidence intervals. Second, SELECTION BIAS is a systematic difference between those selected for study and those not — the healthy-worker effect, self-selection, and loss to follow-up are the classical forms — minimised by randomisation in trials and representative sampling in observational work. Third, PERFORMANCE BIAS is a systematic difference in the care provided to the groups apart from the intervention itself, minimised by blinding participants and clinicians. Fourth, DETECTION BIAS is a systematic difference in how outcomes are assessed, minimised by blinded outcome assessors and standardised measurement. Fifth, ATTRITION BIAS is systematic loss of participants during follow-up that differs between groups, minimised by intention-to-treat analysis, high retention, and imputation. Sixth, REPORTING BIAS is the selective publication or reporting of favourable results — publication bias produces funnel-plot asymmetry and is reduced by prospective trial registration and the CONSORT statement. Seventh, a CONFOUNDER is a third variable associated with BOTH the exposure and the outcome but NOT on the causal pathway between them — smoking confounds the coffee-cancer association, age confounds the anaesthesia-outcome relationship. Eighth, CONFOUNDING is a nuisance to be eliminated whereas EFFECT MODIFICATION is a real biological interaction to be reported — a drug that works in one sex but not the other is effect modification, not confounding. Ninth, in the DESIGN phase, RANDOMISATION is the only method that controls for both known and UNKNOWN confounders; restriction, matching and stratification control only known confounders. Tenth, in the ANALYSIS phase, stratified analysis, multivariable regression (logistic, linear, Cox) and PROPENSITY-SCORE MATCHING create comparable groups from observational data by matching on the predicted probability of treatment. Eleventh, RESIDUAL CONFOUNDING from unmeasured or imperfectly measured variables always limits observational studies, which is why randomised controlled trials sit atop the evidence hierarchy. Built on the postoperative hepatic dysfunction risk-factor meta-analysis (Liu 2026), the vaginal estrogen SEER analysis (Mitchel 2026), the perioperative biologic DMARD safety study (Peng 2026), the propensity-matched cholangiocarcinoma survival analysis (Tian 2026), the propensity-matched dens fracture surgery study (Khan 2026), the preoperative PPI complications cohort (Pollmann 2026), the periodontal therapy systematic review (Ramaglia 2026), and the acupuncture cancer-fatigue meta-analysis (Yang 2026).