Yuan Doctor
Clinical & research tools for physicians: bedside calc, pathways, research Labs. Free, local compute, no data upload.
Calculate without signing in. Sign in to save favorites across devices
Research Labs
All →Shift packs
Common tools bundled by duty scenario — open in one tap
Clinical tools
All 878 tools →Bedside quick-calc cards · share so colleagues can calculate too
Scan to open the same scene workflow — local calc, chart-ready. Short links /r/… for easy sharing.
Turn guidelines into decisions
Enter the patient → risk stratification → thresholds → guideline recommendation, each with class of recommendation, level of evidence and source guideline. Computed locally; decision support for licensed clinicians.
Turn guidelines into pathways
From first contact to disposition, step through the decision tree: red / amber / green stratification → thresholds → guideline recommendation. Each pathway is checked against current guidelines, computed locally — for licensed clinicians.
Suspected Pulmonary Embolism (PE) — Diagnostic Pathway
From hemodynamic assessment to the two-level Wells score, (age-adjusted) D-dimer and CTPA for suspected acute PE.
Adult Hyperkalemia — Management Pathway
Decide whether emergency treatment is needed based on potassium level, ECG changes and symptoms, and manage acute hyperkalemia with the 'stabilize–shift–remove' three-step approach.
Community-Acquired Pneumonia (CAP) — Disposition Pathway
Use CURB-65 to grade CAP severity and decide outpatient / ward / ICU disposition, integrating severe-CAP criteria and sepsis recognition.
Diabetic Ketoacidosis (DKA) — Management Pathway
Confirm DKA, grade by the 2024 ADA consensus, and manage with fluids → check potassium before insulin → monitor → find the trigger.
Sepsis — 1-Hour Bundle (SSC)
After recognizing sepsis / septic shock, start the SSC Hour-1 bundle: lactate, blood cultures, broad-spectrum antibiotics, crystalloid and vasopressors.
Anaphylaxis (Immediate-Type) — Management Pathway
Recognize anaphylaxis by diagnostic criteria and give intramuscular epinephrine first, with airway, volume and adjunctive treatment.
Acute Kidney Injury (AKI) — KDIGO Staging & Management
Diagnose and stage by KDIGO creatinine and urine-output criteria; find the cause, stop nephrotoxins, optimize volume and manage complications.
Atrial Fibrillation — Anticoagulation Decision Pathway
Decide whether and what to anticoagulate by valvular status and CHA2DS2-VASc annual stroke risk (DOAC preferred); HAS-BLED is to improve, not withhold, anticoagulation.
Statistics, ready to run
Fill in your data, get the result: agreement, diagnostic accuracy, survival, meta-analysis, modelling and more. Every tool computes locally in your browser — nothing is uploaded or stored.
Auto Statistical Analysis (paste a table → method + chart)
Paste a data table and the tool detects the shape and picks the method: grouped mean±SD±n summaries → one-way ANOVA per outcome column (with a linear-trend test for ordered groups); raw values one group per line → 2-group t-test / ≥3-group ANOVA (with Mann-Whitney / Kruskal-Wallis backups); two variables → correlation & linear regression. Returns statistics, P values and a result chart, computed locally.
Paired χ² — McNemar / Cochran's Q
Compare paired binary outcomes: two paired conditions (same subjects, two tests or before/after) use McNemar (with continuity correction and exact binomial); ≥3 paired conditions use Cochran's Q. The ordinary chi-square assumes independence and is wrong for paired data.
Effect Size (d / η² / converter)
Two group means → Cohen's d and Hedges's g (with 95% CI); ANOVA F → η²/partial η²; plus d↔r↔OR conversion. P-values say whether a difference exists, effect sizes say how large — required for papers and meta-analysis.
Equivalence / Non-inferiority (TOST)
Prove two groups are practically equivalent or not inferior: pre-set an equivalence margin ±Δ, then run two one-sided tests (TOST). Gives the TOST p-value, (1−2α) confidence interval and an equivalence/non-inferiority verdict. P>0.05 ≠ equal.
Measurement Error — SEM / MDC
Standard error of measurement (SEM) and minimal detectable change (MDC): how large an individual change must be to exceed measurement error and count as real. From SD+reliability (ICC) or test–retest paired data. Common for scales/imaging measurements and follow-up.
Cluster-Randomized Sample Size (Design Effect)
For cluster randomization (randomizing by ward/community/hospital) inflate the sample size by the design effect DE=1+(m−1)ICC. From the individually-randomized sample size (computable here for two proportions or two means) derive total subjects and number of clusters needed.
Incidence Rate & Rate Ratio (IRR)
Outcomes per person-time (person-years/months): one group gives incidence rate with an exact Poisson CI; two groups give the incidence rate ratio IRR (Wald log CI + exact conditional CI). Suits cohorts, adverse-event rates, recurrence rates.
Time-dependent ROC / AUC(t)
Discrimination of a prognostic marker/model across follow-up time: time-dependent AUC(t) using cumulative-case/dynamic-control definitions plus IPCW (inverse probability of censoring weighting) to handle censoring; gives AUC at each time point and the curve.