Predictive Performance

What was run

Analysis

Developer-run synthetic analysis (not real patients). Recomputed from the source code each time the site is built: seed 42, n = 200.

Engine

Vancomyzer a posteriori (Bayesian) engine with the Colin 2019 prior. Model manifest version 2026-09-19.1.

Synthetic population

200 adults (age 26–95 years, 129 male). Age, sex, weight and serum creatinine are drawn from distributions calibrated to summary statistics of the Bai et al. 2025 ICU cohort (median weight 64.6 kg, median serum creatinine 0.68 mg/dL); height uses developer-chosen values. No dialysis, CRRT or ECMO. Augmented renal clearance is not excluded: Cockcroft–Gault CrCl is capped at 200 mL/min, 52 patients are above 130 mL/min and 13 of them are at the cap. 2 patients have a BMI of 40 or more.

Truth model

Goti 2018–based model, different from Vancomyzer’s prior: CL = 4.5 × (CrCl/120)^0.8 × (WT/70)^0.75 L/h, V₁ = 58.4 × WT/70 L, Q = 6.5 × (WT/70)^0.75 L/h, V₂ = 38.4 × WT/70 L, with log-normal between-subject variability (ω_CL = 0.4, ω_V1 = 0.3, ω_Q = 0.5, ω_V2 = 0.4). The weight terms and the variability values are developer choices, not Goti 2018 estimates.

Regimen

15 mg/kg every 12 h, rounded to the nearest 250 mg, limited to 500–3000 mg, infused over 1.5 h. No dose changes.

Fitted samples

Two levels in the dosing interval of dose 5: 3.0 h after the start of the dose (1.5 h after the end of the infusion) and 11.5 h (0.5 h before the next dose). Each has simulated residual error (20% proportional + 1.0 mg/L additive). The simulation and the fit both use steady-state equations.

Endpoint

The concentration 6.0 h after the start of the same dose (4.5 h after the end of the infusion), predicted from the fitted engine. This time is not used in the fit. The prediction is compared with (a) a synthetic observation at that time (truth plus residual error) and (b) the noise-free truth, reported separately.

Fits

200 of 200 posterior fits succeeded; the metrics use the successful fits.

Results · developer-run synthetic analysis (not real patients)

Error of the engine’s prediction at the held-out time, one prediction per patient (seed 42, model manifest 2026-09-19.1). Metric definitions are below.

Error against the synthetic observation includes the residual error added to that observation, so it is larger than error against the noise-free truth; relative errors are inflated most when the observed concentration is low. No acceptance threshold was prespecified for this analysis. Each patient contributes one held-out concentration from one steady-state interval, which is a narrow test (see Limitations).

Metric definitions

C_pred is the engine’s predicted concentration and C_ref is the value it is compared with (the synthetic observation or the noise-free truth). Means are taken over patients.

Bias and precision as measures of predictive performance follow Sheiner and Beal (J Pharmacokinet Biopharm. 1981;9:503–512). Some later studies treat an rBias within ±20% as acceptable; that threshold is a convention, not a criterion set by Sheiner and Beal, and it was not prespecified here.

Published real-patient study · context only, not comparable

These numbers cannot be compared with the synthetic results above. Bai et al. evaluated three Bayesian dosing programs in real ICU patients. The cohort, sampling, dosing and definition of the true value (measured concentrations) all differ from the synthetic analysis, and Vancomyzer was not part of the study. Retrospective, single centre (Beijing). 139 adult ICU patients with 284 measured vancomycin concentrations, mostly troughs; patients on blood purification or ECMO were excluded. Predictions were compared with measured concentrations from routine clinical dosing and monitoring.

Source: Bai G, et al. Predictive performance of Bayesian dosing software for vancomycin in intensive care unit patients. Ther Drug Monit. 2025;47(5):594–602, Table 3 (a posteriori). doi:10.1097/FTD.0000000000001310

Limitations

• Synthetic patients, not real patients

  The truth model contains only the variability that was simulated. It leaves out things that happen in real patients, such as changing renal function, fluid shifts, drug interactions, errors in dose or sample times, and assay problems. Error in real patients has not been measured and could be larger.

• One held-out concentration in one steady-state interval

  Each patient contributes one held-out concentration, 6.0 h into the same steady-state interval as the two fitted levels (between the two fitted sample times). There are no dose changes, no levels before steady state and no change in physiology over time. This is held-out interpolation, not future forecasting: it does not show how well Vancomyzer forecasts later levels after a regimen change or as a patient's condition changes.

• Two-level sampling only

  The engine always receives two levels, one after the infusion and one before the next dose. Trough-only sampling and levels drawn before steady state were not simulated.

• Truth model is partly developer-defined

  Typical values come from Goti 2018, but the weight scaling, the between-subject variability (ω = 0.4 / 0.3 / 0.5 / 0.4) and the residual error are developer choices. Different choices would change the results; the sensitivity has not been quantified.

• Population coverage

  No dialysis, CRRT or ECMO patients are simulated. Augmented renal clearance is included (52 of 200 patients above 130 mL/min), but CrCl is capped at 200 mL/min. Only 2 patients have a BMI of 40 or more, so this analysis says little about high body weight.

• Version

  Results reflect model manifest 2026-09-19.1, in which Colin 2019 is used at every BMI. These results apply to the stated software version and study design; they are not independent clinical validation.

Validation plan