MNGHA Jeddah · AUC-guided vancomycin TDM

Precision Vancomycin
Dosing for MNGHA

منصة الجرعة الدقيقة للفانكومايسين

Population PK + machine learning + MAP Bayesian AUC-guided dosing for adult inpatients across all specialties. Built on 558 MNGHA Jeddah patients. Externally validated on 210.

Launch GuardDose →   How it works
Sign-in required · Contact your administrator for access
558Development patients
210External validation
0.998Ridge external MAE (L/h)
3Dosing engines
Capabilities

Everything you need for AUC-guided vancomycin TDM

From a priori dose estimation to MAP Bayesian individualisation, shared patient database, analytics and batch import — one secure institutional platform.

🧠

A priori dose prediction

Population PK and a 19-feature ridge model predict individual clearance from routine covariates before any level is drawn. A concordance check flags patients where the two disagree.

📐

MAP Bayesian update

One or more levels individualise CL and V with full dose-history superposition, inter-occasion variability, η estimates, OFV and a 90% confidence interval on AUC₂₄.

📊

AUC-guided dose adjustment

Target AUC₂₄ 400–600 mg·h/L per the 2020 ASHP/IDSA/SIDP guideline. Regimen grid with predicted AUC, peak and trough for every option; loading-dose guidance.

🗂️

Patient database

Cases saved centrally with ward, user, outcome and MAP results. Searchable, filterable, reopen any case, export to CSV.

📈

Analytics dashboard

Target attainment, AUC distribution, cases by ward, month and user, PopPK–ML concordance rate — live from the shared database.

👥

Multi-user IAM

Admin, user and viewer roles; ward assignment; suspend or remove accounts; account lockout; full audit log of sign-ins and data changes.

📁

Batch upload

Import hundreds of patients from Excel or CSV. Column names are matched automatically; each row is validated, calculated (MAP if a trough is supplied) and reported individually.

🔒

Secure institutional hosting

HTTPS, role-based sign-in, session expiry, audit trail. Patient data is stored in the platform database, not in individual browsers, so the whole team sees the same cases.

🏥

Built for MNGHA Jeddah

Developed and validated on adult inpatients at King Abdulaziz Medical City – Jeddah, with a dedicated model for haematological malignancy and febrile neutropenia.

Dosing engines

Three engines, one Bayesian step, validated externally

Every model was developed on MNGHA data and evaluated on an independent external cohort. The population model provides the prior; ridge provides an independent second opinion; MAP individualises.

PopPK 558 · 1-cmt + IOV · Monolix SAEM · a posteriori MAPE 11.4%, 94.9% within ±30% ★ default prior
HM model · haematological malignancy · n = 207, external n = 53 · CL 5.11 L/h
Ridge regression · 19 features · external R² 0.582 · MAE 0.998 L/h · bias +9.7%
PopPK a priori benchmark · R² 0.521 · MAE 1.100 L/h · bias +15.0%
MAP Bayesian · dose-history superposition · Nelder–Mead, 7 restarts · Laplace 90% CI
CL = 3.48 × (CrCL/78)0.60 × (Age/68)−0.24 × eη+κ L/h
V  = 93.41 × (Age/68)1.00 × eη L
ωCL 0.37 · ωV 0.38 · γIOV 0.16 · proportional error 0.15
ln(CLML) = 1.2751 + Σ βj·(xj − μj)/σj
19 standardised features from age, sex, weight, height, BMI, SCr, CrCL
Top terms: ln(age) 27.7% · ln(CrCL) 23.0% · ln(weight) 14.5% · ln(age)×ln(CrCL) 11.7%
Workflow

AUC-guided dosing in 4 steps

From prescription to individualised dose adjustment

1

Enter covariates

Age, sex, weight, height, SCr and regimen. CrCL auto-calculated by Cockcroft–Gault; choose the general or HM population.

2

A priori dose

PopPK and ridge predict CL and AUC₂₄; concordance is checked; the best regimen for the target AUC is suggested. Save to the database.

3

Enter TDM sample

Trough, peak + trough or any timed samples — at steady state or with the full dose history. Exact sampling time required.

4

MAP Bayesian update

Individual CL, V and AUC₂₄ with 90% CI and uncertainty reduction. New regimen recommended; residuals flagged if inconsistent.

Authors

Research team

GuardDose is the applied output of a doctoral research programme in pharmacometrics and model-informed precision dosing conducted at MNGHA Jeddah in collaboration with King Abdulaziz University.

👨‍⚕️

Dr. Abdullah M. Alzahrani

PharmD, MSc, BCPS · Developer and principal author · Senior Pharmacist, Department of Pharmaceutical Care, King Abdulaziz Medical City – Jeddah (MNGHA) · PhD candidate, Department of Pharmacology, Faculty of Medicine, King Abdulaziz University

🎓

Prof. Samer Alharthi

Main PhD supervisor · Department of Pharmacology, Faculty of Medicine, King Abdulaziz University

🏥

Dr. Maher Alahmadi

Principal investigator and co-advisor · King Abdulaziz Medical City – Jeddah, Ministry of National Guard – Health Affairs

🔬

Dr. Ragiah Goniem

Doctoral research advisor · King Abdulaziz University

📚

Prof. Abdullah Alsultan

Doctoral research advisor · Pharmacometrics and clinical pharmacokinetics

🧾

Ethics and data

IRB approval NRJ24/006/12. Retrospective–prospective vancomycin TDM data from adult inpatients at KAMC-Jeddah; no patient identifiers leave the institutional server.

About this platform

DeveloperDr. Abdullah M. Alzahrani, PharmD, MSc, BCPS — Department of Pharmaceutical Care, King Abdulaziz Medical City – Jeddah (MNGHA) Contactzahraniab04@mngha.med.sa Version6.0 · Released September 2026 (replaces V4, April 2026) ResearchDoctoral project, Department of Pharmacology, Faculty of Medicine, King Abdulaziz University. Principal investigator at MNGHA: Dr. Maher Alahmadi. Main supervisor: Prof. Samer Alharthi (KAU); advisors: Dr. Ragiah Goniem, Prof. Abdullah Alsultan. EthicsIRB approval NRJ24/006/12
For clinical decision support and research use only. All dosing recommendations must be reviewed and verified by a qualified clinical pharmacist or physician before implementation. The developers and affiliated institutions accept no liability for clinical decisions made on the basis of this tool. Report errors or questions to the developer at the email above.