Related Experiment Video
Updated: May 8, 2026
11:17
Multiplex Therapeutic Drug Monitoring by Isotope-dilution HPLC-MS/MS of Antibiotics in Critical Illnesses
Published on: August 30, 2018
Machine Learning Prediction of Unbound Ceftriaxone Concentrations in Children: Capturing Developmental Changes in
Bo-Hao Tang1,2, Qiu-Yue Li1,2, Jing Sun1
1Department of Pharmacy, The Second Qilu Hospital of Shandong University, Jinan, China.
Clinical Pharmacology and Therapeutics
|May 7, 2026
Summary
This study developed a machine learning model to predict unbound ceftriaxone concentrations in pediatric patients. The model accurately estimates drug levels using routine clinical data, improving individualized dosing.
Area of Science:
- Pharmacology
- Pediatric Medicine
- Machine Learning
Background:
- Antimicrobial activity relies on unbound drug concentrations, but pediatric protein binding changes complicate accurate estimation.
- Developmental variations in protein binding present challenges for predicting free drug fractions in children.
Purpose of the Study:
- To develop a machine learning (ML) model for predicting unbound ceftriaxone concentrations in pediatric patients.
- To incorporate nonlinear developmental effects and routine clinical variables into the predictive model.
Main Methods:
- Trained ten ML algorithms using 176 paired total/unbound ceftriaxone concentrations and clinical data from neonates, infants, and children.
- Evaluated the optimal ExtraTrees Regressor model in an independent cohort and compared it with established mathematical equations.
- Utilized routine variables: total ceftriaxone concentration, serum albumin, weight, and age.
Main Results:
- The ExtraTrees Regressor model achieved high predictive performance (RMSE: 6.95 μg/mL, R²: 0.87).
- The model accurately estimated unbound ceftriaxone across pediatric ages (0-12 years), outperforming existing equations (MAPE reduction of 14.2-14.7%).
- Revealed nonlinear, age-dependent protein binding patterns in pediatric patients.
Conclusions:
- The ML model offers a practical tool for predicting unbound ceftriaxone concentrations in pediatric patients.
- Facilitates individualized dosing and precision medicine by accounting for developmental changes in drug exposure.
- Highlights the utility of machine learning in addressing complex pharmacokinetic challenges in pediatrics.
Related Concept Videos
01:17Pharmacokinetics in Pediatric Patients: Drug Distribution
Drug distribution in the pediatric population exhibits unique challenges and considerations due to the physiological differences between children, particularly neonates and infants, and adults. A crucial aspect of pediatric pharmacology is understanding how these differences impact the pharmacokinetics of various drugs, necessitating age-specific dosing strategies to ensure efficacy and safety.Neonates and infants have a higher total body water content, ~75%–90% of their body weight, compared...
01:26Pharmacokinetics in Pediatric Patients: Drug Excretion
In pediatric medicine, understanding the renal function and drug elimination nuances is crucial for administering safe and effective treatments. Newborns, in particular, display markedly slower renal functions than adults, profoundly affecting how drugs are cleared from their bodies. This slower drug clearance requires clinicians to extend the dosing intervals for many medications to prevent drug accumulation and toxicity while ensuring therapeutic efficacy.One key area where these adjustments...
01:29Drug Dosing: Infants and Children
Pediatric patient dosages diverge from adults due to disparities in body surface area, total body water, and extracellular fluid per kilogram of body weight. The dosing regimen considers the variations in pharmacokinetics and pharmacology across distinct age groups, encompassing preterm newborns, infants, young children, older children, and adolescents. Calculation of pediatric patient doses is predicated on determining body surface area, which exhibits a superior correlation with the child's...
01:21Drug Accumulation During Multiple Dosing: Repetitive IV Injections
Calculating drug dosage and accumulation in multiple-dose regimens is crucial for achieving therapeutic efficacy while avoiding toxicity. This involves determining the plasma drug concentrations over time to optimize dosing schedules. The principle of superposition is fundamental in this process, allowing for the prediction of drug concentration in plasma following multiple doses based on single-dose data.The principle of superposition asserts that the plasma concentration-time curves from...
01:15Determination of Multiple Dosing Parameters: Steady-State, Minimum and Maximum Concentrations
Gentamicin, an aminoglycoside antibiotic, is commonly administered via intermittent intravenous infusion to treat severe infections. An intermittent one-hour infusion of gentamicin, administered at eight-hour intervals, allows for precise control of plasma drug concentrations, minimizing toxicity while ensuring therapeutic efficacy. Pharmacokinetic principles govern the dynamics of plasma concentrations and can be mathematically described using specific equations.The plasma drug concentration...
01:13Physiological Pharmacokinetic Models: Assumption with Protein Binding
Physiological models with protein binding in pharmacokinetics offer a sophisticated approach to understanding drug disposition. These models consider drug-protein interactions, enabling them to effectively predict drug concentrations in different organs and tissues. This precision aids in accurate drug dosing, providing a significant advantage over conventional models. A key process within these models is equilibration, which ensures that drug concentrations achieve a steady state within the...