A5047459188- Antibiotics Pharmacokinetics and Efficacy
- Sepsis Diagnosis and Treatment
- Respiratory Support and Mechanisms
- Hemodynamic Monitoring and Therapy
- Bacterial Identification and Susceptibility Testing
- Antimicrobial Resistance in Staphylococcus
- Pneumonia and Respiratory Infections
- Machine Learning in Healthcare
- Antibiotic Use and Resistance
- Biomedical Text Mining and Ontologies
- Electronic Health Records Systems
- Antibiotic Resistance in Bacteria
- Non-Invasive Vital Sign Monitoring
- Advanced Statistical Process Monitoring
- Clinical Reasoning and Diagnostic Skills
- COVID-19 Clinical Research Studies
- Intensive Care Unit Cognitive Disorders
- Cardiac Arrest and Resuscitation
Amsterdam University Medical Centers
2019-2025
Vrije Universiteit Amsterdam
2019-2024
University of Amsterdam
2023
Amsterdam UMC Location Vrije Universiteit Amsterdam
2019-2020
Abstract Background Adequate antibiotic dosing may improve outcomes in critically ill patients but is challenging due to altered and variable pharmacokinetics. To address this challenge, AutoKinetics was developed, a decision support system for bedside, real-time, data-driven personalised dosing. This study evaluates the feasibility, safety efficacy of its clinical implementation. Methods In two-centre randomised trial, with sepsis or septic shock were standard four antibiotics: vancomycin,...
Dosing of vancomycin is often guided by therapeutic drug monitoring and population pharmacokinetic models in the intensive care unit (ICU). The validity these crucial, as ICU patients have marked variability. Therefore, we set out to evaluate predictive performance published patients. PubMed database was used search for adult identified were evaluated two independent data sets which collected from large hospitals Netherlands (Amsterdam UMC, Location VUmc, OLVG Oost). We also tested a...
Abstract Background Reinforcement learning (RL) holds great promise for intensive care medicine given the abundant availability of data and frequent sequential decision-making. But despite emergence promising algorithms, RL driven bedside clinical decision support is still far from reality. Major challenges include trust safety. To help address these issues, we introduce cross off-policy evaluation policy restriction show how detailed analysis may increase interpretability. As an example,...
Abstract Purpose This study provides an economic evaluation of bedside, data-driven, and model-informed precision dosing antibiotics in comparison with usual care among critically ill patients sepsis or septic shock. Methods was conducted alongside AutoKinetics randomized controlled trial. Effect measures included quality-adjusted life years (QALYs), mortality pharmacokinetic target attainment. Costs were measured from a societal perspective. Missing data multiply imputed, bootstrapping used...
Abstract Background Antibiotic exposure is often inadequate in critically ill patients with severe sepsis or septic shock and this associated worse outcomes. Despite markedly altered rapidly changing pharmacokinetics these patients, guidelines clinicians continue to rely on standard dosing schemes. To address challenge, we developed AutoKinetics, a clinical decision support system for antibiotic dosing. By feeding large amounts of electronic health record patient data into pharmacokinetic...
Antibiotic dosing in critically ill patients is challenging because their pharmacokinetics (PK) are altered and may change rapidly with disease progression. Standard frequently leads to inadequate PK exposure. Therapeutic drug monitoring (TDM) offers a potential solution but requires sampling knowledge, which delays decision support. It our philosophy that antibiotic support should be directly available at the bedside through deep integration into electronic health record (EHR) system....
In recent years, reinforcement learning (RL) has gained traction in the healthcare domain. particular, RL methods have been explored for haemodynamic optimization of septic patients Intensive Care Unit. Most hospitals however, lack data and expertise model development, necessitating transfer models developed using external datasets. This approach assumes generalizability across different patient populations, validity which not previously tested. addition, there is limited knowledge on safety...
With the advent of artificial intelligence, secondary use routinely collected medical data from electronic healthcare records (EHR) has become increasingly popular. However, different EHR systems typically names for same concepts. This obviously hampers scalable model development and subsequent clinical implementation decision support. Therefore, converting original parameter to a so-called ontology, standardized set predefined concepts, is necessary but time-consuming labor-intensive. We...
Antibiotic exposure in intensive care patients with sepsis is frequently inadequate and associated poorer outcomes. dosing challenging the care, as critically ill have altered fluctuating antibiotic pharmacokinetics that make current one-size-fits-all regimens unsatisfactory. Real-time bedside software not available yet, therapeutic drug monitoring typically used for few classes only allows delayed adaptation. Thus, adequate timely continues to rely largely on level of pharmacokinetic...
Abstract Purpose Bayesian forecasting is crucial for model-based dose optimization based on therapeutic drug monitoring (TDM) data of vancomycin in intensive care (ICU) patients. We aimed to evaluate the performance using maximum a posteriori (MAP) estimation TDM. Methods used TDM set ( n = 408 patients). compared standard MAP-based with two alternative approaches: (i) adaptive MAP which handles over multiple iterations, and (ii) weighted weights likelihood contribution data. evaluated...
For mechanically ventilated critically ill COVID-19 patients, prone positioning has quickly become an important treatment strategy, however, is labor intensive and comes with potential adverse effects. Therefore, identifying which intubated patients will benefit may help allocate resources. From the multi-center Dutch Data Warehouse of ICU from 25 hospitals, we selected all 3619 episodes in 1142 invasively patients. We excluded longer than 24 h. Berlin ARDS criteria were not formally...
Previous pharmacokinetic (PK) studies of ciprofloxacin in intensive care (ICU) patients have shown large differences estimated PK parameters, suggesting that further investigation is needed for this population. Hence, we performed a pooled population analysis after intravenous administration using individual patient data from three studies. Additionally, studied the between these through post-hoc analysis. Individual (study 1, 2, and 3) were pooled. The set consisted 1094 concentration–time...
To explore the optimal data sampling scheme and pharmacokinetic (PK) target exposure on which dose computation is based in model-based therapeutic drug monitoring (TDM) practice of vancomycin intensive care (ICU) patients.We simulated concentration for 1 day following four schemes, Cmin , Cmax + Cmid-interval rich where a sample was drawn every hour within interval. The datasets were used Bayesian estimation to obtain PK parameters, compute doses next five exposures: AUC24 = 400, 500, 600...
Abstract Background The identification of risk factors for adverse outcomes and prolonged intensive care unit (ICU) stay in COVID-19 patients is essential prognostication, determining treatment intensity, resource allocation. Previous studies have determined on admission only, included a limited number predictors. Therefore, using data from the highly granular multicenter Dutch Data Warehouse, we developed machine learning models to identify ICU mortality, ventilator-free days ICU-free...
Purpose: This study provides an economic evaluation of bedside, data-driven, and model-informed precision dosing antibiotics in comparison with usual care among critically ill patients sepsis or septic shock.Materials Methods: was conducted alongside a randomized controlled trial. Effect measures included quality-adjusted life years (QALYs), mortality pharmacokinetic treatment attainment. Costs were measured from societal perspective. Missing data multiply imputed bootstrapping used to...