A5107852791- Artificial Intelligence in Healthcare and Education
- Venous Thromboembolism Diagnosis and Management
- Health Systems, Economic Evaluations, Quality of Life
- Meta-analysis and systematic reviews
- Machine Learning in Healthcare
- Diagnosis and Treatment of Venous Diseases
- Statistical Methods and Bayesian Inference
- Radiomics and Machine Learning in Medical Imaging
- Heart Failure Treatment and Management
- Central Venous Catheters and Hemodialysis
- Clinical practice guidelines implementation
- Reliability and Agreement in Measurement
- Explainable Artificial Intelligence (XAI)
- Acute Ischemic Stroke Management
- Health Promotion and Cardiovascular Prevention
- COVID-19 diagnosis using AI
- COVID-19 Clinical Research Studies
- Frailty in Older Adults
- COVID-19 and healthcare impacts
- Artificial Intelligence in Healthcare
- Clinical Reasoning and Diagnostic Skills
- Atrial Fibrillation Management and Outcomes
- Sepsis Diagnosis and Treatment
- Neonatal and fetal brain pathology
- Delphi Technique in Research
University Medical Center Utrecht
2006-2025
Utrecht University
2001-2025
Art Innovation (Netherlands)
2024
University Hospital Heidelberg
2016-2022
Heidelberg University
2016-2022
Oklahoma State University Center for Health Sciences
2014-2022
University of Oxford
2020
Nuffield Orthopaedic Centre
2020
Huisarts en Wetenschap
2016
Cancer Research And Biostatistics
2010
Carl Moons and colleagues provide a checklist background explanation for critically appraising extracting data from systematic reviews of prognostic diagnostic prediction modelling studies. Please see later in the article Editors' Summary
Binary logistic regression is one of the most frequently applied statistical approaches for developing clinical prediction models. Developers such models often rely on an Events Per Variable criterion (EPV), notably EPV ≥10, to determine minimal sample size required and maximum number candidate predictors that can be examined. We present extensive simulation study in which we studied influence EPV, events fraction, predictors, correlations distributions predictor variables, area under ROC...
Ten events per variable (EPV) is a widely advocated minimal criterion for sample size considerations in logistic regression analysis. Of three previous simulation studies that examined this EPV only one supports the use of minimum 10 EPV. In paper, we examine reasons substantial differences between these extensive studies. The current study uses Monte Carlo simulations to evaluate small bias, coverage confidence intervals and mean square error logit coefficients. Logistic models fitted by...
Evaluating the performance of a clinical prediction model is crucial to establish its predictive accuracy in populations and settings intended for use. In this article, first three part series, Collins colleagues describe importance meaningful evaluation using internal, internal-external, external validation, as well exploring heterogeneity, fairness, generalisability performance.
The medical field has seen a rapid increase in the development of artificial intelligence (AI)-based prediction models. With introduction such AI-based model tools and software cardiovascular patient care, researcher healthcare professional are challenged to understand opportunities as well limitations predictions. In this article, we present 12 critical questions for health professionals ask when confronted with an model. We aim support distinguish models that can add value care from AI does not.
ABSTRACT Introduction Risk prediction models are increasingly used in healthcare to aid clinical decision‐making. In most contexts, model calibration (i.e., assessing the reliability of risk estimates) is critical. Data available for development often not perfectly balanced with modeled outcome individuals vs. without event interest equally prevalent data). It common researchers correct class imbalance, yet, effect such imbalance corrections on machine learning largely unknown. Methods We...
To evaluate the possible effects of outpatient preoperative evaluation (OPE) for new surgical patients who will be inpatients, we conducted an observational study at a university hospital in The Netherlands. Various outcomes before and after introduction OPE clinic were compared. population comprised all 21,553 elective adult inpatients operated on between January 1, 1997 December 31, 1999. Cardiac surgery, obstetric pediatric patients, same-day surgery excluded. main outcome measures cases...
The increasing availability of large combined datasets (or big data), such as those from electronic health records and individual participant data meta-analyses, provides new opportunities challenges for researchers developing validating (including updating) prediction models. These typically include individuals multiple clusters (such centres, geographical locations, or different studies). Accounting clustering is important to avoid misleading conclusions enables explore heterogeneity in...
Large Language Models (LLMs) are rapidly being adopted in healthcare, necessitating standardized reporting guidelines. We present TRIPOD-LLM, an extension of the TRIPOD+AI statement, addressing unique challenges LLMs biomedical applications. TRIPOD-LLM provides a comprehensive checklist 19 main items and 50 subitems, covering key aspects from title to discussion. The guidelines introduce modular format accommodating various LLM research designs tasks, with 14 32 subitems applicable across...
To determine the accuracy of gadolinium-enhanced breath-hold magnetic resonance (MR) angiography in diagnosis renal artery stenosis and visualization accessory arteries.Forty-four patients suspected having 10 potential kidney donors, all whom were scheduled to undergo elective intraarterial digital subtraction (DSA), studied. Three-dimensional gradient-echo MR was performed at 1.5 T with following parameters: repetition time, 13.5 msec; echo 3.5 flip angle, 60 degrees; 195 x 512 matrix;...
Background: Up to 90% of patients referred for ultrasonography with suspected deep venous thrombosis (DVT) the leg do not have disease. Objective: To evaluate safety and efficiency using a clinical decision rule that includes point-of-care d-dimer assay at initial presentation in primary care exclude DVT. Design: A prospective management study. Setting: Approximately 300 practices 3 regions Netherlands (Amsterdam, Maastricht, Utrecht). Patients: 1028 consecutive clinically Intervention:...
Combining several tests is a common way to improve the final classification of disease status in diagnostic accuracy studies but often used ambiguously. This article gives advice on proper use and reporting composite reference standards
Increasing evidence shows that flaws in machine learning (ML) algorithm validation are an underestimated global problem. Particularly automatic biomedical image analysis, chosen performance metrics often do not reflect the domain interest, thus failing to adequately measure scientific progress and hindering translation of ML techniques into practice. To overcome this, our large international expert consortium created Metrics Reloaded, a comprehensive framework guiding researchers...
Objectives The Wells rule is often used in primary care to out pulmonary embolism (PE), but its efficiency low as many referred patients do not have PE. In this study, we evaluated an alternative and potentially more efficient diagnostic strategy—the YEARS algorithm; a simplified three-item version of the combined with pretest probability adjusted D-dimer interpretation. Design comprehensive prospective validation suspected PE were enrolled by their general practitioner. All three items...
Abstract The disease course and outcome of COVID-19 greatly varies between individuals. To explore which biological systems may contribute to this variation, we examined how individual metabolites three metabolic scores relate outcomes in hospitalized patients. metabolome 346 patients was measured using the 1H-NMR Nightingale platform. association metabolomic features multi-biomarker scores, i.e. MetaboHealth, MetaboAge, Infectious Disease Score (IDS) (higher reflect poorer health), with...
Expert panels are often used as a reference standard when no gold is available in diagnostic test accuracy research. It unclear what study and expert panel characteristics produce the best estimates of accuracy. We simulated large range scenarios to assess impact on index estimates. Simulations were performed which an was estimate sensitivity specificity test. Diagnostic determined by combining probability target condition presence, provided experts using four component tests, through...
A universal challenge in studies that quantify the accuracy of diagnostic tests is establishing whether each participant has disease interest. Ideally, same preferred reference standard would be used for all participants; however, practical or ethical reasons, alternative standards are often less accurate frequently instead. The use different across participants a single study known as differential verification. Differential verification can cause severely biased estimates test model being...
While the importance of automatic image analysis is continuously increasing, recent meta-research revealed major flaws with respect to algorithm validation. Performance metrics are particularly key for meaningful, objective, and transparent performance assessment validation used algorithms, but relatively little attention has been given practical pitfalls when using specific a task. These typically related (1) disregard inherent metric properties, such as behaviour in presence class...