A5001565828- Machine Learning in Healthcare
- Artificial Intelligence in Healthcare and Education
- COVID-19 diagnosis using AI
- Artificial Intelligence in Healthcare
- Chronic Disease Management Strategies
- Health Systems, Economic Evaluations, Quality of Life
- Explainable Artificial Intelligence (XAI)
- COVID-19 Clinical Research Studies
- Meta-analysis and systematic reviews
- Topic Modeling
- Asthma and respiratory diseases
- COVID-19 and healthcare impacts
- Particle accelerators and beam dynamics
- Sepsis Diagnosis and Treatment
- COVID-19 epidemiological studies
- Health Policy Implementation Science
- Chronic Obstructive Pulmonary Disease (COPD) Research
- Venous Thromboembolism Diagnosis and Management
- Global Health Care Issues
- Wireless Sensor Networks for Data Analysis
- Digital Mental Health Interventions
- Advanced Causal Inference Techniques
- Healthcare Policy and Management
- Heparin-Induced Thrombocytopenia and Thrombosis
- Healthcare Systems and Reforms
Erasmus MC
2020-2025
Erasmus University Rotterdam
2021-2022
Columbia University
2020
Abstract Background We investigated whether we could use influenza data to develop prediction models for COVID-19 increase the speed at which can reliably be developed and validated early in a pandemic. Estimated Risk (COVER) scores that quantify patient’s risk of hospital admission with pneumonia (COVER-H), hospitalization requiring intensive services or death (COVER-I), fatality (COVER-F) 30-days following diagnosis using historical from patients flu-like symptoms tested this patients....
<title>Abstract</title> Objective We investigate whether a trade-off occurs between predictive performance and model interpretability in real-world health care data illustrate how to develop <italic>clinically optimal</italic> decision rules by learning under constraints with the Exhaustive Procedure for Logic-Rule Extraction (EXPLORE) algorithm. Methods enhanced EXPLORE’s scalability enable its use datasets developed an R package that generates simple rules. compared 7 state-of-the-art...
This article's main contributions are twofold: 1) to demonstrate how apply the general European Union's High-Level Expert Group's (EU HLEG) guidelines for trustworthy AI in practice domain of healthcare and 2) investigate research question what does "trustworthy AI" mean at time COVID-19 pandemic. To this end, we present results a post-hoc self-assessment evaluate trustworthiness an system predicting multiregional score conveying degree lung compromise patients, developed verified by...
Objective To develop and externally validate COVID-19 Estimated Risk (COVER) scores that quantify a patient’s risk of hospital admission (COVER-H), requiring intensive services (COVER-I), or fatality (COVER-F) in the 30-days following diagnosis. Methods We analyzed federated network electronic medical records administrative claims data from 14 sources 6 countries. developed validated 3 using 6,869,127 patients with general practice, emergency room, outpatient visit diagnosed influenza...
Background SARS-CoV-2 is straining health care systems globally. The burden on hospitals during the pandemic could be reduced by implementing prediction models that can discriminate patients who require hospitalization from those do not. COVID-19 vulnerability (C-19) index, a model predicts which will admitted to hospital for treatment of pneumonia or proxies, has been developed and proposed as valuable tool decision-making pandemic. However, at high risk bias according “prediction...
There is an increasing interest to use real-world data illustrate how patients with specific medical conditions are treated in real life. Insight the current treatment practices helps improve and tailor patient care, but often held back by a lack of interoperability high-level required resources. We aimed provide easy tool that overcomes these barriers support standardized development analysis patterns for wide variety conditions.We formally defined process constructing pathways implemented...
Many countries have introduced competition among hospitals aiming to improve their performance. We evaluate the introduction of in Netherlands over years 2008-2015. The analysis is based on a unique longitudinal data set covering all Dutch and health insurers, as well demographic geographic data. measure hospital performance using Data Envelopment Analysis distinguish three components competition: fraction freely negotiated services, market power hospitals, insurer bargaining power. present...
Abstract Background SARS-CoV-2 is straining healthcare systems globally. The burden on hospitals during the pandemic could be reduced by implementing prediction models that can discriminate between patients requiring hospitalization and those who do not. COVID-19 vulnerability (C-19) index, a model predicts which will admitted to hospital for treatment of pneumonia or proxies, has been developed proposed as valuable tool decision making pandemic. However, at high risk bias according...
Background: Thrombosis with thrombocytopenia syndrome (TTS) has been identified as a rare adverse event following some COVID-19 vaccines. Various guidelines have issued on the treatment of TTS. We aimed to characterize TTS and other thromboembolic events (venous thromboembolism (VTE), arterial (ATE) after vaccination compared historical (pre-vaccination) data in Europe US. Methods: conducted an international network cohort study using 8 primary care, outpatient, inpatient databases from...
There is a lack of knowledge on how patients with asthma or chronic obstructive pulmonary disease (COPD) are globally treated in the real world, especially regard to initial pharmacological treatment newly diagnosed and different trajectories. This important monitor improve clinical practice.
ABSTRACT Background and objectives There is an increasing interest to use real-world data illustrate how patients with specific medical conditions are treated in real life. Insight the current treatment practices helps improve tailor patient care. We aim provide easy tool support development analysis of pathways for a wide variety conditions. Methods formally defined process constructing developed open-source R package TreatmentPatterns ( https://github.com/mi-erasmusmc/TreatmentPatterns )...
Inequities in waiting times for deceased donor organ transplantation have received considerable attention the last three decades and motivated allocation policy reforms. This holds particularly true kidney United States, where more than 90,000 patients are wait listed average vary considerably among from different blood types ethnic groups. research presents a novel approach to formally model, analyze, optimize equity of transplant probabilities using queuing models, network flows, Rawls’...
Feature importance is often used to explain clinical prediction models. In this work, we examine three challenges using experiments with electronic health record data: computational feasibility, choosing between methods, and interpretation of the resulting explanation. This work aims create awareness disagreement feature methods underscores need for guidance practitioners how deal these discrepancies.
<sec> <title>BACKGROUND</title> SARS-CoV-2 is straining health care systems globally. The burden on hospitals during the pandemic could be reduced by implementing prediction models that can discriminate patients who require hospitalization from those do not. COVID-19 vulnerability (C-19) index, a model predicts which will admitted to hospital for treatment of pneumonia or proxies, has been developed and proposed as valuable tool decision-making pandemic. However, at high risk bias according...