A5009328380- Biomedical Text Mining and Ontologies
- Machine Learning in Healthcare
- Semantic Web and Ontologies
- Artificial Intelligence in Healthcare and Education
- Sepsis Diagnosis and Treatment
- Healthcare Technology and Patient Monitoring
- Electronic Health Records Systems
- Artificial Intelligence in Healthcare
- Data Quality and Management
- Scientific Computing and Data Management
- Quality and Safety in Healthcare
- Advanced Database Systems and Queries
- Data-Driven Disease Surveillance
- Service-Oriented Architecture and Web Services
- Pharmacovigilance and Adverse Drug Reactions
- Advanced Text Analysis Techniques
- Natural Language Processing Techniques
Agfa HealthCare
2011-2016
Agfa-Gevaert (Belgium)
2015
Background Machine learning algorithms are currently used in a wide array of clinical domains to produce models that can predict risk events. Most developed and evaluated with retrospective data, very few workflow, even fewer report performances different hospitals. In this study, we provide detailed evaluations prediction live workflows for three use cases Objective The main objective study was evaluate compare their performance these setting when using data. We also aimed at generalizing...
Machine learning (ML) algorithms are now widely used in predicting acute events for clinical applications. While most of such prediction applications developed to predict the risk a particular event at one hospital, few efforts have been made extending solutions other or different hospitals. We provide scalable solution extend process model development multiple diseases and their deployment Electronic Health Records (EHR) systems. defined generic development. A calibration tool has created...
Antibiotics resistance development poses a significant problem in today's hospital care. Massive amounts of clinical data are being collected and stored proprietary unconnected systems heterogeneous format. The DebugIT EU project promises to make this geographically semantically interoperable for case-based knowledge analysis approaches aiming at the discovery patterns that help align antibiotics treatment schemes. semantic glue endeavor is DCO, an application ontology enables miners query...
Depending mostly on voluntarily sent spontaneous reports, pharmacovigilance studies are hampered by low quantity and quality of patient data. Our objective is to improve postmarket safety enabling analysts seamlessly access a wide range EHR sources for collecting deidentified medical data sets selected populations tracing the reported incidents back original EHRs. We have developed an ontological framework where target clinical research systems can continue using their own local models,...
An inherent difference exists between male and female bodies, the historical under-representation of females in clinical trials widened this gap existing healthcare data. The fairness decision-support tools is at risk when developed based on biased This paper aims to quantitatively assess gender bias prediction models. We aim generalize our findings by performing investigation multiple use cases different hospitals. First, we conduct a thorough analysis source data find gender-based...
Background In recent years, machine learning (ML)–based models have been widely used in clinical domains to predict risk events. However, production, the performances of such heavily rely on changes system and data. The dynamic nature environment, characterized by continuous changes, has significant implications for prediction models, leading performance degradation reduced efficacy. Thus, monitoring model shifts evaluating their impact are utmost importance. Objective This study aimed...
There is a growing need to semantically process and integrate clinical data from different sources for Clinical Data Management Decision Support in the healthcare IT industry. In practice domain, semantic gap between information systems domain ontologies quite often difficult bridge one step. this paper, we report our experience using two-step formalization approach formalize data, i.e. database schemas local formalisms (unifying) formalisms. We use N3 rules explicitly formally state mapping...
The Simple Knowledge Organization System (SKOS) is popular for expressing controlled vocabularies, such as taxonomies, classifications, etc., their use in Semantic Web applications. Using SKOS, concepts can be linked to other and organized into hierarchies inside a single terminology system. Meanwhile, mappings between different systems also possible. This paper discusses potential quality issues using SKOS express these mappings. Problematic patterns are defined corresponding rules...
Objective: Machine learning algorithms are now widely used in predicting acute events for clinical applications. While most of such prediction applications developed to predict the risk a particular event at one hospital, few efforts have been made extending solutions other or different hospitals. We provide scalable solution extend process model development multiple diseases and their deployment Electronic Health Records (EHR) systems. Materials Methods: defined generic development. A...
<sec> <title>BACKGROUND</title> In recent years, machine learning (ML)–based models have been widely used in clinical domains to predict risk events. However, production, the performances of such heavily rely on changes system and data. The dynamic nature environment, characterized by continuous changes, has significant implications for prediction models, leading performance degradation reduced efficacy. Thus, monitoring model shifts evaluating their impact are utmost importance. </sec>...
Proper surveillance of infectious diseases poses special challenges to information technology when it comes data collection, including wide-area, multi-source and trans-border collection aggregation disease drug resistance information. In this project, we present a novel approach efficiently monitor bacterial over multiple international clinical entities.
Bacterial resistance to drugs has reached alarming levels but useful cross-site monitoring systems track evolution are lacking. In this paper we present the TrendMon surveillance system, a platform for querying, integrating and visualising antimicrobial information.
<sec> <title>BACKGROUND</title> Machine learning algorithms are currently used in a wide array of clinical domains to produce models that can predict risk events. Most developed and evaluated with retrospective data, very few workflow, even fewer report performances different hospitals. In this study, we provide detailed evaluations prediction live workflows for three use cases </sec> <title>OBJECTIVE</title> The main objective study was evaluate compare their performance these setting when...