A5000424011- Semantic Web and Ontologies
- Biomedical Text Mining and Ontologies
- Clinical practice guidelines implementation
- AI-based Problem Solving and Planning
- Electronic Health Records Systems
- Logic, Reasoning, and Knowledge
- Business Process Modeling and Analysis
- Natural Language Processing Techniques
- Topic Modeling
- Machine Learning in Healthcare
- Advanced Database Systems and Queries
- Service-Oriented Architecture and Web Services
- Scientific Computing and Data Management
- Meta-analysis and systematic reviews
- Formal Methods in Verification
- Data Quality and Management
- Data Mining Algorithms and Applications
- Rough Sets and Fuzzy Logic
- Chronic Disease Management Strategies
- Artificial Intelligence in Healthcare
- Big Data and Business Intelligence
- Explainable Artificial Intelligence (XAI)
- Evolutionary Algorithms and Applications
- Logic, programming, and type systems
- Colorectal Cancer Screening and Detection
Vrije Universiteit Amsterdam
2016-2025
CNI College
2021
Amsterdam UMC Location Vrije Universiteit Amsterdam
2014-2016
University of Amsterdam
1994-2013
Knowledge Foundation
2003-2008
Utrecht University
2000-2003
Japan External Trade Organization
2002
This paper provides a survey to and comparison of state-of-the-art Semantic Web reasoners that succeed in classifying large ontologies expressed the tractable OWL 2 EL profile. Reasoners are characterized along several dimensions: The first dime
Abstract The unification of statistical (data-driven) and symbolic (knowledge-driven) methods is widely recognized as one the key challenges modern AI. Recent years have seen a large number publications on such hybrid neuro-symbolic AI systems. That rapidly growing literature highly diverse, mostly empirical, lacking unifying view variety these In this paper, we analyze body recent propose set modular design patterns for hybrid, We are able to describe architecture very systems by composing...
We propose a set of compositional design patterns to describe large variety systems that combine statistical techniques from machine learning with symbolic knowledge representation.As in other areas computer science (knowledge engineering, software ontology process mining and others), such help systematize the literature, clarify which combinations serve purposes, encourage re-use components.We have validated our against body recent literature.
Machine Learning (ML) can improve the diagnosis, treatment decisions, and understanding of cancer. However, low explainability how "black box" ML methods produce their output hinders clinical adoption. In this paper, we used data from Netherlands Cancer Registry to generate a ML-based model predict 10-year overall survival breast cancer patients. Then, Local Interpretable Model-Agnostic Explanations (LIME) SHapley Additive exPlanations (SHAP) interpret model's predictions. We found that,...
In a large distributed system it is often infeasible or even impossible to perform diagnosis using single model of the whole system. Instead, several spatially local models have be used detect possible faults. Traditional diagnostic tools, however, are not suitable deal with such set models.A Multi-Agent System agents, where each agent has model\footnote[Here, we focus on Model-Based Diagnosis.] subsystem, may proposed as solution for establishing global diagnoses systems. Unfortunately,...
The formal representation of clinical knowledge is still an open research topic. Classical languages for guidelines are used to produce diagnostic and treatment plans. However, they have important limitations, e.g. when looking ways re-use, combine, reason over ex isting knowledge. These limitations especially problematic in the context multimorbidity; patients that suffer from multiple diseases. To overcome these this paper proposes a model (TMR4I) allows re-use combination guidelines....
Our study aims to assess the influence of data quality on computed Dutch hospital indicators, and whether colorectal cancer surgery indicators can be reliably based routinely recorded from an electronic medical record (EMR). Cross-sectional in a department gastrointestinal oncology university hospital, which set 10 is (1) abstracted manually for national register Surgical Colorectal Audit (DSCA) as reference standard (2) collected EMR. All 75 patients whom has been submitted DSCA reporting...