A5056442086- Advanced Causal Inference Techniques
- Health Systems, Economic Evaluations, Quality of Life
- Natural Language Processing Techniques
- Web Data Mining and Analysis
- Patient-Provider Communication in Healthcare
- Music and Audio Processing
- Semantic Web and Ontologies
- Statistical Methods in Clinical Trials
- Topic Modeling
- Biomedical Text Mining and Ontologies
- Innovative Human-Technology Interaction
- Advanced Text Analysis Techniques
- Statistical Methods and Inference
- Music Technology and Sound Studies
- Global Cancer Incidence and Screening
- Algorithms and Data Compression
- Machine Learning in Healthcare
- Head and Neck Cancer Studies
- Heart Failure Treatment and Management
- AI in cancer detection
- Privacy-Preserving Technologies in Data
- Radiomics and Machine Learning in Medical Imaging
- Colorectal Cancer Surgical Treatments
- Digital Games and Media
- Speech and Audio Processing
Netherlands Comprehensive Cancer Organisation
2018-2025
Tilburg University
2023
Instituut Verbeeten
2020-2023
Philips (Finland)
2009-2019
Philips (Netherlands)
2006-2019
NXP (Netherlands)
2006-2014
Holst Centre (Netherlands)
2008
Cox Proportional Hazards (CPH) analysis is the standard for survival in oncology. Recently, several machine learning (ML) techniques have been adapted this task. Although they shown to yield results at least as good classical methods, are often disregarded because of their lack transparency and little no explainability, which key adoption clinical settings. In paper, we used data from Netherlands Cancer Registry 36,658 non-metastatic breast cancer patients compare performance CPH with ML...
Abstract Childhood cancers are a heterogeneous group of rare diseases, accounting for less than 2% all diagnosed worldwide. Most countries, therefore, do not have enough cases to provide robust information on epidemiology, treatment, and late effects, especially rarer types cancer. Thus, only through concerted effort share data internationally will we be able answer research questions that could otherwise answered. With this goal in mind, the U.S. National Cancer Institute French...
A recipe recommender system may stimulate healthful and varied eating, when the presented recipes fit lifestyle of user. As consumers face barrier to change their eating cooking behavior, we aim for a strategy provide more variations routine recipes. In this paper, similarity measure is derived by taking user-centered approach. Such can be used recommend healthier alternatives commonly selected meals, which are perceived similar. Recipes using demand health variation within boundaries busy...
We present a prototype of personalized recipe advice system, which facilitates its users to make health-aware meal choices based on past selections. To stimulate the adoption healthier lifestyle, goal setting mechanism is applied in combination with suggestions.
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,...
Abstract The difference in incidence of oral cavity cancer (OCC) between Taiwan and the Netherlands is striking. Different risk factors treatment expertise may result survival differences two countries. However due to regulatory restrictions, patient-level analyses combined data from are infeasible. We implemented a software infrastructure for federated on multiple organisations. included 41,633 patients with single-tumour OCC 2004 2016, undergoing surgery, Cancer Registry Registry....
Disclosure of cancer statistics (eg, survival or incidence rates) based on a representative group patients can help increase survivors' understanding their own diagnostic and prognostic situation, care planning. More recently, there has been an increasing interest in the use registry data for disclosing communicating personalized (tailored toward personal clinical characteristics) to survivors relatives.The aim this study was explore breast (BCa) prostate (PCa) survivor needs preferences...
We evaluate and compare the user acceptance of alternative text input methods for an interactive TV application. are interested in whether remote control-based acceptable alternatives to standard keyboard, when is assisted with intelligent entry entering a search term. The users asked music videos by using control or QWERTY keyboard. evaluated HED/UT questionnaire. results show that keyboard intelligence better rated these dimensions than control. However, there no negative attitude towards input.
Given a set of objects and their pairwise distances, we wish to determine visual representation the data. We use quartet paradigm compute hierarchy clusters objects. The method is based on an NP-hard graph optimization problem called Minimum Quartet Tree Cost problem. This paper presents compares several heuristic approaches approximate optimal hierarchy. performance algorithms tested through extensive computational experiments it shown that Reduced Variable Neighborhood Search most...
PURPOSE Randomized controlled trials are considered the golden standard for estimating treatment effect but costly to perform and not always possible. Observational data, although readily available, is sensitive biases such as confounding by indication. Structure learning algorithms Bayesian Networks (BNs) can be used discover underlying model from data. This enables identification of confounders through graph analysis, might contain noncausal edges. We propose using a blacklist aid...
Abstract Background Long-term colon cancer survivors present heterogeneous health-related quality of life (HRQOL) outcomes. We determined unobserved subgroups (classes) with similar HRQOL patterns and investigated their stability over time the association clinical covariates these classes. Materials Methods Data from population-based PROFILES registry were used. Included nonmetastatic (TNM stage I–III) (n = 1,489). was assessed Dutch translation European Organisation for Research Treatment...
This paper describes work in progress the European Artemis project Smarcos. Smarcos focuses on interusability of multi-device embedded and networked services. The presented here is devoted to development context-aware personal coaching service systems that give users personalized feedback empower them make healthy lifestyle choices. Our target group consists diabetes type II patients intervention concerns situated with respect physical activity medicine compliance. We describe stages...
PURPOSE Real-world evidence (RWE)—derived from analysis of real-world data (RWD)—has the potential to guide personalized treatment decisions. However, because confounding, generating valid RWE is challenging. This study demonstrates how responsibly generate for We validate our approach by demonstrating that we can uncover an existing adjuvant chemotherapy (ACT) guideline stage II and III colon cancer (CC)—which came about using both randomized controlled trials expert consensus—solely RWD....