Completed Ph.D Projects [8]

13 Nov 2012: W. Bekkers, Ph.D.: Situational Process Improvement in Software Product Management. [1]

Willem’s dissertation investigates how software product management (SPM) practices can be improved in a situational manner. The first part presents an overview of all practices that constitute SPM in the SPM competence model and the SPM maturity matrix. Then, the situational factors that affect SPM in the situational factor effects catalog are defined. The final part presents the situational assessment method (SAM) which software product management organizations can assess and improve their SPM in a situational manner.

Funded by: Centric IT BV. Current position: Strategic product manager at Centric IT BV.

13 Jan 2016: M. Meulendijk, Ph.D.: Optimizing medication reviews through decision support: prescribing a better pill to swallow. [2]

Michiel’s dissertation investigates the conception and development of a decision support system to facilitate the conduct of structured medication reviews by physicians and pharmacists in primary care. The resulting STRIP Assistant system is validated in both a controlled environment and in daily practice, and is shown to significantly improve practitioners’ effectiveness and efficiency in optimizing medication. This work deepens our understanding of barriers currently impeding the utility of decision support systems in primary care, most notably those of semantic interoperability and safe application of association rule mining.

Funded by: UMCU/UU. Current positions: Head of Data at PHARMO.

20 March 2019: S. Syed, Ph.D.: Topic Discovery from Textual Data: Machine Learning and Natural Language Processing for Knowledge Discovery in the Fisheries Domain. [3]

Shaheen’s dissertation investigates how to optimally and efficiently apply and interpret probabilistic topic models to large collections of documents such as scientific publications. This work shows how different types of textual data, pre-processing steps, and hyper-parameter settings can affect the quality of the derived latent topics, using the Latent Dirichlet Allocation approach in particular.

Funded by: Horizon2020 Marie Skłodowska-Curie (MSC) – ITN – ETN; Current position: Postdoc at Arctic University Norway.

2 October 2019: V. Menger, Ph.D.: Knowledge Discovery in Clinical Psychiatry: Learning from Electronic Patient Records. [4]

Vincent’s dissertation investigates how data from Electronic Health Records can provide relevant insights for psychiatric care. The first three chapters identify key technical, organizational and ethical challenges related to knowledge discovery in EHRs. The next three chapters focus on the knowledge discovery processing by employing natural language processing and cluster ensembling techniques to EHR data to obtain new insights with potential to improve care

Funded by: UMCU. Current position: Machine learning engineer at UMC Utrecht.

14 October 2020: W. Omta: Knowledge Discovery in High Content Screening. [5]

Wienand’s research investigates how multi-parametric data analysis can contribute to effective knowledge discovery in High Content Screening. First, the HC StratoMineR analytic system is designed and validated based on unsupervised data analysis methods. Then, the gains and losses of using supervised data analytics methods and interactive visualizations are quantified. Furthermore, a standard data analysis protocol to automate the preprocessing process is designed and implemented in an R package. Finally, an exemplary laboratory practice application of the systems to a chemical screen demonstrates this research’s utility.

Funded by: UMCU/UU. Current position: CTO at Core Life Analytics B.V. (UU spin-off)

24 November 2020: N. Tawfik: Text Mining for Precision Medicine: Natural Language Processing, Machine Learning and Information Extraction for Knowledge Discovery in the Health Domain. [6]

Noha’s research investigates how biomedical natural language processing (BioNLP) can support and advance the Precision Medicine (PM) approach through collection and analysis of clinical and medical textual resources. The first two chapters contribute to the PM domain by obtaining valuable knowledge from unstructured resources. The other five chapters apply state-of-the-art NLP techniques to multiple data sources in order to better support the PM concept. This work focuses on combining traditional machine learning with deep learning techniques for the Natural Language Inference task, among others.

Funded by: Arab Academy for Science, Technology & Maritime Transport (AAST). Current position: Lecturer at AAST.

15 March 2021: A. Levebfre: Research data management for open science. [7]

Armel’s research investigates investigates research data management practices in laboratories in the context of open science.  First, it discusses organizational and technological issues among stakeholders involved in research data management. Then, Armel elaborates on the concept of reproducibility in experimental science.  Finally, it illustrates several applications of “FAIR technology” and proposes a strategy for open science readiness. The results of this work provides research laboratories and other stakeholders such as libraries, ICT, and funders with insights into reproducibility and open science challenges grounded into an investigation of laboratory work.

Funded by: Utrecht University's department of Information and Technology Services (UU/ITS). Current position: Research information officer at Erasmus Rotterdam university.

11 July 2022: B. Yigit Ozkan: Cybersecurity Maturity Assessment and Standardisation. [8]

Bilge’s dissertation investigates cybersecurity maturity assessment and cybersecurity standardisation to improve organisations' cybersecurity. She states her research objective as follows: To support the improvement of organisations' cybersecurity by means of maturity assessment and standardisation. To guide her research project, Bilge poses her main research question as “How can we integrate cybersecurity maturity assessment and cybersecurity standardisation to provide tailored support for organisations in their cybersecurity improvement efforts?”.

Funded by: Horizon 2020 EU project 740787 (SMESEC). Current position: IT Security Risk and Compliance Officer at DLL.

Current Ph.D Projects [10]

<Ordered based on expected graduation date>

2018-2022: I. Sarhan: Deep Learning for Query-based Summarisation (DEQUES). [1]

Ingy’s research focuses on Natural Language Processing for question answering systems, investigating both information retrieval and deep learning architectures, tentatively
through an implementation of a query-based summarization approach (Funded by Horizon2020, AAST).

2017-2022: A. Shojaifar: Web behaviour analytics in cybersecurity (SMESEC). [2]

Alireza’s SMESEC WP develops an automated cybersecurity assessment platform named Cybersecurity Coach (CySEC) which integrates personalised assessments, web usage behaviour, and advice adherence modelling, specifically for SMEs (Funded by Horizon2020).

2015-2023: Z. Shen: Prescriptive analytics in secondary care (OPERAM). [3]

Ian’s OPERAM WP2 developed a semantically interoperable and artificially intelligent medication prescribing platform named STRIP Assistant (STRIPA) 3.0 for OPtimising thERapy to prevent Avoidable hospital admissions in the Multimorbid elderly throughout Europe in part inspired by OpenCDS (Funded by Horizon2020).

2018-2024: C. van Toledo: Real-time Speech Analytic Systems for HR dialogue support (SpeechAS). [4]

Chaïm’s research focuses on real-time speech analytics for real-time dialogue enrichment within a Human Resources context, and other speech and text analytics applications related to large-scale call centres such as those at P-Direct (Funded by P-Direct).

2018-2024: F. van Dijk: Data Governance (DataGov). [5]

Friso’s research focuses on how an organisation can verifiably process data in a responsible manner, which requires a definition of responsible data usage and metrics to verify and quantify the extent of this, in order to implement an effective data governance strategy (Funded by P-Direct).

2020-2024: E. Rijcken: Dutch NLP in Mental Healthcare (COVIDA). [6]

Emil’s research is embedded wiithin the COVIDA programme on the development of a hybrid Dutch language model for Dutch Mental Healthcare language use, resulting in the public availability of the envisioned COVIDA self-service facility for Dutch NLP (Funded by UU/UMCU/TUe Alliance Fund)

2020-2024: M. van Haastrecht: Self-Service Cybersecurity Metric and Knowledge Graph Development (GEIGER). [7]

Max's work in the GEIGER project focuses on the development of an aggregate and personalised cybersecurity metric for assessing, monitoring, and forecasting risks and reducing these risks by improving SME security with well-curated SMESEC tools and an education program targeting daily practitioners, facilitated by a cybersecurity knowledge graph (Funded by Horizon2020). Co-promotor: M. Brinkhuis (UU).

2020-2024: B. van Dijk: A Telling Story. [8]

Bram works at the intersection of computational linguistics and NLP, in the context of Max van Duijn's NWO/VENI research grant, where he investigates how to model narrative characters’ mental depth in stories told by children aged 4-10. Co-promotor: M. van Duijn (LIACS). (Funded by NWO/VENI).

2021-2025: S. Alfaray: Prediction of Type II Diabetes Progression: Data to bedside. [9]

Sukainah's research reuses routinely collected data from the GP office (ELAN-GP) to create a clinical decision support tool to identify disease progression risk levels in Type Two Diabetes Mellitus (T2DM) patients. Supervisors: R. Groenwold, M. Spruit, D. Mook (LUMC/LIACS).

2021-2025: E. Roorda: Scenario planning for Population Health Management. [10]

Els' research focuses on maturity modelling for situational data infrastructure and scenario planning towards appropriate regional intelligence. Supervisors: M. Spruit, M. Bruijnzeels, J. Struijs (LUMC).

2022-2026: S. Samir Kahlil: Natural Language Processing in Mental Health: Detection, Prediction and Promotion with Multilingual, Multimodal and Federated Techniques. [11]

Samar's research focuses on how current NLP techniques can be applied and extended to support mental health detection and promotion, through collection and analysis of textual resources with multilingual, multimodal and federated techniques. Supervisors: M. Spruit, N. Tawfik (LIACS).

Postdocs/Programmers [4]

2015-2016: M. Meulendijk: OPERAM project [1]

Michiel’s work on the STRIP Assistant prescriptive polypharmacy platform focused on designing a unified information architecture for data integration in secondary care, supporting multicentre data consistency across countries while maintaining data accessibility and security.

Funded by: ZonMW/GGG. PhD from: UU. Subsequent position: postdoc at Leiden UMC.

2018-2018: L. Elloumi: STRIMP project [2]

Lamia’s work on the STRIP Assistant prescriptive polypharmacy platform focused on designing a unified interoperability layer between multiple health information systems in primary care.

Funded by: ZonMW/GGG. PhD from: TU Twente. Subsequent position: assistant prof. at UvT.

2018-2019: E. Brinkhuis: STRIMP project [3]

Edwin’s work as a senior bughunter on the STRIP Assistant prescriptive polypharmacy platform in the OPERAM, STRIMP and OPTICA projects focused on making STRIPA ready for production in daily primary care practices.

Funded by: ZonMW/GGG. MSc from: UvA.

2020-2021: P. Mosteiro: COVIDA project [4]

Pablo’s work revolves around the development of a hybrid Dutch language model for Mental Healthcare language use and to model our computational experiment findings from both Computational Linguistics (i.e. symbolic or rule-based) and Machine Learning (i.e. probabilistic) inspired representations. This will result in the public availability of the COVIDA self-service facility for Dutch Natural Language Processing.

Funded by: UU/UMCU/TUe Alliance Fund. PhD from: Princeton University.