Florian van Daalen

Mr. Florian van Daalen


Research Focus & Metrics

Academic Career Length

5Years (2022-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
23 January 2023 in IEEE Transactions on Parallel and Distributed Systems
Verified
Journal Article
Open access
FDFlorian van Daalen
Florian van Daalen
LILianne Ippel
Lianne Ippel
ADAndre Dekker
Andre Dekker
IBInigo Bermejo
Inigo Bermejo
Privacy-preserving machine learning enables the training of models on decentralized datasets without the need to reveal the information, both on horizontally and vertically partitioned data. However, it requires specialized techniques and algorithms to perform the necessary computations. The privacy preserving scalar product protocol, which enables the dot product of vectors without revealing them, is one popular example for its versatility. For example it can be used to perform analyses that require counting the number of samples which fulfill certain criteria defined across various sites, such as calculating the information gain at a node in a decision tree. Unfortunately, the solutions currently proposed in the literature focus on two-party scenarios, even though scenarios with a higher number of data parties are becoming more relevant. In this paper, we propose a generalization of the protocol for an arbitrary number of parties, based on an existing two-party method. Our proposed solution relies on a recursive resolution of smaller scalar products. After describing our proposed method, we discuss potential scalability issues. Finally, we describe the privacy guarantees and identify any concerns, as well as comparing the proposed method to the original solution in this aspect. Additionally we provide an online repository containing the code.

17 October 2022 in JMIR Cardio
Verified
Journal Article
Open access
BSBart Scheenstra
Bart Scheenstra
ABAnke Bruninx
Anke Bruninx
FDFlorian van Daalen
Florian van Daalen
NSNina Stahl
Nina Stahl
ELElizabeth Latuapon
Elizabeth Latuapon
BKBas Kietselaer
Bas Kietselaer
Digital health is a promising tool to support people with an elevated risk for atherosclerotic cardiovascular disease (ASCVD) and patients with an established disease to improve cardiovascular outcomes. Many digital health initiatives have been developed and employed. However, barriers to their large-scale implementation have remained. This paper focuses on these barriers and presents solutions as proposed by the Dutch CARRIER (ie, Coronary ARtery disease: Risk estimations and Interventions for prevention and EaRly detection) consortium. We will focus in 4 sections on the following: (1) the development process of an eHealth solution that will include design thinking and cocreation with relevant stakeholders; (2) the modeling approach for two clinical prediction models (CPMs) to identify people at risk of developing ASCVD and to guide interventions; (3) description of a federated data infrastructure to train the CPMs and to provide the eHealth solution with relevant data; and (4) discussion of an ethical and legal framework for responsible data handling in health care. The Dutch CARRIER consortium consists of a collaboration between experts in the fields of eHealth development, ASCVD, public health, big data, as well as ethics and law. The consortium focuses on reducing the burden of ASCVD. We believe the future of health care is data driven and supported by digital health. Therefore, we hope that our research will not only facilitate CARRIER consortium but may also facilitate other future health care initiatives.

20 June 2025 in Ethics and Information Technology
Verified
Journal Article
Open access
PDF file
FDFlorian van Daalen
Florian van Daalen
MJMarine Jacquemin
Marine Jacquemin
JSJohan van Soest
Johan van Soest
NSNina Stahl
Nina Stahl
DTDavid Townend
David Townend
IBInigo Bermejo
Inigo Bermejo
Access to large datasets, the rise of the Internet of Things (IoT) and the ease of collecting personal data, have led to significant breakthroughs in machine learning. However, they have also raised new concerns about privacy data protection. Controversies like the Facebook-Cambridge Analytica scandal highlight unethical practices in today’s digital landscape. Historical privacy incidents have led to the development of technical and legal solutions to protect data subjects’ right to privacy. However, within machine learning, these problems have largely been approached from a mathematical point of view, ignoring the larger context in which privacy is relevant. This technical approach has benefited data-controllers and failed to protect individuals adequately. Moreover, it has aligned with Big Tech organizations’ interests and allowed them to further push the discussion in a direction that is favorable to their interests. This paper reflects on current privacy approaches in machine learning and explores how various big organizations guide the public discourse, and how this harms data subjects. It also critiques the current data protection regulations, as they allow superficial compliance without addressing deeper ethical issues. Finally, it argues that redefining privacy to focus on harm to data subjects rather than on data breaches would benefit data subjects as well as society at large.

25 April 2024 in Complex & Intelligent Systems
Verified
Journal Article
Open access
PDF file
FDFlorian van Daalen
Florian van Daalen
LILianne Ippel
Lianne Ippel
ADAndré Dekker
André Dekker
IBInigo Bermejo
Inigo Bermejo
Federated learning makes it possible to train a machine learning model on decentralized data. Bayesian networks are widely used probabilistic graphical models. While some research has been published on the federated learning of Bayesian networks, publications on Bayesian networks in a vertically partitioned data setting are limited, with important omissions, such as handling missing data. We propose a novel method called VertiBayes to train Bayesian networks (structure and parameters) on vertically partitioned data, which can handle missing values as well as an arbitrary number of parties. For structure learning we adapted the K2 algorithm with a privacy-preserving scalar product protocol. For parameter learning, we use a two-step approach: first, we learn an intermediate model using maximum likelihood, treating missing values as a special value, then we train a model on synthetic data generated by the intermediate model using the EM algorithm. The privacy guarantees of VertiBayes are equivalent to those provided by the privacy preserving scalar product protocol used. We experimentally show VertiBayes produces models comparable to those learnt using traditional algorithms. Finally, we propose two alternative approaches to estimate the performance of the model using vertically partitioned data and we show in experiments that these give accurate estimates.

29 September 2025 in Progress in Artificial Intelligence
Verified
Journal Article
Open access
PDF file
FDFlorian van Daalen
Florian van Daalen
RBRalph Brecheisen
Ralph Brecheisen
LWLeonard Wee
Leonard Wee
ADAndré Dekker
André Dekker
IBInigo Bermejo
Inigo Bermejo
Certainty of classifications is crucial when it comes to the practical application of machine learning models. Model performance measures such as accuracy are focused on the average performance of a model. However, when a model is used in a practical setting, such as a medical clinic, it is more important to know how certain the model is of a given prediction or classification than its average performance. Unfortunately, often models only provide a final classification label, usually of the class with the highest probability. This output, however, is not sufficiently informative of the certainty of this particular classification, especially in the presence of multiple classes: the highest probability might be only barely higher than the second highest. Even when a probability distribution is provided, there is no established metric to determine if a particular classification is more certain than a different one. In this article we propose a novel metric we have termed Multinomial Classification Certainty, to represent the certainty of model predictions. We discuss why existing methods cannot represent this type of certainty and we show the mathematical meaning behind important thresholds for this new measure.

31 January 2025 in Cancer Medicine
Verified
Journal Article
Open access
MHMargrethe Bang Henriksen
Margrethe Bang Henriksen
FDFlorian van Daalen
Florian van Daalen
LWLeonard Wee
Leonard Wee
THTorben Hansen
Torben Hansen
LJLars Henrik Jensen
Lars Henrik Jensen
IBInigo Bermejo
Inigo Bermejo
Background: Lung cancer (LC) is the top cause of cancer deaths globally, prompting many countries to adopt LC screening programs. While screening typically relies on age and smoking intensity, more efficient risk models exist. We devised a Bayesian network (BN) for LC detection, testing its resilience with varying degrees of missing data and comparing it to a prior machine learning (ML) model.Methods: We analyzed data from 9940 patients referred for LC assessment in Southern Denmark from 2009 to 2018. Variables included age, sex, smoking, and lab results. Our experiments varied missing data (0%–30%), BN structure (expert‐based vs. data‐driven), and discretization method (standard vs. data‐driven).Results: Across all missing data levels, area under the curve (AUC) remained steady, ranging from 0.737 to 0.757, compared to the ML model's AUC of 0.77. BN structure and discretization method had minimal impact on performance. BNs were well calibrated overall, with a net benefit in decision curve analysis when predicted risk exceeded 5%.Conclusion: BN models showed resilience with up to 30% missing values. Moreover, these BNs exhibited similar performance, calibration, and clinical utility compared to the machine learning model developed using the same dataset. Considering their effectiveness in handling missing data, BNs emerge as a relevant method for the development of future lung cancer detection models.