dr. ir. Axel Faes #LeadingAIinHealth

Postdoctoral Researcher

  • Postdoctoral Researcher (Machine Learning) @ Biomedical Data Sciences, UHasselt
    • Investigating the use of AI in real-world evidence healthcare studies.
    • Creating a federated learning algorithm for heart disease prediction.
    • Developing machine learning models for brain-computer interfaces.
    • Side project: working on algebraic type and effect systems for functional programming.
  • Computational Neuroscientist
  • Scientific Coordinator of the Flanders AI Research Program, Use Case Real World Evidence (FAIR UC RWE)
  • Professional Affiliations:
    • Biomedical Research Institute (BIOMED) @ UHasselt
    • Data Science Institute (DSI) @ UHasselt

Would you like to know more?


Vision for Research Impact (view more )
I envision a future where biomedical data science, machine learning, and artificial intelligence are leveraged to revolutionize healthcare. I aim to:

  • Innovate in Health Data Analysis: By developing innovative methods for analyzing and interpreting complex health data, I seek to advance the field of precision medicine and improve patient outcomes.
  • Advance Brain-Computer Interfaces: My work focuses on the understanding and application of brain-computer interfaces (BCIs) and neural decoding, aiming to enhance the interface between technology and neural activity.
  • Bridge Research and Practice: By combining expertise in data science, engineering, and medicine, I aim to bridge the gap between theoretical research and practical implementations, ultimately contributing to the development of more effective and personalized healthcare solutions.

Vision for Educational Impact
I envision a future where education in biomedical data science and AI is accessible, engaging, and impactful. I aim to:

  • Inspire Future Researchers: By mentoring students and conducting educational workshops, I seek to inspire the next generation of scientists and engineers to pursue innovative research in biomedical data sciences and neurotechnology.
  • Promote Interdisciplinary Learning: My work underscores the importance of interdisciplinary approaches, combining insights from neuroscience, biomedical science, engineering, and computer science to solve complex problems. I aim to foster a learning environment that encourages such cross-disciplinary collaborations.
  • Develop Educational Resources: Through my publications and open-source projects I plan to provide comprehensive resources that make advanced topics in AI and biomedical data science more accessible to learners worldwide.

Updates

Selected Publications (view all )
Decoding Sign Language Finger Movements from high-density ECoG using Graph-Optimized Block Term Tensor Regression

Axel Faes, Mariana P. Branco, Anais Van Hoylandt, Elina Keirse, Tom Theys, Nick F. Ramsey, Marc M. Van Hulle

Submitted to Journal of Neural Engineering (5.4 IF) (Under review) 2024

Objective A novel method is introduced to regress over the Sign Language finger movements from human electrocorticography (ECoG) recordings. Approach The proposed Graph-Optimized Block-Term Tensor Regression (Go-BTTR) method consists of two components: a deflation-based regression model that sequentially Tucker-decomposes multiway ECoG data into a series of blocks, and a Causal Graph Process (CGP) that accounts for the complex relationship between finger movements when expressing sign language gestures. Prior to each regression block, CGP is applied to decide which fingers should be kept separate or grouped and should therefore be referred to BTTR or its extended version eBTTR, respectively. Main results Two ECoG datasets were used, one recorded in 5 patients expressing 4 hand gestures of the American Sign Language Alphabet, and another in 2 patients expressing all gestures of the Flemish Sign Language Alphabet. As Go-BTTR combines fingers in a flexible way, it can better account for the nonlinear relationship ECoG exhibits when expressing hand gestures, including unintentional finger co-activations. This is reflected by the superior joint finger trajectory predictions compared to eBTTR, and predictions that are on par with BTTR in single finger scenarios. Subject 5, Dataset 1, during the movement of hand gestures reached 0.82 Pearson correlation for the pinky for Go-BTTR compared to 0.8 and 0.72 for eBTTR and BTTR respectively. Significance Our findings show that Go-BTTR is capable of decoding complex hand gestures taken from the Sign Language Alphabet. Go-BTTR also demonstrates computational efficiency, providing a notable benefit when intracranial electrodes are inserted during a patient’s pre-surgical evaluation. This efficiency helps reduce the time required for developing and testing a Brain-Computer Interface (BCI) solution.

Decoding Sign Language Finger Movements from high-density ECoG using Graph-Optimized Block Term Tensor Regression

Axel Faes, Mariana P. Branco, Anais Van Hoylandt, Elina Keirse, Tom Theys, Nick F. Ramsey, Marc M. Van Hulle

Submitted to Journal of Neural Engineering (5.4 IF)(Under review) 2024

Objective A novel method is introduced to regress over the Sign Language finger movements from human electrocorticography (ECoG) recordings. Approach The proposed Graph-Optimized Block-Term Tensor Regression (Go-BTTR) method consists of two components: a deflation-based regression model that sequentially Tucker-decomposes multiway ECoG data into a series of blocks, and a Causal Graph Process (CGP) that accounts for the complex relationship between finger movements when expressing sign language gestures. Prior to each regression block, CGP is applied to decide which fingers should be kept separate or grouped and should therefore be referred to BTTR or its extended version eBTTR, respectively. Main results Two ECoG datasets were used, one recorded in 5 patients expressing 4 hand gestures of the American Sign Language Alphabet, and another in 2 patients expressing all gestures of the Flemish Sign Language Alphabet. As Go-BTTR combines fingers in a flexible way, it can better account for the nonlinear relationship ECoG exhibits when expressing hand gestures, including unintentional finger co-activations. This is reflected by the superior joint finger trajectory predictions compared to eBTTR, and predictions that are on par with BTTR in single finger scenarios. Subject 5, Dataset 1, during the movement of hand gestures reached 0.82 Pearson correlation for the pinky for Go-BTTR compared to 0.8 and 0.72 for eBTTR and BTTR respectively. Significance Our findings show that Go-BTTR is capable of decoding complex hand gestures taken from the Sign Language Alphabet. Go-BTTR also demonstrates computational efficiency, providing a notable benefit when intracranial electrodes are inserted during a patient’s pre-surgical evaluation. This efficiency helps reduce the time required for developing and testing a Brain-Computer Interface (BCI) solution.

Federated Block-Term Tensor Regression for Heart Diseases in Realistic Healthcare Settings

Axel Faes, Liesbet Peeters

2024 Spotlight

This paper presents an extension of the Block-Term Tensor Regression (BTTR) algorithm, termed Federated Block-Term Tensor Regression (FBTTR), designed to address the unique challenges of heart disease prediction in realistic healthcare settings. Traditional machine learning models often rely on centralized data, which poses significant privacy risks and limits the scalability of predictive models across multiple institutions. FBTTR adapts BTTR to federated learning scenarios, allowing decentralized data from various healthcare institutions to be utilized without compromising patient privacy. The proposed FBTTR method leverages the strengths of tensor regression in handling multi-dimensional data, enhancing predictive accuracy through collaborative learning while ensuring data confidentiality. By incorporating federated learning principles, FBTTR facilitates secure model training across different sites, effectively mitigating data silos and promoting a more comprehensive understanding of heart disease predictors. Empirical evaluations demonstrate the robustness of FBTTR, showing that it achieves high predictive performance comparable to traditional centralized models. Moreover, the algorithm exhibits efficient computational performance, making it suitable for deployment in real-world healthcare environments where timely and accurate predictions are crucial. The results highlight FBTTR's potential in advancing predictive analytics in healthcare by providing a scalable, privacy-preserving solution for heart disease prediction, ultimately contributing to better patient outcomes and more effective healthcare delivery.

Federated Block-Term Tensor Regression for Heart Diseases in Realistic Healthcare Settings

Axel Faes, Liesbet Peeters

2024 Spotlight

This paper presents an extension of the Block-Term Tensor Regression (BTTR) algorithm, termed Federated Block-Term Tensor Regression (FBTTR), designed to address the unique challenges of heart disease prediction in realistic healthcare settings. Traditional machine learning models often rely on centralized data, which poses significant privacy risks and limits the scalability of predictive models across multiple institutions. FBTTR adapts BTTR to federated learning scenarios, allowing decentralized data from various healthcare institutions to be utilized without compromising patient privacy. The proposed FBTTR method leverages the strengths of tensor regression in handling multi-dimensional data, enhancing predictive accuracy through collaborative learning while ensuring data confidentiality. By incorporating federated learning principles, FBTTR facilitates secure model training across different sites, effectively mitigating data silos and promoting a more comprehensive understanding of heart disease predictors. Empirical evaluations demonstrate the robustness of FBTTR, showing that it achieves high predictive performance comparable to traditional centralized models. Moreover, the algorithm exhibits efficient computational performance, making it suitable for deployment in real-world healthcare environments where timely and accurate predictions are crucial. The results highlight FBTTR's potential in advancing predictive analytics in healthcare by providing a scalable, privacy-preserving solution for heart disease prediction, ultimately contributing to better patient outcomes and more effective healthcare delivery.

Finger movement and coactivation predicted from intracranial brain activity using extended Block-Term Tensor Regression

Axel Faes, Marc M. Van Hulle

Journal of Neural Engineering (5.4 IF) 2023 Spotlight

Multiway- or tensor-based decoding techniques for Brain-Computer Interfaces (BCI) are believed to better account for the multilinear structure of brain signals than conventional vector- or matrix-based ones. However, despite their outlook on significant performance gains, the used parameter optimization approach is often too computationally demanding, so conventional techniques are still preferred. We propose two novel tensor factorizations which we integrate into our Block-Term Tensor Regression (BTTR) algorithm and further introduce a marginalization procedure that guarantees robust predictions while reducing the risk of overfitting (generalized regression). BTTR accounts for the underlying (hidden) data structure in a fully automatic and computationally-efficient manner, leading to a significant performance gain over conventional vector- or matrix-based techniques in a challenging real-world application. As a challenging real-world application, we apply BTTR to accurately predict single finger movement trajectories from intracranial recordings in human subjects. We compare the obtained performance with that of the state-of-the-art.

Finger movement and coactivation predicted from intracranial brain activity using extended Block-Term Tensor Regression

Axel Faes, Marc M. Van Hulle

Journal of Neural Engineering (5.4 IF) 2023 Spotlight

Multiway- or tensor-based decoding techniques for Brain-Computer Interfaces (BCI) are believed to better account for the multilinear structure of brain signals than conventional vector- or matrix-based ones. However, despite their outlook on significant performance gains, the used parameter optimization approach is often too computationally demanding, so conventional techniques are still preferred. We propose two novel tensor factorizations which we integrate into our Block-Term Tensor Regression (BTTR) algorithm and further introduce a marginalization procedure that guarantees robust predictions while reducing the risk of overfitting (generalized regression). BTTR accounts for the underlying (hidden) data structure in a fully automatic and computationally-efficient manner, leading to a significant performance gain over conventional vector- or matrix-based techniques in a challenging real-world application. As a challenging real-world application, we apply BTTR to accurately predict single finger movement trajectories from intracranial recordings in human subjects. We compare the obtained performance with that of the state-of-the-art.

All publications