Biology subjects

Gijsen, S.

Publications and source records attributed to Gijsen, S..

3 recordsLinked to original sources

bioRxiv2026

AI-based Psychiatric Prediction in Youth: Neuroimaging Provides Minimal Gains Beyond Confounds

Recent advances in artificial intelligence (AI) have raised interest in its potential to similarly progress biological psychiatry. This study investigates the current utility of AI models in predicting psychiatric phenotypes in youth - a critical window for psychiatric diagnosis - using neuroimaging data from a large developmental clinical cohort. We assessed the predictive performance of machine learning models on diverse psychiatric and non-psychiatric targets. We show that while models are able to predict various targets from EEG and fMRI data, simple models using only readily-available factors such as demographics and recording site match their performance for clinical phenotypes. This pattern holds across clinical targets and replicates for state-of-the-art deep neural networks, suggesting that either neuroimaging data contains limited disease-specific information or that current methods cannot reliably identify such patterns. These benchmarking results provide important context regarding promises of modern AI in the field of biological psychiatry with a focus on youth.

neuroscience↗

bioRxiv2022

EEG mismatch responses in a multi-modal roving stimulus paradigm provide evidence for probabilistic inference across audition, somatosensation and vision.

The human brain is constantly subjected to a multi-modal stream of probabilistic sensory inputs. EEG signatures, such as the mismatch negativity (MMN) and the P3, can give valuable insight into neuronal probabilistic inference. Although reported for different modalities, mismatch responses have largely been studied in isolation, with a strong focus on the auditory MMN. To investigate the extent to which early and late mismatch responses across modalities represent comparable signatures of uni- and cross-modal probabilistic inference in the hierarchically structured cortex, we recorded EEG from 32 participants undergoing a novel tri-modal roving stimulus paradigm. The employed sequences consisted of high and low intensity stimuli in the auditory, somatosensory and visual modalities and were governed by uni-modal transition probabilities and cross-modal conditional dependencies. We found modality specific signatures of MMN ([~]100-200ms) in all three modalities, which were source localized to the respective sensory cortices and shared right lateralized pre-frontal sources. Additionally, we identified a cross-modal signature of mismatch processing in the P3a time range ([~]300-350ms), for which a common network with frontal dominance was found. Across modalities, the mismatch responses showed highly comparable parametric effects of stimulus train length, which were driven by standard and deviant response modulations in opposite directions. Strikingly, the P3a responses across modalities were increased for mispredicted compared to predicted and unpredictable stimuli, suggesting sensitivity to cross-modal predictive information. Finally, model comparisons indicated that the observed single trial dynamics were best captured by Bayesian learning models tracking uni-modal stimulus transitions as well as cross-modal conditional dependencies.

neuroscience↗

bioRxiv2020

Neural surprise in somatosensory Bayesian learning

Tracking statistical regularities of the environment is important for shaping human behavior and perception. Evidence suggests that the brain learns environmental dependencies using Bayesian principles. However, much remains unknown about the employed algorithms, for somesthesis in particular. Here, we describe the cortical dynamics of the somatosensory learning system to investigate both the form of the generative model as well as its neural surprise signatures. Specifically, we recorded EEG data from 40 participants subjected to a somatosensory roving-stimulus paradigm and performed single-trial modeling across peri-stimulus time in both sensor and source space. Our Bayesian model selection procedure indicates that evoked potentials are best described by a non-hierarchical learning model that tracks transitions between observations using leaky integration. From around 70ms post-stimulus onset, secondary somatosensory cortices are found to represent confidence-corrected surprise as a measure of model inadequacy. Primary somatosensory cortex is found to encode Bayesian surprise, reflecting model updating, from around 140ms. As such, this dissociation indicates that early surprise signals may control subsequent model update rates. In sum, our findings support the hypothesis that early somatosensory processing reflects Bayesian perceptual learning and contribute to an understanding of its precise mechanisms. Author summaryOur environment features statistical regularities, such as a drop of rain predicting imminent rainfall. Despite the importance for behavior and survival, much remains unknown about how these dependencies are learned, particularly for somatosensation. As surprise signalling about novel observations indicates a mismatch between ones beliefs and the world, it has been hypothesized that surprise computation plays an important role in perceptual learning. By analyzing EEG data from human participants receiving sequences of tactile stimulation, we compare different formulations of surprise and investigate the employed underlying learning model. Our results indicate that the brain estimates transitions between observations. Furthermore, we identified different signatures of surprise computation and thereby provide a dissociation of the neural correlates of belief inadequacy and belief updating. Specifically, early surprise responses from around 70ms were found to signal the need for changes to the model, with encoding of its subsequent updating occurring from around 140ms. These results provide insights into how somatosensory surprise signals may contribute to the learning of environmental statistics.

neuroscience↗