A5051277378- Mental Health Research Topics
- Neural dynamics and brain function
- Cell Image Analysis Techniques
- Digital Mental Health Interventions
- Bipolar Disorder and Treatment
- Functional Brain Connectivity Studies
- Generative Adversarial Networks and Image Synthesis
- Advanced Fluorescence Microscopy Techniques
- Emotion and Mood Recognition
- Heart Rate Variability and Autonomic Control
- Electroconvulsive Therapy Studies
- EEG and Brain-Computer Interfaces
- Advanced Image Processing Techniques
- Psychosomatic Disorders and Their Treatments
- Advanced Malware Detection Techniques
- Image Processing Techniques and Applications
- CCD and CMOS Imaging Sensors
- Adversarial Robustness in Machine Learning
- Image and Signal Denoising Methods
- Physics and Engineering Research Articles
- Eating Disorders and Behaviors
- Network Packet Processing and Optimization
- VLSI and Analog Circuit Testing
- Cancer survivorship and care
- Software Engineering Research
University of Edinburgh
2020-2025
The Alan Turing Institute
2025
Hospital Clínic de Barcelona
2022-2023
Universitat de Barcelona
2023
Art Institute of Portland
2019
Depressive and manic episodes within bipolar disorder (BD) major depressive (MDD) involve altered mood, sleep, activity, alongside physiological alterations wearables can capture. Firstly, we explored whether wearable data could predict (aim 1) the severity of an acute affective episode at intra-individual level 2) polarity euthymia among different individuals. Secondarily, which were related to prior predictions, generalization across patients, associations between symptoms data. We...
Mood disorders (MDs) are among the leading causes of disease burden worldwide. Limited specialized care availability remains a major bottleneck thus hindering pre-emptive interventions. MDs manifest with changes in mood, sleep, and motor activity, observable ecological physiological recordings thanks to recent advances wearable technology. Therefore, near-continuous passive collection data from wearables daily life, analyzable machine learning (ML), could mitigate this problem, bringing...
This work details CipherGAN, an architecture inspired by CycleGAN used for inferring the underlying cipher mapping given banks of unpaired ciphertext and plaintext. We demonstrate that CipherGAN is capable cracking language data enciphered using shift Vigenere ciphers to a high degree fidelity vocabularies much larger than previously achieved. present how can be made compatible with discrete train in stable way. then prove technique avoids common problem uninformative discrimination...
Abstract Mood disorders are among the leading causes of disease burden worldwide. They manifest with changes in mood, sleep, and motor-activity, observable physiological data. Despite effective treatments being available, limited specialized care availability is a major bottleneck, hindering preemptive interventions. Nearcontinuous passive collection data from wearables daily life, analyzable machine learning, could mitigate this problem, bringing mood monitoring outside doctor’s office....
Background Bipolar disorder is highly prevalent and consists of biphasic recurrent mood episodes mania depression, which translate into altered mood, sleep activity alongside their physiological expressions. Aims The IdenTifying dIgital bioMarkers illnEss treatment response in BipolAr diSordEr with a novel wearable device (TIMEBASE) project aims to identify digital biomarkers illness bipolar disorder. Method We designed longitudinal observational study including 84 individuals. Group A...
Affective states influence the sympathetic nervous system, inducing variations in electrodermal activity (EDA), however, EDA association with bipolar disorder (BD) remains uncertain real-world settings due to confounders like physical and temperature. We analysed separately during sleep wakefulness varying potential differences mood state discrimination capacities. monitored from 102 participants BD including 35 manic, 29 depressive, 38 euthymic patients, healthy controls (HC), for 48 h....
Vast quantities of Magnetic Resonance Images (MRI) are routinely acquired in clinical practice but, to speed up acquisition, these scans typically a quality that is sufficient for diagnosis but sub-optimal large-scale precision medicine, computational diagnostics, and neuroimaging collaborative research. Here, we present critic-guided framework upsample low-resolution (often 2D) MRI full help overcome limitations. We incorporate feature-importance self-attention methods into our model...
Personal sensing, leveraging data passively and near-continuously collected with wearables from patients in their ecological environment, is a promising paradigm to monitor mood disorders (MDs), major determinant of the worldwide disease burden. However, collecting annotating wearable resource intensive. Studies this kind can thus typically afford recruit only few dozen patients. This constitutes one obstacles applying modern supervised machine learning techniques MD detection.
Bipolar disorder (BD) is a severe psychiatric condition featuring autonomic nervous system dysfunctions, detectable with abnormal heart rate variability (HRV). This promising biomarker, but its dynamics over an acute episode of mania or depression, the two polarities BD, are poorly understood. Studies intra- individual HRV changes in BD cannot afford to recruit more than only few dozen patients, as collecting this kind data very resource-intensive. makes ground treacherous for frequentist...
Abstract Bipolar disorder (BD) is a severe psychiatric condition featuring autonomic nervous system dysfunctions, detectable with abnormal heart rate variability (HRV). This promising biomarker, but its dynamics over an acute episode of mania or depression, the two polarities BD, are poorly understood. Studies intra-individual HRV changes in BD cannot afford to recruit more than only few dozen patients, as collecting this kind data very resource-intensive. makes ground treacherous for...
Bipolar disorder (BD) involves autonomic nervous system dysfunction, detectable through heart rate variability (HRV). HRV is a promising biomarker, but its dynamics during acute mania or depression episodes are poorly understood. Using Bayesian approach, we developed probabilistic model of changes in BD, measured by the natural logarithm Root Mean Square Successive RR interval Differences (lnRMSSD). Patients were assessed three to four times from episode onset euthymia. Unlike previous...
152 Background: Interventions that reduce symptom distress and enhance positive feelings are crucial for improving quality of life and, conceivably, overall survival cancer patients. One remedy is the immersive virtual reality relaxation (VR-R) environment/s to inspire an emotion-focused coping mechanism in Herein, we report on our experience with use this VR-R intervention normal volunteers patient volunteers. Methods: Fifty underwent training used 5 - 30 minutes. a software-based...
A bstract Vast quantities of Magnetic Resonance Images (MRI) are routinely acquired in clinical practice but, to speed up acquisition, these scans typically a quality that is sufficient for diagnosis but sub-optimal large-scale precision medicine, computational diagnostics, and neuroimaging research. Here, we present critic-guided framework upsample low-resolution (often 2D) MRI scans. In addition, incorporated feature-importance self-attention methods into our model improve the...
A bstract Mood disorders are severe and chronic mental conditions exacting high costs from society. The lack of reliable biomarkers to aid clinicians in tailoring pharmacotherapy based on distinguishable patient-specific traits means that the current prescribing paradigm is largely one trial error. Previous studies showed different biological signatures, such as patterns heart rate variability or electro-dermal reactivity, associated with clinically meaningful outcomes. Against this...
Calcium imaging has become a powerful and popular technique to monitor the activity of large populations neurons in vivo. However, for ethical considerations despite recent technical developments, recordings are still constrained limited number trials animals. This limits amount data available from individual experiments hinders development analysis techniques models more realistic sizes neuronal populations. The ability artificially synthesize calcium signals could greatly alleviate this...
Introduction Mood episodes in bipolar disorder (BD) are still identified with subjective retrospective reports and scales. Digital biomarkers, such as actigraphy, heart rate variability, or ElectroDermal activity (EDA) have demonstrated their potential to objectively capture illness activity. Objectives To identify physiological digital signatures of during acute BD compared euthymia healthy controls (HC) using a novel wearable device (Empatica´s E4). Methods A pragmatic exploratory study....
Understanding how activity in neural circuits reshapes following task learning could reveal fundamental mechanisms of learning. Thanks to the recent advances imaging technologies, high-quality recordings can be obtained from hundreds neurons over multiple days or even weeks. However, complexity and dimensionality population responses pose significant challenges for analysis. Existing methods studying neuronal adaptation often impose strong assumptions on data model, resulting biased...
Accurate predictive models of the visual cortex neural response to natural stimuli remain a challenge in computational neuroscience. In this work, we introduce V1T, novel Vision Transformer based architecture that learns shared and behavioral representation across animals. We evaluate our model on two large datasets recorded from mouse primary outperform previous convolution-based by more than 12.7% prediction performance. Moreover, show self-attention weights learned correlate with...