A5067221769- EEG and Brain-Computer Interfaces
- Neonatal and fetal brain pathology
- Voice and Speech Disorders
- Non-Invasive Vital Sign Monitoring
- Functional Brain Connectivity Studies
- Heart Rate Variability and Autonomic Control
- Face Recognition and Perception
- Speech Recognition and Synthesis
- Neural dynamics and brain function
- Climate Change Communication and Perception
- Neonatal Respiratory Health Research
- Thermoregulation and physiological responses
- Blind Source Separation Techniques
- Protein Tyrosine Phosphatases
- Gaze Tracking and Assistive Technology
- Dysphagia Assessment and Management
- Behavioral Health and Interventions
- Infrared Thermography in Medicine
- Infant Development and Preterm Care
- Emotion and Mood Recognition
- Cognitive and developmental aspects of mathematical skills
- Social and Intergroup Psychology
- Decision-Making and Behavioral Economics
- Infant Health and Development
- Aesthetic Perception and Analysis
University of Florence
2017-2025
Massachusetts General Hospital
2024
University of Siena
2020-2023
University of Pisa
2023
Florence (Netherlands)
2019
In Neonatal Intensive Care Units (NICUs), the early detection of neonatal seizures is utmost importance for a timely, effective and efficient clinical intervention. The continuous video electroencephalogram (v-EEG) gold standard monitoring seizures, but it requires specialized equipment expert staff available 24/24h. purpose this study to present an overview main Seizure Detection (NSD) systems developed during last ten years that implement Artificial Intelligence techniques detect report...
The increasing use of Electroencephalography (EEG) in the field pediatric neurology allows more accurate and precise diagnosis several cerebral pathologies, mainly Neonatal Intensive Care Units (NICUs), where it represents gold-standard for neonatal epileptic seizures. However, EEG interpretation is time consuming requires highly specialized staff. For this reason, last years there was a growing interest development systems automatic fast detection To aim, we propose here hybrid that...
Adductor spasmodic dysphonia is a type of adult-onset focal dystonia characterized by involuntary spasms laryngeal muscles. This paper applied machine learning techniques for the severity assessment dysphonia. To this aim, 7 perceptual indices and 48 acoustical parameters were estimated from Italian word /a'jwɔle/ emitted 28 female patients, manually segmented standardized sentence used as features in two classification experiments. Subjects divided into three classes (mild, moderate,...
The human brain's role in face processing (FP) and decision making for social interactions depends on recognizing faces accurately. However, the prevalence of deepfakes, AI-generated images, poses challenges discerning real from synthetic identities. This study investigated healthy individuals' cognitive emotional engagement a visual discrimination task involving deepfake expressing positive, negative, or neutral emotions. Electroencephalographic (EEG) data were collected 23 participants...
The complex physiological dynamics of neonatal seizures make their detection challenging. A timely diagnosis and treatment, especially in intensive care units, are essential for a better prognosis the mitigation possible adverse effects on newborn’s neurodevelopment. In literature, several electroencephalographic (EEG) studies have been proposed parametric characterization or by artificial intelligence techniques. At same time, other sources than EEG, such as electrocardiography,...
In Neonatal Intensive Care Units (NICUs), the early detection of neonatal seizures is utmost importance for a timely clinical intervention. Over years, several seizure systems were proposed to detect automatically and speed up diagnosis, most based on EEG signal analysis. Recently, research has focused other possible markers, such as electrocardiography (ECG). This work proposes an ECG-based NSD system investigate usefulness heart rate variability (HRV) analysis in NICUs. HRV performed...
Abstract This study delves into functional brain-heart interplay (BHI) dynamics during interictal periods before and after seizure events in focal epilepsy. Our analysis focuses on elucidating the causal interaction between cortical autonomic nervous system (ANS) oscillations, employing electroencephalography heart rate variability series. The dataset for this investigation comprises 47 from 14 independent subjects, obtained publicly available Siena Dataset. findings reveal an impaired axis...
Perceptual and statistical evidence has highlighted voice characteristics of individuals affected by genetic syndromes that differ from those normophonic subjects. In this paper, we propose a procedure for systematically collecting such pathological voices developing AI-based automated tools to support differential diagnosis. Guidelines on the most appropriate recording devices, vocal tasks, acoustical parameters are provided simplify, speed up, make whole homogeneous reproducible. The...
Seizures represent one of the most challenging issues neonatal period's neurological emergency. Due to heterogeneity etiologies and clinical characteristics, seizures recognition is tricky time-consuming. Currently, gold standard for seizure diagnosis Electroencephalography (EEG), whose correct interpretation requires a highly specialized team. Thus, speed up facilitate detection ictal events, several EEG-based Neonatal Seizure Detectors (NSDs) have been proposed in literature. Research...
An efficient face detector could be very helpful to point out possible neurological dysfunctions such as seizure events in Neonatal Intensive Care Units. However, its development is still challenging because large public datasets of newborns' faces are missing. Over the years several studies introduced semi-automatic approaches. This study proposes a fully automated for newborns Units, based on Aggregate Channel Feature algorithm. The developed method tested dataset video recordings from 42...
Early neonatal seizures detection is one of the most challenging issues in Neonatal Intensive Care Units. Several EEG-based Seizure Detectors were proposed to support clinical staff. However, less invasive and more easily interpretable methods than EEG are still missing. In this work, we investigated if Heart Rate Variability analysis related measures as input features supervised classifiers could be a valid for discriminating between newborns with seizure-free ones. The validated on 52...
METHODS:Between 2019 and 2020, EEG recordings from two institutions that had been recorded with a ninechannel bipolar montage, included seizure patterns, were collected.The records classifi ed into those before 37 weeks postmenstrual age (preterm EEGs) onward (term EEGs).EEG without patterns also collected.Using the Nihon Kohden seizure-detection program (model QL-162A), these retrospectively re-analyzed to assess capability.Experienced investigators evaluated all EEGs for presence or...
Pseudowords (PW) are invented or possible words (W) that do not really exist. They a tool for assessing speech and learning disorders in various clinical applications, including research children, youth, older adults. This paper analyzes electroencephalographic (EEG) signals from dry-EEG system during 15-by-15 words/pseudowords aloud reading (WPWAR) task group of forty-four healthy volunteers. The N400 event-related potential (ERP) component its power spectrum density (PSD) were analyzed W...
The development of programs and campaigns to promote climate change awareness actions should account for implicit attitudes make them effective. Alongside behavioural measures, it is important investigate understand the neural mechanisms underlying unconscious beliefs, opinions how external factors can influence them. Therefore, this study administered a Single-Category Implicit Association Test 22 healthy volunteers while acquiring EEG signals. After an automatic preprocessing pipeline was...
The early detection of neurodevelopmental disorders in newborns is utmost importance clinical practice. Recently, to predict the neurodevelopment scores preterms, Artificial Intelligence (AI) methods have been proposed mainly based on Electroencephalographic (EEG) or heart rate variability (HRV) analysis. In this work, HRV measures preterm with and without Sepsis are computed used as input features AI regression models. study assesses reliability such predicting BAYLEY-III obtained during...