Paola Galdi

Paola Galdi
University of Edinburgh | UoE · School of Informatics

PhD in Computer Science
Machine learning for health and medicine

About

55
Publications
54,107
Reads
How we measure 'reads'
A 'read' is counted each time someone views a publication summary (such as the title, abstract, and list of authors), clicks on a figure, or views or downloads the full-text. Learn more
1,016
Citations
Introduction
I am a computer scientist with a background in machine learning and statistical modelling. I have worked for several years with neuroimaging and biomedical data with a focus on predictive modelling. I am interested in multi-modal data integration and applications of AI to health data.

Publications

Publications (55)
Preprint
Full-text available
Neurosymbolic (NeSy) artificial intelligence describes the combination of logic or rule-based techniques with neural networks. Compared to neural approaches, NeSy methods often possess enhanced interpretability, which is particularly promising for biomedical applications like drug discovery. However, since interpretability is broadly defined, there...
Preprint
Full-text available
Background Multimorbidity, the co-occurrence of two or more conditions within an individual, is a growing challenge for health and care delivery as well as for research. Combinations of physical and mental health conditions are highlighted as particularly important. The aim of this study was to investigate associations between physical multimorbidi...
Article
Introduction Predicting risk of care home admission could identify older adults for early intervention to support independent living but require external validation in a different dataset before clinical use. We systematically reviewed external validations of care home admission risk prediction models in older adults. Methods We searched Medline,...
Article
The early life environment programmes cortical architecture and cognition across the life course. A measure of cortical organisation that integrates information from multimodal MRI and is unbound by arbitrary parcellations has proven elusive, which hampers efforts to uncover the perinatal origins of cortical health. Here, we use the Vogt‐Bailey ind...
Article
Full-text available
In this work, we take a closer look at the Vogt-Bailey (VB) index, proposed in Bajada et al. (NeuroImage 221:117140, 2020) as a tool for studying local functional homogeneity in the human cortex. We interpret the VB index in terms of the minimum ratio cut, a scaled cut-set weight that indicates whether a network can easily be disconnected into two...
Article
Full-text available
A cardinal feature of the encephalopathy of prematurity is dysmaturation of developing white matter and subsequent hypomyelination. Magnetisation transfer imaging (MTI) offers surrogate markers for myelination, including magnetisation transfer ratio (MTR) and magnetisation transfer saturation (MTsat). Using data from 105 neonates, we characterise M...
Article
Full-text available
Importance: Preterm birth and socioeconomic status (SES) are associated with brain structure in childhood, but the relative contributions of each during the neonatal period are unknown. Objective: To investigate associations of birth gestational age (GA) and SES with neonatal brain morphology by testing 3 hypotheses: GA and SES are associated wi...
Preprint
Full-text available
A cardinal feature of the encephalopathy of prematurity is dysmaturation of developing white matter and subsequent hypomyelination. Magnetisation transfer imaging (MTI) offers surrogate markers for myelination including magnetisation transfer ratio (MTR) and magnetisation transfer saturation (MTsat). Using data from 105 neonates, we characterise MT...
Preprint
Full-text available
Importance: Preterm birth and socioeconomic status (SES) are associated with brain structure in childhood, but the relative contributions of each during the neonatal period are unknown. Objective: To investigate associations of gestational age (GA) and SES with neonatal brain morphology, by testing 3 hypotheses: GA and SES are associated with brain...
Article
Objective: Breast milk (BM) exposure is associated with improved neurocognitive outcomes following preterm birth but the neural substrates linking BM with outcome are uncertain. We tested the hypothesis that high versus low BM exposure in preterm infants results in cortical morphology that more closely resembles that of term-born infants. Methods...
Preprint
Full-text available
The early life environment programmes cortical architecture and cognition across the life course. A measure of cortical organisation that integrates information from multi-modal MRI and is unbound by arbitrary parcellations has proven elusive, which hampers efforts to uncover the perinatal origins of cortical health. Here, we use the Vogt-Bailey in...
Article
Full-text available
In this work, we identify a problem with the process of volume-to-surface mapping of functional Magnetic Resonance Imaging (fMRI) data that emerges in local connectivity analysis. We show that neighborhood correlations on the surface of the brain vary spatially with the gyral structure, even when the underlying volumetric data are uncorrelated nois...
Article
Full-text available
Preterm birth is closely associated with diffuse white matter dysmaturation inferred from diffusion MRI and neurocognitive impairment in childhood. Diffusion tensor imaging (DTI) and neurite orientation dispersion and density imaging (NODDI) are distinct dMRI modalities, yet metrics derived from these two methods share variance across tracts. This...
Article
Full-text available
This data release of 117 healthy community-dwelling adults provides multimodal high-quality neuroimaging and behavioral data for the investigation of brain-behavior relationships. We provide structural MRI, resting-state functional MRI, movie functional MRI, together with questionnaire-based and task-based psychological variables; many of the parti...
Article
Full-text available
Preterm birth is associated with dysconnectivity of structural brain networks and is a leading cause of neurocognitive impairment in childhood. Variation in DNA methylation is associated with early exposure to extrauterine life but there has been little research exploring its relationship with brain development. Using genome-wide DNA methylation da...
Preprint
Full-text available
Breast milk exposure is associated with improved neurocognitive outcomes following preterm birth but the neural substrates linking nutrition with outcome are uncertain. By combining nutritional data with brain MRI, we tested the hypothesis that high versus low breast milk exposure in preterm infants during neonatal care results in a cortical morpho...
Preprint
Full-text available
Preterm birth is closely associated with diffuse white matter dysmaturation inferred from diffusion MRI and neurocognitive impairment in childhood. Diffusion tensor imaging (DTI) and neurite orientation dispersion and density imaging (NODDI) are distinct dMRI modalities, yet metrics derived from these two methods share variance across tracts. This...
Article
Full-text available
Background: Preterm birth can lead to impaired language development. This study aimed to predict language outcomes at 2 years corrected gestational age (CGA) for children born preterm. Methods: We analysed data from 89 preterm neonates (median GA 29 weeks) who underwent diffusion MRI (dMRI) at term-equivalent age and language assessment at 2 yea...
Article
Full-text available
Introduction Preterm infants are at increased risk of exposure to histologic chorioamnionitis (HCA) when compared to term-born controls, and this is associated with several neonatal morbidities involving brain, lungs and gut. Preterm infants could benefit from immunomodulatory therapies in the perinatal period, but development of rational treatment...
Preprint
Full-text available
Objective To characterise the umbilical cord blood immune profile in preterm infants compared to term-born controls and the postnatal immune response following exposure to histologic chorioamnionitis (HCA) in preterm infants. Design Descriptive, observational cohort study. Setting Edinburgh, UK. Population 118 preterm infants (mean gestational a...
Preprint
Full-text available
Preterm birth is associated with dysconnectivity of structural brain networks and is a leading cause of neurocognitive impairment in childhood. Variation in DNA methylation (DNAm) is associated with early exposure to extrauterine life but there has been little research exploring its relationship with brain development. Using genome-wide DNA methyla...
Article
Adult hair glucocorticoid concentrations reflect months of hypothalamic-pituitary-adrenal axis activity. However, little is known about the determinants of neonatal hair glucocorticoids. We tested associations between perinatal exposures and neonatal hair glucocorticoids. Cortisol and cortisone were measured by LC-MS/MS in paired maternal and infan...
Article
Full-text available
The human adult structural connectome has a rich nodal hierarchy, with highly diverse connectivity patterns aligned to the diverse range of functional specializations in the brain. The emergence of this hierarchical complexity in human development is unknown. Here, we substantiate the hierarchical tiers and hierarchical complexity of brain networks...
Article
Full-text available
The mechanisms linking maternal stress in pregnancy with infant neurodevelopment in a sexually dimorphic manner are poorly understood. We tested the hypothesis that maternal hypothalamic-pituitary-adrenal axis activity, measured by hair cortisol concentration (HCC), is associated with microstructure, structural connectivity, and volume of the infan...
Article
Full-text available
Background: Preterm birth is associated with dysconnectivity of structural brain networks, impaired cognition and psychiatric disease. Systemic inflammation contributes to cerebral dysconnectivity, but the immune mediators driving this association are poorly understood. We analysed information from placenta, umbilical cord and neonatal blood, and...
Preprint
Full-text available
The mechanisms linking maternal stress in pregnancy with infant neurodevelopment in a sexually dimorphic manner are poorly understood. We tested the hypothesis that maternal hypothalamic-pituitary-adrenal axis activity, measured by hair cortisol concentration, is associated with microstructure, structural connectivity and volume of the infant amygd...
Article
Full-text available
Preterm birth is closely associated with cognitive impairment and generalized dysconnectivity of neural networks inferred from water diffusion MRI (dMRI) metrics. Peak width of skeletonized mean diffusivity (PSMD) is a metric derived from histogram analysis of mean diffusivity across the white matter skeleton, and it is a useful biomarker of genera...
Article
Full-text available
Preterm birth is closely associated with cognitive impairment and generalized dysconnectivity of neural networks inferred from water diffusion MRI (dMRI) metrics. Peak width of skeletonized mean diffusivity (PSMD) is a metric derived from histogram analysis of mean diffusivity across the white matter skeleton, and it is a useful biomarker of genera...
Article
Full-text available
Multi-contrast MRI captures information about brain macro- and micro-structure which can be combined in an integrated model to obtain a detailed "fingerprint" of the anatomical properties of an individual's brain. Inter-regional similarities between features derived from structural and diffusion MRI, including regional volumes, diffusion tensor met...
Preprint
Full-text available
The human adult structural connectome has a rich topology composed of nodal hierarchies containing highly diverse connectivity patterns, aligned to the diverse range of functional specialisations in the brain. The emergence of this hierarchical complexity in human development is unknown. Here, we substantiate the hierarchical tiers and complexity o...
Chapter
Full-text available
Electroencephalography (EEG)-based Brain–computer interface (BCI) technology allows a user to control an external device without muscle intervention through recorded neural activity. Ongoing research on BCI systems includes applications in the medical field to assist subjects with impaired motor functionality (e.g., for the control of prosthetic de...
Article
Full-text available
Background and aims: The main challenge in analysing functional magnetic resonance imaging (fMRI) data from extended samples of subject (N>100) is to extract as much relevant information as possible from big amounts of noisy data. When studying neurodegenerative diseases with resting-state fMRI, one of the objectives is to determine regions with ab...
Preprint
Full-text available
Multi-contrast MRI captures information about brain macro- and micro-structure which can be combined in an integrated model to obtain a detailed “fingerprint” of the anatomical properties of an individual’s brain. Inter-regional similarities between features derived from structural and diffusion MRI, including regional volumes, diffusion tensor met...
Preprint
Full-text available
Magnetic resonance imaging allows acquiring functional and structural connectivity data from which high-density whole-brain networks can be derived to carry out connectome-wide analyses in normal and clinical populations. Graph theory has been widely applied to investigate the modular structure of brain connections by using centrality measures to i...
Article
Full-text available
Magnetic resonance imaging allows acquiring functional and structural connectivity data from which high-density whole-brain networks can be derived to carry out connectome-wide analyses in normal and clinical populations. Graph theory has been widely applied to investigate the modular structure of brain connections by using centrality measures to i...
Chapter
Full-text available
Morphometric similarity networks (MSNs) have been recently proposed as a novel, robust, and biologically plausible approach to generate structural connectomes from neuroimaging data. In this work, we apply this method to multi-centre neonatal data (postmenstrual age range: 37–45 weeks) to predict brain dysmaturation in preterm infants. To achieve t...
Article
Full-text available
Individual people differ in their ability to reason, solve problems, think abstractly, plan and learn. A reliable measure of this general ability, also known as intelligence, can be derived from scores across a diverse set of cognitive tasks. There is great interest in understanding the neural underpinnings of individual differences in intelligence...
Article
Full-text available
The high-dimensional nature of resting state functional MRI (fMRI) data implies the need of suitable feature selection techniques. Traditional univariate techniques are fast and straightforward to interpret, but are unable to unveil relationships among multiple features. The aim of this work is to evaluate the applicability of clustering based tech...
Chapter
Full-text available
In the era of big data, the richness and variety of available data sets has opened new horizons for investigators in the bio-medical field. The ultimate challenge consists in building an integrated base of knowledge derived from heterogeneous sources. Multi-view learning is the branch of machine learning concerned with the analysis of multi-modal d...
Preprint
Full-text available
Background and aims: The main challenge in analysing functional magnetic resonance imaging (fMRI) data from extended samples of subject (N>100) is to extract as much relevant information as possible from big amounts of noisy data. When studying neurodegenerative diseases with resting-state fMRI, one of the objectives is to determine regions with ab...
Preprint
Full-text available
Individual people differ in their ability to reason, solve problems, think abstractly, plan and learn. A reliable measure of this general ability, also known as intelligence, can be derived from scores across a diverse set of cognitive tasks. There is great interest in understanding the neural underpinnings of individual differences in intelligence...
Article
Full-text available
Personality neuroscience aims to find associations between brain measures and personality traits. Findings to date have been severely limited by a number of factors, including small sample size and omission of out-of-sample prediction. We capitalized on the recent availability of a large database, together with the emergence of specific criteria fo...
Preprint
Full-text available
Personality neuroscience aims to find associations between brain measures and personality traits. Findings to date have been severely limited by a number of factors, including small sample size and omission of out-of-sample prediction. We capitalized on the recent availability of a large database, together with the emergence of specific criteria fo...
Article
Full-text available
Machine Learning (ML) is a well‐known paradigm that refers to the ability of systems to learn a specific task from the data and aims to develop computer algorithms that improve with experience. It involves computational methodologies to address complex real‐world problems and promises to enable computers to assist humans in the analysis of large, c...
Chapter
Full-text available
A variety of measures exist to assess the accuracy of predictive models in data mining and several aspects should be considered when evaluating the performance of learning algorithms. In this chapter, the most common accuracy and error scores for classification and regression are reviewed and compared. Moreover, the standard approaches to model sel...
Chapter
Full-text available
In this work we present Rotation clustering, a novel method for consensus clustering inspired by the classifier ensemble model Rotation Forest. We demonstrate the effectiveness of our method in a real world application, the identification of enriched gene sets in a TCGA dataset derived from a clinical study on Glioblastoma multiforme. The proposed...
Conference Paper
Full-text available
Real-world datasets, such as genomic data, are noisy and high-dimensional, and are therefore difficult to analyse without a preliminary step aimed to reduce data dimensionality and to select relevant features. Projection techniques are a useful tool to pre-process high dimensional data since they allow to achieve a simpler representation of the ori...
Conference Paper
Full-text available
In data analysis, clustering is the process of finding groups in unlabelled data according to similarities among them in such a way that data items belonging to the same group are more similar between each other than items in different groups. Consensus clustering is a methodology for combining different clustering solutions from the same data set...
Conference Paper
Full-text available
Clustering is an unsupervised learning technique used in data analysis to discover the underlying natural structure of data, without using prior knowledge. A fundamental issue with unsupervised clustering problems is how to find the optimal number of clusters. A few algorithms have been developed that try to find it automatically. Other approaches...

Network

Cited By