Biology subjects

Pedroni, A.

Publications and source records attributed to Pedroni, A..

6 recordsLinked to original sources

bioRxiv2022

The AI Neuropsychologist: Automatic scoring of memory deficits with deep learning

BackgroundMemory deficits are a hallmark of many different neurological and psychiatric conditions. The Rey-Osterrieth complex figure (ROCF) is the state-of-the-art assessment tool for neuropsychologists across the globe to assess the degree of non-verbal visual memory deterioration. To obtain a score, a trained clinician inspects a patients ROCF drawing and quantifies deviations from the original figure. This manual procedure is time-consuming, slow and scores vary depending on the clinicians experience, motivation and tiredness. MethodsHere, we leverage novel deep learning architectures to automatize the rating of memory deficits. For this, we collected more than 20k hand-drawn ROCF drawings from patients with various neurological and psychiatric disorders as well as healthy participants. Unbiased ground truth ROCF scores were obtained from crowdsourced human intelligence. This dataset was used to train and evaluate a multi-head convolutional neural network. ResultsThe model performs highly unbiased as it yielded predictions very close to the ground truth and the error was similarly distributed around zero. The neural network outperforms both online raters and clinicians. The scoring system can reliably identify and accurately score individual figure elements in previously unseen ROCF drawings, which facilitates explainability of the AI-scoring system. To ensure generalizability and clinical utility, the model performance was successfully replicated in a large independent prospective validation study that was pre-registered prior to data collection. ConclusionsOur AI-powered scoring system provides healthcare institutions worldwide with a digital tool to assess objectively, reliably and time-efficiently the performance in the ROCF test from hand-drawn images.

neuroscience↗

bioRxiv2021

Decomposing age effects in EEG alpha power

Increasing life expectancy is prompting the need to understand how the brain changes during healthy aging. Research utilizing Electroencephalography (EEG) has found that the power of alpha oscillations decrease from adulthood on. However, non-oscillatory (aperiodic) components in the data may confound results and thus require re-investigation of these findings. The present report aims at analyzing a pilot and two additional independent samples (total N = 533) of resting-state EEG from healthy young and elderly individuals. A newly developed algorithm will be utilized that allows the decomposition of the measured signal into aperiodic and aperiodic-adjusted signal components. By using multivariate sequential Bayesian updating of the age effect in each signal component, evidence across the datasets will be accumulated. It is hypothesized that previously reported age-related alpha power differences will disappear when absolute power is adjusted for the aperiodic signal component. Consequently, age-related differences in the intercept and slope of the aperiodic signal component are expected. Importantly, using a battery of neuropsychological tests, we will assess how the previously reported relationship between cognitive functions and alpha oscillations changes when taking the aperiodic signal into account; this will be done on data of the young and aged individuals separately. The aperiodic signal components and adjusted alpha parameters could potentially offer a promising biomarker for cognitive decline, thus finally the test-retest reliability of the aperiodic and aperiodic-adjusted signal components will be assessed.

neuroscience↗

bioRxiv2019

Large scale analysis of the diversity and complexity of the adult spinal cord neurotransmitter typology

The development of nervous system atlases is a fundamental pursuit in neuroscience, since they constitute a fundamental tool to improve our understanding of the nervous system and behavior. As such, neurotransmitter maps are valuable resources to decipher the nervous system organization and functionality. We present here the first comprehensive quantitative map of neurons found in the adult zebrafish spinal cord. Our study overlays detailed information regarding the anatomical positions, sizes, neurotransmitter phenotypes, and the projection patterns of the spinal neurons. We also show that neurotransmitter co-expression is much more extensive than previously assumed, suggesting that spinal networks are more complex than first recognized. As a first direct application of this atlas, we investigated the neurotransmitter diversity in the putative glutamatergic V2a interneuron assembly of the adult zebrafish spinal cord. These studies shed new light on the diverse and complex functions of this important interneuron class in the neuronal interplay governing the precise operation of the central pattern generators.

neuroscience↗

bioRxiv2018

AUTOMAGIC: Standardized Preprocessing of Big EEG Data

Electroencephalography (EEG) recordings have been rarely included in large-scale studies. This is arguably not due to a lack of information that lies in EEG recordings but mainly on account of methodological issues. In many cases, particularly in clinical, pediatric and aging populations, the EEG has a high degree of artifact contamination and the quality of EEG recordings often substantially differs between subjects. Although there exists a variety of standardized preprocessing methods to clean EEG from artifacts, currently there is no method to objectively quantify the quality of preprocessed EEG. This makes the commonly accepted procedure of excluding subjects from analyses due to exceeding contamination of artifacts highly subjective. As a consequence, P-hacking is fostered, the replicability of results is decreased, and it is difficult to pool data from different study sites. In addition, in large-scale studies, data are collected over years or even decades, requiring software that controls and manages the preprocessing of ongoing and dynamically growing studies. To address these challenges, we developed Automagic, an open-source MATLAB toolbox that acts as a wrapper to run currently available preprocessing methods and offers objective standardized quality assessment for growing studies. The software is compatible with the Brain Imaging Data Structure (BIDS) standard and hence facilitates data sharing. In the present paper we outline the functionality of Automagic and examine the effect of applying combinations of methods on a sample of resting EEG data. This examination suggests that applying a pipeline of algorithms to detect artifactual channels in combination with Multiple Artifact Rejection Algorithm (MARA), an independent component analysis (ICA)-based artifact correction method, is sufficient to reduce a large extent of artifacts.

neuroscience↗

bioRxiv2018

Microstate EEGlab toolbox: An introductory guide

EEG microstate analysis offers a sparse characterisation of the spatio-temporal features of large-scale brain network activity. However, despite the concept of microstates is straight-forward and offers various quantifications of the EEG signal with a relatively clear neurophysiological interpretation, a few important aspects about the currently applied methods are not readily comprehensible. Here we aim to increase the transparency about the methods to facilitate widespread application and reproducibility of EEG microstate analysis by introducing a new EEGlab toolbox for Matlab. EEGlab and the Microstate toolbox are open source, allowing the user to keep track of all details in every analysis step. The toolbox is specifically designed to facilitate the development of new methods. While the toolbox can be controlled with a graphical user interface (GUI), making it easier for newcomers to take their first steps in exploring the possibilities of microstate analysis, the Matlab framework allows advanced users to create scripts to automatise analysis for multiple subjects to avoid tediously repeating steps for every subject. This manuscript provides an overview of the most commonly applied microstate methods as well as a tutorial consisting of a comprehensive walk-through of the analysis of a small, publicly available dataset.

neuroscience↗

bioRxiv2017

A multi-modal approach to decomposing standard neuropsychological test performance: Symbol Search

Neuropsychological test batteries provide normed assessments of cognitive performance across multiple functional domains. Although each test emphasizes a certain component of cognition, a poor score can reflect many possible processing deficits. Here we explore the use of simultaneous eye tracking and EEG to decompose test performance into interpretable, components of cognitive processing. We examine the specific case of Symbol Search, a \"processing speed\" subtest of the WISC, which involves searching for the presence of either of two target symbols among five search symbols. To characterize the signatures of effective performance of the test, we asked 26 healthy adults to perform a computerized version of it while recording continuous EEG and eye tracking. We first established basic gaze-shifting patterns in the task, such as more frequent and prolonged fixation of each target than each search symbol, and longer search symbol fixations and overall trial duration for target-absent trials. We then entered multiple such metrics into a least absolute shrinkage and selection operator (LASSO) analysis, which revealed that short trial completion times were mainly predicted by longer initial fixations on the targets and fewer subsequent confirmatory saccades directed back to the targets. Further, the tendency to make confirmatory saccades was associated with stronger gamma-amplitude modulation by mid-frontal theta-phase in the EEG during initial target symbol encoding. Taken together, these findings indicate that efficient Symbol Search performance depends more on effective memory encoding than on general \"processing speed\".

neuroscience↗