Search

Human faces capture attention, provide information about group belonging, and elicit automatic prepared responses. Early experiences with other-race faces play a critical role in acquiring face expertise, but the exact mechanism through which early experience exerts its influence is still to be elucidated. Genetic factors and a multi-ethnic context are likely involved, but their specific influences have not been explored. This study investigated how oxytocin receptor gene (OXTR) genotypes and childcare experience interacted to regulate face categorization in adults. Information about single nucleotide polymorphisms of OXTR (rs53576) and experiences with own- and other-race child caregivers was collected from 89 Singaporean adults, who completed a visual categorization task with own- versus other-race faces. Participants were grouped into A/A homozygotes and G carriers and assigned a score to account for their type of child caregiver experience. A multivariate linear regression model was used to estimate the effect of genetic group, child caregiver experience, and their interaction on categorization reaction time. A significant interaction of genetic group and child caregiver experience (t = 2.48, p = 0.015), as well as main effects of both genetic group (t = -2.17, p = 0.033) and child caregiver experience (t = -4.29, p

Synchrony in developmental science reflects the coordination of mother and child to one another’s mental states. Mentalisation processes are influenced by individual attachment styles. A mother with an anxious attachment pattern tends to be hypervigilant to cues of rejection and likely to rely on her child’s facial expressions to interpret his/her mental states. We hypothesised that anxiously attached mothers are less able to attune to their child’s emotional state during an everyday joint activity, a state reflected in reduced brain-to-brain synchrony. To test this hypothesis, we profiled mothers’ Need for Approval (NfA), an index of attachment, and used functional Near-infrared Spectroscopy (fNIRS) hyperscanning with 31 mother-child dyads to measure prefrontal cortex (PFC) brain-to-brain synchrony while mother-child dyads watched three 1-min animation videos together. Greater maternal NfA is associated with less synchrony in the frontal left and medial left prefrontal clusters, which map to the left lateral PFC. This area of the brain is implicated in mentalisation. Anxiously attached mothers appear to exhibit less brain-to-brain synchrony with their child which indicates less attunement to his/her mental state, potentially undermining the quality of their shared experiences during everyday joint activities.

In recent years, the number of studies investigating possible noninvasive health screening techniques for infants have increased exponentially. Amongst those, one of the most prominent is health screening based on the acoustic investigation of infant cry. Clinicians involved in the field moved from visual inspection of the audible spectrum to automatized analysis of cry samples using computer software. A software that has been more widely adopted in recent years is Praat, a free software designed for speech analysis. Unfortunately, the software’s default settings are not suitable for investigation of cry samples, yet rarely used settings are reported in final manuscripts. In this article, we tested 4 different computer generated signals, with frequency features comparable to cry frequencies, and 3 real cry samples using both Praat’s standards and tuned settings. Our results highlight the importance of properly tuning software’s parameters when expanding their field of usage, and provide a starting point for the development of optimal Praat algorithm’s parameters selection for cry analysis Accepted version

Artificial Intelligence is exponentially increasing its impact on healthcare. As deep learning is mastering computer vision tasks, its application to digital pathology is natural, with the promise of aiding in routine reporting and standardizing results across trials. Deep learning features inferred from digital pathology scans can improve validity and robustness of current clinico-pathological features, up to identifying novel histological patterns, e.g. from tumor infiltrating lymphocytes. In this study, we examine the issue of evaluating accuracy of predictive models from deep learning features in digital pathology, as an hallmark of reproducibility. We introduce the DAPPER framework for validation based on a rigorous Data Analysis Plan derived from the FDA’s MAQC project, designed to analyse causes of variability in predictive biomarkers. We apply the framework on models that identify tissue of origin on 787 Whole Slide Images from the Genotype-Tissue Expression (GTEx) project. We test 3 different deep learning architectures (VGG, ResNet, Inception) as feature extractors and three classifiers (a fully connected multilayer, Support Vector Machine and Random Forests) and work with 4 datasets (5, 10, 20 or 30 classes), for a total 53000 tiles at 512 × 512 resolution. We analyze accuracy and feature stability of the machine learning classifiers, also demonstrating the need for random features and random labels diagnostic tests to identify selection bias and risks for reproducibility. Further, we use the deep features from the VGG model from GTEx on the KIMIA24 dataset for identification of slide of origin (24 classes) to train a classifier on 1060 annotated tiles and validated on 265 unseen ones. The DAPPER software, including its deep learning backbone pipeline and the HINT (Histological Imaging - Newsy Tiles) benchmark dataset derived from GTEx, is released as a basis for standardization and validation initiatives in AI for Digital Pathology.Author summaryIn this study, we examine the issue of evaluating accuracy of predictive models from deep learning features in digital pathology, as an hallmark of reproducibility. It is indeed a top priority that reproducibility-by-design gets adopted as standard practice in building and validating AI methods in the healthcare domain. Here we introduce DAPPER, a first framework to evaluate deep features and classifiers in digital pathology, based on a rigorous data analysis plan originally developed in the FDA’s MAQC initiative for predictive biomarkers from massive omics data. We apply DAPPER on models trained to identify tissue of origin from the HINT benchmark dataset of 53000 tiles from 787 Whole Slide Images in the Genotype-Tissue Expression (GTEx) project. We analyze accuracy and feature stability of different deep learning architectures (VGG, ResNet and Inception) as feature extractors and classifiers (a fully connected multilayer, SVMs and Random Forests) on up to 20 classes. Further, we use the deep features from the VGG model (trained on HINT) on the 1300 annotated tiles of the KIMIA24 dataset for identification of slide of origin (24 classes). The DAPPER software is available together with the HINT benchmark dataset.

Wearable devices have emerged as the most innovative opportunity to enable acquisition and quantification of physiological signals in real-world indoor or outdoor contexts. However, their use in research should be based on a reproducible analytics process, ensuring that all the critical steps in data collection and processing are managed in a reliable experimental setup. The aim of this thesis is to investigate the actual value and technical limitations of wearable devices for their use in a research context, such as physiological monitoring of sleep and crying states in infants, of parenting of typical or atypical children, synchrony in educational contexts, and of fatigue patterns in outdoor sport activity, e.g. skiing. The thesis describes an approach and solutions that aim to compensate the effects of such technical limits. Besides providing a set of appropriate signal processing algorithms, a real-life sensing architecture is designed and implemented enabling synchronized acquisition from multiple subjects and multiple sensors, including cardiac signals, electrodermal activity and inertial data streams. The signal processing pipeline and the real-life sensing architecture are merged in a unique data analytics framework (Physiolitix). The framework is validated on a fairly wide range of sensors, including medical quality multi-sensor smartwatches and smart textile garments applied in diverse research contexts. In particular, a calibration dataset is developed to compare wearable and clinical devices in an affective computing task. We found that wearables can be employed as a valid substitute for medical quality devices with the help of adequate signal processing and machine learning solutions.