Search

Abstract Alzheimer's disease (AD) shows a high pathological and symptomatological heterogeneity. To study this heterogeneity, we have developed a patient stratification technique based on one of the most significant risk factors for the development of AD: genetics. We addressed this challenge by including network biology concepts, mapping genetic variants data into a brain-specific protein–protein interaction (PPI) network, and obtaining individualized PPI scores that we then used as input for a clustering technique. We then phenotyped each obtained cluster regarding genetics, sociodemographics, biomarkers, fluorodeoxyglucose-positron emission tomography (FDG-PET) imaging, and neurocognitive assessments. We found three clusters defined mainly by genetic variants found in MAPT, APP, and APOE, considering known variants associated with AD and other neurodegenerative disease genetic architectures. Profiling of these clusters revealed minimal variation in AD symptoms and pathology, suggesting different biological mechanisms may activate the neurodegeneration and pathobiological patterns behind AD and result in similar clinical and pathological presentations, even a shared disease diagnosis. Lastly, our research highlighted MAPT, APP, and APOE as key genes where these genetic distinctions manifest, suggesting them as potential targets for personalized drug development strategies to address each AD subgroup individually.

Abstract We present an extensive study of the joint effects of heterogeneous social agents and their heterogeneous social links in a bounded confidence opinion dynamics model. The full phase diagram of the model is explored for two different network’s topologies and compared to two opposed extreme cases: on one hand, the heterogeneous agents constitute a mixed population and on the other, their interactions are modeled by a lattice. The results show that when agents prone to compromise coexist with close-minded ones, the steady state of the dynamics shows coexistent phases. In particular, unlike the case of homogeneous agents in networks, or heterogeneous agents in a fully mixed population, it is possible that the society ends up in consensus around one extreme opinion. Moreover, during the dynamics, the consensus may be overturned from one extreme to the other of the opinion space. We also show that the standard order parameter, the normalized average size of the largest opinion cluster, may be misleading in this case, as it hides the existence of these phases. The phase where the opinion of the society is overturned does not require the presence of agents with special characteristics, (stubborn, extremists, etc.); it results from the interplay of agents which have agreed on an extreme opinion with the remaining group that holds the opposite one. Among the former, some may be prone to compromise with other agents which are out of the majority group, these agents, according to their location in the network, may act like bridges between the two groups and slowly attract the whole society to the other extreme.

Abstract Given the barriers to early detection of gestational diabetes mellitus (GDM), this study aimed to develop an artificial intelligence (AI)-based prediction model for GDM in pregnant Mexican women. Data were retrieved from 1709 pregnant women who participated in the multicenter prospective cohort study ‘Cuido mi embarazo’. A machine-learning-driven method was used to select the best predictive variables for GDM risk: age, family history of type 2 diabetes, previous diagnosis of hypertension, pregestational body mass index, gestational week, parity, birth weight of last child, and random capillary glucose. An artificial neural network approach was then used to build the model, which achieved a high level of accuracy (70.3%) and sensitivity (83.3%) for identifying women at high risk of developing GDM. This AI-based model will be applied throughout Mexico to improve the timing and quality of GDM interventions. Given the ease of obtaining the model variables, this model is expected to be clinically strategic, allowing prioritization of preventative treatment and promising a paradigm shift in prevention and primary healthcare during pregnancy. This AI model uses variables that are easily collected to identify pregnant women at risk of developing GDM with a high level of accuracy and precision.

Abstract We study the dynamics of interactions between a traditional medium, the New York Times journal, and its followers in Twitter, using a massive dataset. It consists of the metadata of the articles published by the journal during the first year of the COVID-19 pandemic, and the posts published in Twitter by a large set of followers of the @nytimes account along with those published by a set of followers of several other media of different kind. The dynamics of discussions held in Twitter by exclusive followers of a medium show a strong dependence on the medium they follow: the followers of @FoxNews show the highest similarity to each other and a strong differentiation of interests with the general group. Our results also reveal the difference in the attention payed to U.S. presidential elections by the journal and by its followers, and show that the topic related to the “Black Lives Matter” movement started in Twitter, and was addressed later by the journal.

Abstract Alzheimer's disease (AD) is a neurodegenerative disease whose molecular mechanisms are activated several years before cognitive symptoms appear. Genotype-based prediction of the phenotype is thus a key challenge for the early diagnosis of AD. Machine learning techniques that have been proposed to address this challenge do not consider known biological interactions between the genes used as input features, thus neglecting important information about the disease mechanisms at play. To mitigate this, we first extracted AD subnetworks from several protein–protein interaction (PPI) databases and labeled these with genotype information (number of missense variants) to make them patient-specific. Next, we trained Graph Neural Networks (GNNs) on the patient-specific networks for phenotype prediction. We tested different PPI databases and compared the performance of the GNN models to baseline models using classical machine learning techniques, as well as randomized networks and input datasets. The overall results showed that GNNs could not outperform a baseline predictor only using the APOE gene, suggesting that missense variants are not sufficient to explain disease risk beyond the APOE status. Nevertheless, our results show that GNNs outperformed other machine learning techniques and that protein–protein interactions lead to superior results compared to randomized networks. These findings highlight that gene interactions are a valuable source of information in predicting disease status.

Abstract Digital counting methods were developed to decrease the high intra- and inter-observer variability of immunohistochemical markers such as Ki67, with most presenting a good correlation coefficient (CC). Since Ki67 is one of the major contributors to Oncotype DX, it is conceivable that Ki67 expression and the recurrence score (RS) obtained by the multigene panel are positively correlated. We decided first to test to what extent conventional and digital Ki67 quantification methods correlate in daily practice and, second, to determine which of these methods correlates better with the prognostic capacity of the Oncotype DX test. Both Ki67 evaluations were performed in 89 core biopsies with a diagnosis of estrogen receptor (ER) positive HER2-negative breast cancer (BC). Cases were, thus, classified twice for surrogate subtype: first by conventional analysis and then by digital evaluation. The Oncotype RS was obtained in 55 cases that were subsequently correlated to Ki67 evaluation by both methods. Conventional and digital Ki67 evaluation showed good concordance and correlation (CC = 0.81 (95% CI 0.73–0.89)). The correlation of Oncotype DX risk groups and surrogate derived subtypes was slightly higher for the digital technique (rs = 0.46, p

Abstract Acute respiratory distress syndrome is a heterogeneous pathophysiological process responsible for significant morbidity and mortality in pediatric intensive care patients. Diagnosis is defined by clinical characteristics that identify the syndrome after development. Subphenotyping patients at risk of progression to ARDS could provide the opportunity for therapeutic intervention. microRNAs, non-coding RNAs stable in circulation, are a promising biomarker candidate. We conducted a single-center prospective cohort study to evaluate random forest classification of microarray-quantified circulating microRNAs in critically ill pediatric patients. We additionally selected a sub-cohort for parallel metabolomics profiling as a pilot study for concurrent use of miRNAs and metabolites as circulating biomarkers. In 35 patients (n = 21 acute respiratory distress, n = 14 control) 15 microRNAs were differentially expressed. Unsupervised random forest classification accurately grouped ARDS and control patients with an area under the curve of 0.762, which was improved to 0.839 when subset to only patients with bacterial infection. Nine metabolites were differentially abundant between acute respiratory distress and control patients (n = 4, both groups) and abundance was highly correlated with miRNA expression. Random forest classification of microRNAs differentiated critically ill pediatric patients who developed acute respiratory distress relative to those who do not. The differential expression of microRNAs and metabolites provides a strong foundation for further work to validate their use as a prognostic biomarker.

Abstract The current study examines the potential moderating effect of depression and anxiety on the relationship between visual acuity and health-related quality of life in patients with chronic eye diseases. Of the 71 patients, 37 (52%) were female and 34 (48%) were male, age (mean ± SD) was 69 ± 12 years. A significant multivariate regression model was found for patients’ health-related quality of life (EQ-5D-5L index) (R2 = 0.43, p