RESUMO
Nowadays, Artificial Intelligence systems have expanded their competence field from research to industry and daily life, so understanding how they make decisions is becoming fundamental to reducing the lack of trust between users and machines and increasing the transparency of the model. This paper aims to automate the generation of explanations for model-free Reinforcement Learning algorithms by answering "why" and "why not" questions. To this end, we use Bayesian Networks in combination with the NOTEARS algorithm for automatic structure learning. This approach complements an existing framework very well and demonstrates thus a step towards generating explanations with as little user input as possible. This approach is computationally evaluated in three benchmarks using different Reinforcement Learning methods to highlight that it is independent of the type of model used and the explanations are then rated through a human study. The results obtained are compared to other baseline explanation models to underline the satisfying performance of the framework presented in terms of increasing the understanding, transparency and trust in the action chosen by the agent.
RESUMO
AIMS: The aim of this work was to assess the effects of a probiotic diet on well-being of healthy seniors living in boarding and private homes in Marche Region, Italy. In particular, we focused on the modulation of high-sensitivity C-reactive protein (HsCRP), intestinal microbiota and short-chain fatty acids (SCFAs). METHODS AND RESULTS: Ninety-seven healthy seniors took part in a double-blind, placebo-controlled feeding study (59 fed probiotics, 38 fed placebo) for 6 months. Each volunteer ingested daily one food product or a dietary supplement enriched with Synbio® blend (Synbiotec Srl, Camerino, Italy) or the placebo (control group). Blood and faecal samples were collected before and at the end of the intervention period to perform biochemical and microbiological analyses. The serum HsCRP difference value after 6 months of treatment was significantly higher in the probiotic group than placebo (p < 0.05). After the intervention, a significant increase in faecal lactobacilli and a bifidobacteria increase in more participants were observed in the probiotic group. The 16S NGS analysis on the probiotic group showed a decreasing trend of Proteobacteria at the end of the treatment and conversely, an increasing trend of Actinobacteria and Verrucomicrobia phyla, to which the increase of Akkermansiaceae and Bifidobacteriaceae contributes at the family level. Finally, total short-chain fatty acids (SCFAs) and butyric acid were significantly higher in the probiotic group at the end of the treatment respect to the beginning. CONCLUSIONS: Overall, this study emphasizes the beneficial anti-inflammageing effect of a prolonged diet based on functional foods enriched with Synbio® through the modulation of the intestinal microbiota and the consequent increase in the SCFA production. SIGNIFICANCE AND IMPACT OF THE STUDY: Synbio® integration in elderly daily diet may be a preventive strategy to support healthy ageing.
Assuntos
Proteína C-Reativa , Probióticos , Humanos , Idoso , Fezes/microbiologia , Ácidos Graxos Voláteis , Dieta , Ácido Butírico , Método Duplo-CegoRESUMO
BACKGROUND: The scope of this work is to build a Machine Learning model able to predict patients risk to contract a multidrug resistant urinary tract infection (MDR UTI) after hospitalization. To achieve this goal, we used different popular Machine Learning tools. Moreover, we integrated an easy-to-use cloud platform, called DSaaS (Data Science as a Service), well suited for hospital structures, where healthcare operators might not have specific competences in using programming languages but still, they do need to analyze data as a continuous process. Moreover, DSaaS allows the validation of data analysis models based on supervised Machine Learning regression and classification algorithms. RESULTS: We used DSaaS on a real antibiotic stewardship dataset to make predictions about antibiotic resistance in the Clinical Pathology Operative Unit of the Principe di Piemonte Hospital in Senigallia, Marche, Italy. Data related to a total of 1486 hospitalized patients with nosocomial urinary tract infection (UTI). Sex, age, age class, ward and time period, were used to predict the onset of a MDR UTI. Machine Learning methods such as Catboost, Support Vector Machine and Neural Networks were utilized to build predictive models. Among the performance evaluators, already implemented in DSaaS, we used accuracy (ACC), area under receiver operating characteristic curve (AUC-ROC), area under Precision-Recall curve (AUC-PRC), F1 score, sensitivity (SEN), specificity and Matthews correlation coefficient (MCC). Catboost exhibited the best predictive results (MCC 0.909; SEN 0.904; F1 score 0.809; AUC-PRC 0.853, AUC-ROC 0.739; ACC 0.717) with the highest value in every metric. CONCLUSIONS: the predictive model built with DSaaS may serve as a useful support tool for physicians treating hospitalized patients with a high risk to acquire MDR UTIs. We obtained these results using only five easy and fast predictors accessible for each patient hospitalization. In future, DSaaS will be enriched with more features like unsupervised Machine Learning techniques, streaming data analysis, distributed calculation and big data storage and management to allow researchers to perform a complete data analysis pipeline. The DSaaS prototype is available as a demo at the following address: https://dsaas-demo.shinyapps.io/Server/.
Assuntos
Algoritmos , Farmacorresistência Bacteriana Múltipla , Aprendizado de Máquina , Modelos Biológicos , Infecções Urinárias/diagnóstico , Idoso , Área Sob a Curva , Feminino , Humanos , Itália , Masculino , Pessoa de Meia-Idade , Redes Neurais de Computação , Curva ROC , Máquina de Vetores de SuporteRESUMO
A randomised, double-blind, placebo-controlled, parallel group study assessed in healthy adults how daily consumption of the probiotic combination SYNBIO®, administered in probiotic-enriched foods or in a dietary supplement, affected bowel habits. Primary and secondary outcomes gave the overall assessment of bowel well-being, while a Psychological General Well-Being Index compiled by participants estimated the health-related quality of life as well as the gastrointestinal tolerance determined with the Gastrointestinal Symptom Rating Scale. Support Vector Machine models for classification problems were used to validate the total outcomes on bowel well-being. SYNBIO® consumption improved bowel habits of volunteers consuming the probiotic foods or capsules, while the same effects were not registered in the control groups. The recovery of probiotic bacteria from the faeces of a cohort of 100 subjects for each supplemented group showed the persistence of strains in the gastrointestinal tract.
Assuntos
Bactérias , Defecação , Microbiologia de Alimentos , Probióticos , Adulto , Bactérias/crescimento & desenvolvimento , Constipação Intestinal/prevenção & controle , Método Duplo-Cego , Fezes/microbiologia , Feminino , Alimentos Fortificados/microbiologia , Hábitos , Saúde , Humanos , Intestinos/microbiologia , Lactobacillus , Lacticaseibacillus rhamnosus , Masculino , Probióticos/administração & dosagem , Qualidade de Vida , Valores de Referência , Máquina de Vetores de SuporteRESUMO
The physiological changes associated with ageing contribute to the incidence of diseases, morbidity, and mortality. For modern society, it is essential to find solutions to improve elderly people's health and quality of life. Among promising strategies, the PROBIOSENIOR project proposed a daily six-month supplementation with new probiotic functional foods and nutraceuticals. The aim of this work was to evaluate the modulating effects of the probiotic diet on inflammatory markers and nutritional status. Ninety-seven elderly volunteers were randomly assigned to either a placebo-diet group or a probiotic-diet group (SYNBIO®). Faeces, urine, and blood samples were collected before and after the supplementation to determine serum cytokines, biogenic amines, and inflammation markers. Comparing the results obtained before and after the intervention, probiotic supplementations significantly decreased the TNF-α circulating levels and significantly increased those of IGF-1. Biogenic-amine levels showed high variability, with significant variation only for histamine that decreased after the probiotic supplementation. The supplementation influenced the serum concentration of some crucial cytokines (IL-6, IL-8, and MIP-1α) that significantly decreased in the probiotic group. In addition, the Mini Nutritional Assessment questionnaire revealed that the probiotic-supplemented group had a significant improvement in nutritional status. In conclusion, the PROBIOSENIOR project demonstrated how SYNBIO® supplementation may positively influence some nutritional and inflammatory parameters in the elderly.
RESUMO
BACKGROUND AND OBJECTIVE: Functional brain graph (FBG), by describing the interactions between different brain regions, provides an effective representation of fMRI data for identifying mild cognitive impairment (MCI), an early stage of Alzheimer's Disease (AD). Prior to the identification task, selecting features from the estimated FBG is a necessary step for reducing computational cost, alleviating the risk of overfitting, and finding potential biomarkers of brain diseases. In practice, either node-based features (e.g., local clustering coefficients) or edge-based features (e.g., adjacency weights) are generally considered in current studies. Despite their popularity, these schemes can only capture one granularity (node or edge) of information in the FBG, which might be insufficient for the classification task and the interpretation of the classification result. METHODS: To address this issue, in this paper, we propose to jointly select nodes and edges from the estimated FBGs. Specifically, we first assign the edges to different node groups. Then, sparse group least absolute shrinkage and selection operator (sgLASSO) is used to select groups (nodes) and edges in the groups towards a better classification performance. Such a technique enables us to simultaneously locate discriminative brain regions, as well as connections between these brain regions, making the classification results more interpretable. RESULTS: Experimental results show that the proposed method achieves better classification performance than state-of-the-art methods. Moreover, by exploring brain network "features" that contributed most to MCI identification, we discover potential biomarkers for MCI diagnosis. CONCLUSION: A novel method for jointly selecting nodes and edges from the estimated functional brain graphs (FBGs) is proposed.
Assuntos
Doença de Alzheimer , Disfunção Cognitiva , Doença de Alzheimer/diagnóstico por imagem , Biomarcadores , Encéfalo/diagnóstico por imagem , Disfunção Cognitiva/diagnóstico por imagem , Humanos , Imageamento por Ressonância Magnética/métodosRESUMO
Brain functional network (BFN), usually estimated from blood oxygen level dependent (BOLD) functional magnetic resonance imaging (fMRI), has been proven to be a powerful tool to study the organization of the brain and discover biomarkers for diagnosis of brain disorders. Prior to BFN estimation and classification, extracting representative BOLD signals from brain regions of interest (ROIs) is a critical step. Traditional extraction methods include averaging, peaking operation and dimensionality reduction, often leading to signal cancellation and information loss. In this paper, we propose a novel method, namely time-constrained multiset canonical correlation analysis (TMCCA), to extract representative BOLD signals for subsequent BFN estimation and classification. Different from traditional methods that equally treat all BOLD signals in a ROI, the proposed method assigns weights to different BOLD signals, and learns the optimal weights to make the extracted representative signals jointly maximize the multiple correlations between ROIs. Importantly, time-constraint is incorporated into our proposed method, which can effectively encode nonlinear relationship among BOLD signals. To evaluate the effectiveness of the proposed method, the extracted BOLD signals is used to estimate BFN and, in turn, identify brain disorders, including mild cognitive impairment (MCI) and autistic spectrum disorder (ASD). Experimental results demonstrate that our proposed TMCCA can lead to better performance than traditional methods.
Assuntos
Encéfalo/diagnóstico por imagem , Rede Nervosa/diagnóstico por imagem , Transtorno do Espectro Autista/diagnóstico por imagem , Mapeamento Encefálico , Análise de Correlação Canônica , Disfunção Cognitiva/diagnóstico por imagem , Humanos , Imageamento por Ressonância MagnéticaRESUMO
Brain functional network (BFN) has become an increasingly important tool to understand the inherent organization of the brain and explore informative biomarkers of neurological disorders. Pearson's correlation (PC) is the most widely accepted method for constructing BFNs and provides a basis for designing new BFN estimation schemes. Particularly, a recent study proposes to use two sequential PC operations, namely, correlation's correlation (CC), for constructing the high-order BFN. Despite its empirical effectiveness in identifying neurological disorders and detecting subtle changes of connections in different subject groups, CC is defined intuitively without a solid and sustainable theoretical foundation. For understanding CC more rigorously and providing a systematic BFN learning framework, in this paper, we reformulate it in the Bayesian view with a prior of matrix-variate normal distribution. As a result, we obtain a probabilistic explanation of CC. In addition, we develop a Bayesian high-order method (BHM) to automatically and simultaneously estimate the high- and low-order BFN based on the probabilistic framework. An efficient optimization algorithm is also proposed. Finally, we evaluate BHM in identifying subjects with autism spectrum disorder (ASD) from typical controls based on the estimated BFNs. Experimental results suggest that the automatically learned high- and low-order BFNs yield a superior performance over the artificially defined BFNs via conventional CC and PC.
RESUMO
Support vector machines (SVMs) are a powerful technique developed in the last decade to effectively tackle classification and regression problems. In this paper we describe how support vector machines and artificial neural networks can be integrated in order to classify objects correctly. This technique has been successfully applied to the problem of determining the quality of tiles. Using an optical reader system, some features are automatically extracted, then a subset of the features is determined and the tiles are classified based on this subset.