Adverse drug reaction classification with deep neural networks

We study the problem of detecting sentences describing adverse drug reactions (ADRs) and frame the problem as binary classification. We investigate different neural network (NN) architectures for ADR classification. In particular, we propose two new neural network models, Convolutional Recurrent Neural Network (CRNN) by concatenating convolutional neural networks with recurrent neural networks, and Convolutional Neural Network with Attention (CNNA) by adding attention weights into convolutional neural networks. We evaluate various NN architectures on a Twitter dataset containing informal language and an Adverse Drug Effects (ADE) dataset constructed by sampling from MEDLINE case reports. Experimental results show that all the NN architectures outperform the traditional maximum entropy classifiers trained from n-grams with different weighting strategies considerably on both datasets. On the Twitter dataset, all the NN architectures perform similarly. But on the ADE dataset, CNN performs better than other more complex CNN variants. Nevertheless, CNNA allows the visualisation of attention weights of words when making classification decisions and hence is more appropriate for the extraction of word subsequences describing ADRs.

Towards person-centered neuroimaging markers for resilience and vulnerability in Bipolar Disorder

Improved clinical care for Bipolar Disorder (BD) relies on the identification of diagnostic markers that can reliably detect disease-related signals in clinically heterogeneous populations. At the very least, diagnostic markers should be able to differentiate patients with BD from healthy individuals and from individuals at familial risk for BD who either remain well or develop other psychopathology, most commonly Major Depressive Disorder (MDD). These issues are particularly pertinent to the development of translational applications of neuroimaging as they represent challenges for which clinical observation alone is insufficient. We therefore applied pattern classification to task-based functional magnetic resonance imaging (fMRI) data of the n-back working memory task, to test their predictive value in differentiating patients with BD (n=30) from healthy individuals (n=30) and from patients' relatives who were either diagnosed with MDD (n=30) or were free of any personal lifetime history of psychopathology (n=30). Diagnostic stability in these groups was confirmed with 4-year prospective follow-up. Task-based activation patterns from the fMRI data were analyzed with Gaussian Process Classifiers (GPC), a machine learning approach to detecting multivariate patterns in neuroimaging datasets. Consistent significant classification results were only obtained using data from the 3-back versus 0-back contrast. Using contrast, patients with BD were correctly classified compared to unrelated healthy individuals with an accuracy of 83.5%, sensitivity of 84.6% and specificity of 92.3%. Classification accuracy, sensitivity and specificity when comparing patients with BD to their relatives with MDD, were respectively 73.1%, 53.9% and 94.5%. Classification accuracy, sensitivity and specificity when comparing patients with BD to their healthy relatives were respectively 81.8%, 72.7% and 90.9%. We show that significant individual classification can be achieved using whole brain pattern analysis of task-based working memory fMRI data. The high accuracy and specificity achieved by all three classifiers suggest that multivariate pattern recognition analyses can aid clinicians in the clinical care of BD in situations of true clinical uncertainty regarding the diagnosis and prognosis.

Ultrasonido a la cabecera del paciente, una herramienta diagnóstica de disección aórtica en el departamento de emergencias

El síndrome aórtico agudo puede presentarse como un cuadro clínico característico de una emergencia vascular, o por el contrario de una forma completamente atípica, donde el diagnóstico reta al médico de emergencias, llevando a errores fatales al pasar por alto el diagnóstico de esta entidad. Con el objetivo de mostrar la utilidad del ultrasonido realizado a la cabecera del paciente en el diagnóstico de disección aórtica, se describen 9 casos de pacientes que ingresaron al departamento de emergencias y que fueron diagnosticados con síndrome aórtico agudo, gracias a la valoración ultrasonográfica inicial realizada por residentes y Especialistas en Medicina de Emergencias en un hospital de Bogotá D.C., Colombia. Este reporte de casos muestra que el ultrasonido a la cabecera del paciente, es un método diagnóstico no invasivo, accesible y útil para la detección temprana de esta patología en los servicios de emergencias.

Age and Gender Identification using Stacking for Classification⋆ Notebook for PAN at CLEF 2016

This paper presents our approach of identifying the profile of an unknown user based on the activities of known users. The aim of author profiling task of PAN@CLEF 2016 is cross-genre identification of the gender and age of an unknown user. This means training the system using the behavior of different users from one social media platform and identifying the profile of other user on some different platform. Instead of using single classifier to build the system we used a combination of different classifiers, also known as stacking. This approach allowed us explore the strength of all the classifiers and minimize the bias or error enforced by a single classifier.

Multilingual author profiling using svms and linguistic features

This paper describes various experiments done to investigate author profiling of tweets in 4 different languages – English, Dutch, Italian, and Spanish. Profiling consists of age and gender classification, as well as regression on 5 different person- ality dimensions – extroversion, stability, agreeableness, open- ness, and conscientiousness. Different sets of features were tested – bag-of-words, word ngrams, POS ngrams, and average of word embeddings. SVM was used as the classifier. Tfidf worked best for most English tasks while for most of the tasks from the other languages, the combination of the best features worked better.

Experiments on identification of argumentative sentences

The main purpose of this study is to evaluate the best set of features that automatically enables the identification of argumentative sentences from unstructured text. As corpus, we use case laws from the European Court of Human Rights (ECHR). Three kinds of experiments are conducted: Basic Experiments, Multi Feature Experiments and Tree Kernel Experiments. These experiments are basically categorized according to the type of features available in the corpus. The features are extracted from the corpus and Support Vector Machine (SVM) and Random Forest are the used as Machine learning algorithms. We achieved F1 score of 0.705 for identifying the argumentative sentences which is quite promising result and can be used as the basis for a general argument-mining framework.

Detecting outliers and asserting consistency in agriculture ground truth information by using temporal VI data from modis.

Collecting ground truth data is an important step to be accomplished before performing a supervised classification. However, its quality depends on human, financial and time ressources. It is then important to apply a validation process to assess the reliability of the acquired data. In this study, agricultural infomation was collected in the Brazilian Amazonian State of Mato Grosso in order to map crop expansion based on MODIS EVI temporal profiles. The field work was carried out through interviews for the years 2005-2006 and 2006-2007. This work presents a methodology to validate the training data quality and determine the optimal sample to be used according to the classifier employed. The technique is based on the detection of outlier pixels for each class and is carried out by computing Mahalanobis distances for each pixel. The higher the distance, the further the pixel is from the class centre. Preliminary observations through variation coefficent validate the efficiency of the technique to detect outliers. Then, various subsamples are defined by applying different thresholds to exclude outlier pixels from the classification process. The classification results prove the robustness of the Maximum Likelihood and Spectral Angle Mapper classifiers. Indeed, those classifiers were insensitive to outlier exclusion. On the contrary, the decision tree classifier showed better results when deleting 7.5% of pixels in the training data. The technique managed to detect outliers for all classes. In this study, few outliers were present in the training data, so that the classification quality was not deeply affected by the outliers.

Comparison of multitemporal MODIS-EVI smoothing algorithms and its contribution to crop monitoring.

Crop monitoring and more generally land use change detection are of primary importance in order to analyze spatio-temporal dynamics and its impacts on environment. This aspect is especially true in such a region as the State of Mato Grosso (south of the Brazilian Amazon Basin) which hosts an intensive pioneer front. Deforestation in this region as often been explained by soybean expansion in the last three decades. Remote sensing techniques may now represent an efficient and objective manner to quantify how crops expansion really represents a factor of deforestation through crop mapping studies. Due to the special characteristics of the soybean productions' farms in Mato Grosso (area varying between 1000 hectares and 40000 hectares and individual fields often bigger than 100 hectares), the Moderate Resolution Imaging Spectroradiometer (MODIS) data with a near daily temporal resolution and 250 m spatial resolution can be considered as adequate resources to crop mapping. Especially, multitemporal vegetation indices (VI) studies have been currently used to realize this task [1] [2]. In this study, 16-days compositions of EVI (MODQ13 product) data are used. However, although these data are already processed, multitemporal VI profiles still remain noisy due to cloudiness (which is extremely frequent in a tropical region such as south Amazon Basin), sensor problems, errors in atmospheric corrections or BRDF effect. Thus, many works tried to develop algorithms that could smooth the multitemporal VI profiles in order to improve further classification. The goal of this study is to compare and test different smoothing algorithms in order to select the one which satisfies better to the demand which is classifying crop classes. Those classes correspond to 6 different agricultural managements observed in Mato Grosso through an intensive field work which resulted in mapping more than 1000 individual fields. The agricultural managements above mentioned are based on combination of soy, cotton, corn, millet and sorghum crops sowed in single or double crop systems. Due to the difficulty in separating certain classes because of too similar agricultural calendars, the classification will be reduced to 3 classes : Cotton (single crop), Soy and cotton (double crop), soy (single or double crop with corn, millet or sorghum). The classification will use training data obtained in the 2005-2006 harvest and then be tested on the 2006-2007 harvest. In a first step, four smoothing techniques are presented and criticized. Those techniques are Best Index Slope Extraction (BISE) [3], Mean Value Iteration (MVI) [4], Weighted Least Squares (WLS) [5] and Savitzky-Golay Filter (SG) [6] [7]. These techniques are then implemented and visually compared on a few individual pixels so that it allows doing a first selection between the five studied techniques. The WLS and SG techniques are selected according to criteria proposed by [8]. Those criteria are: ability in eliminating frequent noises, conserving the upper values of the VI profiles and keeping the temporality of the profiles. Those selected algorithms are then programmed and applied to the MODIS/TERRA EVI data (16-days composition periods). Tests of separability are realized based on the Jeffries-Matusita distance in order to see if the algorithms managed in improving the potential of differentiation between the classes. Those tests are realized on the overall profile (comprising 23 MODIS images) as well as on each MODIS sub-period of the profile [1]. This last test is a double interest process because it allows comparing the smoothing techniques and also enables to select a set of images which carries more information on the separability between the classes. Those selected dates can then be used to realize a supervised classification. Here three different classifiers are tested to evaluate if the smoothing techniques as a particular effect on the classification depending on the classifiers used. Those classifiers are Maximum Likelihood classifier, Spectral Angle Mapper (SAM) classifier and CHAID Improved Decision tree. It appears through the separability tests on the overall process that the smoothed profiles don't improve efficiently the potential of discrimination between classes when compared with the original data. However, the same tests realized on the MODIS sub-periods show better results obtained with the smoothed algorithms. The results of the classification confirm this first analyze. The Kappa coefficients are always better with the smoothing techniques and the results obtained with the WLS and SG smoothed profiles are nearly equal. However, the results are different depending on the classifier used. The impact of the smoothing algorithms is much better while using the decision tree model. Indeed, it allows a gain of 0.1 in the Kappa coefficient. While using the Maximum Likelihood end SAM models, the gain remains positive but is much lower (Kappa improved of 0.02 only). Thus, this work's aim is to prove the utility in smoothing the VI profiles in order to improve the final results. However, the choice of the smoothing algorithm has to be made considering the original data used and the classifier models used. In that case the Savitzky-Golay filter gave the better results.

Machine Learning Unsupervised Methods in the Design of an On-board Health Monitoring System for Satellite Applications

The dissertation starts by providing a description of the phenomena related to the increasing importance recently acquired by satellite applications. The spread of such technology comes with implications, such as an increase in maintenance cost, from which derives the interest in developing advanced techniques that favor an augmented autonomy of spacecrafts in health monitoring. Machine learning techniques are widely employed to lay a foundation for effective systems specialized in fault detection by examining telemetry data. Telemetry consists of a considerable amount of information; therefore, the adopted algorithms must be able to handle multivariate data while facing the limitations imposed by on-board hardware features. In the framework of outlier detection, the dissertation addresses the topic of unsupervised machine learning methods. In the unsupervised scenario, lack of prior knowledge of the data behavior is assumed. In the specific, two models are brought to attention, namely Local Outlier Factor and One-Class Support Vector Machines. Their performances are compared in terms of both the achieved prediction accuracy and the equivalent computational cost. Both models are trained and tested upon the same sets of time series data in a variety of settings, finalized at gaining insights on the effect of the increase in dimensionality. The obtained results allow to claim that both models, combined with a proper tuning of their characteristic parameters, successfully comply with the role of outlier detectors in multivariate time series data. Nevertheless, under this specific context, Local Outlier Factor results to be outperforming One-Class SVM, in that it proves to be more stable over a wider range of input parameter values. This property is especially valuable in unsupervised learning since it suggests that the model is keen to adapting to unforeseen patterns.

Modelling and classification with quantile-based distributions

In this work, we explore and demonstrate the potential for modeling and classification using quantile-based distributions, which are random variables defined by their quantile function. In the first part we formalize a least squares estimation framework for the class of linear quantile functions, leading to unbiased and asymptotically normal estimators. Among the distributions with a linear quantile function, we focus on the flattened generalized logistic distribution (fgld), which offers a wide range of distributional shapes. A novel naïve-Bayes classifier is proposed that utilizes the fgld estimated via least squares, and through simulations and applications, we demonstrate its competitiveness against state-of-the-art alternatives. In the second part we consider the Bayesian estimation of quantile-based distributions. We introduce a factor model with independent latent variables, which are distributed according to the fgld. Similar to the independent factor analysis model, this approach accommodates flexible factor distributions while using fewer parameters. The model is presented within a Bayesian framework, an MCMC algorithm for its estimation is developed, and its effectiveness is illustrated with data coming from the European Social Survey. The third part focuses on depth functions, which extend the concept of quantiles to multivariate data by imposing a center-outward ordering in the multivariate space. We investigate the recently introduced integrated rank-weighted (IRW) depth function, which is based on the distribution of random spherical projections of the multivariate data. This depth function proves to be computationally efficient and to increase its flexibility we propose different methods to explicitly model the projected univariate distributions. Its usefulness is shown in classification tasks: the maximum depth classifier based on the IRW depth is proven to be asymptotically optimal under certain conditions, and classifiers based on the IRW depth are shown to perform well in simulated and real data experiments.

The predictive role of the human gut microbiota in covid-19: implications for disease severity and post-covid syndrome

The COVID-19 pandemic, sparked by the SARS-CoV-2 virus, stirred global comparisons to historical pandemics. Initially presenting a high mortality rate, it later stabilized globally at around 0.5-3%. Patients manifest a spectrum of symptoms, necessitating efficient triaging for appropriate treatment strategies, ranging from symptomatic relief to antivirals or monoclonal antibodies. Beyond traditional approaches, emerging research suggests a potential link between COVID-19 severity and alterations in gut microbiota composition, impacting inflammatory responses. However, most studies focus on severe hospitalized cases without standardized criteria for severity. Addressing this gap, the first study in this thesis spans diverse COVID-19 severity levels, utilizing 16S rRNA amplicon sequencing on fecal samples from 315 subjects. The findings highlight significant microbiota differences correlated with severity. Machine learning classifiers, including a multi-layer convoluted neural network, demonstrated the potential of microbiota compositional data to predict patient severity, achieving an 84.2% mean balanced accuracy starting one week post-symptom onset. These preliminary results underscore the gut microbiota's potential as a biomarker in clinical decision-making for COVID-19. The second study delves into mild COVID-19 cases, exploring their implications for ‘long COVID’ or Post-Acute COVID-19 Syndrome (PACS). Employing longitudinal analysis, the study unveils dynamic shifts in microbial composition during the acute phase, akin to severe cases. Innovative techniques, including network approaches and spline-based longitudinal analysis, were deployed to assess microbiota dynamics and potential associations with PACS. The research suggests that even in mild cases, similar mechanisms to hospitalized patients are established regarding changes in intestinal microbiota during the acute phase of the infection. These findings lay the foundation for potential microbiota-targeted therapies to mitigate inflammation, potentially preventing long COVID symptoms in the broader population. In essence, these studies offer valuable insights into the intricate relationships between COVID-19 severity, gut microbiota, and the potential for innovative clinical applications.

Data-driven Signal Processing per Jamming Detection in Sistemi Satellitari

In questo elaborato vengono analizzate differenti tecniche per la detection di jammer attivi e costanti in una comunicazione satellitare in uplink. Osservando un numero limitato di campioni ricevuti si vuole identificare la presenza di un jammer. A tal fine sono stati implementati i seguenti classificatori binari: support vector machine (SVM), multilayer perceptron (MLP), spectrum guarding e autoencoder. Questi algoritmi di apprendimento automatico dipendono dalle features che ricevono in ingresso, per questo motivo è stata posta particolare attenzione alla loro scelta. A tal fine, sono state confrontate le accuratezze ottenute dai detector addestrati utilizzando differenti tipologie di informazione come: i segnali grezzi nel tempo, le statistical features, le trasformate wavelet e lo spettro ciclico. I pattern prodotti dall’estrazione di queste features dai segnali satellitari possono avere dimensioni elevate, quindi, prima della detection, vengono utilizzati i seguenti algoritmi per la riduzione della dimensionalità: principal component analysis (PCA) e linear discriminant analysis (LDA). Lo scopo di tale processo non è quello di eliminare le features meno rilevanti, ma combinarle in modo da preservare al massimo l’informazione, evitando problemi di overfitting e underfitting. Le simulazioni numeriche effettuate hanno evidenziato come lo spettro ciclico sia in grado di fornire le features migliori per la detection producendo però pattern di dimensioni elevate, per questo motivo è stato necessario l’utilizzo di algoritmi di riduzione della dimensionalità. In particolare, l'algoritmo PCA è stato in grado di estrarre delle informazioni migliori rispetto a LDA, le cui accuratezze risentivano troppo del tipo di jammer utilizzato nella fase di addestramento. Infine, l’algoritmo che ha fornito le prestazioni migliori è stato il Multilayer Perceptron che ha richiesto tempi di addestramento contenuti e dei valori di accuratezza elevati.

Predicting corticospinal excitability from pre-TMS EEG using convolutional neural networks

The amplitude of motor evoked potentials (MEPs) elicited by transcranial magnetic stimulation (TMS) of the primary motor cortex (M1) shows a large variability from trial to trial, although MEPs are evoked by the same repeated stimulus. A multitude of factors is believed to influence MEP amplitudes, such as cortical, spinal and motor excitability state. The goal of this work is to explore to which degree the variation in MEP amplitudes can be explained by the cortical state right before the stimulation. Specifically, we analyzed a dataset acquired on eleven healthy subjects comprising, for each subject, 840 single TMS pulses applied to the left M1 during acquisition of electroencephalography (EEG) and electromyography (EMG). An interpretable convolutional neural network, named SincEEGNet, was utilized to discriminate between low- and high-corticospinal excitability trials, defined according to the MEP amplitude, using in input the pre-TMS EEG. This data-driven approach enabled considering multiple brain locations and frequency bands without any a priori selection. Post-hoc interpretation techniques were adopted to enhance interpretation by identifying the more relevant EEG features for the classification. Results show that individualized classifiers successfully discriminated between low and high M1 excitability states in all participants. Outcomes of the interpretation methods suggest the importance of the electrodes situated over the TMS stimulation site, as well as the relevance of the temporal samples of the input EEG closer to the stimulation time. This novel decoding method allows causal investigation of the cortical excitability state, which may be relevant for personalizing and increasing the efficacy of therapeutic brain-state dependent brain stimulation (for example in patients affected by Parkinson’s disease).

Machine Learning in Applicazione alla Prevenzione del Morbo di Alzheimer

Il morbo di Alzheimer è ancora una malattia incurabile. Negli ultimi anni l'aumento progressivo dell'aspettativa di vita ha contribuito a un'insorgenza maggiore di questa patologia, specialmente negli stati con l'età media più alta, tra cui l'Italia. La prevenzione risulta una delle poche vie con cui è possibile arginarne lo sviluppo, ed in questo testo vengono analizzate le potenzialità di alcune tecniche di Machine Learning atte alla creazione di modelli di supporto diagnostico per Alzheimer. Dopo un'opportuna introduzione al morbo di Alzheimer ed al funzionamento generale del Machine Learning, vengono presentate e approfondite due delle tecniche più promettenti per la diagnosi di patologie neurologiche, ovvero la Support Vector Machine (macchina a supporto vettoriale, SVM) e la Convolutional Neural Network (rete neurale convoluzionale, CNN), con annessi risultati, punti di forza e principali debolezze. La conclusione verterà sul possibile futuro delle intelligenze artificiali, con particolare attenzione all'ambito sanitario, e verranno discusse le principali difficoltà nelle quali queste incombono prima di essere commercializzate, insieme a plausibili soluzioni.

Hierarchical Multi-Label Text Classification in a Low-Resource Setting

In this thesis we address a multi-label hierarchical text classification problem in a low-resource setting and explore different approaches to identify the best one for our case. The goal is to train a model that classifies English school exercises according to a hierarchical taxonomy with few labeled data. The experiments made in this work employ different machine learning models and text representation techniques: CatBoost with tf-idf features, classifiers based on pre-trained models (mBERT, LASER), and SetFit, a framework for few-shot text classification. SetFit proved to be the most promising approach, achieving better performance when during training only a few labeled examples per class are available. However, this thesis does not consider all the hierarchical taxonomy, but only the first two levels: to address classification with the classes at the third level further experiments should be carried out, exploring methods for zero-shot text classification, data augmentation, and strategies to exploit the hierarchical structure of the taxonomy during training.