Combined Machine Learning Techniques for Decision Making Support in Medicine

Computational intelligent support for decision making is becoming increasingly popular and essential among medical professionals. Also, with the modern medical devices being capable to communicate with ICT, created models can easily find practical translation into software. Machine learning solutions for medicine range from the robust but opaque paradigms of support vector machines and neural networks to the also performant, yet more comprehensible, decision trees and rule-based models. So how can such different techniques be combined such that the professional obtains the whole spectrum of their particular advantages? The presented approaches have been conceived for various medical problems, while permanently bearing in mind the balance between good accuracy and understandable interpretation of the decision in order to truly establish a trustworthy ‘artificial’ second opinion for the medical expert.

Automatic email organization

Introdução Actualmente, as mensagens electrónicas são consideradas um importante meio de comunicação. As mensagens electrónicas – vulgarmente conhecidas como emails – são utilizadas fácil e frequentemente para enviar e receber o mais variado tipo de informação. O seu uso tem diversos fins gerando diariamente um grande número de mensagens e, consequentemente um enorme volume de informação. Este grande volume de informação requer uma constante manipulação das mensagens de forma a manter o conjunto organizado. Tipicamente esta manipulação consiste em organizar as mensagens numa taxonomia. A taxonomia adoptada reflecte os interesses e as preferências particulares do utilizador. Motivação A organização manual de emails é uma actividade morosa e que consome tempo. A optimização deste processo através da implementação de um método automático, tende a melhorar a satisfação do utilizador. Cada vez mais existe a necessidade de encontrar novas soluções para a manipulação de conteúdo digital poupando esforços e custos ao utilizador; esta necessidade, concretamente no âmbito da manipulação de emails, motivou a realização deste trabalho. Hipótese O objectivo principal deste projecto consiste em permitir a organização ad-hoc de emails com um esforço reduzido por parte do utilizador. A metodologia proposta visa organizar os emails num conjunto de categorias, disjuntas, que reflectem as preferências do utilizador. A principal finalidade deste processo é produzir uma organização onde as mensagens sejam classificadas em classes apropriadas requerendo o mínimo número esforço possível por parte do utilizador. Para alcançar os objectivos estipulados, este projecto recorre a técnicas de mineração de texto, em especial categorização automática de texto, e aprendizagem activa. Para reduzir a necessidade de inquirir o utilizador – para etiquetar exemplos de acordo com as categorias desejadas – foi utilizado o algoritmo d-confidence. Processo de organização automática de emails O processo de organizar automaticamente emails é desenvolvido em três fases distintas: indexação, classificação e avaliação. Na primeira fase, fase de indexação, os emails passam por um processo transformativo de limpeza que visa essencialmente gerar uma representação dos emails adequada ao processamento automático. A segunda fase é a fase de classificação. Esta fase recorre ao conjunto de dados resultantes da fase anterior para produzir um modelo de classificação, aplicando-o posteriormente a novos emails. Partindo de uma matriz onde são representados emails, termos e os seus respectivos pesos, e um conjunto de exemplos classificados manualmente, um classificador é gerado a partir de um processo de aprendizagem. O classificador obtido é então aplicado ao conjunto de emails e a classificação de todos os emails é alcançada. O processo de classificação é feito com base num classificador de máquinas de vectores de suporte recorrendo ao algoritmo de aprendizagem activa d-confidence. O algoritmo d-confidence tem como objectivo propor ao utilizador os exemplos mais significativos para etiquetagem. Ao identificar os emails com informação mais relevante para o processo de aprendizagem, diminui-se o número de iterações e consequentemente o esforço exigido por parte dos utilizadores. A terceira e última fase é a fase de avaliação. Nesta fase a performance do processo de classificação e a eficiência do algoritmo d-confidence são avaliadas. O método de avaliação adoptado é o método de validação cruzada denominado 10-fold cross validation. Conclusões O processo de organização automática de emails foi desenvolvido com sucesso, a performance do classificador gerado e do algoritmo d-confidence foi relativamente boa. Em média as categorias apresentam taxas de erro relativamente baixas, a não ser as classes mais genéricas. O esforço exigido pelo utilizador foi reduzido, já que com a utilização do algoritmo d-confidence obteve-se uma taxa de erro próxima do valor final, mesmo com um número de casos etiquetados abaixo daquele que é requerido por um método supervisionado. É importante salientar, que além do processo automático de organização de emails, este projecto foi uma excelente oportunidade para adquirir conhecimento consistente sobre mineração de texto e sobre os processos de classificação automática e recuperação de informação. O estudo de áreas tão interessantes despertou novos interesses que consistem em verdadeiros desafios futuros.

Enhancing Multimodal Silent Speech Interfaces With Feature Selection

In research on Silent Speech Interfaces (SSI), different sources of information (modalities) have been combined, aiming at obtaining better performance than the individual modalities. However, when combining these modalities, the dimensionality of the feature space rapidly increases, yielding the well-known "curse of dimensionality". As a consequence, in order to extract useful information from this data, one has to resort to feature selection (FS) techniques to lower the dimensionality of the learning space. In this paper, we assess the impact of FS techniques for silent speech data, in a dataset with 4 non-invasive and promising modalities, namely: video, depth, ultrasonic Doppler sensing, and surface electromyography. We consider two supervised (mutual information and Fisher's ratio) and two unsupervised (meanmedian and arithmetic mean geometric mean) FS filters. The evaluation was made by assessing the classification accuracy (word recognition error) of three well-known classifiers (knearest neighbors, support vector machines, and dynamic time warping). The key results of this study show that both unsupervised and supervised FS techniques improve on the classification accuracy on both individual and combined modalities. For instance, on the video component, we attain relative performance gains of 36.2% in error rates. FS is also useful as pre-processing for feature fusion. Copyright © 2014 ISCA.

Estimativa dos parâmetros de compactação de solos usando técnicas de data mining

Dissertação de mestrado integrado em Engenharia Civil

Mejora diagnóstica de hepatopatías de afectación difusa mediante técnicas de inteligencia artificial

The automatic diagnostic discrimination is an application of artificial intelligence techniques that can solve clinical cases based on imaging. Diffuse liver diseases are diseases of wide prominence in the population and insidious course, yet early in its progression. Early and effective diagnosis is necessary because many of these diseases progress to cirrhosis and liver cancer. The usual technique of choice for accurate diagnosis is liver biopsy, an invasive and not without incompatibilities one. It is proposed in this project an alternative non-invasive and free of contraindications method based on liver ultrasonography. The images are digitized and then analyzed using statistical techniques and analysis of texture. The results are validated from the pathology report. Finally, we apply artificial intelligence techniques as Fuzzy k-Means or Support Vector Machines and compare its significance to the analysis Statistics and the report of the clinician. The results show that this technique is significantly valid and a promising alternative as a noninvasive diagnostic chronic liver disease from diffuse involvement. Artificial Intelligence classifying techniques significantly improve the diagnosing discrimination compared to other statistics.

A behavioral ecology of shermen: hidden stories from trajectory data in the Northern Humboldt Current System

This work proposes an original contribution to the understanding of shermen spatial behavior, based on the behavioral ecology and movement ecology paradigms. Through the analysis of Vessel Monitoring System (VMS) data, we characterized the spatial behavior of Peruvian anchovy shermen at di erent scales: (1) the behavioral modes within shing trips (i.e., searching, shing and cruising); (2) the behavioral patterns among shing trips; (3) the behavioral patterns by shing season conditioned by ecosystem scenarios; and (4) the computation of maps of anchovy presence proxy from the spatial patterns of behavioral mode positions. At the rst scale considered, we compared several Markovian (hidden Markov and semi-Markov models) and discriminative models (random forests, support vector machines and arti cial neural networks) for inferring the behavioral modes associated with VMS tracks. The models were trained under a supervised setting and validated using tracks for which behavioral modes were known (from on-board observers records). Hidden semi-Markov models performed better, and were retained for inferring the behavioral modes on the entire VMS dataset. At the second scale considered, each shing trip was characterized by several features, including the time spent within each behavioral mode. Using a clustering analysis, shing trip patterns were classi ed into groups associated to management zones, eet segments and skippers' personalities. At the third scale considered, we analyzed how ecological conditions shaped shermen behavior. By means of co-inertia analyses, we found signi cant associations between shermen, anchovy and environmental spatial dynamics, and shermen behavioral responses were characterized according to contrasted environmental scenarios. At the fourth scale considered, we investigated whether the spatial behavior of shermen re ected to some extent the spatial distribution of anchovy. Finally, this work provides a wider view of shermen behavior: shermen are not only economic agents, but they are also foragers, constrained by ecosystem variability. To conclude, we discuss how these ndings may be of importance for sheries management, collective behavior analyses and end-to-end models.

Investigating the role of single point mutations in the human proteome: a computational study

In the post genomic era with the massive production of biological data the understanding of factors affecting protein stability is one of the most important and challenging tasks for highlighting the role of mutations in relation to human maladies. The problem is at the basis of what is referred to as molecular medicine with the underlying idea that pathologies can be detailed at a molecular level. To this purpose scientific efforts focus on characterising mutations that hamper protein functions and by these affect biological processes at the basis of cell physiology. New techniques have been developed with the aim of detailing single nucleotide polymorphisms (SNPs) at large in all the human chromosomes and by this information in specific databases are exponentially increasing. Eventually mutations that can be found at the DNA level, when occurring in transcribed regions may then lead to mutated proteins and this can be a serious medical problem, largely affecting the phenotype. Bioinformatics tools are urgently needed to cope with the flood of genomic data stored in database and in order to analyse the role of SNPs at the protein level. In principle several experimental and theoretical observations are suggesting that protein stability in the solvent-protein space is responsible of the correct protein functioning. Then mutations that are found disease related during DNA analysis are often assumed to perturb protein stability as well. However so far no extensive analysis at the proteome level has investigated whether this is the case. Also computationally methods have been developed to infer whether a mutation is disease related and independently whether it affects protein stability. Therefore whether the perturbation of protein stability is related to what it is routinely referred to as a disease is still a big question mark. In this work we have tried for the first time to explore the relation among mutations at the protein level and their relevance to diseases with a large-scale computational study of the data from different databases. To this aim in the first part of the thesis for each mutation type we have derived two probabilistic indices (for 141 out of 150 possible SNPs): the perturbing index (Pp), which indicates the probability that a given mutation effects protein stability considering all the “in vitro” thermodynamic data available and the disease index (Pd), which indicates the probability of a mutation to be disease related, given all the mutations that have been clinically associated so far. We find with a robust statistics that the two indexes correlate with the exception of all the mutations that are somatic cancer related. By this each mutation of the 150 can be coded by two values that allow a direct comparison with data base information. Furthermore we also implement computational methods that starting from the protein structure is suited to predict the effect of a mutation on protein stability and find that overpasses a set of other predictors performing the same task. The predictor is based on support vector machines and takes as input protein tertiary structures. We show that the predicted data well correlate with the data from the databases. All our efforts therefore add to the SNP annotation process and more importantly found the relationship among protein stability perturbation and the human variome leading to the diseasome.

Inference of binding affinity from neuronal receptors in humans

Tese de mestrado, Bioinformática e Biologia Computacional (Bioinformática), Universidade de Lisboa, Faculdade de Ciências, 2016

Machine learning for matching astronomy catalogues

An emerging issue in the field of astronomy is the integration, management and utilization of databases from around the world to facilitate scientific discovery. In this paper, we investigate application of the machine learning techniques of support vector machines and neural networks to the problem of amalgamating catalogues of galaxies as objects from two disparate data sources: radio and optical. Formulating this as a classification problem presents several challenges, including dealing with a highly unbalanced data set. Unlike the conventional approach to the problem (which is based on a likelihood ratio) machine learning does not require density estimation and is shown here to provide a significant improvement in performance. We also report some experiments that explore the importance of the radio and optical data features for the matching problem.

Unconstrained Handwritten Malayalam Character Recognition using Wavelet Transform and Support vector Machine Classifier

This paper presents the application of wavelet processing in the domain of handwritten character recognition. To attain high recognition rate, robust feature extractors and powerful classifiers that are invariant to degree of variability of human writing are needed. The proposed scheme consists of two stages: a feature extraction stage, which is based on Haar wavelet transform and a classification stage that uses support vector machine classifier. Experimental results show that the proposed method is effective

Classification and staging of chronic liver disease from multimodal data

Chronic liver disease (CLD) is most of the time an asymptomatic, progressive, and ultimately potentially fatal disease. In this study, an automatic hierarchical procedure to stage CLD using ultrasound images, laboratory tests, and clinical records are described. The first stage of the proposed method, called clinical based classifier (CBC), discriminates healthy from pathologic conditions. When nonhealthy conditions are detected, the method refines the results in three exclusive pathologies in a hierarchical basis: 1) chronic hepatitis; 2) compensated cirrhosis; and 3) decompensated cirrhosis. The features used as well as the classifiers (Bayes, Parzen, support vector machine, and k-nearest neighbor) are optimally selected for each stage. A large multimodal feature database was specifically built for this study containing 30 chronic hepatitis cases, 34 compensated cirrhosis cases, and 36 decompensated cirrhosis cases, all validated after histopathologic analysis by liver biopsy. The CBC classification scheme outperformed the nonhierachical one against all scheme, achieving an overall accuracy of 98.67% for the normal detector, 87.45% for the chronic hepatitis detector, and 95.71% for the cirrhosis detector.

An unsupervised approach to feature discretization and selection

Many learning problems require handling high dimensional datasets with a relatively small number of instances. Learning algorithms are thus confronted with the curse of dimensionality, and need to address it in order to be effective. Examples of these types of data include the bag-of-words representation in text classification problems and gene expression data for tumor detection/classification. Usually, among the high number of features characterizing the instances, many may be irrelevant (or even detrimental) for the learning tasks. It is thus clear that there is a need for adequate techniques for feature representation, reduction, and selection, to improve both the classification accuracy and the memory requirements. In this paper, we propose combined unsupervised feature discretization and feature selection techniques, suitable for medium and high-dimensional datasets. The experimental results on several standard datasets, with both sparse and dense features, show the efficiency of the proposed techniques as well as improvements over previous related techniques.

Using data mining techniques to support breast cancer diagnosis

More than ever, there is an increase of the number of decision support methods and computer aided diagnostic systems applied to various areas of medicine. In breast cancer research, many works have been done in order to reduce false-positives when used as a double reading method. In this study, we aimed to present a set of data mining techniques that were applied to approach a decision support system in the area of breast cancer diagnosis. This method is geared to assist clinical practice in identifying mammographic findings such as microcalcifications, masses and even normal tissues, in order to avoid misdiagnosis. In this work a reliable database was used, with 410 images from about 115 patients, containing previous reviews performed by radiologists as microcalcifications, masses and also normal tissue findings. Throughout this work, two feature extraction techniques were used: the gray level co-occurrence matrix and the gray level run length matrix. For classification purposes, we considered various scenarios according to different distinct patterns of injuries and several classifiers in order to distinguish the best performance in each case described. The many classifiers used were Naïve Bayes, Support Vector Machines, k-nearest Neighbors and Decision Trees (J48 and Random Forests). The results in distinguishing mammographic findings revealed great percentages of PPV and very good accuracy values. Furthermore, it also presented other related results of classification of breast density and BI-RADS® scale. The best predictive method found for all tested groups was the Random Forest classifier, and the best performance has been achieved through the distinction of microcalcifications. The conclusions based on the several tested scenarios represent a new perspective in breast cancer diagnosis using data mining techniques.

Using Neural Network Classifier Support Vector Machine Regression for the prediction of Melting Point of Drug – like compounds

In our study we use a kernel based classification technique, Support Vector Machine Regression for predicting the Melting Point of Drug – like compounds in terms of Topological Descriptors, Topological Charge Indices, Connectivity Indices and 2D Auto Correlations. The Machine Learning model was designed, trained and tested using a dataset of 100 compounds and it was found that an SVMReg model with RBF Kernel could predict the Melting Point with a mean absolute error 15.5854 and Root Mean Squared Error 19.7576

Can neuroimaging be used as a support to diagnosis of borderline personality disorder? An approach based on computational neuroanatomy and machine learning

Several recent studies in literature have identified brain morphological alterations associated to Borderline Personality Disorder (BPD) patients. These findings are reported by studies based on voxel-based-morphometry analysis of structural MRI data, comparing mean gray-matter concentration between groups of BPD patients and healthy controls. On the other hand, mean differences between groups are not informative about the discriminative value of neuroimaging data to predict the group of individual subjects. In this paper, we go beyond mean differences analyses, and explore to what extent individual BPD patients can be differentiated from controls (25 subjects in each group), using a combination of automated-morphometric tools for regional cortical thickness/volumetric estimation and Support Vector Machine classifier. The approach included a feature selection step in order to identify the regions containing most discriminative information. The accuracy of this classifier was evaluated using the leave-one-subject-out procedure. The brain regions indicated as containing relevant information to discriminate groups were the orbitofrontal, rostral anterior cingulate, posterior cingulate, middle temporal cortices, among others. These areas, which are distinctively involved in emotional and affect regulation of BPD patients, were the most informative regions to achieve both sensitivity and specificity values of 80% in SVM classification. The findings suggest that this new methodology can add clinical and potential diagnostic value to neuroimaging of psychiatric disorders. (C) 2012 Elsevier Ltd. All rights reserved.