Cookies Policy
We use cookies to improve our site and your experience. By continuing to browse our site you accept our cookie policy. Find out More
Close
  • Menu
About

About

Pedro Ferreira was born in Oporto in 1984. In 2010 he received his MSc. degree in Network and Information Systems Engineering from University of Porto. Since March 2010 he is a researcher in the Center for Research in Advanced Computing Systems (CRACS-INESC TEC).
His main areas of interest are data mining and machine learning applied to clinical data. Pedro is currently pursuing a PhD. degree at University of Porto.

Interest
Topics
Details

Details

  • Name

    Pedro Silva Ferreira
  • Cluster

    Computer Science
  • Role

    Research Assistant
  • Since

    24th August 2011
001
Publications

2016

A Speech-to-Text Interface for MammoClass

Authors
Roche, RS; Ferreira, P; Dutra, I; Correia, R; Salvini, R; Burnside, E;

Publication
2016 IEEE 29TH INTERNATIONAL SYMPOSIUM ON COMPUTER-BASED MEDICAL SYSTEMS (CBMS)

Abstract
Mammoclass is a web tool that allows users to enter a small set of variable values that describe a finding in a mammography, and produces a probability of this finding being malignant or benign. The tool requires that the user types in every variable a value in order to perform a prediction. In this work, we present a speech-to-text interface integrated to MammoClass that allows radiologists to speak up a mammography report instead of typing it in. This new MammoClass module can take audio content, transcribe it into written words, and automatically extract the variable values by applying a parser to the recognized text. Results of spoken mammography reports show that the same variables are extracted for both types of input: typed in or dictated text.

2016

Interpretable Models to Predict Breast Cancer

Authors
Ferreira, P; Dutra, I; Salvini, R; Burnside, E;

Publication
2016 IEEE INTERNATIONAL CONFERENCE ON BIOINFORMATICS AND BIOMEDICINE (BIBM)

Abstract
Several works in the literature use propositional ("black box") approaches to generate prediction models. In this work we employ the Inductive Logic Programming technique, whose prediction model is based on first order rules, to the domain of breast cancer. These rules have the advantage of being interpretable and convenient to be used as a common language between the computer scientists and the medical experts. We also explore the relevance of some of variables usually collected to predict breast cancer. We compare our results with a propositional classifier that was considered best for the same dataset studied in this paper.

2015

Predicting malignancy from mammography findings and image-guided core biopsies

Authors
Ferreira, P; Fonseca, NA; Dutra, I; Woods, R; Burnside, E;

Publication
INTERNATIONAL JOURNAL OF DATA MINING AND BIOINFORMATICS

Abstract
The main goal of this work is to produce machine learning models that predict the outcome of a mammography from a reduced set of annotated mammography findings. In the study we used a dataset consisting of 348 consecutive breast masses that underwent image guided core biopsy performed between October 2005 and December 2007 on 328 female subjects. We applied various algorithms with parameter variation to learn from the data. The tasks were to predict mass density and to predict malignancy. The best classifier that predicts mass density is based on a support vector machine and has accuracy of 81.3%. The expert correctly annotated 70% of the mass densities. The best classifier that predicts malignancy is also based on a support vector machine and has accuracy of 85.6%, with a positive predictive value of 85%. One important contribution of this work is that our model can predict malignancy in the absence of the mass density attribute, since we can fill up this attribute using our mass density predictor.

2014

ExpertBayes: Automatically refining manually built Bayesian networks

Authors
Almeida, E; Ferreira, P; Vinhoza, TTV; Dutra, I; Borges, P; Wu, Y; Burnside, E;

Publication
Proceedings - 2014 13th International Conference on Machine Learning and Applications, ICMLA 2014

Abstract
Bayesian network structures are usually built using only the data and starting from an empty network or from a naive Bayes structure. Very often, in some domains, like medicine, a prior structure is already known based on expert knowledge. This structure can be automatically or manually refined in search for better performance models. In this work, we take Bayesian networks built by specialists and show that minor perturbations to this original network can yield better classifiers, while maintaining most of the interpretability of the original network. © 2014 IEEE.

2013

Knowledge on Heart Condition of Children based on Demographic and Physiological Features

Authors
Ferreira, P; Vinhoza, TTV; Castro, A; Mourato, F; Tavares, T; Mattos, S; Dutra, I; Coimbra, M;

Publication
2013 IEEE 26TH INTERNATIONAL SYMPOSIUM ON COMPUTER-BASED MEDICAL SYSTEMS (CBMS)

Abstract
We evaluated a population of 7199 children between 2 and 19 years old to study the relations between the observed demographic and physiological features in the occurrence of a pathological/non-pathological heart condition. The data was collected at the Real Hospital Portugues, Pernambuco, Brazil, We performed a feature importance study, with the aim of categorizing the most relevant variables, indicative of abnormalities. Results show that second heart sound, weight, heart rate, height and secondary reason for consultation are important features, but not nearly as decisive as the presence of heart murmurs. Quantitatively speaking. systolic murmurs and a hyperphonetic second heart sound increase the odds of having a pathology by a factor of 320 and 6, respectively.