June 22, 2017

GT1 Data Analysis and Knowledge Discovery

Sameer Antani's picture
Sameer Antani
U.S. National Library of Medicine / NIH (USA)
Agma J. M. Traina's picture
Agma J. M. Traina
University of Sao Paulo (BR)
Conference room
Session time
Thursday, June 22, 2017 - 14:00 to 15:30
A Tool for Optimizing De-Identified Health Data for Use in Statistical Classification
Abstract: 
When individual-level health data is shared in biomedical research the privacy of patients and probands must be protected. This is typically achieved with methods of data de-identification, which transform data in such a way that formal guarantees about the degree of protection from re-identification can be provided. In the process it is important to minimize loss of information to ensure that the resulting data is useful. A typical use case is the creation of predictive models for knowledge discovery and decision support, e.g. to infer diagnoses or to predict outcomes of therapies.
Fabian Prasser's picture
Fabian Prasser
TUM (DE)
Johanna Eicher's picture
Johanna Eicher
Raffael Bild's picture
Raffael Bild
Helmut Spengler's picture
Helmut Spengler
Klaus Kuhn's picture
Klaus Kuhn
A Recall Analysis of Core Word Lists over Children’s Utterances for Augmentative and Alternative Communication
Abstract: 
The vocabulary definition is of paramount importance in the customization of AAC devices, and it can be based on core word lists proposals. However, despite having the same purpose, there is no consensus among these core word lists. Therefore, in order to present evidence that helps to decide which list has a better recall, in this paper, 9 core word lists for children were reviewed; in addition, a Super List by merging these 9 lists was made.
Natalia Franco's picture
Natalia Franco
Federal University of Pernambuco (BR)
Augusto Lazzarotto Lima's picture
Augusto Lazzarotto Lima
Thiago Pinheiro Lima's picture
Thiago Pinheiro Lima
Edson Alves Silva's picture
Edson Alves Silva
Rinaldo José Lima's picture
Rinaldo José Lima
Robson Fidalgo's picture
Robson Fidalgo
Computational Analysis of BRCA1 Mutations in Pediatric Patients with Malignancies and Their Mothers
Abstract: 
Breast and ovarian cancers are the most prevalent amongst women. Similar incidence appear in childhood malignancies, where the basic ontogenetic mechanisms still remain to be elucidated. Such approaches, of relating mother’s cancer mutations with the prevalence of childhood cancer in their offspring could prove useful in the prognosis, early detection and therapy of childhood malignancies. The aim of the present study was to use computational and bioinformatics tools to investigate the incidence of mutations in mothers with children suffering from neoplasms.
George Lambrou's picture
George Lambrou
National Technical University of Athens (GR)
Ioanna Barbounaki's picture
Ioanna Barbounaki
Fotini Tzortzatou-Stathopoulou's picture
Fotini Tzortzatou-Stathopoulou
Ourania Petropoulou's picture
Ourania Petropoulou
Panagiotis Katrakazas's picture
Panagiotis Katrakazas
Dimitra Iliopoulou's picture
Dimitra Iliopoulou
Dimitrios Koutsouris's picture
Dimitrios Koutsouris
National Technical University of Athens (GR)
Multi-Label Modality Classification for Figures in Biomedical Literature
Abstract: 
The figures found in biomedical literature are a vital part of biomedical research, education and clinical decision. The multitude of their modalities and the lack of corresponding meta-data, constitute search and information retrieval a difficult task. We present multi-label modality classification approaches for biomedical figures. In particular, we investigate using both simple and compound figures for training a multi-label model to be used for annotating either all figures, or only those predicted as compound by an initial compound figure detection model.
Athanasios Lagopoulos's picture
Athanasios Lagopoulos
Aristotle University of Thessaloniki (GR)
Anestis Fachantidis's picture
Anestis Fachantidis
Grigorios Tsoumakas's picture
Grigorios Tsoumakas
Personalization of Infectious Disease Risk Prediction: Towards Automatic Generation of a Bayesian Network
Abstract: 
Infectious diseases have been a major cause of human morbidity, but most are avoidable. A relevant and accurate risk prediction is expected to alert people to the risk of getting exposed to infectious diseases. However, current approaches are limited to the contexts and static risk prediction model. Thus, a dynamic and growing prediction model, based on Bayesian Network (BN), is proposed to overcome these limitations.
Retno Vinarti's picture
Retno Vinarti
Lucy Hederman's picture
Lucy Hederman
Trinity College Dublin (IE)
BREATH: Heat Maps Assisting the Detection of Abnormal Lung Regions in CT Scans
Abstract: 
Computed Tomography (CT) scans are often employed to diagnose lung diseases, as abnormal tissue regions may indicate whether proper treatment is required. However, detecting specific regions containing abnormalities in a CT scan demands time and effort of specialists. Moreover, different parts of a single lung image may present both normal and abnormal characteristics, what makes inaccurate the classification of a single lung as healthy (normal) or not.
Mirela T. Cazzolato's picture
Mirela T. Cazzolato
University of Sao Paulo - ICMC (BR)
Lucas C. Scabora's picture
Lucas C. Scabora
Alceu F. Costa's picture
Alceu F. Costa
Marcos R. Nesso-Jr's picture
Marcos R. Nesso-Jr
Luis F. Milano-Oliveira's picture
Luis F. Milano-Oliveira
Daniel S. Kaster's picture
Daniel S. Kaster
Caetano Traina-Jr's picture
Caetano Traina-Jr
University of Sao Paulo (BR)
Agma J. M. Traina's picture
Agma J. M. Traina
University of Sao Paulo (BR)

ST5 - Empowering Patients with Cancer through Connected Health

Luis Fernandez-Luque's picture
Luis Fernandez-Luque
Qatar Computing Research Institute (QA)
Brian Caulfield's picture
Brian Caulfield
Conference room
Session time
Thursday, June 22, 2017 - 14:00 to 14:45
iManageCancer:Empowering patients and strengthening self-management in cancer diseases
Abstract: 
Cancer research has led to more cancer patients being cured, and many more enabled to live with their cancer. As such, some cancers are now considered a chronic disease, where patients and their families face the challenge to take an active role in their own care and in some cases in their treatment. To this direction the iManageCancer project aims to provide a cancer specific self-management platform designed according to the needs of patient groups while focusing, in parallel, on the wellbeing of the cancer patient.
Haridimos Kondylakis's picture
Haridimos Kondylakis
Institute of Computer Science FORTH (GR)
Anca Bucur's picture
Anca Bucur
Feng Dong's picture
Feng Dong
Chiara Renzi's picture
Chiara Renzi
Andrea Manfrinati's picture
Andrea Manfrinati
Norbert Graf's picture
Norbert Graf
Stefan Hoffman's picture
Stefan Hoffman
Lefteris Koumakis's picture
Lefteris Koumakis
Gabriella Pravettoni's picture
Gabriella Pravettoni
Kostas Marias's picture
Kostas Marias
Manolis Tsiknakis's picture
Manolis Tsiknakis
Stephan Kiefer's picture
Stephan Kiefer
The Design of a Mobile App for Promotion of Physical Activity and Self-Management in Prostate Cancer Survivors: Personas, Feature Ideation and Low-Fidelity Prototyping
Abstract: 
"Most prostate cancer survivors are confronted with disease-related and treatment-related side effects that impact their quality of life. A tool that combines specific physical activity coaching with the promotion of a healthy lifestyle and self-management guidance might be a successful method to enhance a lifestyle change in these patients. As a prerequisite for useful health technology, it is important to consider a design process centred in the patients.
Francisco Monteiro-Guerra's picture
Francisco Monteiro-Guerra
Salumedia Tecnologias (SP)
Octavio Rivera-Romero's picture
Octavio Rivera-Romero
Vasiliki Mylonopoulou's picture
Vasiliki Mylonopoulou
Gabriel R. Signorelli's picture
Gabriel R. Signorelli
Oncoavanze (SP)
Francisco Zambrana's picture
Francisco Zambrana
Luis Fernandez-Luque's picture
Luis Fernandez-Luque
Qatar Computing Research Institute (QA)
The application of neuromuscular electrical stimulation (NMES) technologies in cancer care
Abstract: 
Despite the increase in long term cancer survivors, successful treatment is associated with significant sequelae. As a result, participation in voluntary exercise becomes difficult highlighting the need for pragmatic alternatives. Neuromuscular electrical stimulation (NMES) has been shown as effective in pathological conditions for improving muscle strength. However, its use in cancer care is sparse and has provided equivocal results. This paper outlines a proposed approach to the design, development, evaluation and implementation of NMES technology into cancer pathways.
Dominic OConnor's picture
Dominic OConnor
University College Dublin (IE)
Brian Caulfield's picture
Brian Caulfield

ST7 - MultiModal Interfaces for Natural Human Computer Interaction: Theory and Applications

Spiros Nikolopoulos's picture
Spiros Nikolopoulos
Centre for Research and Technology Hellas ITI-CERTH (GR)
Elisavet Chatzilari's picture
Elisavet Chatzilari
Centre for Research and Technology Hellas ITI-CERTH (GR)
Conference room
Session time
Thursday, June 22, 2017 - 14:45 to 15:30
An Error Aware SSVEP-based BCI
Abstract: 
ErrPs have been used lately in order to improve several existing BCI applications. In our study we investigate the contribution of ErrPs in a SSVEP based BCI. An extensive study is presented in order to discover the limitations of the proposed scheme. Using Common Spatial Patterns and Random Forests we manage to show encouraging results regarding the incorporation of ErrPs in a SSVEP system. Finally, we provide a novel methodology (ICRT) that can measure the gain of a BCI system by incorporating ErrPs in terms of time efficiency.
Fotis Kalaganis's picture
Fotis Kalaganis
CERTH/ITI (GR)
Elisavet Chatzilari's picture
Elisavet Chatzilari
Centre for Research and Technology Hellas ITI-CERTH (GR)
Kostas Georgiadis's picture
Kostas Georgiadis
Spiros Nikolopoulos's picture
Spiros Nikolopoulos
Centre for Research and Technology Hellas ITI-CERTH (GR)
Nikos Laskaris's picture
Nikos Laskaris
Ioannis Kompatsiaris's picture
Ioannis Kompatsiaris
Analyzing the Impact of Cognitive Load in Evaluating Gaze-based Typing
Abstract: 
Gaze-based virtual keyboards allow people with motor disability a method for text entry by eye movements. The effectiveness and usability of these keyboards have traditionally been evaluated with conventional text entry performance measures such as words per minute, keystroke saving, error rate, accuracy, etc. However, in comparison to the conventional text entry approaches, gaze-based typing involves natural eye movements that are highly correlated with human brain cognition.
Korok Sengupta's picture
Korok Sengupta
University of Koblenz (DE)
Jun Sun's picture
Jun Sun
Raphael Menges's picture
Raphael Menges
Institute for Web Science and Technologies (DE)
Chandan Kumar's picture
Chandan Kumar
University of Koblenz (DE)
Steffen Staab's picture
Steffen Staab
Assessing the Usability of Gaze-Adapted Interface against Conventional Eye-Based Input Emulation
Abstract: 
In recent years, eye tracking systems have greatly improved, beginning to play a promising role as an input medium. Eye trackers can be used for application control either by simply emulating the mouse device in the traditional graphical user interface, or by customized interfaces for eye gaze events. In this work we evaluate these two approaches to assess their impact in usability. We present a gaze-adapted Twitter application interface with direct interaction of eye gaze input, and compare it to the Twitter in a conventional browser interface with gaze-based mouse and keyboard emulation.
Chandan Kumar's picture
Chandan Kumar
University of Koblenz (DE)
Raphael Menges's picture
Raphael Menges
Institute for Web Science and Technologies (DE)
Steffen Staab's picture
Steffen Staab

ST9 - Cloud Security and Data Privacy by Design

Iraklis Paraskakis's picture
Iraklis Paraskakis
SEERC (GR) & The University of Sheffield (UK)
Conference room
Session time
Thursday, June 22, 2017 - 16:00 to 17:15
Secure Database Outsourcing to the Cloud: Side-Channels, Counter-Measures and Trusted Execution
Abstract: 
"Outsourcing data processing and storage to the cloud is a persistent trend in the last years. Cloud computing offers many advantages like flexibility in resource allocation, cost reduction and high availability. However, when sensitive information is handed to a third party, security questions are raised since the cloud provider and his employees are not fully trusted. Standard security mechanisms like transport encryption and regular audits alone can't solve the issue of insider attacks. Additional cryptographic techniques are required. In this paper we build upon an existing
Matthias Gabel's picture
Matthias Gabel
Jeremias Mechler's picture
Jeremias Mechler
Karlsruhe Institute of Technology (DE)
Ontological Templates for Regulating Access to Sensitive Medical Data in the Cloud
Abstract: 
By embracing the cloud computing paradigm for storing and processing electronic medical records (EMRs), modern healthcare providers are able to realise significant cost savings. However, relinquishing control of sensitive medical data by delegating their storage and processing to third-party cloud providers naturally raises significant security concerns. One way to alleviate these concerns is to devise appropriate policies that infuse adequate access controls in cloud services.
Simeon Veloudis's picture
Simeon Veloudis
South East European Research Centre (SEERC) The University of Sheffield
Iraklis Paraskakis's picture
Iraklis Paraskakis
SEERC (GR) & The University of Sheffield (UK)
Yiannis Verginadis's picture
Yiannis Verginadis
Ioannis Patiniotakis's picture
Ioannis Patiniotakis
Gregoris Mentzas's picture
Gregoris Mentzas
HealthShare: Using Attribute-Based Encryption for Secure Data Sharing Between Multiple Clouds
Abstract: 
"In this paper, we propose HealthShare –a forwardlooking approach for secure ehealth data sharing between multiple organizations that are hosting patients’ data in different clouds. The proposed protocol is based on a Revocable Key-Policy Attribute-Based Encryption scheme and allows users to share encrypted health records based on a policy that has been defined by the data owner (i.e. patient, a member of the hospital, etc). Furthermore, access to a malicious or compromised user/organization can be easily revoked without the need to generate fresh encryption keys."
Antonis Michalas's picture
Antonis Michalas
University of Westminster (UK)
Noam Weingarten's picture
Noam Weingarten
Security in a Distributed Key Management Approach
Abstract: 
Cloud computing offers many advantages as flexibility or resource-efficiency and can significantly reduce costs. However, when sensitive medical data is outsourced to a cloud provider, classified records can leak. To protect the patients and application providers from a privacy breach data must be encrypted before it is uploaded. In this work, we present a distributed key management scheme that handles user-specific keys in a single-tenant scenario. The underlying database is encrypted and the secret key is only reconstructed temporarily in memory.
Gunther Schiefer's picture
Gunther Schiefer
Karlsruhe Institute of Technology (DE)
Murat Citak's picture
Murat Citak
Andreas Schoknecht's picture
Andreas Schoknecht
Matthias Gabel's picture
Matthias Gabel
Jeremias Mechler's picture
Jeremias Mechler
Karlsruhe Institute of Technology (DE)

GT2 Decision Support Systems and Methods

Leontios Hadjileontiadis's picture
Leontios Hadjileontiadis
Aristotle University of Thessaloniki (GR)
Spiros Denaxas's picture
Spiros Denaxas
University College London (UK)
Conference room
Session time
Thursday, June 22, 2017 - 16:00 to 17:15
EEG Signal Analysis of Real-word Reading and Nonsense-word Reading between Adults with Dyslexia and without Dyslexia
Abstract: 
The evolution in technology plays a major role in improving diagnostic accuracies. Pattern recognition and classification are techniques that may help uncover answers that are not always obvious. This paper attempts to discover such patterns found in brain wave signals in people with dyslexia using classifiers. Electroencephalogram (EEG) signals captured during real-word and nonsense-word reading activities from individuals with dyslexia are compared with normal controls.
Harshani Perera's picture
Harshani Perera
Murdoch University (AU)
Mohd Fairuz Shiratuddin's picture
Mohd Fairuz Shiratuddin
Kok Wai Wong's picture
Kok Wai Wong
Kelly Fullarton's picture
Kelly Fullarton
Emotional state recognition using advanced machine learning techniques on EEG data
Abstract: 
This study investigates the discrimination between calm, exciting positive and exciting negative emotional states using EEG signals. Towards this direction, a publicly available dataset from eNTERFACE Workshop 2006 was used having as stimuli emotionally evocative images. At first, EEG features were extracted based on literature review. Then, a computational framework is proposed using machine learning techniques, performing feature selection and classification into two at a time emotional states.
Katerina Giannakaki's picture
Katerina Giannakaki
University of Crete (GR)
Giorgos Giannakakis's picture
Giorgos Giannakakis
Christina Farmaki's picture
Christina Farmaki
Vangelis Sakkalis's picture
Vangelis Sakkalis
Estimation of Heart Failure Patients Medication Adherence through the Utilization of Saliva and Breath Biomarkers and Data Mining Techniques
Abstract: 
The aim of this work is to estimate the medication adherence of patients with heart failure through the application of a data mining approach on a dataset including information from saliva and breath biomarkers. The method consists of two stages. In the first stage, a model for the estimation of adherence risk of a patient, exploiting anamnestic and instrumental data, is applied.
Evanthia Tripoliti's picture
Evanthia Tripoliti
Theofilos Papadopoulos's picture
Theofilos Papadopoulos
Georgia Karanasiou's picture
Georgia Karanasiou
FORTH (GR)
Fanis Kalatzis's picture
Fanis Kalatzis
Yorgos Goletsis's picture
Yorgos Goletsis
Aris Bechlioulis's picture
Aris Bechlioulis
Silivia Ghimenti's picture
Silivia Ghimenti
Tommaso Lomonaco's picture
Tommaso Lomonaco
Francesca Bellagambi's picture
Francesca Bellagambi
Roger Fuoco's picture
Roger Fuoco
Mario Marzilli's picture
Mario Marzilli
Maria Chiara Scali's picture
Maria Chiara Scali
Katerina Naka's picture
Katerina Naka
Abdelhamid Errachid's picture
Abdelhamid Errachid
Dimitris Fotiadis's picture
Dimitris Fotiadis
University of Ioannina (GR)
Exploiting active microRNA interactions for diagnosis from expression profiling experiments
Abstract: 
In silico diagnosis through microRNA expression profiling experiments is a promising direction in the clinical practices of bioinformatics science. The task is computationally defined as a classification problem where a query experiment is required to be assigned into one of the predefined diseases using a learned model from previously labeled samples. While several powerful machine learning models exist to perform this task, the challenging issue is how to feed these models by effectively encoded samples. This encoding requires a sensible representation of experiment content.
Erdem Corapcioglu's picture
Erdem Corapcioglu
Hasan Ogul's picture
Hasan Ogul
Baskent University (TR)
The Effect of Mammogram Preprocessing on Microcalcification Detection with Convolutional Neural Networks
Abstract: 
"Microcalcifications are an early mammographic indicator of breast cancer. To assist screening radiologists in reading mammograms, machine learning techniques have been developed for the automated detection of microcalcifications. In the last few years, Convolutional Neural Networks (CNNs) have achieved state-of-the-art performance in many computer vision and medical image analysis applications. A key step in CNN-based detection is image preprocessing, including brightness and contrast variations.
Agnese Marchesi's picture
Agnese Marchesi
University of Cassino and Southern Latium (IT)
Alessandro Bria's picture
Alessandro Bria
Claudio Marrocco's picture
Claudio Marrocco
Mario Molinara's picture
Mario Molinara
Francesco Tortorella's picture
Francesco Tortorella
University of Cassino and South Lazio (IT)
Jan-Jurre Mordang's picture
Jan-Jurre Mordang
Nico Karssemeijer's picture
Nico Karssemeijer

Keynote Speech

Leontios Hadjileontiadis's picture
Leontios Hadjileontiadis
Aristotle University of Thessaloniki (GR)
Terry Poulton's picture
Terry Poulton
Saint George's University of London (UK)
Conference room
Session time
Thursday, June 22, 2017 - 17:30 to 18:15

The proposed lecture will present advanced achievements in the field of affective computing towards more enhanced human-computer-interaction interfaces, presenting advanced signal processing techniques and implementations applied to Electroencephalogram (EEG) recordings. In particular, the way emotions are 'reflected' in our brain signals and the way actions (both in explicit and implicit way, e.g., gestures in music) are combined with internal representations in our brain (involving mirror neuron system activation), will be presented and discussed. Moreover, potential implementations of the findings in the field of human assistive technology will be shown, including innovative ways of pain management, bullying identification, and Parkinson’s and Alzheimer's community support. 

Keynote Speech

Tony Solomonides's picture
Tony Solomonides
NorthShore University HealthSystem (USA)
Allan Tucker's picture
Allan Tucker
Brunel University London (UK)
Conference room
Session time
Thursday, June 22, 2017 - 18:15 to 19:00

There are many diagnosis and treatment guidelines for certain conditions, but there are others, especially undifferentiated complaints, the problem of diagnosis is wide open. A team from NorthShore, Case Western Reserve, Carnegie Mellon, Weill Cornell, and Johns Hopkins is working on a joint project to study the diagnostic process in the case of several undifferentiated complaints, including (a) Abdominal Pain, and (b) Dizziness. There are many different approaches to the problem of discovery of good diagnostic pathways from the electronic health record. I will discuss several approaches and show some results from each. The problem of finding optimal pathways -- i.e. courses of action that would minimize time to diagnosis without an unacceptable risk of diagnostic error -- remains elusive, so it would give us something to discuss further.