nach oben

2015 | Buch

Kapitel lesen Erstes Kapitel lesen

Information Technology in Bio- and Medical Informatics

6th International Conference, ITBAM 2015, Valencia, Spain, September 3-4, 2015, Proceedings

herausgegeben von: M. Elena Renda, Miroslav Bursa, Andreas Holzinger, Sami Khuri

Verlag: Springer International Publishing

Buchreihe : Lecture Notes in Computer Science

Enthalten in: Springer Professional "Wirtschaft+Technik" , Springer Professional "Technik" , Springer Professional "Wirtschaft"

Einloggen, um Zugang zu erhalten

Über dieses Buch

This book constitutes the refereed proceedings of the 6th International Conference on Information Technology in Bio- and Medical Informatics, ITBAM 2015, held in Valencia, Spain, in September 2015, in conjunction with DEXA 2015.

The 9 revised long papers presented together with 1 poster paper were carefully reviewed and selected from 15 submissions. The papers address the following two topics: medical terminology and clinical processes and machine learning in biomedicine.

Inhaltsverzeichnis

Frontmatter

Medical Terminology and Clinical Processes

Frontmatter

From Literature to Knowledge: Exploiting PubMed to Answer Biomedical Questions in Natural Language

Abstract

Researchers, practitioners and the general public strive to be constantly up to date with the latest developments in the subjects of bio-medical research of their interest. Meanwhile the collection of high quality research papers freely available on the Web has increase dramatically in the last few years and this trend is likely to continue. This state of facts brings about opportunities as well as challenges for the construction of effective web-based searching tools. Question/Answering systems based on user interactions in Natural Language have emerged as a promising alternative to traditional keyword based search engines. However this technology still needs to mature in order to fulfill its promises. In this paper we present and test a new graph-based proof-of-concept paradigm for processing the knowledge base and the user queries expressed in natural Language. The user query is mapped as a subgraph matching problem onto the internal graph representation, and thus can handle efficiently also partial matches. Preliminary user-based output quality measurements confirm the viability of our method.

Pinaki Bhaskar, Marina Buzzi, Filippo Geraci, Marco Pellegrini

Using Twitter Data and Sentiment Analysis to Study Diseases Dynamics

Abstract

Twitter has been recently used to predict and/or monitor real world outcomes, and this is also true for health related topic. In this work, we extract information about diseases from Twitter with spatio-temporal constraints, i.e. considering a specific geographic area during a given period. We exploit the SNOMED-CT terminology to correctly detect medical terms, using sentiment analysis to assess to what extent each disease is perceived by persons. We show our first results for a monitoring tool that allow to study the dynamic of diseases.

Vincenza Carchiolo, Alessandro Longheu, Michele Malgeri

An Open Data Approach for Clinical Appropriateness

Abstract

In recent years there have been partially unexpected qualitative and quantitative increase in clinical exams demand. Although on the one hand this is the positive result of better health awareness, mostly in terms of prevention, on the other hand it is the direct and logical consequence of the defensive behaviour, which arises from the potential occurrence of legal controversies and of the clinician’s unawareness about the cost of examinations. To reduce the occurrence of unnecessary clinical tests we propose an approach based on Open Data and Open Software that can be adapted to existing medical information systems to enforce a suitable set of “appropriateness rules”. The idea is to directly intervene at the moment of the request emission, in order to avoid unnecessary demands, which have no urgent and valid motivations and/or no value for patients.

Mario A. Bochicchio, Lucia Vaira, Marco Zappatore, Giambattista Lobreglio, Marilena Greco

Machine Learning in Biomedicine

Frontmatter

A Logistic Regression Approach for Identifying Hot Spots in Protein Interfaces

Abstract

Protein–protein interactions occur when two or more proteins bind together, often to carry out their biological function. A small fraction of interfaces on protein surface found providing major contributions to the binding free energy are referred as hot spots. Identifying hot spots is important for examining the actions and properties occurring around the binding sites. However experimental studies require significant effort; and computational methods still have limitations in prediction performance and feature interpretation.

In this paper we describe a hot spots residues prediction measure which provides a significant improvement over other existing methods. Combining 8 features derived from accessibility, sequence conservation, inter-residue potentials, computational alanine scanning, small-world structure characteristics, phi-psi interaction, and contact number, logistic regression is used to derive a prediction model. To demonstrate its effectiveness, the proposed method is applied to ASEdb. Our prediction model achieves an accuracy of 0.819, F1 score of 0.743. Experimental results show that the additional features can improve the prediction performance. Especially phi-psi has been found to give important effort. We then perform an exhaustive comparison of our method with various machine learning based methods and those previously published prediction models in the literature. Empirical studies show that our method can yield significantly better prediction performance.

Peipei Li, Keun Ho Ryu

The Discovery of Prognosis Factors Using Association Rule Mining in Acute Myocardial Infarction with ST-Segment Elevation

Abstract

Association rule mining has been applied actively in order to discover the hidden factors in acute myocardial infarction. There has been minimal research regarding the prognosis factor of acute myocardial infarction, and several previous studies has some limitations which are generation of incorrect population and potential data bias. Thus, we suggest the generation of prognosis factor based on association rule mining for acute myocardial infarction with ST-segment elevation. In our experiments, we obtain high interestingness factor based on Korean acute myocardial infarction registry which is corrected by 51 participating hospitals since 2005. The interestingness of the factor is evaluated by confidence. It is expected to contribute to prognosis management by high reliability factor.

Kwang Sun Ryu, Hyun Woo Park, Soo Ho Park, Ibrahim M. Ishag, Jang Hwang Bae, Keun Ho Ryu

Data Mining Techniques in Health Informatics: A Case Study from Breast Cancer Research

Abstract

This paper presents a case study of using data mining techniques in the analysis of diagnosis and treatment events related to Breast Cancer disease. Data from over 16,000 patients has been pre-processed and several data mining techniques have been implemented by using Weka (Waikato Environment for Knowledge Analysis). In particular, Generalized Sequential Patterns mining has been used to discover frequent patterns from disease event sequence profiles based on groups of living and deceased patients. Furthermore, five models have been evaluated in Classification with the objective to classify the patients based on selected attributes. This research showcases the data mining process and techniques to transform large amounts of patient data into useful information and potentially valuable patterns to help understand cancer outcomes.

Jing Lu, Alan Hales, David Rew, Malcolm Keech, Christian Fröhlingsdorf, Alex Mills-Mullett, Christian Wette

Artificial Neural Networks in Diagnosis of Liver Diseases

Abstract

Liver diseases have severe patients’ consequences, being one of the main causes of premature death. These facts reveal the centrality of one`s daily habits, and how important it is the early diagnosis of these kind of illnesses, not only to the patients themselves, but also to the society in general. Therefore, this work will focus on the development of a diagnosis support system to these kind of maladies, built under a formal framework based on Logic Programming, in terms of its knowledge representation and reasoning procedures, complemented with an approach to computing grounded on Artificial Neural Networks.

José Neves, Adriana Cunha, Ana Almeida, André Carvalho, João Neves, António Abelha, José Machado, Henrique Vicente

How to Increase the Effectiveness of the Hepatitis Diagnostics by Means of Appropriate Machine Learning Methods

Abstract

This paper presents how to improve the diagnostic process of hepatitis B and C based on collected questionnaires from patients hospitalized in all regional departments of infectology in Slovakia. Performed experiments were oriented in two directions: economic demands of the recommended treatment based on realized diagnostics and possible improvement of hepatitis diagnostics by means of exploratory and predictive analysis of additional information provided by patients. Exploratory data analysis was used to confirm or to reject some expected relationships between input attributes (e.g. ager or gender) and target diagnosis. Also, predictive mining resulted into interesting decision rules that can be used in medical practice as supporting information at an early stage of the diagnostic process. Finally, analysis of the treatment economic demands based on the estimated costs showed the need for timely and quality diagnostics to minimize the percentage of patients for which was hepatitis diagnosed late.

Alexandra Lukáčová, František Babič, Zuzana Paraličová, Ján Paralič

Ant-Inspired Algorithms for Decision Tree Induction

An Evaluation on Biomedical Signals

Abstract

In this paper we present an evaluation of ant-inspired method called ACO_DTree over biomedical data. The algorithm maintains and evolves a population of decision trees induced from data. The core of the algorithm is inspired by the Min-Max Ant System.

In order to increase the speed of the algorithm we have introduced a local optimization phase. The generalization ability has been improved using error based pruning of the solutions.

After parameter tuning, we have conducted experimental evaluation of the ACO_DTree method over the total of 32 different datasets versus 41 distinct classifiers. We conducted 10-fold crossvalidation and for each experiment obtained about 20 quantitative objective measures. The averaged and best-so-far values of the selected measures (precision, recall, f-measure, ...) have been statistically evaluated using Friedman test with Holm and Hochberg post-hoc procedures (on the levels of \(\alpha =0.05\) and \(\alpha =0.10\)). The ACO_DTree algorithm performed significantly better (\(\alpha =0.05\)) in 29 test cases for the averaged f-measure and in 14 cases for the best-so-far f-measure.

The best results have been obtained for various subsets of the UCI database and for the dataset combining cardiotocography data and data of myocardial infarction.

Miroslav Bursa, Lenka Lhotska

Poster Session

Frontmatter

Microsleep Classifier Using EOG Channel Recording: A Feasibility Study

Abstract

The microsleeps (MS) cause many accidents and can have a huge social impact. Automated prediction or early detection of the MS states could help to monitor level of fatigue. An automated MS classifier based on the EOG signal is proposed. There were analysed 28 episodes of MS. We observed slow eye movements without rapid changes during MS episodes. An automated feature extraction and classification using EOG channels showed promising results (sensitivity 93 %, positive predictivity 57 %). To confirm the hypothesis it is crucial to extend the study and to analyse larger amount of MS data.

Martin Holub, Martina Šrutová, Lenka Lhotská

Backmatter

Titel: Information Technology in Bio- and Medical Informatics
herausgegeben von: M. Elena Renda
Miroslav Bursa
Andreas Holzinger
Sami Khuri
Verlag: Springer International Publishing
Electronic ISBN: 978-3-319-22741-2
Print ISBN: 978-3-319-22740-5
DOI: https://doi.org/10.1007/978-3-319-22741-2