Evangelos Kaimakamis

KnowBaSICS-M: An ontology-based system for semantic management of medical problems and computerised algorithmic solutions

In this paper, an ontology-based system (KnowBaSICS-M) is presented for the semantic management of Medical Computational Problems (MCPs), i.e., medical problems and computerised algorithmic solutions. The system provides an open environment, which: (1) allows clinicians and researchers to retrieve potential algorithmic solutions pertinent to a medical problem and (2) enables incorporation of new MCPs into its underlying Knowledge Base (KB). KnowBaSICS-M is a modular system for MCP acquisition and discovery that relies on an innovative ontology-based model incorporating concepts from the Unified Medical Language System (UMLS). Information retrieval (IR) is based on an ontology-based Vector Space Model (VSM) that estimates the similarity among user-defined MCP search criteria and registered MCP solutions in the KB. The results of a preliminary evaluation and specific examples of use are presented to illustrate the benefits of the system. KnowBaSICS-M constitutes an approach towards the construction of an integrated and manageable MCP repository for the biomedical research community.

Ontology-based Vector Space Model and Fuzzy Query Expansion to Retrieve Knowledge on Medical Computational Problem Solutions

Medical Computational Problem (MCP) solving is related to medical problems and their computerized algorithmic solutions. In this paper, an extension of an ontology-based model to fuzzy logic is presented, as a means to enhance the information retrieval (IR) procedure in semantic management of MCPs. We present herein the methodology followed for the fuzzy expansion of the ontology model, the fuzzy query expansion procedure, as well as an appropriate ontology-based Vector Space Model (VSM) that was constructed for efficient mapping of user-defined MCP search criteria and MCP acquired knowledge. The relevant fuzzy thesaurus is constructed by calculating the simultaneous occurrences of terms and the term-to-term similarities derived from the ontology that utilizes UMLS (Unified Medical Language System) concepts by using Concept Unique Identifiers (CUI), synonyms, semantic types, and broader- narrower relationships for fuzzy query expansion. The current approach constitutes a sophisticated advance for effective, semantics-based MCP-related IR.

Screening of patients with obstructive sleep Apnea syndrome using C4.5 algorithm based on non linear analysis of respiratory signals during sleep

Aim: To classify patients with possible diagnosis of Obstructive Sleep Apnea Syndrome (OSAS) into groups according to the severity of the disease using a decision tree producing algorithm based on nonlinear analysis of 3 respiratory signals instead of the use of full polysomnography. Patients-Methods: Eighty-six consecutive patients referred to the Sleep Unit of a Pulmonology Department underwent full polysomnography and their tests were manually scored. Three nonlinear indices (Largest Lyapunov Exponent-LLE, Detrended Fluctuation Analysis-DFA and Approximate Entropy-APEN) were extracted from two respiratory signals (nasal cannula flow-F and thoracic belt-T). The oxygen saturation signal (SpO2) was also selected. The above measurements provided data to the C4.5 algorithm using a data mining application. Results: Two decision trees were produced using linear and nonlinear data from 3 respiratory signals. The discrimination between normal subjects and sufferers from OSAS presented an accuracy of 84.9% and a recall of 90.3% using the variables age, sex, DFA from F and Time with SpO2<90% (T90). The classification of patients into severity groups had an accuracy of 74.2% and a recall of 81.1% using the variables APEN from F, DFA from F and T90. Conclusion: It is possible to have reliable predictions of the severity of OSAS using linear and nonlinear indices from only two respiratory signals during sleep instead of performing full polysomnography. The proposed algorithm could be used for screening patients suspected to suffer from OSAS.

COPD care delivery pathways in five European Union countries: mapping and health care professionals’ perceptions

Background COPD is among the leading causes of chronic morbidity and mortality in the European Union with an estimated annual economic burden of €25.1 billion. Various care pathways for COPD exist across Europe leading to different responses to similar problems. Determining these differences and the similarities may improve health and the functioning of health services. Objective The aim of this study was to compare COPD patients’ care pathway in five European Union countries including England, Ireland, the Netherlands, Greece, and Germany and to explore health care professionals’ (HCPs) perceptions about the current pathways. Methods HCPs were interviewed in two stages using a qualitative, semistructured email interview and a face-to-face semistructured interview. Results Lack of communication among different health care providers managing COPD and comorbidities was a common feature of the studied care pathways. General practitioners/family doctors are responsible for liaising between different teams/services, except in Greece where this is done through pulmonologists. Ireland and the UK are the only countries with services for patients at home to shorten unnecessary hospital stay. HCPs emphasized lack of communication, limited resources, and poor patient engagement as issues in the current pathways. Furthermore, no specified role exists for pharmacists and informal carers. Conclusion Service and professional integration between care settings using a unified system targeting COPD and comorbidities is a priority. Better communication between health care providers, establishing a clear role for informal carers, and enhancing patients’ engagement could optimize current care pathways resulting in a better integrated system.

Detection of crackle events using a multi-feature approach

The automatic detection of adventitious lung sounds is a valuable tool to monitor respiratory diseases like chronic obstructive pulmonary disease. Crackles are adventitious and explosive respiratory sounds that are usually associated with the inflammation or infection of the small bronchi, bronchioles and alveoli. In this study a multi-feature approach is proposed for the detection of events, in the frame space, that contain one or more crackles. The performance of thirty-five features was tested. These features include thirty-one features usually used in the context of Music Information Retrieval, a wavelet based feature as well as the Teager energy and the entropy. The classification was done using a logistic regression classifier. Data from seventeen patients with manifestations of adventitious sounds and three healthy volunteers were used to evaluate the performance of the proposed method. The dataset includes crackles, wheezes and normal lung sounds. The optimal detection parameters, such as the number of features, were chosen based on a grid search. The performance of the detection was studied taking into account the sensitivity and the positive predictive value. For the conditions tested, the best results were obtained for the frame size equal to 128 ms and twenty-seven features.

Detection of wheezes using their signature in the spectrogram space and musical features

In this work thirty features were tested in order to identify the best feature set for the robust detection of wheezes. The features include the detection of the wheezes signature in the spectrogram space (WS-SS) and twenty-nine musical features usually used in the context of Music Information Retrieval. The method proposed to detect the signature of wheezes imposes a temporal Gaussian regularization and a reduction of the false positives based on the (geodesic) morphological opening by reconstruction operator. Our dataset contains wheezes, crackles and normal breath sounds. Four selection algorithms were used to rank the features. The performance of the features was asserted having into account the Matthews correlation coefficient (MCC). All the selection algorithms ranked the WS-SS feature as the most important. A significant boost in performance was obtained by using around ten features. This improvement was independent of the selection algorithm. The use of more than ten features only allows for a small increase of the MCC value.

Dynamic Composition of Semantic Pathways for Medical Computational Problem Solving by Means of Semantic Rules

This paper presents a semantic rule-based system for the composition of successful algorithmic pathways capable of solving medical computational problems (MCPs). A subset of medical algorithms referring to MCP solving concerns well-known medical problems and their computational algorithmic solutions. These solutions result from computations within mathematical models aiming to enhance healthcare quality via support for diagnosis and treatment automation, especially useful for educational purposes. Currently, there is a plethora of computational algorithms on the web, which pertain to MCPs and provide all computational facilities required to solve a medical problem. An inherent requirement for the successful construction of algorithmic pathways for managing real medical cases is the composition of a sequence of computational algorithms. The aim of this paper is to approach the composition of such pathways via the design of appropriate finite-state machines (FSMs), the use of ontologies, and SWRL semantic rules. The goal of semantic rules is to automatically associate different algorithms that are represented as different states of the FSM in order to result in a successful pathway. The rule-based approach is herein implemented on top of Knowledge-Based System for Intelligent Computational Search in Medicine (KnowBaSICS-M), an ontology-based system for MCP semantic management. Preliminary results have shown that the proposed system adequately produces algorithmic pathways in agreement with current international medical guidelines.

An Ontology-Based Approach to Constructing Medical Computational Problems for Use in Electronic Medical Education

Recently, a great interest has emerged in e-learning approaches for medical education. In particular, problem/case based learning constitutes a significant initiative in the domain. In this paper, we propose an ontology-based approach to constructing medical computational problems (MCPs) to be used in electronic medical education. Specifically, we elaborate on a novel ontological schema for MCP description that semantically annotates problems and their associated solutions (in terms of algorithms and implementations), linked with the IEEE metadata standard for learning objects (LOM) and its healthcare extension (Healthcare LOM). We present the overall procedure involved in the construction of the educational framework on MCPs, the involved actors, and the semantic schema of the corresponding knowledge model developed. The applicability and virtue of the proposed approach is illustrated via an example test case lesson on pulmonary embolism.

Α Respiratory Sound Database for the Development of Automated Classification

The automatic analysis of respiratory sounds has been a field of great research interest during the last decades. Automated classification of respiratory sounds has the potential to detect abnormalities in the early stages of a respiratory dysfunction and thus enhance the effectiveness of decision making. However, the existence of a publically available large database, in which new algorithms can be implemented, evaluated, and compared, is still lacking and is vital for further developments in the field. In the context of the International Conference on Biomedical and Health Informatics (ICBHI), the first scientific challenge was organized with the main goal of developing algorithms able to characterize respiratory sound recordings derived from clinical and non-clinical environments. The database was created by two research teams in Portugal and in Greece, and it includes 920 recordings acquired from 126 subjects. A total of 6898 respiration cycles were recorded. The cycles were annotated by respiratory experts as including crackles, wheezes, a combination of them, or no adventitious respiratory sounds. The recordings were collected using heterogeneous equipment and their duration ranged from 10 to 90 s. The chest locations from which the recordings were acquired was also provided. Noise levels in some respiration cycles were high, which simulated real life conditions and made the classification process more challenging.

Evaluation of a Decision Support System for Obstructive Sleep Apnea with Nonlinear Analysis of Respiratory Signals.

Introduction Obstructive Sleep Apnea (OSA) is a common sleep disorder requiring the time/money consuming polysomnography for diagnosis. Alternative methods for initial evaluation are sought. Our aim was the prediction of Apnea-Hypopnea Index (AHI) in patients potentially suffering from OSA based on nonlinear analysis of respiratory biosignals during sleep, a method that is related to the pathophysiology of the disorder. Materials and Methods Patients referred to a Sleep Unit (135) underwent full polysomnography. Three nonlinear indices (Largest Lyapunov Exponent, Detrended Fluctuation Analysis and Approximate Entropy) extracted from two biosignals (airflow from a nasal cannula, thoracic movement) and one linear derived from Oxygen saturation provided input to a data mining application with contemporary classification algorithms for the creation of predictive models for AHI. Results A linear regression model presented a correlation coefficient of 0.77 in predicting AHI. With a cutoff value of AHI = 8, the sensitivity and specificity were 93% and 71.4% in discrimination between patients and normal subjects. The decision tree for the discrimination between patients and normal had sensitivity and specificity of 91% and 60%, respectively. Certain obtained nonlinear values correlated significantly with commonly accepted physiological parameters of people suffering from OSA. Discussion We developed a predictive model for the presence/severity of OSA using a simple linear equation and additional decision trees with nonlinear features extracted from 3 respiratory recordings. The accuracy of the methodology is high and the findings provide insight to the underlying pathophysiology of the syndrome. Conclusions Reliable predictions of OSA are possible using linear and nonlinear indices from only 3 respiratory signals during sleep. The proposed models could lead to a better study of the pathophysiology of OSA and facilitate initial evaluation/follow up of suspected patients OSA utilizing a practical low cost methodology. Trial Registration ClinicalTrials.gov NCT01161381