Skip to main content

2017 | Buch

Health Information Science

6th International Conference, HIS 2017, Moscow, Russia, October 7-9, 2017, Proceedings

herausgegeben von: Siuly Siuly, Zhisheng Huang, Uwe Aickelin, Rui Zhou, Hua Wang, Dr. Yanchun Zhang, Dr. Stanislav Klimenko

Verlag: Springer International Publishing

Buchreihe : Lecture Notes in Computer Science

insite
SUCHEN

Über dieses Buch

This book constitutes the refereed proceedings of the 6th International Conference on Health Information Science, HIS 2017, held in Moscow, Russia, in October 2017.
The 11 full papers and 7 short papers presented were carefully reviewed and selected from 44 submissions. The papers feature multidisciplinary research results in health information science and systems that support health information management and health service delivery. They relate to all aspects of the conference scope, such as medical/health/biomedicine information resources such as patient medical records, devices and equipments, software and tools to capture, store, retrieve, process, analyze, and optimize the use of information in the health domain; data management, data mining, and knowledge discovery, management of publichealth, examination of standards, privacy and security issues; computer visualization and artificial intelligence for computer aided diagnosis; development of new architectures and applications for health information systems.

Inhaltsverzeichnis

Frontmatter
Software for Full-Color 3D Reconstruction of the Biological Tissues Internal Structure
Abstract
A software for processing sets of full-color images of biological tissue histological sections is developed. We used histological sections obtained by the method of high-precision layer-by-layer grinding of frozen biological tissues. The software allows restoring the image of the tissue for an arbitrary cross-section of the tissue sample. Thus, our method is designed to create a full-color 3D reconstruction of the biological tissue structure. The resolution of 3D reconstruction is determined by the quality of the initial histological sections. The newly developed technology available to us provides a resolution of up to 5–10 μm in three dimensions.
A. V. Khoperskov, M. E. Kovalev, A. S. Astakhov, V. V. Novochadov, A. A. Terpilovskiy, K. P. Tiras, D. A. Malanin
Epileptic Seizure Detection Using EEGs Based on Kernel Radius of Intrinsic Mode Functions
Abstract
The study of automated epileptic seizure detection using EEGs has attracted more and more researchers in these decades. How to extract appropriate features in EEGs, which can be applied to differentiate non-seizure EEG from seizure EEG, is considered to be crucial in the successful realization. In this work, we proposed a novel kernel-radius-based feature extraction method from the perspective of nonlinear dynamics analysis. The given EEG signal is first decomposed into different numbers of intrinsic mode functions (IMFs) adaptively by using empirical mode decomposition. Then the three-dimensional phase space representation (3D-PSR) is reconstructed for each IMF according to the time delay method. At last, the kernel radius of the corresponding 3D-PSR is defined, which aims to characterize the concentration degree of all the points in 3D-PSR. With the extracted feature KRF, we employ extreme learning machine and support vector machine as the classifiers to achieve the task of the automate epileptic seizure detection. Performances of the proposed method are finally verified on the Bonn EEG database.
Qiang Li, Meina Ye, Jiang-Ling Song, Rui Zhang
Some Directions of Medical Informatics in Russia
Abstract
Israel Gelfand, one of the leaders of 20th century mathematics, devoted many years to biology and medical informatics. The directions, created by him, are not well known, but the main ideas are relevant even now. The ideology of the medical knowledge formalization was applied in developing by Michael Shifrin in Medical Information System of the Burdenko’s Neurosurgery Institute. Under directorship of Andrei Vorobiev (Gelfand’s disciple-physician), one of the largest healthcare informatizations of the 20th century was done: unified system introduced in most blood banks of the Russian Federation. Accompanying, obtaining, storing and distributing blood products “from the donor’s vein to the patient’s vein”, the National Standard for Labeling Blood Products and the Law on Donation (with the task of forming the Unified Transfusion Information Space) were done. The same team, led by mathematician Boris Zingerman, developed the Medical Information System of the National Research Hematology Center, which was conceived as a unified system for managing all functions of the institution (out-patients and in-patients clinics, blood bank, pharmacy, research, accounting, personnel department and administration). The system focused on the full electronic document circulation with a single identification of participants and objects (including information objects). The National Standard “Electronic Case History” was created with the concepts of the Electronic Medical Record (EMR) first formulated as well as a number of other important definitions. The ideology of “Disease Image”, based on the graphic presentation of data and the presentation of all medical events (records) from the EMR on a single time axis became the realization of Gelfand’s idea of using physician experience for generation of intellectual algorithms in medical informatics.
Nikita Shklovskiy-Kordi, Michael Shifrin, Boris Zingerman, Andrei Vorobiev
A Computer Simulation Approach to Reduce Appointment Lead-Time in Outpatient Perinatology Departments: A Case Study in a Maternal-Child Hospital
Abstract
A significant problem in outpatient perinatology departments is the long waiting time for pregnant women to receive an appointment. In this respect, appointment delays are related to patient dissatisfaction, no shows and sudden infant death syndrome. This paper aims to model and evaluate improvement proposals to outpatient care delivery by applying computer simulation approaches. First, suitable data is collected and analyzed. Then, a discrete-event simulation (DES) model is created and validated to determine whether it is statistically equivalent to the current system. Afterward, the average appointment lead-time is calculated and studied. Finally, improvement proposals are designed and pretested by simulation modelling and statistical comparison tests. A case study of an outpatient perinatology department from a maternal-child is shown to validate the effectiveness of DES to fully understand and manage healthcare systems. The results evidenced that changes to care delivery can be effectively assessed and appointment lead-times may be significantly reduced based on the proposed framework within this paper.
Miguel Ortíz-Barrios, Genett Jimenez-Delgado, Jeferson De Avila-Villalobos
Engaging Patients, Empowering Doctors in Digitalization of Healthcare
Abstract
Patients can monitor their own physiological parameters and medical events using mobile applications. The problem is how to involve patients in regular use. The key problem seems to convince the patient that doctor will get acquainted with the data sent in service of Patient Health Records (PHR) on time. From other hand we have to organize for doctors the comfortable access to such data and do not overload them. The dynamics of clinical parameters of diabetes, hypertension, anticoagulation – vital for successful treatment, so these patients and their physicians seems to be perspective for innovation methods. Pulse, blood pressure, weight, glucose level and confirmation of a dose of medication taken, organized to be immediately delivered in the PHR from mobile application and household measuring devices used by the patient. The doctor choosing variants of presentation of medical monitoring information transmitted from the patient. In addition, specialized Medical Messenger (MM) allows the patient to ask questions to the doctor at the moment when they arise without disturbing the life of the doctor via his personal mobile phone or e-mail. We expect this exchange of messages will serve as a base of innovative interactive case history, managed not only by physician, but by patient as well. Personal monitoring also used for evaluating the “adherence to treatment”: system of reminders about medication and measurements, the results of which become available to doctor according intellectual algorithms he chooses.
Nikita Shklovsky-Kordi, Boris Zingerman, Michael Shifrin, Rostislav Borodin, Tatiana Shestakova, Andrei Vorobiev
Developing a Tunable Q-Factor Wavelet Transform Based Algorithm for Epileptic EEG Feature Extraction
Abstract
Brain signals refer to electroencephalogram (EEG) data that contain the most important information in the human brain, which are non-stationary and nonlinear in nature. EEG signals are a mixture of sustained oscillation and non-oscillatory transients that are difficult to deal with by linear methods. This paper proposes a new technique based on a tunable Q-factor wavelet transform (TQWT) and statistical method (SM), denoted as TQWT-SM, to analyze epileptic EEG recordings. Firstly, EEG signals are decomposed into different sub—bands by the TWQT method, which is parameterized by its Q-factor and redundancy. This approach depends on the resonance of signals, instead of frequency or scales as the Fourier and wavelet transforms do. Secondly, each type of the sub-band vector is divided into n windows, and 10 statistical features from each window are extracted. Finally all the obtained statistical features are forwarded to a k nearest neighbor (k-NN) classifier to evaluate the performance of the proposed TQWT-SM method. The TQWT-SM features extraction method achieves good experimental results for the seven different epileptic EEG binary-categories by the k-NN classifier, in terms of accuracy (Acc), Matthew’s correlation coefficient (MCC), and F score (F1). The outcomes of the proposed technique can assist the experts to detect epileptic seizures.
Hadi Ratham Al Ghayab, Yan Li, Siuly, Shahab Abdulla, Paul Wen
Granular Computing Combined with Support Vector Machines for Diagnosing Erythemato-Squamous Diseases
Abstract
A computational model with a new hybrid feature selection approach is developed in this paper to determine the type of erythemato-squamous disease. The new feature selection method combines the strength of granular computing (GrC) and support vector machines (SVM) together with the advantages of filters and wrappers to select the optimal feature subset to build a sound classifier. We treat the erythemato-squamous disease dataset as a decision information system, where the sample features are considered as condition attributes and the class label the decision attribute. We calculate the granular of each feature and decision attribute, then evaluate the significance of each feature to classification by the difference between its granularity and that of decision attribute, after that we rank features in descending order by their significance. Generalized sequential forward search (GSFS) strategy together with SVM is adopted to select the necessary features to condense decision information system without compromising its classification capacity. 5-fold cross validation experiments have been conducted on the erythemato-squamous disease dataset taken from UCI (University of California Irvine) machine learning repository. Experimental results demonstrate that our diagnostic model has got condensed decision information system for erythemato-squamous disease with less features than the original ones while achieving a comparable accuracy in the literature.
Yongchao Wang, Juanying Xie
A Semantically-Enabled System for Inflammatory Bowel Diseases
Abstract
The incidence rate of Inflammatory Bowel Disease (IBD) in China is increasing in recent years and the cause of this disease is still not clear. In order to promote the development of this study, in this paper, we propose a Semantically-enabled System for Inflammatory Bowel Diseases (SeSIBD). It provides functions of semantic retrieval over patient data, statistical analysis and literature retrieval based on patient characteristics. SeSIBID is built on the top of LarKC, a semantic platform for scalable semantic data processing and reasoning. Although the current implementation of SeSIBID is a prototype system, it will provide an infrastructure for clinical decision making support for deep excavation and knowledge discovery on various of medical resources of IBD in the future.
Lei Xu, Zhisheng Huang, Hao Fan, Siwei Yu
Early Classification of Multivariate Time Series Based on Piecewise Aggregate Approximation
Abstract
Early Classification on Time Series is becoming more significant in the field of Time Series Data Ming. Especially in some time-sensitive filed, it is obviously preferred to make earlier classification, such as Medical science, Health informatics et al. However, the research tasks are mainly focused on UTS, those of MTS are less. MTS is faced with variable-based and time-based dimensionality. It is significant to find appropriate dimensionality reduction in the practical application of early classification on multivariate time series. We propose a novel method MTEECP based on center sequence and Piecewise Aggregate Approximation which achieve early classification in low-dimension space. Experimental results on 6 real datasets intuitively show our proposed method can reach favorable early classification on MTS.
ChaoHong Ma, XiaoQing Weng, ZhongNan Shan
A Data-Driven Approach for Discovering the Recent Research Status of Diabetes in China
Abstract
This paper aims at discovering the recent research status of diabetes in China through a data-driven bibliometrics and knowledge mapping analysis method on diabetes-related literature. With the basis of 24,561 publication documents from CNKI during 2007–2016, the quantitative analysis are conducted in three aspects: (1) descriptive statistical method for acquiring literature distribution characteristics; (2) hierarchical clustering, k-means clustering analysis, and multidimensional scaling analysis based on a keyword co-occurrence matrix for discovering research hotspots; and (3) network analysis for revealing cooperation relationships among authors and affiliations. The result shows some findings about the recent diabetes research in China. It also demonstrates the close cooperation of diabetes research among productive authors and affiliations through network generation and visualization.
Xieling Chen, Heng Weng, Tianyong Hao
Generation of Semantic Patient Data for Depression
Abstract
In the medicine practice, due to the privacy and safety of electronic medical record (EMR), the sharing, research and application of EMR have been hindered to a certain extent. Thus, it becomes increasingly important to study semantic electronic medical data integration, so as to meet the needs of doctors and researchers and help them quickly access high-quality information. This paper focuses on the realization of semantic EMRs. It shows how to uses APDG (Advanced Patient Data Generator) to create a set of virtual patient data for depression. Furthermore, it explains how to develop clinical and semantic description rules to construct semantic EMRs for depression and discusses how those generated virtual patient data can be used in the system of Smart Ward for the test and demonstration, without violating the legal issues (e.g., privacy and security) of patient data.
Yanan Du, Shaofu Lin, Zhisheng Huang
Analyses of the Dual Immune Roles Cytokines Play in Ischemic Stroke
Abstract
Stroke is one of the leading causes of morbidity and permanent disability worldwide. There is a need for an efficacious alternative therapy administered beyond the limitation of time window based on the biological characteristics of stroke, currently. The immunomodulatory therapy could extend the time window while not increase the risk of hemorrhage which made it become candidate treatments. In this paper, we integrated several gene expression profiles generated from the peripheral blood of ischemic stroke patients and health people. Differential expressed cytokines were first selected as candidate cytokines. Enrichment analyses were then performed to filter the candidate cytokines as biomarkers (E-CKs) by checking the relationships between them and the stroke related functional terms. More cytokines were found as biomarkers in the sub-acute stage of ischemic stroke compared with acute and chronic stages which could be explained by the great changes in microenvironment in this necrosis stage. Analyses based on microRNomics level showed that more E-CKs one miRNA regulated, the more important role it played in stroke related processes. Similarly, analyses on proteomics level showed that E-CKs with top degrees in the protein-protein interaction network were proved to be closely related to stroke. Most E-CKs participate in both the stroke processing and rehabilitation, thus, the dual immune characters made them become valuable potential targets of immunomodulatory therapies.
Yingying Wang, Jianfeng Liu, Haibo Yu, Yunpeng Cai
Multidimensional Analysis Framework on Massive Data of Observations of Daily Living
Abstract
Observations of daily living (ODLs) are cues that people attend to in the course of their everyday life, that inform them about their health. In order to better understand the ODLs, we propose a set of innovative multi-dimensional analysis concepts and methods. Firstly, the ODLs are organized as directed graphs according the “observation-property” relationships and the chronological order of observations, which represents all the information in a flexible way; Secondly, a novel concept, the structure dimension, is proposed to integrate into the traditional multidimensional analysis framework. From the structure dimension that consists of three granularities, vertices, edges and subgraphs, one can get a clearer view of the ODLs; Finally, the hierarchy of ODLs Cube is introduced, and the semantics of OLAP operations, Roll-up, Drill-down and Slice/dice, are redefined to accommodate the structure dimension. The proposed structure dimension and ODLs cube are effective for multidimensional analysis of ODLs.
Jianhua Lu, Baili Zhang, Xueyan Wang, Ningyun Lu
Numerical Modeling of the Internal Temperature in the Mammary Gland
Abstract
The microwave thermometry method for the diagnosis of breast cancer is based on an analysis of the internal temperature distribution. This paper is devoted to the construction of a mathematical model for increasing the accuracy of measuring the internal temperature of mammary glands, which are regarded as a complex combination of several components, such as fat tissue, muscle tissue, milk lobules, skin, blood flows, tumor tissue. Each of these biocomponents is determined by its own set of physical parameters. Our numerical model is designed to calculate the spatial distributions of the electric microwave field and the temperature inside the biological tissue. We compare the numerical simulations results to the real medical measurements of the internal temperature.
M. V. Polyakov, A. V. Khoperskov, T. V. Zamechnic
Research on Multidimensional Modelling for Personal Health Record
Abstract
Personal Health Records (PHRs) have characteristics of continuous high speed growth and rich value, which are the prerequisite and foundation for implementing services of intelligent health care, personalized medicine, remote treatment, disease prevention and prediction, and the strong support for the hospital, health care institutions, insurance companies and other organizations to maintain personal health. PHR contents have multidimensional features such as time, region, population and role orientation, which have different semantic meaning and application value. As the fundamental element of semantic web technology architecture, ontology provides an expressive framework for reusing, sharing, representing and reasoning knowledge, and has been widely applied in modelling biological, medicine and health care fields. This paper analyzes the multidimensional features of PHRs, and investigates an approach for modelling PHRs based on current existing health record standards by using ontology modelling methods and theoretical frameworks.
Hao Fan, Jianping He, Gang Liu
Constructing Knowledge Graphs of Depression
Abstract
Knowledge Graphs have been shown to be useful tools for integrating multiple medical knowledge sources, and to support such tasks as medical decision making, literature retrieval, determining healthcare quality indicators, co-morbodity analysis and many others. A large number of medical knowledge sources have by now been converted to knowledge graphs, covering everything from drugs to trials and from vocabularies to gene-disease associations. Such knowledge graphs have typically been generic, covering very large areas of medicine. (e.g. all of internal medicine, or arbitrary drugs, arbitrary trials, etc.). This has had the effect that such knowledge graphs become prohibitively large, hampering both efficiency for machines and usability for people. In this paper we show how we use multiple large knowledge sources to construct a much smaller knowledge graph that is focussed on single disease (in our case major depression disorder). Such a disease-centric knowledge-graph makes it more convenient for doctors (in our case psychiatric doctors) to explore the relationship among various knowledge resources and to answer realistic clinical queries (This paper is an extended version of [1].).
Zhisheng Huang, Jie Yang, Frank van Harmelen, Qing Hu
Constructing Three-Dimensional Models for Surgical Training Simulators
Abstract
New technologies introduced into medicine necessitate training of medical personnel to operate new equipment and techniques. For this purpose, training simulators and educational materials should be provided to the medical staff involved. This work concerns creating 3D model of surgical field for simulators to promote minimally invasive surgery. The paper reports the modes of constructing a photorealistic model of surgical field from endoscopic video streams, SFM, SLAM methods, as well as the problem of surface reconstruction from a point cloud and texture mapping on the constructed model.
Marina Gavrilova, Stanislav Klimenko, Vladimir Pestrikov, Arkadiy Chernetskiy
A Framework for Automated Knowledge Graph Construction Towards Traditional Chinese Medicine
Abstract
Medical knowledge graph can potentially help knowledge discovery from clinical data, assisting clinical decision making and personalized treatment recommendation. This paper proposes a framework for automated medical knowledge graph construction based on semantic analysis. The framework consists of a number of modules including a medical ontology constructor, a knowledge element generator, a structured knowledge dataset generator, and a graph model constructor. We also present the implementation and application of the constructed knowledge graph with the framework for personalized treatment recommendation. Our experiment dataset contains 886 patient records with hypertension. The result shows that the application of the constructed knowledge graph achieves dramatic accuracy improvements, demonstrating the effectiveness of the framework in automated medical knowledge graph construction and application.
Heng Weng, Ziqing Liu, Shixing Yan, Meiyu Fan, Aihua Ou, Dacan Chen, Tianyong Hao
Backmatter
Metadaten
Titel
Health Information Science
herausgegeben von
Siuly Siuly
Zhisheng Huang
Uwe Aickelin
Rui Zhou
Hua Wang
Dr. Yanchun Zhang
Dr. Stanislav Klimenko
Copyright-Jahr
2017
Electronic ISBN
978-3-319-69182-4
Print ISBN
978-3-319-69181-7
DOI
https://doi.org/10.1007/978-3-319-69182-4