..

健康・医療情報学ジャーナル

原稿を提出する arrow_forward arrow_forward ..

音量 4, 問題 2 (2013)

研究論文

Intelligent Information System of Diagnosis and Monitoring Application in the Emergency Medical Aid for Poisonings by Toxic Substances

Abdullayeva Gulchin Gulhuseyn,Irada Mirzazadeh Khatam,Naghizade Ulker Rauf*,Naghiyev Rauf Gasan

 According to statistical data, a considerable increase in the number of acute carbon monoxide poisonings has been

observed in Azerbaijan in the last few years. The difficulty of diagnosis is caused by the fact that the same symptoms
and even syndromes may be seen in case of poisonings by different toxic substances. For this reason, the problem
of necessity of performing differential diagnosis becomes urgent. The danger of poisonings is that they can be the
causes of serious pathologies with the passage of time. This article is proposing development of a system carrying out
differential diagnosis and monitoring, based on up-to-date methods of evidence medicine.
研究論文

Using Three Machine Learning Techniques for Predicting Breast Cancer Recurrence

Ahmad LG*,Eshlaghy AT,Poorebrahimi A,Ebrahimi M,Razavi AR

Objective: The number and size of medical databases are increasing rapidly but most of these data are not analyzed
for finding the valuable and hidden knowledge. Advanced data mining techniques can be used to discover hidden
patterns and relationships. Models developed from these techniques are useful for medical practitioners to make right
decisions. The present research studied the application of data mining techniques to develop predictive models for
breast cancer recurrence in patients who were followed-up for two years.
Method: The patients were registered in the Iranian Center for Breast Cancer (ICBC) program from 1997 to 2008.
The dataset contained 1189 records, 22 predictor variables, and one outcome variable. We implemented machine
learning techniques, i.e., Decision Tree (C4.5), Support Vector Machine (SVM), and Artificial Neural Network (ANN) to
develop the predictive models. The main goal of this paper is to compare the performance of these three well-known
algorithms on our data through sensitivity, specificity, and accuracy.
Results and Conclusion: Our analysis shows that accuracy of DT, ANN and SVM are 0.936, 0.947 and 0.957
respectively. The SVM classification model predicts breast cancer recurrence with least error rate and highest accuracy.
The predicted accuracy of the DT model is the lowest of all. The results are achieved using 10-fold cross-validation for
measuring the unbiased prediction accuracy of each model.
研究論文

Exploratory Factor Analysis of User’s Compliance Behaviour towards Health Information System’s Security

Norshima Humaidi*,Vimala Balakrishnan

 One of the main problems in information security was human error due to improper human behaviour. Therefore, this preliminary study was conducted with aims to identify possible factors that can affect user’s compliance behaviour towards information security in terms of two aspects: management support and security technology. Two theories were integrated for development of research framework: I) Theory of Planned Behaviour; II) Theory of Acceptance Model. The respondents of this study were the health professionals and IT officers whereby 42 questionnaires were obtained and verified. Exploratory Factor Analysis (EFA) results revealed that the six factors were obtained: Transactional_Leadership_ Style, Transformational_Leadership_Style, ISP_Training_Support, PU_Security, PU_Security-Countermeasure and PEOU_ISPs. The higher loadings signalled the correlations of the indicated items with the factors on which they were loaded with each of the correspondence factors achieving score of alpha value above 0.80. According to the descriptive analysis, most of the respondents are agreed with all the indicated factors. The preliminary study facilitates researcher in developing new model that integrates TPB and TAM that can be used to increase knowledge of user’s compliance behaviour towards health information system’s security.

研究論文

The Asymptotic Noise Distribution in Karhunen-Loeve Transform Eigenmodes

Yu Ding,Hui Xue*,Ning Jin,Yiu-Cho Chung,Xin Liu,Yongqin Zhang,Orlando P. Simonetti

 Karhunen-Loeve Transform (KLT) is widely used in signal processing. Yet the well-accepted result is that, the noise

is uniformly distributed in all eigenmodes is not accurate. We apply a result of the random matrix theory to understand
the asymptotic noise distribution in KLT eigenmodes. Noise variances in noise-only eigenmodes follow the Marcenko-
Pastur distribution, while noise variances in signal-dominated eigenmodes still follow the uniform distribution. Both the
mathematical expectation of noise level in each eigenmode and an analytical formula of KLT filter noise reduction effect
with a hard threshold were derived. Numerical simulations agree with our theoretical analysis. The noise variance of
an eigenmode may deviate more than 60% from the uniform distribution. These results can be modified slightly, and
generalized to non-IID (independently and identically-distributed) noise scenario. Magnetic resonance imaging experiments
show that the generalized result is applicable and accurate. These generic results can help us understand the
noise behavior in the KLT and related topics.
総説

A Hospital Healthcare Monitoring System Using Wireless Sensor Networks

Media Aminian,Hamid Reza Naji*

In a hospital health care monitoring system it is necessary to constantly monitor the patient’s physiological
parameters. For example a pregnant woman parameters such as blood pressure (BP) and heart rate of the woman and
heart rate and movements of fetal to control their health condition. This paper presents a monitoring system that has
the capability to monitor physiological parameters from multiple patient bodies. In the proposed system, a coordinator
node has attached on patient body to collect all the signals from the wireless sensors and sends them to the base
station. The attached sensors on patient’s body form a wireless body sensor network (WBSN) and they are able to
sense the heart rate, blood pressure and so on. This system can detect the abnormal conditions, issue an alarm to the
patient and send a SMS/E-mail to the physician. Also, the proposed system consists of several wireless relay nodes
which are responsible for relaying the data sent by the coordinator node and forward them to the base station. The
main advantage of this system in comparison to previous systems is to reduce the energy consumption to prolong
the network lifetime, speed up and extend the communication coverage to increase the freedom for enhance patient
quality of life. We have developed this system in multi-patient architecture for hospital healthcare and compared it with
the other existing networks based on multi-hop relay node in terms of coverage, energy consumption and speed.
研究論文

Electronic Health Record Acceptance: A Descriptive Study in Zahedan, Southeast Iran

Jahanpour Alipour,Leila Erfannia*,Afsaneh Karimi,Ali Aliabadi

Electronic Health Record (EHR) is a necessary tool for providing uninterrupted flow of information about the health
of population. The role of physicians cannot be overemphasized in the implementation of EHR; therefore, the purpose
of this study is to determine the physician’s attitude towards the acceptance of EHR project. In this regard, a descriptive
analytical study was carried out in 2011; however, sampling was done by convenience sampling method that includes
70 physicians of public hospitals affiliated to Zahedan University of Medical Sciences. Data collection was made through
a self-administered questionnaire and data processing was done using descriptive statistics and analysed by Oneway
ANOVA and One-sample t-test. The factors affecting acceptance of electronic health record by physicians were
determined as follows: management support 4.01 ± 0.60, physician involvement 4.06 ± 0.51, adequate training 4.04 ±
0.51, physician autonomy 3.20 ± 0.61, doctor-patient relationship 2.33 ± 0.82, perceived usefulness 3.91 ± 0.46 and
attitude about electronic health record acceptance 4.03 ± 0.46. Physician’s attitude towards Electronic Health Record
acceptance was determined in optimal level. In order to facilitate successful adoption of electronic health record,
involvement of physicians would be essentially required during the EHR designing, implementation and usage phase.
研究論文

Extraction of Genetic Mutations Associated with Cancer from Public Literature

Martin Schenck,Oliver Politz,Philip Groth*

Genomic mutations may result in severe diseases, e.g. cancer, a disease with a significant genetic component. The mutation state of cancer tissues is e.g. being determined experimentally in order to find the most likely response to a drug treatment. Results of such experiments are typically published in scientific literature. We have developed a workflow of several text-mining algorithms, in order to harvest this wealth of information relevant to developing novel therapeutic approaches in cancer. Our workflow has successfully scanned over 150,000 abstracts related to cancer and genetic mutations. New information on mutated genes in cancer could be extracted with a precision and recall of 86.8% and 30.3%, respectively. By applying the workflow, novel associations of mutations in specific cancer tissues could be extracted for 264 genes.

症例報告

Characterizing Clinical Text and Sublanguage: A Case Study of the VA Clinical Notes

Qing T. Zeng,Doug Redd,Guy Divita*,Samah Jarad,Cynthia Brandt,Jonathan R. Nebeker

Objective: To characterize text and sublanguage in medical records to better address challenges within Natural Language Processing (NLP) tasks such as information extraction, word sense disambiguation, information retrieval, and text summarization. The text and sublanguage analysis is needed to scale up the NLP development for large and diverse free-text clinical data sets. Design: This is a quantitative descriptive study which analyzes the text and sublanguage characteristics of a very large Veteran Affairs (VA) clinical note corpus (569 million notes) to guide the customization of natural language processing (NLP) of VA notes. Methods: We randomly sampled 100,000 notes from the top 100 most frequently appearing document types. We examined surface features and used those features to identify sublanguage groups using unsupervised clustering. Results: Using the text features we are able to characterize each of the 100 document types and identify 16 distinct sublanguage groups. The identified sublanguages reflect different clinical domains and types of encounters within the sample corpus. We also found much variance within each of the document types. Such characteristics will facilitate the tuning and crafting of NLP tools. Conclusion: Using a diverse and large sample of clinical text, we were able to show there are a relatively large number of sublanguages and variance both within and between document types. These findings will guide NLP development to create more customizable and generalizable solutions across medical domains and sublanguages.

研究論文

Divergence Weighted Independence Graphs for the Exploratory Analysis of Biological Expression Data

Yang Xiang,Marja Talikka,Vincenzo Belcastro,Peter Sperisen,Manuel C. Peitsch,Julia Hoeng*,Joe Whittaker*

Motivation: Understanding biological processes requires tools for the exploratory analysis of multivariate data generated from in vitro and in vivo experiments. Part of such analyses is to visualise the interrelationships between observed variables. Results: We build on recent work using partial correlation, graphical Gaussian models, and stability selection to add divergence weighted independence graphs (DWIGs) to this toolbox. We measure all quantities in information units (bits and millibits), to give a common quantification of the strength of associations between variables and of the information explained by a fitted graphical model. The marginal mutual information (MI) and conditional MI between variables directly account for components of the information explained. The conditional MIs are displayed as edge weights in the independence graph of the variables, making the complete graph informative as to the unique association between those variables. The summary table of the information decomposition ‘total = explained + residual’ provides a simple comparison of graphical models suggested by different search routines, including stabilised versions. We demonstrate the relevance of the conditional MI statistics to the graphical model of the data by analysing simulated data from the insulin pathway with a known ground truth. Here the method of thresholding these statistics to suggest a network performs at least as well as several other network searching algorithms. In searching a biological data set for novel insight, we contrast the DWIGs from the fitted maximum weight spanning tree and from the fitted model of a stabilised ARACNE network. DWIG is a powerful tool for the display of properties of the fitted model or of the empirical data directly.

研究論文

ICU Communication Representation: Clinician-Clinician and Clinician-Computer Interactions

Saif Khairat*,Yang Gong

Objective: The aim of this study was to analyze clinical communication factors and interruptions and to develop clinician-clinician and clinician-computer knowledge representation models. Methods: An ICU observational study was combined with medical error reported cases to address the above questions. Researchers shadowed the ICU team, for 55 hours during patient rounds, to capture 6 main communication factors. Simultaneously, a systematic literature search was conducted to identify and extract reported medical error cases caused by clinical communication problem. The search included patient safety data banks, literature databases, newspaper, and reported lawsuits. Results: Out of 242 reported communication errors, 100 cases resulted in active errors while only 13 cases resulted in13 near misses; most of those errors were reported in journal articles (n = 302). As to the observation data, the most frequent communicator during ICU patient rounds was the Attending Physicians. The ratio of interruptions caused by clinicians to technology-aided devices was 3:1 per patient visit. The mean frequency of an Attending Physician interacting with a computer was once per patient visit. Analyzing data from both sources, two communication models representing the clinical communication framework were developed. Conclusion: Clinical communication is essential for effective health care delivery and for improved care outcomes. To further understand clinical communication, primary and secondary data were collected and analyzed and as a result, clinician-clinician and clinician-computer interaction models were

インデックス付き

arrow_upward arrow_upward