Showing papers in "Journal of Medical Systems in 2005"

Artificial Neural Network Based Epileptic Detection Using Time-Domain and Frequency-Domain Features

Abstract: Electroencephalogram (EEG) signal plays an important role in the diagnosis of epilepsy. The long-term EEG recordings of an epileptic patient obtained from the ambulatory recording systems contain a large volume of EEG data. Detection of the epileptic activity requires a time consuming analysis of the entire length of the EEG data by an expert. The traditional methods of analysis being tedious, many automated diagnostic systems for epilepsy have emerged in recent years. This paper discusses an automated diagnostic method for epileptic detection using a special type of recurrent neural network known as Elman network. The experiments are carried out by using time-domain as well as frequency-domain features of the EEG signal. Experimental results show that Elman network yields epileptic detection accuracy rates as high as 99.6% with a single input feature which is better than the results obtained by using other types of neural networks with two and more input features.

Classification of EMG Signals Using PCA and FFT

Abstract: In this study, the fast Fourier transform (FFT) analysis was applied to EMG signals recorded from ulnar nerves of 59 patients to interpret data. The data of the patients were diagnosed by the neurologists as 19 patients were normal, 20 patients had neuropathy and 20 patients had myopathy. The amount of FFT coefficients had been reduced by using principal components analysis (PCA). This would facilitate calculation and storage of EMG data. PCA coefficients were applied to multilayer perceptron (MLP) and support vector machine (SVM) and both classified systems of performance values were computed. Consequently, the results show that SVM has high anticipation level in the diagnosis of neuromuscular disorders. It is proved that its test performance is high compared with MLP.

Combining Neural Network and Genetic Algorithm for Prediction of Lung Sounds

Abstract: Recognition of lung sounds is an important goal in pulmonary medicine. In this work, we present a study for neural networks--genetic algorithm approach intended to aid in lung sound classification. Lung sound was captured from the chest wall of The subjects with different pulmonary diseases and also from the healthy subjects. Sound intervals with duration of 15--20 s were sampled from subjects. From each interval, full breath cycles were selected. Of each selected breath cycle, a 256-point Fourier Power Spectrum Density (PSD) was calculated. Total of 129 data values calculated by the spectral analysis are selected by genetic algorithm and applied to neural network. Multilayer perceptron (MLP) neural network employing backpropagation training algorithm was used to predict the presence or absence of adventitious sounds (wheeze and crackle). We used genetic algorithms to search for optimal structure and training parameters of neural network for a better predicting of lung sounds. This application resulted in designing of optimum network structure and, hence reducing the processing load and time.

An Evaluation Framework for a Rural Home-Based Telerehabilitation Network

Abstract: This study was a needs assessment to inform the design and evaluation of a home-based telerehabilitation network for rural elderly patients. We conducted a literature review of telerehabilitation studies and a needs-assessment by interviewing 43 professionals, including homecare nursing staff, members of volunteer organizations and service agencies, social workers, discharge planners, researchers, and rehabilitation therapists. The survey addressed perceived needs, advantages, and disadvantages with the use of telemedicine technologies for rehabilitation services. All respondents agreed that there are unmet needs among elderly people who are discharged from hospital settings, and identified several problems including: medication noncompliance, isolation, limited access to specialists and community-based services. Our findings defined a framework for the development of a client-oriented rural telehealth network that will be used to guide patients discharged to homecare following stroke, through a complex array of health, mental health, and social services, spanning all levels of care.

Wavelet Transformation Based Watermarking Technique for Human Electrocardiogram (ECG)

Abstract: Nowadays, watermarking has become a technology of choice for a broad range of multimedia copyright protection applications. Watermarks have also been used to embed prespecified data in biomedical signals. Thus, the watermarked biomedical signals being transmitted through communication are resistant to some attacks. This paper investigates discrete wavelet transform based watermarking technique for signal integrity verification in an Electrocardiogram (ECG) coming from four ECG classes for monitoring application of cardiovascular diseases. The proposed technique is evaluated under different noisy conditions for different wavelet functions. Daubechies (db2) wavelet function based technique performs better than those of Biorthogonal (bior5.5) wavelet function. For the beat-to-beat applications, all performance results belonging to four ECG classes are highly moderate.

A Review on Diffusion of Personal Digital Assistants in Healthcare

Abstract: This review draws from a comprehensive literature search and reviews the adoption, usage and impact of personal digital assistants (PDAs) in healthcare. Adoption relates to the rationale for, barriers to and scope of adopting PDAs. Usage relates to the types of health professionals using PDAs, and their functionalities and features. Impact relates to perceived outcomes, actual outcomes and improved productivity from PDA use. The review shows that although PDA adoption and usage in healthcare are growing, there are very few studies that provide evidence-based results about impacts of such adoption and use. However, the preliminary impact studies that have been done have shown promise with regards to PDA use improving patient outcomes. We feel this review will increase awareness and encourage research about PDAs and their use in healthcare.

Use of Support Vector Machines and Neural Network in Diagnosis of Neuromuscular Disorders

Abstract: In this study the performance of support vector machine (SVM)and back-propagation neural network were applied to analyze the classification of the electromyogram (EMG) signals obtained from normal, neuropathy and myopathy subjects. By using autoregressive (AR) modeling, AR coefficients were obtained from EMG signals. Moreover, the support vector machine and artificial neural network (ANN) were used as base classifiers. The AR coefficients were benefited as inputs for SVM and ANN. Besides, these coefficients were tested both in ANN and SVM. The results show that SVM has high anticipation level in the diagnosis of neuromuscular disorders. It is proved that its test performance is high compared with ANN.

Patient Safety-Related Information Technology Utilization in Urban and Rural Hospitals

Abstract: Ongoing research has linked certain information technology applications to reduction of medical errors and improved patient outcomes. The purpose of this study was to assess both the use of patient safety-related information technologies (PSIT) in urban and rural hospitals, as well as the organizational factors which may be linked to overall PSIT adoption. Florida's 199 acute care hospitals (170 urban; 29 rural) were surveyed regarding their utilization of PSIT. Of the 10 technologies studied, rural hospitals averaged 30% utilization compared to 48% for urban hospitals. Individual PSIT applications such as pharmacy-based systems, clinical decision support systems, and outcomes and quality management tools were all more likely to be present in urban hospitals. Hospital bed size (less than 100 beds), tax status (not-for-profit vs. for-profit), and system-affiliation appeared to be related to overall PSIT utilization. These findings are valuable for those interested in the current status of hospital PSIT and set the stage for further studies relating these applications to clinical outcomes in urban and rural hospitals.

A Mixture of Experts Network Structure for Breast Cancer Diagnosis

Abstract: Mixture of experts (ME) is a modular neural network architecture for supervised learning. This paper illustrates the use of ME network structure to guide diagnosing of breast cancer. Expectation-maximization (EM) algorithm was used for training the ME so that the learning process is decoupled in a manner that fits well with the modular structure. Diagnosis tasks are among the most interesting activities in which to implement intelligent systems. Specifically, diagnosis is an attempt to accurately forecast the outcome of a specific situation, using as input information obtained from a concrete set of variables that potentially describe the situation. The ME network structure was implemented for breast cancer diagnosis using the attributes of each record in the Wisconsin breast cancer database. To improve diagnostic accuracy, the outputs of expert networks were combined by a gating network simultaneously trained in order to stochastically select the expert that is performing the best at solving the problem. For the Wisconsin breast cancer diagnosis problem, the obtained total classification accuracy by the ME network structure was 98.85%. The ME network structure achieved accuracy rates which were higher than that of the stand-alone neural network models.

Does Use of CAM for Specific Health Problems Increase With Reduced Access to Care

Abstract: The objective of this paper was to determine predictors of complementary and alternative medicine (CAM) use among individuals with specific health problems. Data were derived from the 1998 Medical Expenditure Panel Survey (MEPS). After adjustment for potential confounders, individuals with perceived barriers to obatining care were more likely to use any CAM treatment (OR 2.16), herbal therapy (OR 2.70) and spiritual care (OR 3.99) for a specific health problem. Individuals dissatisfied with their family's access to care were more likely to use acupuncture (OR 3.43). Dissatisfaction with quality of care was associated with increased use of spiritual therapy (OR 4.74). Perceptions of inadequate access to health care may contribute to utilization of CAM therapies; such therapies in this instance appear to be used as an alternative to mainstream medicine.

The State of Medical Informatics in India: A Roadmap for Optimal Organization

Abstract: In India, the healthcare delivery systems are based on manual record keeping despite a good telecommunication infrastructure. Unfortunately, Indian policy makers are yet to realize the importance of medical informatics (including tele-health, which comprises e-Health and Telemedicine) in delivering healthcare. In the medical curriculum also, nowhere is this treated as a subject or even as a tool for learning. The final aim of most of the medical and paramedical students should be to become good users, and if possible, also experts for advancing medical knowledge base through medical informatics. In view of the fast changing world of medical informatics, it is essential to formulate a flexible syllabus rather than a rigid one for incorporating into the regular curriculum of medical and paramedical education. Only after that one may expect all members of the healthcare delivery systems to adopt and apply medical informatics optimally as a routine tool for their services.

Application of Classical and Model-Based Spectral Methods to Describe the State of Alertness in EEG

Abstract: Electrophysiological recordings are considered a reliable method of assessing a person's alertness. Sleep medicine is asked to offer objective methods to measure daytime alertness, tiredness and sleepiness. In this study, EEG signals recorded from 30 subjects were processed by PC-computer using classical and model-based methods. The classical method (fast Fourier transform) and three model-based methods (Burg autoregresse, moving average, least-squares modified Yule---Walker autoregressive moving average methods) were selected for processing EEG signals to discriminate the alertness level of subject. Power spectra of EEG signals were obtained by using these spectrum analysis techniques. These EEG spectra were then used to compare the applied methods in terms of their frequency resolution and the effects in determination of vigilance state of subject. It is found that, FFT and MA methods have low spectral resolution, these two methods are not appropriate for the analysis of the a wake---sleep correlation. Burg AR and least-squares modified Yule---Walker ARMA methods' performance characteristics have been found extremely valuable for the determination of vigilance state of a healthy subject, because of their clear spectra.

Prediction of Minor Head Injured Patients Using Logistic Regression and MLP Neural Network

Abstract: In this study it is aimed to assess the posttraumatic cerebral hemodynamia in minor head injured patients. Eighty patients with minor head injury (Group 1) evaluated in the early 8 h of posttraumatic period between July 2003 and February 2004. The control group (Group 2) has composed of 32 healthy people. Bilateral blood flow velocities of middle cerebral arteries (MCA) had measured using transtemporal technique while internal carotid arteries were evaluated by submandibular examination. Two different mathematical models such as the traditional statistical method on the basis of logistic regression and a multi-layer perceptron (MLP) neural network are used to classify the age, sex, velocitiy parameters of MCA, mean velocity of extracranial ICAs and VMCA/ VICA ratios. The neural network was trained, cross-validated and tested with subject's transcranial Doppler signals. As a result of these classifications, we found the success rate of logistic regression, the success rate of MLP neural network is 88.2 and 89.1%, respectively. The classification results show that MLP neural network is offering the best results in the case of diagnosis.

The Measurement of Nursing Home Quality: Multilevel Confirmatory Factor Analysis of Panel Data

Abstract: This study examined the validity of a measurement model of nursing home quality by using multilevel confirmatory factor analysis. Based on Mullan and Harrington's (2001) facility-level quality measurement model, a two-level analysis (facility and state) of the measurement model were performed. Two research questions were asked: (1) Can the measurement model developed at the facility-level be applied to state-level nursing home quality measurement? (2) Is the measurement model of nursing home quality stable over time? Panel data of 1997 and 2001, from the national OSCAR database, were used to test the assumptions. The results show that the state-level measurement model fits the data better than the facility-level model does. When the indicator "assessment" was removed from the state-level measurement model, a better-fitted measurement model was found. The two-level measurement model is relatively stable over time, demonstrating the construct validity of this measurement model.

The Impact of Structured Laboratory Routines in Computerized Medical Records in a Primary Care Service Setting

Abstract: Inappropriate laboratory ordering is a problem affecting medical systems worldwide. An intervention was called for as a result of increasing laboratory costs. Thus, we aimed to assess the impact of introducing computerized laboratory routines to a computerized primary care setting. The study included 380 primary care physician practices of Clalit Health Service (HMO) southern district (CHS-SD) in Israel, caring for 470,000 members. Consensus laboratory routines order sets were electronically introduced into all physicians' computerized medical record (CMR) software, after consensus and internal marketing process. The primary findings were that a previously observed annual increase in laboratory test utilization was stopped, a 2% reduction in total number of tests and a 4% reduction in the total number of tests per age adjusted person was observed. In conclusion the wide use of CMRs and communication technology combined with an appropriate organizational process can be used to increase appropriate utilization of laboratory tests.

Canonical Correlation Analysis of Risk Factors and Clinical Outcomes in Cardiac Surgery

Abstract: Assessment of the association between risk factors and outcomes in cardiac surgery is a complex problem. The aim of this study was to explore the relationship between possible risk factors and several clinical outcomes in cardiac surgery by using canonical correlation analysis (CCA). This retrospective study of 2605 consecutive adult patients who underwent cardiac surgery, evaluated 74 potential risk factors and up to 12 outcomes by canonical correlation analysis. For three serious outcomes, sternal wound complications/mediastinitis, cerebral complications, and perioperative myocardial infarctions, CCA was preceded by univariate analyses and backward stepwise multivariate logistic regression analyses. The CCA suggests that the major risk factors for complications in these models are intraoperative and postoperative risk factors. The power of risk prediction models developed with multivariate regression analysis can be enhanced by application of canonical correlation analysis, thereby offering new ways of analyzing and interpreting sets of potential risk factors in relation to sets of clinical outcomes.

Dolphin Project--Cooperative Regional Clinical System Centered on Clinical Information Center

Abstract: In 2001, a system was created to improve patient service, improve the quality of medical care, and achieve efficient medical care. A Data Center was established to accumulate and manage clinical information in the regions and share clinical information safely and appropriately. The system has already been in operation for 3 years. Even though a patient may have been examined at multiple hospitals, his medical record information will be integrated at the Center. This ensures medical care continuity and enables the patient to view his own medical records at home. Its usefulness in obtaining informed consent has been demonstrated as well. XML instances established in the MML standards (MML (Medical Markup Language): http://www.medxml.net/E_mml30/mmlv3_E_index.htm Accessed July 2004; Jpn. J. Med. Informatics (JJMI) 17(3):203--207, 1997; J. Med. Syst. 24(3):195--211, 2000; J. Med. Syst. 27(4):357--366, 2003; J. Med. Syst. 28(6):523--533, 2004) are used for Electronic Medical Record System data exchange between the Data Center and each medical institution. The openness provided by XML makes it possible to connect diverse electronic medical records to the Center. As of the year 2004, over 10 types of electronic medical records have an MML interface, enabling connection to the Center.

Electronic Clinical Path System Based on Semistructured Data Model Using Personal Digital Assistant for Onsite Access

Abstract: Clinical Paths (Paths) have been introduced by different hospitals for patient care management. An Electronic Clinical Path (ECP) with onsite access provision seems to improve the efficiency of medical staffs because they can share vast medical information about patients at a time and also can reuse accumulated data easily, which is impossible with paper-based Path. Data model is the basis for implementing ECP. However, there is no established model for ECP. The purpose of this study is to introduce a model for ECP and implement an ECP with onsite access system. We introduced a Semistructured Data Model (SSDM) for ECP, and implemented a Web application system based on this model using Personal Digital Assistant (PDA) as inputting device. Our system functioned as expected with wireless LAN, and users handled the data on bedside using PDA. By introducing SSDM, we showed the correspondence between schema of Paths and implementation of ECP.

Web Based Health Education, E-learning, for Weight Management

Abstract: Obesity is a major health problem across the United States and becoming a progressive world wide problem. An overweight person could access the weight management program and develop a personalized weight reduction plan. The customer enters specific data to personalize the program and in the future an artificial intelligence program can evaluate customer behavior and adjust accordingly. This is an on-line program with class room support, offered as back up when desired by the patient.

Anteroposterior Difference in EEG Sleep Depth Measure is Reduced in Apnea Patients

Abstract: In the present work, mean frequencies of FFT amplitude spectra from six EEG derivations were used to provide a frontopolar, a central and an occipital sleep depth measure. Parameters quantifying the anteroposterior differences in these three sleep depth measures during the night were also developed. The method was applied to analysis of 30 all-night recordings from 15 healthy control subjects and 15 apnea patients. Control subjects showed larger differences in sleep depth between frontopolar and central positions than the apnea patients. The relatively reduced frontal sleep depth in apnea patients might reflect the disruption of the dynamic sleep process caused by apneas.

Peer-to-Peer Computing in Health-Promoting Voluntary Organizations: A System Design Analysis

Abstract: A large part of the health promotion in today's society is performed as peer-to-peer empowerment in voluntary organisations such as sports clubs, charities, and trade unions. In order to prevent work-related illness and long-term sickness absence, the aim of this study is to explore computer network services for empowerment of employees by peer-to-peer communication. The `technique trade-off' method was used for the analysis of the system design. A Critical Incident Technique questionnaire was distributed to a representative sample of trade union shop stewards (n = 386), and focus-group seminars were arranged where a preliminary set of requirements was discussed. Seven basic requirements were identified and matched to a set of 12 design issues for computer network services, allocating a subset of design issues to each requirement. The conclusion is that the systems design displays an inexpensive and potentially feasible method for peer-to-peer computing in voluntary health-promoting organisations.

Factors That Influence Efficiency in Performing ENT Cases: A Qualitative and Quantitative Analysis

Abstract: The aim of this study was to assess procedures with high turnover time to procedure time ratios, estimate the effect of productivity changes on case efficiency, and determine causative factors. We specifically focused on suspension direct microlaryngoscopy (SML) (CPT 31526) cases because significantly greater productivity was possible for these cases in terms of ratios. After determining process times, we developed economic scenarios that employed time-reductions, and then assessed involved staff opinions using brainstorming and cause--effect methods. Improving all process times by 30% achieved up to a 50% improvement in revenue and the return on investment in additional scope equipment occurred within 2 months.

Examination of Electric Field Effects on Tissues by Using Back Propagation Neural Network

Abstract: The aim of this study is to determine lipid peroxidation and antioxidant enzyme levels in spleen and testis tissues of guinea pigs which were exposed to different intensities and periods of DC (direct current) and AC (alternating current) electric fields. The experimental results are applied to neural networks as learning data and the training of the feed forward neural network is realized. At the end of this training; without applying electric field to the tissues, the determination of the effects of the electric field on tissues by using computer is predicted by the neural network. After the experiments, the prediction of the neural network is averagely 99%.

A New Microcontroller-Based Human Brain Hypothermia System

Abstract: Many studies show that artificial hypothermia of brain in conditions of anesthesia with the rectal temperature lowered down to 33?C produces pronounced prophylactic effect protecting the brain from anoxia. Out of the methods employed now in clinical practice for reducing the oxygen consumption by the cerebral tissue, the most efficacious is craniocerebral hypothermia (CCH). It is finding even more extensive application in cardiovascular surgery, neurosurgery, neurorenimatology and many other fields of medical practice. In this study, a microcontroller-based designed human brain hypothermia system (HBHS) is designed and constructed. The system is intended for cooling and heating the brain. HBHS consists of a thermoelectric hypothermic helmet, a control and a power unit. Helmet temperature is controlled by 8-bit PIC16F877 microcontroller which is programmed using MPLAB editor. Temperature is converted to 10-bit digital and is controlled automatically by the preset values which have been already entered in the microcontroller. Calibration is controlled and the working range is tested. Temperature of helmet is controlled between ?5 and +46?C by microcontroller, with the accuracy of ± 0.5?C.

Collaborative Technology Use by Healthcare Teams

Abstract: This paper reviews the literature on the use of collaborative technologies by healthcare teams between 1980 and 2003. Multiple databases were searched with explicit inclusion criteria that yielded 17 conceptual and empirical papers. The discussions of these literatures centered on the individual, team, and technological dimensions of collaborative technology use within healthcare teams. Results show that collaborative healthcare technologies can have positive effects on team work processes at both the individual and group level. The limited number of research studies accentuates the need for additional research in this area. Future research should focus on defining team tasks; determining which type of groupware works for a particular health setting; and exploring the effects of groupware on patient care delivery and the organization. Without research in these areas, it will be difficult to harness the full advantages of using groupware technologies by collaborative healthcare teams.

CLAIM (CLinical Accounting InforMation)--An XML-Based Data Exchange Standard for Connecting Electronic Medical Record Systems to Patient Accounting Systems

Abstract: With the evolving and diverse electronic medical record (EMR) systems, there appears to be an ever greater need to link EMR systems and patient accounting systems with a standardized data exchange format. To this end, the CLinical Accounting InforMation (CLAIM) data exchange standard was developed. CLAIM is subordinate to the Medical Markup Language (MML) standard, which allows the exchange of medical data among different medical institutions. CLAIM uses eXtensible Markup Language (XML) as a meta-language. The current version, 2.1, inherited the basic structure of MML 2.x and contains two modules including information related to registration, appointment, procedure and charging. CLAIM 2.1 was implemented successfully in Japan in 2001. Consequently, it was confirmed that CLAIM could be used as an effective data exchange format between EMR systems and patient accounting systems.

TPMG Northern California Appointments and Advice Call Center

Abstract: Kaiser Permanente (KP) has been developing its use of call centers as a way to provide an expansive set of healthcare services to KP members efficiently and cost effectively. Since 1995, when The Permanente Medical Group (TPMG) began to consolidate primary care phone services into three physical call centers, the TPMG Appointments and Advice Call Center (AACC) has become the "front office" for primary care services across approximately 89% of Northern California. The AACC provides primary care phone service for approximately 3 million Kaiser Foundation Health Plan members in Northern California and responds to approximately 1 million calls per month across the three AACC sites. A database records each caller'ss identity as well as the day, time, and duration of each call; reason for calling; services provided to callers as a result of calls; and clinical outcomes of calls. We here summarize this information for the period 2000 through 2003.

Public Health Data Collection and Sharing Using HIPAA Messages

Abstract: Public health information has significant value for doctors, public health officials, epidemiological researchers, the general public, and government agencies. Unfortunately, these data are difficult to obtain and are typically collected on as-needed basis and maintained locally. This localized process unavoidably limits the access to important public health data by its users. Moreover, the diversity of data transmission standards and collection techniques make the collected data less usable. This paper proposes a new standardized public health information system based on the HIPAA (Health Insurance Portability and Accountability Act) messages, which are the standard transactions between hospitals and insurance companies. In particular, this paper explores the applicability of HIPAA messages as a data source and transmission standard, and proposes a prototype design of a new system to collect and share public health data using HIPAA messages.

Enhancement of MML Medical Data Exchange Standard for a Localized Chinese Version

Abstract: Medical Markup Language (MML) is a standard for the exchange of medical data among different medical institutions. It was developed in Japan in 1995. Since version 2.21, MML has used eXtensible Markup Language (XML) as a meta-language. The latest version, 3.0, conforms to HL7 Clinical Document Architecture (CDA) and contains 14 modules and 36 data definition tables. In China, a standard which structures entire medical records in XML does not yet exist. Taking advantage of MML's flexibility, we created a localized Chinese version based on MML 3.0. Parts of the original specifications have been enhanced; these include a newly developed health insurance information module and 12 additional or redefined data definition tables. The Chinese version takes local needs into account and now makes it possible to exchange medical data among Chinese medical institutions.

Design and Construction of Thermoelectric Footwear Heating System for Illness Feet

Abstract: In this study, a Thermoelectric Footwear Heating System is developed to use in cold weather conditions. The temperature is controlled by an analog electronic control system. Thermoelectric module is used to heat the bottom of the foot. A negative temperature coefficient (NTC) temperature sensor is used to sense the temperature and the temperature is controlled by an electronic circuit proportionally. A 3.5 V, 5000 mAh rechargeable battery is used as the power source. The temperature range of the system is between +15?C and +50?C. Developed footwear heating system is tested against various temperature conditions, and offer better results in the case of heating the illness feet.