Showing papers in "Journal of Medical Systems in 2009"
TL;DR: A novel method for glaucoma detection using digital fundus images is presented and it is indicated that the features are clinically significant in the detection of glAUcoma.
Abstract: Glaucoma is a disease of the optic nerve caused by the increase in the intraocular pressure of the eye. Glaucoma mainly affects the optic disc by increasing the cup size. It can lead to the blindness if it is not detected and treated in proper time. The detection of glaucoma through Optical Coherence Tomography (OCT) and Heidelberg Retinal Tomography (HRT) is very expensive. This paper presents a novel method for glaucoma detection using digital fundus images. Digital image processing techniques, such as preprocessing, morphological operations and thresholding, are widely used for the automatic detection of optic disc, blood vessels and computation of the features. We have extracted features such as cup to disc (c/d) ratio, ratio of the distance between optic disc center and optic nerve head to diameter of the optic disc, and the ratio of blood vessels area in inferior-superior side to area of blood vessel in the nasal-temporal side. These features are validated by classifying the normal and glaucoma images using neural network classifier. The results presented in this paper indicate that the features are clinically significant in the detection of glaucoma. Our system is able to classify the glaucoma automatically with a sensitivity and specificity of 100% and 80% respectively.
294 citations
TL;DR: This proposed method can be used for non-constrained blood pressure monitoring for the purpose of personal healthcare and does not require an aircuff and only a minimal inconvenience of attaching electrodes and LED/photo detector sensors on a subject.
Abstract: Blood pressure (BP) is one of the important vital signs that need to be monitored for personal healthcare. Arterial blood pressure (BP) was estimated from pulse transit time (PTT) and PPG waveform. PTT is a time interval between an R-wave of electrocardiography (ECG) and a photoplethysmography (PPG) signal. This method does not require an aircuff and only a minimal inconvenience of attaching electrodes and LED/photo detector sensors on a subject. PTT computed between the ECG R-wave and the maximum first derivative PPG was strongly correlated with systolic blood pressure (SBP) (R?=??0.712) compared with other PTT values, and the diastolic time proved to be appropriate for estimation diastolic blood pressure (DBP) (R?=??0.764). The percent errors of SBP using the individual regression line (4---11%) were lower than those using the regression line obtained from all five subjects (9---14%). On the other hand, the DBP estimation did not show much difference between the individual regression (4---10%) and total regression line (6---10%). Our developed device had a total size of 7?×?13.5 cm and was operated by single 3-V battery. Biosignals can be measured for 72 h continuously without external interruptions. Through a serial network communication, an external personal computer can monitor measured waveforms in real time. Our proposed method can be used for non-constrained, thus continuous BP monitoring for the purpose of personal healthcare.
159 citations
TL;DR: By using the grouping proof protocol, the medical staffs could confirm the authentication and integrity of a group of Radio-Frequency Identification (RFID) tags which are embedded on inpatient bracelets and the containers of drugs.
Abstract: In order to provide enhanced medication safety for inpatients, the medical mechanism which adopts the modified grouping proof protocol is proposed in this paper By using the grouping proof protocol, the medical staffs could confirm the authentication and integrity of a group of Radio-Frequency Identification (RFID) tags which are embedded on inpatient bracelets and the containers of drugs This mechanism is designed to be compatible with EPCglobal Class-1 Generation-2 standard which is the most popular specification of RFID tags Due to the light-weight computational capacity of passive tags, only the pseudo-random number generator (PRNG) and cyclic redundancy code (CRC) are allowed to be used in the communication protocol Furthermore, a practical scenario of using this proposed mechanism in hospital to examine the medication safety is also presented
99 citations
TL;DR: A novel approach to automatically segment the OD and exudates is proposed, which makes use of the green component of the image and preprocessing steps such as average filtering, contrast adjustment, and thresholding.
Abstract: The detection of bright objects such as optic disc (OD) and exudates in color fundus images is an important step in the diagnosis of eye diseases such as diabetic retinopathy and glaucoma. In this paper, a novel approach to automatically segment the OD and exudates is proposed. The proposed algorithm makes use of the green component of the image and preprocessing steps such as average filtering, contrast adjustment, and thresholding. The other processing techniques used are morphological opening, extended maxima operator, minima imposition, and watershed transformation. The proposed algorithm is evaluated using the test images of STARE and DRIVE databases with fixed and variable thresholds. The images drawn by human expert are taken as the reference images. The proposed method yields sensitivity values as high as 96.7%, which are better than the results reported in the literature.
97 citations
TL;DR: An ICU patient flow simulation model was developed and it was demonstrated that by scheduling not more than four elective surgeries per day ICU diversion due to ‘no ICU beds’ would be practically eliminated.
Abstract: Despite the considerable number of publications on ICU patient flow and analysis of its variability, a basic and practically important question remained unanswered: what maximum number of elective surgeries per day should be scheduled (along with the competing demand from emergency surgeries) in order to reduce diversion in an ICU with fixed bed capacity to an acceptable low level, or prevent it at all? The goal of this work was to develop a methodology to answer this question. An ICU patient flow simulation model was developed to establish a quantitative link between the daily load leveling of elective surgeries (elective schedule smoothing) and ICU diversion. It was demonstrated that by scheduling not more than four elective surgeries per day ICU diversion due to `no ICU beds' would be practically eliminated. However this would require bumping `extra' daily surgeries to the block time day of another week which could be up to 2 months apart. Because not all patients could wait that long for their elective surgery, another more practical scenario was tested that would also result in a very low ICU diversion: bumping `extra' daily elective surgeries within less than 2 weeks apart, scheduling not more than five elective surgeries per day, and strict adherence to the ICU admission/discharge criteria.
93 citations
TL;DR: Results indicate system users were more likely to access HIE for patients for whom the information might be considered most beneficial, implying that HIE information access did not transform care in the ways many would expect.
Abstract: Health information exchange (HIE) makes previously inaccessible data available to clinicians, resulting in more complete information. This study tested the hypotheses that HIE information access reduced emergency room visits and inpatient hospitalizations for ambulatory care sensitive conditions among medically indigent adults. HIE access was quantified by how frequently system users' accessed patients' data. Encounter counts were modeled using zero inflated binomial regression. HIE was not accessed for 43% of individuals. Patient factors associated with accessed data included: prior utilization, chronic conditions, and age. Higher levels of information access were significantly associated with increased counts of all encounter types. Results indicate system users were more likely to access HIE for patients for whom the information might be considered most beneficial. Ultimately, these results imply that HIE information access did not transform care in the ways many would expect. Expectations in utilization reductions, however logical, may have to be reevaluated or postponed.
87 citations
TL;DR: It is found that merely implementing an HIS will not automatically increase organizational efficiency and strategic, tactical, and operational actions have to be taken into consideration, including management involvement, integration in healthcare workflow, establishing compatibility between software and hardware and, most importantly, user involvement, education and training.
Abstract: Healthcare information systems (HISs) are often implemented to enhance the quality of care and the degree to which it is patient-centered, as well as to improve the efficiency and safety of services. However, the outcomes of HIS implementations have not met expectations. We set out to organize the knowledge gained in qualitative studies performed in association with HIS implementations and to use this knowledge to outline an updated structure for implementation planning. A multi-disciplinary team performed the analyses in order to cover as many aspects of the primary studies as possible. We found that merely implementing an HIS will not automatically increase organizational efficiency. Strategic, tactical, and operational actions have to be taken into consideration, including management involvement, integration in healthcare workflow, establishing compatibility between software and hardware and, most importantly, user involvement, education and training. The results should be interpreted as a high-order scheme, and not a predictive theory.
85 citations
TL;DR: A framework of twelve factors affecting the decision to adopt/not to adopt the MNIS in the nursing department is developed, and tested from the perspective of the nursing administrators.
Abstract: The trend towards point-of-care and the advance in mobile technologies bring the potential to employ Mobile Nursing Information Systems (MNIS) in nursing care routines. However, adopting the MNIS is not simply a case of purchasing the required hardware and software, but rather a social interaction process between users, organizations, and the environment. Therefore, this study developed a framework of twelve factors affecting the decision to adopt/not to adopt the MNIS in the nursing department, and tested it from the perspective of the nursing administrators. A mail survey was conducted to collect the opinions of 84 nursing administrators, and a discriminant analysis was used to identify the critical factors for the adoption/non-adoption of the MNIS. Business competition, external suppliers' support, and internal needs were identified as being significantly associated with the adoption of MNIS. Potential adopters can apply the results of this study as a reference when making the adoption decision regarding MNIS, while non-adopters and vendors can examine the resistance to MNIS.
71 citations
TL;DR: The performance of the ANFis model was evaluated in terms of training performances and classification accuracies and the results confirmed that the proposed ANFIS model has potential in detecting the breast cancer.
Abstract: This paper intends to an integrated view of implementing adaptive neuro-fuzzy inference system (ANFIS) for breast cancer detection. The Wisconsin breast cancer database contained records of patients with known diagnosis. The ANFIS classifiers learned how to differentiate a new case in the domain by given a training set of such records. The ANFIS classifier was used to detect the breast cancer when nine features defining breast cancer indications were used as inputs. The proposed ANFIS model combined the neural network adaptive capabilities and the fuzzy logic qualitative approach. Some conclusions concerning the impacts of features on the detection of breast cancer were obtained through analysis of the ANFIS. The performance of the ANFIS model was evaluated in terms of training performances and classification accuracies and the results confirmed that the proposed ANFIS model has potential in detecting the breast cancer.
69 citations
TL;DR: It was determined that non-profits were more efficient than for-profit hospitals for all 4 years examined in this study, and teaching hospitals were more efficiency than non-teaching hospitals in 2001–2003, but not in 2004.
Abstract: This study assessed the association between hospital ownership and technical efficiency in a managed care environment. Hospital technical efficiency scores were calculated via the data envelopment analysis (DEA) method, employing four input variables and three output variables from the American Hospital Association Hospital Survey Data for acute care general hospitals in Florida. By utilizing the hospital technical efficiency scores as a dependent variable, we determined that non-profit hospitals were more efficient than for-profit hospitals for all 4 years examined in this study. In particular, for-profit hospitals with between 100 and 249 beds and those with more than 400 beds had lower technical efficiency scores as compared to their nonprofit peers. Another finding was that teaching hospitals were more efficient than non-teaching hospitals in 2001---2003, but not in 2004. Those variables associated with managed care, namely "number of HMO contracts" and "contracted with HMO", however, were not shown to be statistically significant.
66 citations
TL;DR: This analysis investigates what patients and practitioners can do to improve their interactive communications to achieve optimal patient-centric (PC) care.
Abstract: This analysis investigates what patients and practitioners can do to improve their interactive communications to achieve optimal patient-centric (PC) care One goal of this clinical practice approach is to improve patient satisfaction, compliance, and outcomes The mutual responsibilities required of both the patients and practitioners to attain PC care are discussed Innovative, information technology techniques in the healthcare environment in general and in care delivery in particular are explored Practitioner-to-patient encouragement vis-a-vis self education on their conditions is also provided
TL;DR: The case of recent changes in the structure of Quebec’s health care organizations and a change in the commercial policies of a key vendor are used to illustrate the conclusions regarding barriers to adoption of open source products.
Abstract: We conducted in-depth interviews with 15 CIOs to identify the principal impediments to adoption of open source software in the Quebec health sector. We found that key factors for not adopting an open source solution were closely linked to the orientations of ministry level policy makers and a seeming lack of information on the part of operational level IT managers concerning commercially oriented open source providers. We use the case of recent changes in the structure of Quebec's health care organizations and a change in the commercial policies of a key vendor to illustrate our conclusions regarding barriers to adoption of open source products.
TL;DR: Two parameters, average ocular temperature and the temperature deviation were proposed to study the variability of OST in different normal category subjects and shows that, the two parameters proposed, show distinct ranges for different groups with ‘p' values less than 0.05.
Abstract: The human body temperature is a good health indicator. All objects emit thermal radiation as a function temperature and wavelength for all wavelengths. The wavelength of infrared rays lies between visible and microwave radiations ranging between 700 nm to 0.1 mm. Infrared (IR) imaging is relatively inexpensive, noninvasive and harmless. Nowadays, it is widely used in the medical field for diagnosis. In this work, we have applied image processing techniques on the IR images of the eye for the analysis of the ocular surface temperature (OST) of the normal subjects of three categories (young, middle and old ages). In our study, 67 IR normal images were analyzed. Two parameters, average ocular temperature and the temperature deviation were proposed to study the variability of OST in different normal category subjects. Our study shows that, the two parameters proposed, show distinct ranges for different groups with `p' values less than 0.05.
TL;DR: A comparative study on chronic obstructive pulmonary and pneumonia diseases diagnosis was realized by using neural networks and artificial immune systems for three different neural networks structures and one artificial immune system.
Abstract: Millions of people are diagnosed every year with a chest disease in the world. Chronic obstructive pulmonary and pneumonia diseases are two of the most important chest diseases. And these are very common illnesses in Turkey. In this paper, a comparative study on chronic obstructive pulmonary and pneumonia diseases diagnosis was realized by using neural networks and artificial immune systems. For this purpose, three different neural networks structures and one artificial immune system were used. Used neural network structures in this study were multilayer, probabilistic, and learning vector quantization neural networks. The results of the study were compared with the results of the pervious similar studies reported focusing on chronic obstructive pulmonary and pneumonia diseases diagnosis. The chronic obstructive pulmonary and pneumonia diseases dataset were prepared from a chest diseases hospital's database using patient's epicrisis reports.
TL;DR: Examination of computer literacy levels of nurses in Taiwan and South Korea revealed that personal innovativeness in IT, computer education, and age are significant factors that affected computer Literacy levels.
Abstract: Healthcare is experiencing a major transformation in its information technology base. Hospitals are adopting information technology (IT) to reduce costs and increase competitiveness. IT applications in healthcare are trending towards electronic patient records and even health records. Therefore, practices in nursing are also affected by IT. Many researchers have studied what computer literacy a nurse should possess, but have focused less on factors that actually impact computer literacy. The purposes of this study are to examine current computer literacy levels of nurses, and to indicate what variables influence their computer literacy. Taiwan and South Korea both implemented a national health insurance system, and used state-of-the art IT to provide higher volume and better quality of services. The data were collected from two case hospitals which are located in Taiwan and South Korea, respectively. By using a structured questionnaire, a total of 203 nurses responded; 104 from Taiwan and 99 from South Korea. The results revealed that personal innovativeness in IT, computer education, and age are significant factors that affected computer literacy levels. These factors serve as reference for administrators and executives in hospitals, or nursing educators seeking the data necessary to make decisions on curriculum.
TL;DR: The new automated detection method for electrocardiogram (ECG) arrhythmias is implemented with integration of complex valued feature extraction and classification parts and accuracy rates were obtained as 99.8% and 99.2% for the first and second classification tasks, respectively.
Abstract: This paper presents the new automated detection method for electrocardiogram (ECG) arrhythmias. The detection system is implemented with integration of complex valued feature extraction and classification parts. In feature extraction phase of proposed method, the feature values for each arrhythmia are extracted using complex discrete wavelet transform (CWT). The aim of using CWT is to compress data and to reduce training time of network without decreasing accuracy rate. Obtained complex valued features are used as input to the complex valued artificial neural network (CVANN) for classification of ECG arrhythmias. Ten types of the ECG arrhythmias used in this study were selected from MIT-BIH ECG Arrhythmias Database. Two different classification tasks were performed by the proposed method. In first classification task (CT-1), whether CWT-CVANN can distinguish ECG arrhythmia from normal sinus rhythm was examined one by one. For this purpose, nine classifiers were improved and executed in CT-1. Second classification task (CT-2) was to recognize ten different ECG arrhythmias by one complex valued classifier with ten outputs. Training and test sets were formed by mixing the arrhythmias in a certain order. Accuracy rates were obtained as 99.8% (averaged) and 99.2% for the first and second classification tasks, respectively. All arrhythmias in training and test phases were classified correctly for both of the classification tasks.
TL;DR: Attention to training in the use of CPOE should start early, ideally integrated into medical and nursing school curricula and form a continuous, long-term and user-specific process, to increase familiarity with the system, reducing stress and leading to improved user satisfaction and to subsequent enhanced safety and efficiency.
Abstract: To evaluate the impact of Computerized Provider Order Entry (CPOE) on workplace stress and overall job performance, as perceived by medical students, housestaff, attending physicians and nurses, after CPOE implementation at Penn State--Milton S. Hershey Medical Center, an academic tertiary care facility, in 2005. Using an online survey, the authors studied attitudes towards CPOE among 862 health care professionals. The main outcome measures were job performance and perceived stress levels. Statistical analyses were conducted using the Statistical Analytical Software (SAS Inc, Carey, NC). A total of 413 respondents completed the entire survey (47.9 % response rate). Respondents in the younger age group were more familiar with the system, used it more frequently, and were more satisfied with it. Interns and residents were the most satisfied groups with the system, while attending physicians expressed the least satisfaction. Attending physicians and fellows found the system least user friendly compared with other groups, and also tended to express more stress and frustration with the system. Participants with previous CPOE experience were more familiar with the system, would use the system more frequently and were more likely to perceive the system as user friendly. User satisfaction with CPOE increases by familiarity and frequent use of the system. Improvement in system characteristics and avoidance of confusing terminology and inconsistent display of data is expected to enhance user satisfaction. Training in the use of CPOE should start early, ideally integrated into medical and nursing school curricula and form a continuous, long-term and user-specific process. This is expected to increase familiarity with the system, reducing stress and leading to improved user satisfaction and to subsequent enhanced safety and efficiency.
TL;DR: This study develops an instrument to assess the quality of a web-based learning system for nurses’ continuing education based on the quality dimensions of a mature information systems success model and results show that all indicators of the instrument provide a fit to the quality measurement.
Abstract: Continuing professional education is essential for nurses to update their clinical skills and knowledge to meet the complex demands of current patient care. Compared to traditional in-class continuing education, a web-based learning system is efficient for nurses with a three shift-working schedule and is timely to deliver knowledge about newly emerging epidemics such as Severe Acute Respiratory Syndrome. Many studies reveal the advantages of various web-based learning systems but seldom evaluate them from the perspective of quality. This study develops an instrument to assess the quality of a web-based learning system for nurses' continuing education based on the quality dimensions of a mature information systems success model. The research results show that all indicators of the instrument provide a fit to the quality measurement of a web-based learning system and have high reliability and validity. Based on the research findings, implications and limitations are discussed.
TL;DR: A patient scheduling approach for a university radiation oncology department is introduced to minimize delays in treatments due to potential prolongations in treatments of current patients and to maintain efficient use of the daily treatment capacity.
Abstract: Physical therapy, hemodialysis and radiation oncology departments in which patients go through lengthy and periodic treatments need to utilize their limited and expensive equipment and human resources efficiently. In such departments, it is an important task to continue to treat current patients without any interruption along with incoming patients. In this study, a patient scheduling approach for a university radiation oncology department is introduced to minimize delays in treatments due to potential prolongations in treatments of current patients and to maintain efficient use of the daily treatment capacity. A simulation analysis of the scheduling approach is also conducted to assess its efficiency under different environmental conditions and to determine appropriate scheduling policy parameter values. Also, the simulation analysis of the suggested scheduling approach enables to determine appropriate scheduling parameters under given circumstances. Therefore, the system can perform more efficiently.
TL;DR: This work is proposing a novel method for the compact storage and transmission of patient information with the medical images using a reversible watermarking technique to hide the patient information within the retinal fundus image.
Abstract: Handling of patient records is increasing overhead costs for most of the hospitals in this digital age. In most hospitals and health care centers, the patient text information and corresponding medical images are stored separately as different files. There is a possibility of mishandling the text file containing patient history. We are proposing a novel method for the compact storage and transmission of patient information with the medical images. In this technique, we are using a reversible watermarking technique to hide the patient information within the retinal fundus image. There is a possibility that these medical images, which carry patient information, can get corrupted by the noise during the storage or transmission. The safe recovery of patient information is important in this situation. So, to recover the maximum amount of text information in the noisy environment, the encrypted patient information is coded with error control coding (ECC) techniques. The performance of three types of ECC for various levels of salt & pepper (S & P) noise is tabulated for a specific example. The proposed system is more reliable even in a noisy environment and saves memory.
TL;DR: This is the first study classifying primary generalized epilepsy using Multilayer Perceptron Neural Networks (MLPNNs), and outcomes indicate that this model classified the subgroups ofPrimary generalized epilepsy successfully.
Abstract: Epilepsy is a disorder of cortical excitability and still an important medical problem. The correct diagnosis of a patient's epilepsy syndrome clarifies the choice of drug treatment and also allows an accurate assessment of prognosis in many cases. The aim of this study is to classify subgroups of primary generalized epilepsy by using Multilayer Perceptron Neural Networks (MLPNNs). This is the first study classifying primary generalized epilepsy using MLPNNs. MLPNN classified primary generalized epilepsy with the accuracy of 84.4%. This model also classified generalized tonik---klonik, absans, myoclonic and more than one type seizures epilepsy groups correctly with the accuracy of 78.5%, 80%, 50% and 91.6%, respectively. Moreover, new MLPNNs were constructed for determining significant variables affecting the classification accuracy of neural networks. The loss of consciousness in the course of seizure time variable caused the largest decrease in the classification accuracy when it was left out. These outcomes indicate that this model classified the subgroups of primary generalized epilepsy successfully.
TL;DR: The feasibility of applying analytical software techniques together with the real-time functional thermal analysis to develop a potential tool for the detection and classification of breast cancer is shown.
Abstract: Breast cancer is the second leading cause of death in women. It occurs when cells in the breast begin to grow out of control and invade nearby tissues or spread throughout the body. The limitations of mammography as a screening modality, especially in young women with denser breasts, necessitated the development of novel and more effective screening strategies with acceptable sensitivity and specificity. The aim of this study was to develop a feasible interpretive software system which was able to detect and classify breast cancer patients by employing techniques of different analytical software. The protocol described uses 6,000 pieces of thermal data collected from 16-sensors, eight placed on the surface of each breast. Data was collected every 5 min for the duration of the test period. Placement of sensors was accomplished with the use of a template design from information provided by the national tumor registry to insure that the information was collected in areas of the breast where most breast cancers develop. Data in this study was collected from 90 individuals exhibiting four different breast conditions, namely: normal, benign, cancer and suspected-cancer. The temperature data collected from these 16 sensors placed on the surface of each breast were fed as inputs to the classifiers. Comparisons were made on five different kinds of classifiers: back-propagation algorithm, probabilistic neural network, fuzzy (Sugeno-type), Gaussian mixture model and support vector machine. These classifiers were able to attain approximately 80% accuracy in classifying the four different diagnoses (normal, benign, cancer and suspected-cancer). Gaussian mixture model was the most sensitive classifier, achieving the highest sensitivity of 94.8%. Support vector machine was considered the best classifier as it was able to produce the most specific and accurate results. Based on these evaluations, this current effort shows the feasibility of applying analytical software techniques together with the real-time functional thermal analysis to develop a potential tool for the detection and classification of breast cancer.
TL;DR: The present research demonstrated that the modified mixture of experts (MME) achieved diagnostic accuracies which were higher than that of the other automated diagnostic systems.
Abstract: Diagnosis tasks are among the most interesting activities in which to implement intelligent systems. The major objective of the paper is to be a guide for the readers, who want to develop an automated decision support system for detection of diabetics and subjects having risk factors of diabetes. The purpose was to determine an optimum classification scheme with high diagnostic accuracy for this problem. Several different classification algorithms were tested and their performances in detection of diabetics were compared. The performance of the classification algorithms was illustrated on the Pima Indians diabetes data set. The present research demonstrated that the modified mixture of experts (MME) achieved diagnostic accuracies which were higher than that of the other automated diagnostic systems.
TL;DR: The objective of this study was to examine the determinants of primary care physicians' acceptance of the technological innovation and the reduction of medication error rates and the improvement of communication between medical caregivers.
Abstract: In Germany e-health cards will be distributed nationwide to over 80 million patients. Given the impending mandatory introduction of the e-health technology, the objective of this study was to examine the determinants of primary care physicians' acceptance of the technological innovation. The study was conducted prior to the introduction of the e-health cards. A questionnaire survey was carried out addressing primary care physicians from different fields. The reduction of medication error rates and the improvement of communication between medical caregivers are central aspects of the perceived usefulness. Primary care physicians rate their involvement in the process of the development of the technology and their own IT expertise concerning the technological innovation as rather low. User involvement and IT expertise can explain 46 % of the variance of perceived usefulness of the e-health card. User involvement plays a crucial role in the adoption of the German e-health card. Primary care physician's perspective should be represented in the process of developing and designing the technology.
TL;DR: This work presents techniques that allow the embedding and retrieval of sensitive numerical data, such as the patient’s social security number or birth date, within the medical signal, and builds upon watermarking notions.
Abstract: Due to the recent explosion of `identity theft' cases, the safeguarding of private data has been the focus of many scientific efforts. Medical data contain a number of sensitive attributes, whose access the rightful owner would ideally like to disclose only to authorized personnel. One way of providing limited access to sensitive data is through means of encryption. In this work we follow a different path, by proposing the fusion of the sensitive metadata within the medical data. Our work is focused on medical time-series signals and in particular on Electrocardiograms (ECG). We present techniques that allow the embedding and retrieval of sensitive numerical data, such as the patient's social security number or birth date, within the medical signal. The proposed technique not only allows the effective hiding of the sensitive metadata within the signal itself, but it additionally provides a way of authenticating the data ownership or providing assurances about the origin of the data. Our methodology builds upon watermarking notions, and presents the following desirable characteristics: (a) it does not distort important ECG characteristics, which are essential for proper medical diagnosis, (b) it allows not only the embedding but also the efficient retrieval of the embedded data, (c) it provides resilience and fault tolerance by employing multistage watermarks (both robust and fragile). Our experiments on real ECG data indicate the viability of the proposed scheme.
TL;DR: The results suggest that an ANN, which is based on limited clinical parameters, appears to be a promising method in forecasting of the skeletal metastasis in patients with prostate cancer.
Abstract: The application of an artificial neural network (ANN) in prediction of outcomes using clinical data is being increasingly used. The aim of this study was to assess whether an ANN model is a useful tool for predicting skeletal metastasis in patients with prostate cancer. Consecutive patients with prostate cancer who underwent the technetium-99m methylene diphosphate (Tc-99m MDP) whole body bone scintigraphies were retrospectively analyzed between 2001 and 2005. The predictors were the patient's age and radioimmunometric serum PSA concentration. The outcome variable was dichotomous, either skeletal metastasis or non-skeletal metastasis, based on the results of Tc-99m MDP whole body bone scintigraphy. To assess the performance for classification model in clinical study, the discrimination and calibration of an ANN model was calculated. The enrolled subjects consisted of 111 consecutive male patients aged 72.41?±?7.69 years with prostate cancer. Sixty-seven patients (60.4%) had skeletal metastasis based on the scintigraphic diagnosis. The final best architecture of neural network model was four-layered perceptrons. The area under the receiver-operating characteristics curve (0.88?±?0.07) revealed excellent discriminatory power (p? ?0.05), which represented a good-fit calibration. These results suggest that an ANN, which is based on limited clinical parameters, appears to be a promising method in forecasting of the skeletal metastasis in patients with prostate cancer.
TL;DR: Given this existing relationship between hospital IT capabilities and physician adoption patterns, federal policies designed to encourage this more directly will positively promote the proliferation of EMR systems.
Abstract: In light of new federal policies allowing hospitals to subsidize the cost of information systems for physicians, we examine the relationship between local hospital investments in information technology (IT) and physician EMR adoption. Data from two Florida surveys were combined with secondary data from the State of Florida and the Area Resource File (ARF). Hierarchal logistic regression was used to examine the effect of hospital adoption of clinical information systems on physician adoption of EMR systems after controlling for confounders. In multivariate analysis, each additional clinical IT application adopted by a local hospital was associated with an 8% increase in the odds of EMR adoption by physicians practicing in that county. Given this existing relationship between hospital IT capabilities and physician adoption patterns, federal policies designed to encourage this more directly will positively promote the proliferation of EMR systems.
TL;DR: A new ECG feature detection mechanism was presented, which was compared against existing cross correlation (CC) based template matching algorithms and a newECG obfuscation method was designed and implemented on 15 subjects using added noises corresponding to each of the ECG features.
Abstract: With cardiovascular disease as the number one killer of modern era, Electrocardiogram (ECG) is collected, stored and transmitted in greater frequency than ever before. However, in reality, ECG is rarely transmitted and stored in a secured manner. Recent research shows that eavesdropper can reveal the identity and cardiovascular condition from an intercepted ECG. Therefore, ECG data must be anonymized before transmission over the network and also stored as such in medical repositories. To achieve this, first of all, this paper presents a new ECG feature detection mechanism, which was compared against existing cross correlation (CC) based template matching algorithms. Two types of CC methods were used for comparison. Compared to the CC based approaches, which had 40% and 53% misclassification rates, the proposed detection algorithm did not perform any single misclassification. Secondly, a new ECG obfuscation method was designed and implemented on 15 subjects using added noises corresponding to each of the ECG features. This obfuscated ECG can be freely distributed over the internet without the necessity of encryption, since the original features needed to identify personal information of the patient remain concealed. Only authorized personnel possessing a secret key will be able to reconstruct the original ECG from the obfuscated ECG. Distribution of the key is extremely efficient and fast due to small size (only 0.04---0.09% of the original ECG file). Moreover, if the obfuscated ECG reaches to the wrong hand (hacker), it would appear as regular ECG without encryption. Therefore, traditional decryption techniques including powerful brute force attack are useless against this obfuscation.
TL;DR: A prototype for automatic data collection from intensive care devices developed at Pedro Hispano Hospital in Portugal is described, which eliminates transcription errors, improves the quality of records and allows the assembly of large electronic archives of vital sign data.
Abstract: The integration of computer systems into clinical practice is a consequence of the growing sophistication of medical machinery. The fact that patient management in large institutions is handled by complex information systems brings about the need for integration between applications on both sides. The paper describes a prototype for automatic data collection from intensive care devices developed at Pedro Hispano Hospital in Portugal. The system acts as an application gateway between the network of patient monitoring devices and the general-purpose hospital network. The conformance to medical standards is one of the main concerns. The international standard Health Level 7 (HL7) has been adopted to import vital signs, as well as to prepare data for visualization in departmental applications and to organize archives. The design has followed the administrative and clinical processes in the hospital closely, leading to a successful interaction with the health professionals. Automatic acquisition eliminates transcription errors, improves the quality of records and allows the assembly of large electronic archives of vital sign data. The concern with data archiving in standard formats opens many possibilities for further analysis of the collected data sets. The possibility of communicating via the HL7 standard makes the whole system easily interoperable with applications in related domains.
TL;DR: The results let us suggest that the isolated administrative agents profile is no more effective in a dynamic and changing world and contemporary decision makers need to be more active intellectually and to take risks in their decisions.
Abstract: Information and Communication Technology (ICT) and Organizational Innovation (OI) are seen as the miracle of post-modernity in organizations. In this way, they are supposed to resolve most organizational problems, efficiently and rapidly. OI is highly dependent on the capacity and the investment in knowledge management (internal and external) to support decision making process and to implement significant changes. We know what explains ICT utilization (ICTU) and what determines OI development (OID) in healthcare services. Moreover, the literature tends to link ICTU to OID and vice versa. However, this dependency has never been explored empirically through the lens of roles combination. To identify the existing combined roles profiles of ICTU and OID among healthcare decision makers and determine factors of the shift from a profile to another. We did the following: (1) a structured review of the literature on healthcare management by focusing on ICTU and OID which allowed us to build two indexes and a comprehensive framework; (2) a copula methodology to identify with high precision the thresholds for ICTU and OID; and (3) a cross-sectional study based on a survey done with a sample of 942 decision makers from Canadian healthcare organizations through a multinomial logit model to identify determinants of the shift. ICTU and OID are correlated at 22% (Kendal’s Tau). The joint distribution (combination) of ICTU and OID shows that four major profiles exist among decision makers in Canadian healthcare organizations: the traditional decision maker, the innovative decision maker, the technologic decision maker and the contemporary decision maker. We found out that classic factors act as barriers to the shift from one profile to the desired profile (from 1 to 4, from 2 to 4 and from 3 to 4). We have identified that the attitude toward research and relational capital are transversal barriers of shift. We have also found that some factors have a specific impact such as engaging in activities of research acquisition, the administrative position (being a manager), the preference for applied research results as source of information, the degree of novelty of research results, and the gender. Modern Canadian healthcare organizations need contemporary decision makers who use ICT and develop OI, if performance is the target. Our results let us suggest that the isolated administrative agents profile is no more effective in a dynamic and changing world. Contemporary decision makers need to be more active intellectually and to take risks in their decisions. Relying exclusively on research results and on their social network is no more helpful for a real shift. Moreover, the traditional factors, i.e. organization size, time, experience…are no more effective, especially when we consider combined roles. We propose some practical and theoretical recommendations to support these changes.