Search

Abstract: Objective: Healthcare organizations are increasingly implementing electronic health records (EHRs) and other related health information technology (IT). Even in institutions which have long adopted these computerized systems, employees continue to rely on paper to complete their work. The objective of this study was to explore and understand human-technology integration factors that may be causing employees to rely on paper alternatives to the EHR. Methods: We conducted semi-structured interviews with 20 key-informants in a large Veterans Affairs Medical Center (VAMC), with a fully implemented EHR, to understand the use of paper-based alternatives. Participants included clinicians, administrators, and IT specialists across several service areas in the medical center. Results: We found 11 distinct categories of paper-based workarounds to the use of the EHR. Paper use related to the following: (1) efficiency; (2) knowledge/skill/ease of use; (3) memory; (4) sensorimotor preferences; (5) awareness; (6) task specificity; (7) task complexity; (8) data organization; (9) longitudinal data processes; (10) trust; and (11) security. We define each of these and provide examples that demonstrate how these categories promoted paper use in spite of a fully implemented EHR. Conclusions: In several cases, paper served as an important tool and assisted healthcare employees in their work. In other cases, paper use circumvented the intended EHR design, introduced potential gaps in documentation, and generated possible paths to medical error. We discuss implications of these findings for EHR design and implementation. [Copyright &y& Elsevier]

The recognition that restructuring care processes is central to effective and efficient health care will result in the emergence of process-oriented electronic patient records (EPRs). How will these technologies come into being? Within informatics, it is often stated that to informate something, we should first model it. This paper queries whether a detailed modeling of work processes and data flows is the primary step that needs to be completed before such EPRs can be developed or tailored. Building upon a sociotechnical understanding of ICT development, we argue for a reinterpretation of ‘models’ in such development processes. We do so through a reverse engineering of parts of the paper-based medical record, which has received little attention in medical informatics. In process-oriented EPR design, we argue, modeling should not be conceived as the crucial first step in this design, but rather as an intervention in the organizational change-processes that constitute proper ICT development. [Copyright &y& Elsevier]

Objective: Most preventable adverse drug events and medication errors occur during medication ordering. Medication order entry and clinical decision support are available on paper or as computerized systems. In this post-hoc analysis we investigated frequency and clinical impact of blood glucose (BG) documentation- and user-related calculation errors as well as workflow deviations in diabetes management. We aimed to compare a paper-based protocol to a computerized medication management system combined with clinical workflow and decision support.Methods: Seventy-nine hospitalized patients with type 2 diabetes mellitus were treated with an algorithm driven basal-bolus insulin regimen. BG measurements, which were the basis for insulin dose calculations, were manually entered either into the paper-based workflow protocol (PaperG: 37 patients) or into GlucoTab(®)-a mobile tablet PC based system (CompG: 42 patients). We used BG values from the laboratory information system as a reference. A workflow simulator was used to determine user calculation errors as well as workflow deviations and to estimate the effect of errors on insulin doses. The clinical impact of insulin dosing errors and workflow deviations on hypo- and hyperglycemia was investigated.Results: The BG documentation error rate was similar for PaperG (4.9%) and CompG group (4.0%). In PaperG group, 11.1% of manual insulin dose calculations were erroneous and the odds ratio (OR) of a hypoglycemic event following an insulin dosing error was 3.1 (95% CI: 1.4-6.8). The number of BG values influenced by insulin dosing errors was eightfold higher than in the CompG group. In the CompG group, workflow deviations occurred in 5.0% of the tasks which led to an increased likelihood of hyperglycemia, OR 2.2 (95% CI: 1.1-4.6).Discussion: Manual insulin dose calculations were the major source of error and had a particularly strong influence on hypoglycemia. By using GlucoTab(®), user calculation errors were entirely excluded. The immediate availability and automated handling of BG values from medical devices directly at the point of care has a high potential to reduce errors. Computerized systems facilitate the safe use of more complex insulin dosing algorithms without compromising usability. In CompG group, missed or delayed tasks had a significant effect on hyperglycemia, while in PaperG group insufficient precision of documentation times limited analysis. The use of old BG measurements was clinically less relevant.Conclusion: Insulin dosing errors and workflow deviations led to measurable changes in clinical outcome. Diabetes management systems including decision support should address nurses as well as physicians in a computerized way. Our analysis shows that such systems reduce the frequency of errors and therefore decrease the probability of hypo- and hyperglycemia. [ABSTRACT FROM AUTHOR]

Computerized image analysis methods for dermoscopy are primarily of great interest and benefit, as it provides significant information about the lesion, which can be of pertinence for the clinicians and a stand-alone warning implement. Computer-based diagnostic systems require dedicated image processing algorithms to provide mathematical descriptions of the suspected regions, such systems hold a great potential in oncology. In this paper, we have performed a review of the state of art techniques used in computer-aided diagnostic systems, by giving the domain aspects of melanoma followed by the prominent techniques used in each of the steps. The steps include dermoscopic image pre-processing, segmentation, extraction and selection of peculiar features, and relegation of skin lesions. The paper also presents cognizance to judge the consequentiality of every methodology utilized in the literature, in addition to the corresponding results obtained in this perspective. The inadequacies and the future research directions are accentuated. [ABSTRACT FROM AUTHOR]

Abstract: Background and purpose: EpiData and Epi Info are often used together by public health agencies around the world, particularly in developing countries, to meet their needs of low-cost public health data management; however, the current open source data management technology lacks a mobile component to meet the needs of mobile public health data collectors. The goal of this project is to explore the opportunity of filling this gap through developing and trial of a personal digital assistant (PDA) based data collection/entry system. It evaluated whether such a system could increase efficiency and reduce data transcription errors for public surveillance data collection in developing countries represented by Fiji. Methods: A generic PDA-based data collection software eSTEPS was developed. The software and the data collected using it directly interfaces with EpiData. A field trial was conducted to test the viability of public health surveillance data collection using eSTEPS. The design was a randomised, controlled trial with cross-over design. 120 participants recruited from the Fiji School of Medicine were randomly assigned to be interviewed by one of six interviewers in one of the two ways: (1) paper-based survey followed by PDA survey and (2) PDA survey followed by paper-based survey. Data quality was measured by error rates (logical range errors/inconsistencies, skip errors, missing values, date or time field errors and incorrect data type). Work flow and cost were evaluated in three stages of the survey process: (1) preparation of data collection instrument, (2) data collection and (3) data entry, validation and cleaning. User acceptance was also evaluated in the two groups of participants: (1) data collectors and (2) survey participants. Results: None of the errors presented in 20.8% of the paper questionnaires was found in the data set collected using PDA. Sixty-two percent of the participants perceived that the PDA-based questionnaire took less time to complete. Data entry, validation and cleaning for the PDA-based data collection from 120 participants took a total of 1.5h, a 93.26% reduction of time from 20.5h required using paper and pen. The cost is also significantly reduced with PDA-based protocol. Both data collectors and participants prefer to use PDA instead of paper for data collection. The trial results prove that eSTEPS is a feasible solution for public health surveillance data collection in the field. Several deficiencies of the software were also identified and would be addressed in the next version. Conclusion: eSTEPS offers the potential to meet the need for an effective mobile public health data collection tool for use in the field. The eSTEPS field trial proves that PDA was more efficient than paper for public health survey data collection. It also significantly reduced errors in data entry. The later benefit was derived from the software providing its users with the flexibility of building their own constraints to control the data type, range and logic of data entry. [Copyright &y& Elsevier]

Abstract: Purpose: The present study was performed to determine the standard functions of electronic clinical pathways (eCP) embedded in electronic medical records with regard to demand definition. Methods: The standard functions of eCP were decided by the required functions determined from interviews with hospital staff, those derived from the implementation of paper-based clinical pathways (CPs), and additional functions generated through the shift from a paper-based to an electronic system. Moreover, the proposed standard functions and those of eCP embedded in electronic medical records for large hospitals were compared by interviews with five vendors. Results: Seventeen functions were deemed necessary for eCP, and these were classified into six categories: displaying, recording, ordering, editing, variance, and statistics. Although most of these functions are already included in eCP products, their implementations differ between products. Conclusions: We propose 17 standard functions required for eCP embedded in electronic medical records. The functions for editing patient checklists, checking the occurrence of variance, and statistics are especially important and should be implemented as standard functions. This study will aid in the future development of eCP embedded in electronic medical records. [Copyright &y& Elsevier]

Prostate cancer is considered to be the third and sixth leading cause of death from cancer in men in developed and developing countries, respectively. As Multiparametric Magnetic Resonance Imaging (mp-MRI) and Magnetic Resonance Spectroscopic Imaging (MRSI) play an important role in the detection and the localization of cancerous tissues, in this paper, we propose a SVM and Random Forest based supervised classification schema, based on three classes (Healthy, Benign, Malignant) and on an MRI/MRSI data base of 34 patients. A total of 7711 spectroscopy voxels were exploited. The first contribution of this paper is to present improvements of the automatic classification results compared with those of Parfait, thanks to an improvement in the quality of spectra. We also improved the global detection by introducing mp-MRI based features in the classification process. We selected the most discriminative features by evaluating several combinations of MRI modalities. Moreover, we have extended the analysis to the entire prostate gland (peripheral zone (PZ) and central gland (CG)). We evaluated the SVM classifier's ability to discriminate healthy and malignant voxels and the proposed method produces a global error rate of 1%, sensitivity of 99.1% and specificity of 98.4%. The three classes, including benign voxels data were then evaluated. An error rate of 18.2%, a sensitivity of 72% and a specificity of 88% were obtained when associating Random Forest classifier, MRSI, Dynamic Contrast-Enhanced MRI and Diffusion-Weighted MRI. We finally present classification results in the form of color-coded maps, which are a computer aided diagnosis tool which could help in the evaluation of the results and could also provide an estimation of tumor shape and volume. [ABSTRACT FROM AUTHOR]

Purposes: This study aimed to compare between electronic medication administration records and paper-based records in the nursing time spent on various activities in a medication round and the medication administration processes followed by nurses in an Australian residential aged care home. It also aimed to identify the benefits and unintended adverse consequences of using the electronic medication administration records.Methods: Time-motion observation, taking of field notes, informal conversation and document review were used to collect data in two units of a residential aged care home. Each unit had one nurse administer medication. Seven nurses were observed over 12 morning shifts. Unit 1 used electronic medication administration records and Unit 2 used paper-based records.Results: No significant difference between the two units was found in the nursing time spent on various activities in a medication round, including documentation, verbal communication, medication administration, infection control and transit. Comparison of the medication administration processes between the electronic and paper-based medication administration records identified a procedural problem which violated the organization's documentation requirement. This problem was documenting before providing medication to a resident when using the paper-based records. It was not observed with the electronic medication administration records. Benefits of introducing the electronic medication administration records included improving nurses' compliance with documentation requirements, freedom from the error of signing twice, reducing the possibility of forgetting to medicate a resident, facilitating nurses to record the time of medication administration to a resident and increasing documentation space. Unintended adverse consequences of introducing the electronic medication administration records included inadequate information about residents, late addition of a new resident's medication profile in the records and nurses' forgetting to medicate a resident due to power outage of the portable device.Conclusions: The electronic medication administration records may not change nursing time spent on various activities in a medication round or substantially alter the medication administration processes, but can generate both benefits and unintended adverse consequences. Future research may investigate whether and how the adverse consequences can be prevented. [ABSTRACT FROM AUTHOR]

Objective: This paper presents benchmarking results of human epithelial type 2 (HEp-2) interphase cell image classification methods on a very large dataset. The indirect immunofluorescence method applied on HEp-2 cells has been the gold standard to identify connective tissue diseases such as systemic lupus erythematosus and Sjögren's syndrome. However, the method suffers from numerous issues such as being subjective, time consuming and labor intensive. This has been the main motivation for the development of various computer-aided diagnosis systems whose main task is to automatically classify a given cell image into one of the predefined classes.Methods and Material: The benchmarking was performed in the form of an international competition held in conjunction with the International Conference of Image Processing in 2013: fourteen teams, composed of practitioners and researchers in this area, took part in the initiative. The system developed by each team was trained and tested on a very large HEp-2 cell dataset comprising over 68,000 images of HEp-2 cell. The dataset contains cells with six different staining patterns and two levels of fluorescence intensity. For each method we provide a brief description highlighting the design choices and an in-depth analysis on the benchmarking results.Results: The staining pattern recognition accuracy attained by the methods varies between 47.91% and slightly above 83.65%. However, the difference between the top performing method and the seventh ranked method is only 5%. In the paper, we also study the performance achieved by fusing the best methods, finding that a recognition rate of 85.60% is reached when the top seven methods are employed.Conclusions: We found that highest performance is obtained when using a strong classifier (typically a kernelised support vector machine) in conjunction with features extracted from local statistics. Furthermore, the misclassification profiles of the different methods highlight that some staining patterns are intrinsically more difficult to recognize. We also noted that performance is strongly affected by the fluorescence intensity level. Thus, low accuracy is to be expected when analyzing low contrasted images. [ABSTRACT FROM AUTHOR]

Background: Over the past 30 years, the international conference on Artificial Intelligence in MEdicine (AIME) has been organized at different venues across Europe every 2 years, establishing a forum for scientific exchange and creating an active research community. The Artificial Intelligence in Medicine journal has published theme issues with extended versions of selected AIME papers since 1998.Objectives: To review the history of AIME conferences, investigate its impact on the wider research field, and identify challenges for its future.Methods: We analyzed a total of 122 session titles to create a taxonomy of research themes and topics. We classified all 734 AIME conference papers published between 1985 and 2013 with this taxonomy. We also analyzed the citations to these conference papers and to 55 special issue papers.Results: We identified 30 research topics across 12 themes. AIME was dominated by knowledge engineering research in its first decade, while machine learning and data mining prevailed thereafter. Together these two themes have contributed about 51% of all papers. There have been eight AIME papers that were cited at least 10 times per year since their publication.Conclusions: There has been a major shift from knowledge-based to data-driven methods while the interest for other research themes such as uncertainty management, image and signal processing, and natural language processing has been stable since the early 1990s. AIME papers relating to guidelines and protocols are among the most highly cited. [ABSTRACT FROM AUTHOR]

Chronic diseases are becoming one of the world's leading causes of death and disability. By 2020, it is predicted to account for almost three quarters of all deaths. A potential approach to monitor patients with chronic diseases is the implementation of home healthcare systems, using new technologies. The Internet of Things (IoT) and the Radio Frequency Identification (RFID) technologies are evolving rapidly with innovative applications, particularly in the healthcare sector. The aim of this paper is to develop a Tele-health system, based on IoT technology, for monitoring elderly individuals suffering from Alzheimer's. This paper describes a working prototype that is able to capture the vital signs and deliver the desired data care remotely for elderly patients staying at home, using wearable ECG wireless sensor. A UHF passive wearable RFID wristband is used to monitor the whereabouts of the elderly. This prototype is successfully tested on a number of patients at the King Fahd University of Petroleum and Minerals (KFUPM) Medical Centre in Saudi Arabia. [ABSTRACT FROM AUTHOR]

Abstract: Objective: The goal of this study was to examine the effects of medical notes (MD) in an electronic medical records (EMR) system on doctors’ work practices at an Emergency Department (ED). Methods: We conducted a six-month qualitative study, including in situ field observations and semi-structured interviews, in an ED affiliated with a large teaching hospital during the time periods of before, after, and during the paper-to-electronic transition of the rollout of an EMR system. Data were analyzed using open coding method and various visual representations of workflow diagrams. Results: The use of the EMR in the ED resulted in both direct and indirect effects on ED doctors’ work practices. It directly influenced the ED doctors’ documentation process: (i) increasing documentation time four to five fold, which in turn significantly increased the number of incomplete charts, (ii) obscuring the distinction between residents’ charting inputs and those of attendings, shifting more documentation responsibilities to the residents, and (iii) leading to the use of paper notes as documentation aids to transfer information from the patient bedside to the charting room. EMR use also had indirect consequences: it increased the cognitive burden of doctors, since they had to remember multiple patients’ data; it aggravated doctors’ multi-tasking due to flexibility in the system use allowing more interruptions; and it caused ED doctors’ work to become largely stationary in the charting room, which further contributed to reducing doctors’ time with patients and their interaction with nurses. Discussion: We suggest three guidelines for designing future EMR systems to be used in teaching hospitals. First, the design of documentation tools in EMR needs to take into account what we called “note-intensive tasks” to support the collaborative nature of medical work. Second, it should clearly define roles and responsibilities. Lastly, the system should provide a balance between flexibility and interruption to better manage the complex nature of medical work and to facilitate necessary interactions among ED staff and patients in the work environment. [Copyright &y& Elsevier]

Highlights • There are no significant studies that provide a guide for the developers of therapeutic system interfaces for attention deficit in children. • Through a reverse engineering process, it is possible to extract patterns from existing mobile applications. • Currently in the market there are no more than 30 applications that support the therapeutic process of attention deficit in children. • Through the patterns extracted from the proposed methodology, an important starting point for the construction of a guide for the design of interfaces for the attention deficit in children is defined. Abstract The lack of guidelines that help to design interfaces for the treatment of attention deficit in children, has made it necessary to perform a reverse engineering process through which patterns can be extracted considering the review of existing Android mobile applications. However, this process is not simple. This paper presents the methodology for a reverse engineering process applied in Android applications that consists of 3 main steps: the selection of applications, the selection of patterns and the analysis of existing patterns in the selected applications. In the same way, some important contributions are presented, such as the selection of patterns and common characteristics found among the applications for the treatment of attention deficit like the use of the Call to Action Button pattern, the use of Tactile (tap), use of sounds and the use of static images. [ABSTRACT FROM AUTHOR]

Abstract: Purpose: To determine whether the introduction of an electronic nursing documentation system in a nursing home reduces the proportion of time nursing staff spend on documentation, and to use this information in evaluating the usefulness of the system in improving the work of nursing staff. Methods: An observational work sampling study was conducted in 2009 and 2010, 2months before, and 3, 6 and 12months after the introduction of an electronic nursing documentation system. An observer (ENM) used a work classification tool to record documentation activities being performed using paper and with a computer by nursing staff at particular times for periods of 5days. Results: Three hundred and eighty three (383) activities were recorded before implementation of the electronic system, 472 activities at 3months, 502 at 6months, and 338 at 12months after implementation. There was no significant difference between the proportion of time nursing staff spent on documentation 2months before and 3months after the implementation of the electronic system. Six months after implementation, the proportion of time on documentation increased significantly and after 12months, settled back to original levels that were recorded in the paper-based system. Over half of the proportion of time on documentation at 6 and 12months after implementation was spent on paper documentation tasks. Conclusion: Introduction of an electronic nursing documentation system did not reduce the proportion of time nursing staff spent on documentation. This may in part have been a result of the practice of documenting some information items on paper and others on a computer. To reduce the use of paper documentation or to achieve a paper-free documentation environment in this setting, an in-depth understanding of nursing staff''s information needs, and documentation workflow is necessary. [Copyright &y& Elsevier]

Abstract: Objective: To evaluate the problems experienced after implementing a computerized physician order entry (CPOE) system, their possible root causes, and the responses of providers in order to incorporate the system into daily workflow. Methods: A qualitative study in the medication-use process after implementation of a CPOE system in an academic hospital in The Netherlands. Data included 21 interviews with clinical end-users, paper-based and system-generated documents used daily in the process, and educational materials used to train users. Findings: The problems in the medication-use process included cognitive overload on physicians and nurses, unmet information needs, miscommunication of orders and ideas, problematic coordination of interrelated tasks between co-working professionals, a potentially faulty administration phase, and suboptimal monitoring of the medication plans. These problems were mainly rooted in the lack of mobile computer devices, the uneasy integration of coexisting electronic and paper-based systems, suboptimal usability of the system, and certain organizational factors with regard to procuring drugs affecting the technology use. Various types of workarounds were used to address the difficulties, including phone calls, taking multiple paper notes, issuing paper-based and verbal orders, double-checking, using other patients’ procured drugs or another department''s drug supply, and modifying and annotating the printed orders. Conclusion: This study shows how providers are actively involved in working around the interruptions in workflow by bypassing the technology or adapting the work processes. Although certain workarounds help to maintain smooth workflow and/or to ensure patient safety, others may burden providers by necessitating extra time and effort and/or endangering patient safety. It is important that workarounds having a negative nature are recognized and discussed in order to find solutions to mitigate their effects. [Copyright &y& Elsevier]

Abstract: Myocardial infarction (MI) has been the major cause of mortality in humans. The diagnostic process of MI in humans is critical and requires careful examination of the general symptoms, heart activity rate and blood chemistry apart from considering the patient history and contextual information of the diagnostic process. The manual diagnostic process often results in high misclassification rate due to the higher level of complexity involved therein. Thus, computer-based diagnostic systems have been developed to assist the medical practitioners for accurately diagnosing MI. However, most of the computer-based techniques are unable to handle and incorporate contextual information associated with the diagnostic process effectively. This paper aims at enhancing the computer aided diagnostic performance and solving the problem of handling contextual information through the development of a novel nature-inspired computational model. The model presented in this paper is based on the defense mechanism associated with the Human Digestive System. It incorporates multi-level decision making approach and the reasoning behind diagnostic indications at different levels of diagnostic process. The proposed diagnostic system, implemented using MATLAB, has been tested on real medical data set. The experimental results of the proposed model have been compared with five standard AI-based classification techniques. The results obtained suggest that the new classification approach presented in this paper is better than the standard AI-based classification solutions in most cases. [ABSTRACT FROM AUTHOR]

Abstract: Electronic patient records (EPRs) contain a wealth of patient-related data and capture clinical problem-solving experiences and decisions. Excelicare is such a system which is also a platform for the national generic clinical system in the UK. Objective: This paper presents, ExcelicareCBR, a case-based reasoning (CBR) system which has been developed to complement Excelicare. Objective of this work is to integrate CBR to support clinical decision making by harnessing electronic patient records for clinical experience reuse. Methods: CBR is a proven problem solving methodology in which past solutions are reused to solve new problems. A key challenge that we address in this paper is how to extract and represent a case from an EPR. Using an example from the lung cancer domain we demonstrate our generic case representation approach where Excelicare fields are mapped to case features. Once the case base is populated with cases containing data from the EPRs database a standard weighted k-nearest neighbour algorithm combined with a genetic algorithm based feature weighting mechanism is used for case retrieval and reuse. Conclusions: We conclude that incorporating case authoring functionality and a generic retrieval mechanism were key to successful integration of ExcelicareCBR. This paper also demonstrates how the application of CBR can enable sharing of lessons learned through the retrieval and reuse of EPRs captured as cases in a case base. [Copyright &y& Elsevier]

Abstract: Objectives: This paper aims at systematizing the ways in which the contextual knowledge embedded in the case library can support decision making, within case-based reasoning (CBR) systems. In particular, CBR applications to the medical domain are considered. Methods and material: After a quick survey on the definition and on the role of context in artificial intelligence research, we have focused on CBR, with a particular emphasis on medical applications. In this field, we have identified a number of very recent contributions, which strongly recognize context per se as a major knowledge source. These contributions propose to maintain and to rely on contextual information, in order to support human reasoning in different fashions. Results: We have distinguished three main directions in which contextual knowledge can be resorted to, in order to optimize physicians’ decision making. Such directions can be summarized as follows: (1) to reduce the search space in the case retrieval step; (2) to maintain the overall knowledge content always valid and up to date, and (3) to adapt knowledge application and reasoning to local/personal constraints. We have also properly categorized the surveyed works within these three clusters, and identified the most significant ones, able to exploit contextual knowledge along more than one direction. Conclusions: Innovative applications of the contextual knowledge recorded in the case library, described and systematized in this paper, can trace promising research directions for the future. [Copyright &y& Elsevier]

Abstract: Application of biomechanical modeling techniques in the area of medical image analysis and surgical simulation implies two conflicting requirements: accurate results and high solution speeds. Accurate results can be obtained only by using appropriate models and solution algorithms. In our previous papers we have presented algorithms and solution methods for performing accurate nonlinear finite element analysis of brain shift (which includes mixed mesh, different non-linear material models, finite deformations and brain–skull contacts) in less than a minute on a personal computer for models having up to 50,000 degrees of freedom. In this paper we present an implementation of our algorithms on a graphics processing unit (GPU) using the new NVIDIA Compute Unified Device Architecture (CUDA) which leads to more than 20 times increase in the computation speed. This makes possible the use of meshes with more elements, which better represent the geometry, are easier to generate, and provide more accurate results. [ABSTRACT FROM AUTHOR]

Abstract: Objective: This paper reviews a methodology for evolving fuzzy classification which allows data to be processed in online mode by recursively modifying a fuzzy rule base on a per-sample basis from data streams. In addition, it shows how this methodology can be improved and applied to the field of diagnostics, for two popular medical problems. Method: The vast majority of existing methodologies for fuzzy medical diagnostics require the data records to be processed in offline mode, as a batch. Unfortunately this allows only a snapshot of the actual domain to be analysed. Should new data records become available they require cost sensitive calculations due to the fact that re-learning is an iterative procedure. eClass is a relatively new architecture for evolving fuzzy rule-based systems, which overcomes these problems. However, it is data order dependent as different orders of the data result into different rule bases. Nonetheless, it is shown that models of eClass can be improved by arranging the order of the incoming data using a simple optimization strategy. Results: In regards to the Pima Indians diabetes dataset, an accuracy of 79.37% was obtained, which is 0.84% lower than the highest in the literature. The proposed optimization strategy increased the accuracy and specificity of the model by 4.05% and 7.63% respectively. For the dermatology dataset, an accuracy of 97.55% was obtained, which is 1.65% lower than the highest in the literature. In this case, the proposed optimization strategy improved the accuracy of the model by 4.82%. The improved algorithm has been compared to other existing algorithms and seems to outperform the majority. Conclusions: This paper has shown that eClass can effectively be applied to the classification of diabetes and dermatological diseases from discrete numerical samples. The results of using a novel optimization strategy indicate that the accuracy of eClass models can be further improved. Finally, the system can mine human readable rules which could enable medical experts to gain better understanding of a sample under analysis throughout the traditional diagnostic process. [Copyright &y& Elsevier]

Abstract: Purpose: The agent-oriented paradigm has emerged as a viable approach for the development of autonomic systems in the healthcare domain. This paper reviews representative works in this area in order to identify the main research lines and study their level of applicability. Moreover, from the analysis of those works and the authors’ own experiences, some lines of future research are suggested. Methods: This paper presents a review of the literature (2002–2008) of applications of agents in healthcare collected from medical databases as well as international conferences. Results: 15 agent-based systems were selected according to a set of criteria of work relevancy. Their internal architecture as well as communication-based coordination techniques were reviewed. A classification considering the main goal of the systems has been made. For each category, a discussion of the suitability of agent technology in resolving healthcare problems is presented. Conclusions: Agent-based systems offer added values over classical software approaches (e.g., reusability, reliability, flexibility, robustness, maintainability and adaptability). Furthermore, agent technology supports the integration of legacy systems, tackling the shortcomings of centralised systems, such as performance bottlenecks, resource limitations, and different kinds of failures. During the review, we found a huge number of contributions in this area, showing a growing interest of researchers. However, most of the analysed systems are only prototypes, they are not widely deployed in real environments and they are difficult to extend to others domains. Several aspects (security, reusability, modularity, personalisation, system maintenance) should be studied carefully in the next years in order to bring agent technology to real settings. [Copyright &y& Elsevier]

Abstract: Background: Medication errors in hospital discharge summaries have the potential to cause serious harm to patients. These errors are generally associated with manual transcription of medications between medication charts and discharge summaries. Studies also show junior doctors are more likely to contribute to discharge medication error rates. Electronic discharge summaries have the potential to reduce discharge medication errors to ensure the safe handover of care to the primary care provider. Objectives: (1) Quantify and compare the medication transcription error rate from handwritten medications on manual discharge summaries to typed medications on electronic discharge summaries, and (2) examine the quality of medication documentation according to the level of medical training of the doctors who created the discharge summaries. Methods: A retrospective examination of 966 handwritten and 842 electronically generated discharge summaries was conducted in an Australian metropolitan hospital. The electronic discharge summaries at the study site were not integrated with an electronic medication management system and hence discharge medications were typed into the electronic discharge summary by the doctor. The discharge medication documentation in both types of summaries was transcribed, either handwritten or typed, from inpatient medication charts in paper-based medical records. Documentation differences between medications in discharge summaries and inpatient medication charts constituted medication errors. Results: 12.1% of handwritten and 13.3% of electronic summaries contained medication errors. The highest number of errors occurred with cardiovascular drugs. Medication omission was the commonest error. The confidence intervals of all odds ratios indicate handwritten and electronic summaries were similar for all areas of medication error. Error rates regarding all 13,566 individual medications for the 1808 summaries were similar by doctor medical training level (intern, resident, and registrar). Conclusion: Similar medication error rates in handwritten and electronic summaries may be due to the common factor of transcription, either handwritten or typed, known to be associated with medication errors. Clinical information systems evolve and often in the early stages of implementation electronic discharge summaries are integrated with existing paper-based patient record systems. Automatic transfer of medications from an electronic medication management system to the electronic discharge summary holds the potential to reduce medication errors through the elimination of the transcription process. [Copyright &y& Elsevier]

Abstract: Introduction: Evaluations of computerized clinical decision support systems (CDSS) typically focus on clinical performance changes and do not include social, organizational, and contextual characteristics explaining use and effectiveness. Studies of CDSS for intensive insulin therapy (IIT) are no exception, and the literature lacks an understanding of effective computer-based IIT implementation and operation. Results: This paper presents (1) a literature review of computer-based IIT evaluations through the lens of institutional theory, a discipline from sociology and organization studies, to demonstrate the inconsistent reporting of workflow and care process execution and (2) a single-site case study to illustrate how computer-based IIT requires substantial organizational change and creates additional complexity with unintended consequences including error. Discussion: Computer-based IIT requires organizational commitment and attention to site-specific technology, workflow, and care processes to achieve intensive insulin therapy goals. The complex interaction between clinicians, blood glucose testing devices, and CDSS may contribute to workflow inefficiency and error. Evaluations rarely focus on the perspective of nurses, the primary users of computer-based IIT whose knowledge can potentially lead to process and care improvements. Conclusion: This paper addresses a gap in the literature concerning the social, organizational, and contextual characteristics of CDSS in general and for intensive insulin therapy specifically. Additionally, this paper identifies areas for future research to define optimal computer-based IIT process execution: the frequency and effect of manual data entry error of blood glucose values, the frequency and effect of nurse overrides of CDSS insulin dosing recommendations, and comprehensive ethnographic study of CDSS for IIT. [Copyright &y& Elsevier]

Abstract: Introduction: Data acquisition is still one of the important challenges to be met in clinical settings. This is even more critic in settings with high cognitive workloads, such as emergency room (ER). Observations in these settings are difficult to realize without biases and there is little means to trace fine acquisition activities done in natural environments, using pen and papers. This study is based on the usage of a digital pen and paper (DPP) technology for the acquisition of triage information by nurses in ER. The DPP technology has been used to ease acquisition using a natural mechanism; it also minimizes the external influence of observation during acquisition activities. The aim of this study is to determine whether data recorded by the DPP technology allows explaining how ER triage nurses use the triage forms in real working conditions. Methodology: The chief physicians of the ER service wanted to have answers about three main concerns pertaining to the triage process: (1) the average time spent during the triage process; (2) the sequence in which the fields of the forms were filled and; (3) the contribution of objective measurements, such as vital signs, to the triage emergency level and decisions. In order to answer these questions, detailed log data recorded by the DPP during form filling as been analyzed and allowed to built several representations of the triage process. In addition, we completed this analysis with ethnographical-like observations. Results: For seven consecutive days, 1183 triage forms have been recorded in the ER for all patients admitted. Among them, 954 forms have been digitalized and 906 forms have been considered as valid and complete. Based on this set of data, the median duration of the triage process is 143s. There are no converging habits in filling the forms and the sequence of filling fields present a high variability. The emphasis of the objective measurements in the decisional process is rather low, as vital signs are recorded in less than 17% of the cases. Conclusion: The DPP technology is an original approach to study data acquisition processes in unbiased conditions. The technical raw data recorded by the DPP allows building the time series of all activities on the paper, therefore letting to constructing several representations of the process. However, the technology is not able to provide information about the context of use, for example interruptions of the form filling processes due to calls or other activities. Therefore, it is necessary to complete these analyses with qualitative approaches such as observational studies and interviews. Noticeably, as a result of this study, the head physicians of ER have redesigned the triage form to enforce the use of objective measurements and ease the data acquisition process. [Copyright &y& Elsevier]

Summary: Objective: One of the toughest challenges in medical diagnosis is uncertainty handling. The detection of intestinal bacteria such as Salmonella and Shigella which cause typhoid fever and dysentery, respectively, is one such challenging problem for microbiologists. They detect the bacteria by the comparison with predefined classes to find the most similar one. Consequently, we observe uncertainty in determining the similarity degrees, and therefore, in the bacteria classification. In this paper, we take an intelligent approach towards the bacteria classification problem by using five similarity measures of fuzzy sets (FSs) and intuitionistic fuzzy sets (IFSs) to examine their capabilities in encountering uncertainty in the medical pattern recognition. Methods: FSs and IFSs are two strong frameworks for uncertainty handling. The membership degree in FSs and both membership and non-membership degrees in IFSs are the operators that these frameworks use to represent the degree of which a member of the universe of discourse belongs to a subset of it. In this paper, the similarity measures, which both frameworks provide are used, so as the intestinal bacteria are detected and classified through uncertainty quantification in feature vectors. Also, the experimental results of using the measures are illustrated and compared. Results: We obtained 263 unknown bacteria from microbiology section of Resalat laboratory in Tehran to examine the similarity measures in practice. Finally, the detection rates of the measures were calculated between which IFS Hausdorf and Mitchel similarity measures scored the best results with 95.27% and 94.48% detection rates, respectively. On the other hand, FS Euclidean distance yielded only 85% detection rate. Conclusions: Our investigation shows that both frameworks have powerful capabilities to cope with the uncertainty in the medical pattern recognition problems. But, IFSs yield better detection rate as a result of more accurate modeling which is involved with incurring more computational cost. Our research also shows that among different IFS similarity measures, IFS Hausdorf and Mitchel ones score the best results. [Copyright &y& Elsevier]

Abstract: The SHARE 1 [1] SHARE was a European Union Framework Programme 6 Information Society Technologies Specific Support Action, project identifier FP6-2005-IST-027694. Its principal deliverable, the integrated road map for healthgrids is at http://eu-share.org/about-share/deliverables-and-documents.html. project (http://www.eu-share.org) was asked to identify the key developments needed to achieve wide adoption and deployment of HealthGrids throughout Europe. The project was asked to organise these as milestones on a road map, so that all technical advances, social actions, economic investments and ethical or legal initiatives necessary for HealthGrids would be seen together in a single coherent document. The full road map includes an extensive analysis of several case studies exploring their technical requirements, full discussion of the ethical, legal, social and economic issues which may impede early deployment, and concludes with an attempt to reconcile the tensions between technological developments and regulatory frameworks. This paper has been restricted to the technical aspects of the project. SHARE built on the work of the ‘HealthGrid’ initiative so we begin by, reviewing work carried out in various European HealthGrid projects and report on joint work with numerous European collaborators. Following many successful HealthGrid projects, HealthGrid published a ‘White Paper’ which establishes the foundations, potential scope and prospects of an approach to health informatics based on a grid infrastructure. The White Paper demonstrates the ways in which the HealthGrid approach supports many modern trends in medicine and healthcare, such as evidence-based practice, integration across levels, from molecules and cells, through tissues and organs to the whole person and community, and the promise of individualised healthcare. SHARE was funded by the European Commission to define a research roadmap for a ‘HealthGrid for Europe’, to be seen as the preferred infrastructure for biomedical and healthcare projects in the European Research Area. [Copyright &y& Elsevier]

Abstract: Purpose: Clinical guidelines are useful tools to standardize and improve health care. The automation of the guideline execution process is a basic step towards its widespread use in medical centres. This paper presents an analysis and a comparison of eight systems that allow the enactment of clinical guidelines in a (semi) automatic fashion. Methods: This paper presents a review of the literature (2000–2007) collected from medical databases as well as international conferences in the medical informatics area. Results: Eight systems containing a guideline execution engine were selected. The language used to represent the guidelines as well as the architecture of these systems were compared. Different aspects have been assessed for each system, such as the integration with external elements or the coordination mechanisms used in the execution of clinical guidelines. Security and terminology issues complement the above study. Conclusions: Although these systems could be beneficial for clinicians and patients, it is an ongoing research area, and they are not yet fully implemented and integrated into existing careflow management systems and hence used in daily practice in health care institutions. [Copyright &y& Elsevier]

Abstract: Objective: To evaluate effects of a natural CPOE implementation in a hospital setting and inform the efficacy of using CPOE rather than traditional paper medication orders. Design: A multiple-baseline, quasi-experimental study of a naturally occurring CPOE intervention, with a non-equivalent control site. Measurements: Compliance with medication-ordering protocols and time to first dose of antibiotics. Results: Medication orders placed using CPOE were significantly more compliant than paper-based medication orders, and first doses of antibiotics were delivered significantly faster when ordered with CPOE than when placed using the standard paper-based system (p <.01). Conclusion: Findings support the use of CPOE and justify the need for interventions to increase CPOE adoption and consistent use among physicians. [Copyright &y& Elsevier]

Abstract: Purpose: Documentation of medical treatment and observation of patients during evacuation from the point of injury to definitive treatment is important both for optimizing patient treatment and managing the evacuation process. The current practice in military medical field documentation uses paper forms and voice communication. There are many shortcomings associated with this approach, especially with respect to information capture and sharing processes. Current research addresses the use of new technology for civilian ambulance-to-hospital communication. The research work presented in this article addresses information capture and sharing in extreme military conditions by evaluating a targeted computerized information system called EvacSys during a military exercise in northern Norway in December 2003. Methods and materials: EvacSys was designed and implemented in close cooperation with military medical personnel in both Norway and the USA. The system was evaluated and compared to the traditional paper-based documentation method during a military exercise. The on-site evaluation was conducted in a military medical platoon in the Norwegian Armed Forces, using questionnaires, semi-structured interviews, observation and video recording to capture the users’ system acceptance. Results: A prototype software system running on a commercial off-the-shelf hardware platform was successfully developed. The evaluation of this system shows that the usability of digital information capturing and sharing are perceived to be at least as good as the traditional paper-based method. The medics found the new digital method to be more viable than the old one. No technical problems were encountered. Conclusions: Our research shows that it is feasible to utilize digital information systems for medical documentation in extreme outdoor environments. The usability concern is of utmost importance, and more research should be put into the design and alignment with existing workflow. Successful digitalization of information at the point of care will provide accurate and timely information for the management of resources during disaster response. [Copyright &y& Elsevier]

Abstract: This paper addresses the issue of how semantic information can be automatically assigned to compound terms, i.e. both a definition and a set of semantic relations. This is particularly crucial when elaborating multilingual databases and when developing cross-language information retrieval systems. The paper shows how morphosemantics can contribute in the constitution of multilingual lexical networks in biomedical corpora. It presents a system capable of labelling terms with morphologically related words, i.e. providing them with a definition, and grouping them according to synonymy, hyponymy and proximity relations. The approach requires the interaction of three techniques: (1) a language-specific morphosemantic parser, (2) a multilingual table defining basic relations between word roots and (3) a set of language-independent rules to draw up the list of related terms. This approach has been fully implemented for French, on an about 29,000 terms biomedical lexicon, resulting to more than 3000 lexical families. A validation of the results against a manually annotated file by experts of the domain is presented, followed by a discussion of our method. [Copyright &y& Elsevier]

Summary: Objective: In this paper, we aim at defining a general-purpose data model and query language coping with both “telic” and “atelic” medical data. Background: In the area of Medical Informatics, there is an increasing realization that temporal information plays a crucial role, so that suitable database models and query languages are needed to store and support it. However, despite the wide range of approaches in the area, in this paper we show that a relevant class of medical data cannot be properly dealt with. Methodology: We first show that data models based on the “point-based” semantics, which is (implicitly or explicitly) assumed by the totality of temporal database approaches, have several limitations when dealing with “telic” data. We then propose a new model (based on the “interval-based” semantics) to cope with such data, and extend the query language accordingly. Results: We propose a new three-sorted model and a query language to properly deal with both “telic” and “atelic” medical data (as well as non-temporal data). Our query language is flexible, since it allows one to switch from “atelic” to “telic” data, and vice versa. Conclusion: In this paper, we demostrate the feasibilty of a database approach copying with both telic and atelic data as needed in several (medical) applications. [Copyright &y& Elsevier]

Summary: Objective: In many medical areas, there exist different regression formulas to predict/evaluate a medical outcome on the same problem, each of them being efficient only in a particular sub-space of the problem space. The paper aims at the development of a generic, incremental learning model that includes all available regression formulas for a particular prediction problem to define local areas of the problem space with their best performing formula along with useful explanation rules. Another objective of the paper is to develop a specific model for renal function evaluation using nine existing formulas. Methods and materials: We have used a connectionist neuro-fuzzy approach and have developed a knowledge-based neural network model (KBNN) which incorporates and adapts incrementally several existing regression formulas and kernel functions. The model incorporates different non-linear regression functions as neurons in its hidden layer and adapts these functions through incremental learning from data in particular local areas of the space. More specifically, each hidden neural node has a pair of functions associated with it—one regression formula, that represents existing knowledge and one Gaussian kernel function, that defines the sub-space of the whole problem space, in which the formula is locally adapted to new data. All these functions are aggregated and changed through incremental learning. The proposed KBNN model is illustrated using a medical dataset of observed patient glomerular filtration rate (GFR) measurements for renal function evaluation. In this case study, the regression function for each cluster is selected by the model from nine formulas commonly used by medical practitioners to predict GFR. 441 GFR data vectors from 141 patients taken from 12 sites in Australia and New Zealand have been used as a case study experimental data set. Results: The proposed GFR prediction model, based on the proposed generic KBNN model, outperforms at least by 10% accuracy any of the individual regression formulas or a standard neural network model. Furthermore, we have derived locally adapted regression formulas to perform best on local clusters of data along with useful explanatory rules. Conclusion: The proposed KBNN model manifests better accuracy then existing regression formulas or neural network models for renal function evaluation and extracts modified formulas that perform well in local areas of the problem space. [Copyright &y& Elsevier]

Background and Purpose: The generalised assumption of health information systems (HIS) success is questioned by a few commentators in the medical informatics field. They point to widespread HIS failure. The purpose of this paper was therefore to develop a better conceptual foundation for, and practical guidance on, health information systems failure (and success). Methods: Literature and case analysis plus pilot testing of developed model. Results: Defining HIS failure and success is complex, and the current evidence base on HIS success and failure rates was found to be weak. Nonetheless, the best current estimate is that HIS failure is an important problem. The paper therefore derives and explains the "design-reality gap" conceptual model. This is shown to be robust in explaining multiple cases of HIS success and failure, yet provides a contingency that encompasses the differences which exist in different HIS contexts. The design-reality gap model is piloted to demonstrate its value as a tool for risk assessment and mitigation on HIS projects. It also throws into question traditional, structured development methodologies, highlighting the importance of emergent change and improvisation in HIS. Conclusions: The design-reality gap model can be used to address the problem of HIS failure, both as a post hoc evaluative tool and as a pre hoc risk assessment and mitigation tool. It also validates a set of methods, techniques, roles and competencies needed to support the dynamic improvisations that are found to underpin cases of HIS success. [ABSTRACT FROM AUTHOR]

Summary: Objective: The objective of this paper is to demonstrate how a formal spatial theory can be used as an important tool for disambiguating the spatial information embodied in biomedical ontologies and for enhancing their automatic reasoning capabilities. Method and materials: This paper presents a formal theory of parthood and location relations among individuals, called Basic Inclusion Theory (BIT). Since biomedical ontologies are comprised of assertions about classes of individuals (rather than assertions about individuals), we define parthood and location relations among classes in the extended theory Basic Inclusion Theory for Classes (BIT+Cl). We then demonstrate the usefulness of this formal theory for making the logical structure of spatial information more precise in two ontologies concerned with human anatomy: the Foundational Model of Anatomy (FMA) and GALEN. Results: We find that in both the FMA and GALEN, class-level spatial relations with different logical properties are not always explicitly distinguished. As a result, the spatial information included in these biomedical ontologies is often ambiguous and the possibilities for implementing consistent automatic reasoning within or across ontologies are limited. Conclusion: Precise formal characterizations of all spatial relations assumed by a biomedical ontology are necessary to ensure that the information embodied in the ontology can be fully and coherently utilized in a computational environment. This paper can be seen as an important beginning step toward achieving this goal, but much more work along these lines is required. [Copyright &y& Elsevier]

Summary: Purpose:: This paper appraises empirical studies examining the impact of clinical information-retrieval technology on physicians and medical students. Methods:: The world literature was reviewed up to February 2004. Two reviewers independently identified studies by scrutinising 3368 and 3249 references from bibliographic databases. Additional studies were retrieved by hand searches, and by searching ISI Web of Science for citations of articles. Six hundred and five paper-based articles were assessed for relevance. Of those, 40 (6.6%) were independently appraised by two reviewers for relevance and methodological quality. These articles were quantitative, qualitative or of mixed methods, and 26 (4.3%) were retained for further analysis. For each retained article, two teams used content analysis to review extracted textual material (quantitative results and qualitative findings). Results:: Observational studies suggest that nearly one-third of searches using information-retrieval technology may have a positive impact on physicians. Two experimental and three laboratory studies do not reach consensus in support of a greater impact of this technology compared with other sources of information, notably printed educational material. Clinical information-retrieval technology may affect physicians, and further research is needed to examine its impact in everyday practice. [Copyright &y& Elsevier]

Summary: The paper provides detailed descriptions of general practitioners (GPs’) interactions, both with their computers and their patients, with the aim of facilitating the detailed understanding of how GPs use their computers while in consultation with patients. The focus is on the coordinated activities of the doctor and patient and the multitasking that is required during consultation. The data consists of primary care doctor–patient consultations for asthma and angina where clinical scenarios, supported by dummy electronic and paper records for use by the doctor, were played out. Although not ‘naturally occurring’, the mock scenario is a traditional medical training technique. Objective and methods:: This paper describes and demonstrates a data transcription methodology, involving seven discrete levels of activities, developed to account for the intricate multitasking that occurs in a GP consultation. The transcription method, developed to support the evaluation of a prototype medical prescribing decision support system (Prodigy) for use by general practitioners in consultation with patients, builds on data description techniques from conversation analysis (CA) and video analysis (VA). Conclusions:: It is suggested that the methodology described could also be applicable to other scenarios involving the observation of human–computer–human interaction. [Copyright &y& Elsevier]

Mediative fuzzy logic is an approach able to deal with inconsistent information providing a solution when contradiction exists. The aim of this paper is to design an expert system based on this type of fuzzy logic in order to diagnose a possible heart disease for a patient. Our proposed system is an extension of the standard Mamdani fuzzy logic controller and contains 44 rules of the type single input-single output. The system works with 11 variables as inputs and one variable as output. [ABSTRACT FROM AUTHOR]

Diagnostic information regarding the health status of the corneal endothelium may be obtained by analyzing the size and the shape of the endothelial cells in specular microscopy images. Prior to the analysis, the endothelial cells need to be extracted from the image. Up to today, this has been performed manually or semi-automatically. Several approaches to automatic segmentation of endothelial cells exist; however, none of them is perfect. Therefore this paper proposes to perform cell segmentation using a U-Net-based convolutional neural network. Particularly, the network is trained to discriminate pixels located at the borders between cells. The edge probability map outputted by the network is next binarized and skeletonized in order to obtain one-pixel wide edges. The proposed solution was tested on a dataset consisting of 30 corneal endothelial images presenting cells of different sizes, achieving an AUROC level of 0.92. The resulting DICE is on average equal to 0.86, which is a good result, regarding the thickness of the compared edges. The corresponding mean absolute percentage error of cell number is at the level of 4.5% which confirms the high accuracy of the proposed approach. The resulting cell edges are well aligned to the ground truths and require a limited number of manual corrections. This also results in accurate values of the cell morphometric parameters. The corresponding errors range from 5.2% for endothelial cell density, through 6.2% for cell hexagonality to 11.93% for the coefficient of variation of the cell size. [ABSTRACT FROM AUTHOR]

Background: Physician-patient communication is essential in the physician-patient relationship. Concerns were raised about the impact of the computer on this relationship with the increase in use of electronic medical records (EMR). Most studies addressed the physician's perspective and only few explored the patient's perspective.Aim: This study aims to assess the patient's perspective of the effect of the physician's computer use during the clinical encounter on the interpersonal and communication skills of the physician using a validated communication assessment tool (CAT).Design and Settings: This is a cross-sectional survey of three hundred eighty-two patients who visited the family medicine clinics (FMC) at the American University of Beirut Medical Center (AUBMC).Material and Methods: At the end of the visit with the physician, the patients were approached by the clinical assistant to fill a paper-based questionnaire privately in the waiting room to measure communication skills of physicians using CAT.Results: Nearly two-thirds of the patients (62%) did not consider that using the computer by their physician during the visit would negatively affect the patient-doctor communication. Patients rated their physician with a higher communication score when there was an ongoing relationship between the physician and the patient. Higher communication scores were reported for extensive use of the computer by the physician to check results (p<0.001), to retrieve patient record information (p<0.001) and to educate patients (p<0.001) as compared to less use.Conclusions: Physician-patient communication was not negatively affected by the physician use of the computer as rated by patients. An ongoing relationship with the physician remains a significant predictor of better physician-patient communication even in the presence of the computer. [ABSTRACT FROM AUTHOR]

Motivation: Patients under radiotherapy for head-and-neck cancer often suffer of long-term xerostomia, and/or consistent shrinkage of parotid glands. In order to avoid these drawbacks, adaptive therapy can be planned for patients at risk, if the prediction is obtained timely, before or during the early phase of treatment. Artificial intelligence can address the problem, by learning from examples and building classification models. In particular, fuzzy logic has shown its suitability for medical applications, in order to manage uncertain data, and to build transparent rule-based classifiers. In previous works, clinical, dosimetric and image-based features were considered separately, to find different possible predictors of parotid shrinkage. On the other hand, a few works reported possible image-based predictors of xerostomia, while the combination of different types of features has been little addressed.Objective: This paper proposes the application of a novel machine learning approach, based on both statistics and fuzzy logic, aimed at the classification of patients at risk of i) parotid gland shrinkage and ii) 12-months xerostomia. Both problems are addressed with the aim of individuating predictors and models to classify respective outcomes.Methods: Knowledge is extracted from a real dataset of radiotherapy patients, by means of a recently developed method named Likelihood-Fuzzy Analysis, based on the representation of statistical information by fuzzy rule-based models. This method enables to manage heterogeneous variables and missing data, and to obtain interpretable fuzzy models presenting good generalization power (thus high performance), and to measure classification confidence. Numerous features are extracted to characterize patients, coming from different sources, i.e. clinical features, dosimetric parameters, and radiomics-based measures obtained by texture analysis of Computed Tomography images. A learning approach based on the composition of simple models in a more complicated one allows to consider the features separately, in order to identify predictors and models to use when only some data source is available, and obtaining more accurate results when more information can be combined.Results: Regarding parotid shrinkage, a number of good predictors is detected, some already known and confirmed here, and some others found here, in particular among radiomics-based features. A number of models are also designed, some using single features and others involving models composition to improve classification accuracy. In particular, the best model to be used at the initial treatment stage, and another one applicable at the half treatment stage are identified. Regarding 12-months toxicity, some possible predictors are detected, in particular among radiomics-based features. Moreover, the relation between final parotid shrinkage rate and 12-months xerostomia is evaluated. The method is compared to the naïve Bayes classifier, which reveals similar results in terms of classification accuracy and best predictors. The interpretable fuzzy rule-based models are explicitly presented, and the dependence between predictors and outcome is explained, thus furnishing in some cases helpful insights about the considered problems.Conclusion: Thanks to the performance and interpretability of the fuzzy classification method employed, predictors of both parotid shrinkage and xerostomia are detected, and their influence on each outcome is revealed. Moreover, models for predicting parotid shrinkage at initial and half radiotherapy stages are found. [ABSTRACT FROM AUTHOR]

Premature ventricular contraction (PVC), which is a common form of cardiac arrhythmia caused by ectopic heartbeat, can lead to life-threatening cardiac conditions. Computer-aided PVC detection is of considerable importance in medical centers or outpatient ECG rooms. In this paper, we proposed a new approach that combined deep neural networks and rules inference for PVC detection. The detection performance and generalization were studied using publicly available databases: the MIT-BIH arrhythmia database (MIT-BIH-AR) and the Chinese Cardiovascular Disease Database (CCDD). The PVC detection accuracy on the MIT-BIH-AR database was 99.41%, with a sensitivity and specificity of 97.59% and 99.54%, respectively, which were better than the results from other existing methods. To test the generalization capability, the detection performance was also evaluated on the CCDD. The effectiveness of the proposed method was confirmed by the accuracy (98.03%), sensitivity (96.42%) and specificity (98.06%) with the dataset over 140,000 ECG recordings of the CCDD. [ABSTRACT FROM AUTHOR]

Breast and pectoral muscle segmentation is an essential pre-processing step for the subsequent processes in computer aided diagnosis (CAD) systems. Estimating the breast and pectoral boundaries is a difficult task especially in mammograms due to artifacts, homogeneity between the pectoral and breast regions, and low contrast along the skin-air boundary. In this paper, a breast boundary and pectoral muscle segmentation method in mammograms is proposed. For breast boundary estimation, we determine the initial breast boundary via thresholding and employ Active Contour Models without edges to search for the actual boundary. A post-processing technique is proposed to correct the overestimated boundary caused by artifacts. The pectoral muscle boundary is estimated using Canny edge detection and a pre-processing technique is proposed to remove noisy edges. Subsequently, we identify five edge features to find the edge that has the highest probability of being the initial pectoral contour and search for the actual boundary via contour growing. The segmentation results for the proposed method are compared with manual segmentations using 322, 208 and 100mammograms from the Mammographic Image Analysis Society (MIAS), INBreast and Breast Cancer Digital Repository (BCDR) databases, respectively. Experimental results show that the breast boundary and pectoral muscle estimation methods achieved dice similarity coefficients of 98.8% and 97.8% (MIAS), 98.9% and 89.6% (INBreast) and 99.2% and 91.9% (BCDR), respectively. [ABSTRACT FROM AUTHOR]

Computed tomography (CT) is one of the most widely used methods in Medical Imaging. Despite of its relevance in the diagnosis of diseases with a high impact in our society (such as cancer), it is one of the most potentially harmful modalities. CT requires a high X-ray dose to be induced to the patients. Solving the CT Image Reconstruction problem iteratively in order to approximate the solution allows working with only a subset of the input data required by direct methods. This directly implies a reduction of the radiation received by the patient and a strong reduction on the potential morbidity. Therefore, we aim to study the feasibility of such methods for their actual application, with the purpose of concluding if they are accurate and can obtain good quality images with a lower dose of X rays. This paper discusses the use of containers within a Grid Computing platform to perform a thorough study of all the possible configurations and parameters of various methods being developed to reconstruct CT images iteratively, which could lead to find the optimal configuration of the parameters. The work compares two approaches for managing the software dependencies of the code: store the software libraries on a Storage Element and using containers for executing the job. [ABSTRACT FROM AUTHOR]

Individual-based models are convenient to study the spread of infectious diseases in combination with heterogeneous social mixing patterns. In this paper, we present an open-source and generic, individual-based simulator for the transmission of infectious diseases (Stride) in which social contact rates are dependent on both the context and the age of the individuals. Using a case study, we illustrate the effect of different social contact hypotheses on disease dynamics. [ABSTRACT FROM AUTHOR]

This paper compares the accuracy of different statistical methods for influenza peaks prediction. The research demonstrates the performance of long short-term memory neural networks along with the results obtained by proved statistical methods, which are the Serfling model, averaging and point-to-point estimates. The prediction accuracy of the methods is compared with the accuracy of the modeling approaches. Possible applications of the methods and the ways to improve their accuracy are discussed. [ABSTRACT FROM AUTHOR]

Recently, Electroencephalogram (EEG)-based computer-aided (CAD) techniques have shown their promise as decision-making tools to diagnose major depressive disorder (MDD) or simply depression. Although the research results have motivated the use of CAD techniques to help assist psychiatrists in clinics yet their clinical translation has been less clear and remains a research topic. In this paper, a proposed machine learning (ML) scheme was tested and validated with resting-state EEG data involving 33 MDD patients and 30 healthy controls. The EEG-derived measures such as power of different EEG frequency bands and EEG alpha interhemispheric asymmetry were investigated as input features to the proposed ML scheme to discriminate the MDD patients and healthy controls, and to prove their feasibility for diagnosing depression. The acquired EEG data were subjected to noise removal and feature extraction. As a result, a data matrix was constructed by the columns-wise concatenation of the extracted features. Furthermore, the z-score standardization was performed to standardize each column of the data matrix according to its mean and variance. The data matrix may have redundant and irrelevant features; therefore, to determine the most significant features, a weight was assigned to each feature based on its ability to separate the target classes according to the criterion, i.e., receiver operating characteristics (roc). Hence, only the most significant features were used for testing and training the classifier models: Logistic regression (LR), Support vector machine (SVM), and Naïve Bayesian (NB). Finally, the classifier models were validated with 10-fold cross-validation that has provided the performance metrics such as test accuracy, sensitivity, and specificity. As a result of the investigations, most significant features such as EEG signal power and EEG alpha interhemispheric asymmetry from the brain areas such as frontal, temporal, parietal and occipital were found significant. In addition, the proposed ML framework proved automatic identification of aberrant EEG patterns specific to disease conditions and provide high classification results i.e., LR classifier (accuracy = 97.6%, sensitivity = 96.66%, specificity = 98.5%), NB classification (accuracy = 96.8%, sensitivity = 96.6%, specificity = 97.02%), and SVM (accuracy = 98.4%, sensitivity = 96.66%, specificity = 100%). In conclusion, the proposed ML scheme along with the EEG signal power and EEG alpha interhemispheric asymmetry are proved suitable as clinical diagnostic tools for MDD. [ABSTRACT FROM AUTHOR]

As research on Health Behavior Change Support Systems (HBCSS) proliferates, meaningful management of the different findings is becoming a challenge. We argue that for the field to evolve, it is important to establish the study of HBCSSs as an independent research area, which means that instead of only applying theories from related disciplines to HBCSSs, we need to significantly extend and adapt these theories, or develop new theories, to explain the phenomena that are encountered. Current research in HBCSSs is carried out in different disciplines, with a different approach in each of these disciplines. However, both the CeHRes roadmap and the Persuasive System Design Model show that HBCSSs are complex and the development and evaluation of these systems need to deal with this complexity to be successful. Therefore, an integrative approach is needed to study the combination of content, system, and context. Although research into the separate areas has yielded important findings that are discussed in this paper, we argue that an integrated approach of HBCSSs is useful. We discuss two examples to show how a truly integrative approach can be utilized to enhance the field involving tailoring, personalization, and support. In conclusion we present three practical and relatively easy-to-implement recommendations for researchers who want to contribute to this discipline: Avoid the black box, be specific about the terms used, and look past the borders of one's own discipline. [ABSTRACT FROM AUTHOR]

In this paper, the urinary bladder cancer diagnostic method which is based on Multi-Layer Perceptron and Laplacian edge detector is presented. The aim of this paper is to investigate the implementation possibility of a simpler method (Multi-Layer Perceptron) alongside commonly used methods, such as Deep Learning Convolutional Neural Networks, for the urinary bladder cancer detection. The dataset used for this research consisted of 1997 images of bladder cancer and 986 images of non-cancer tissue. The results of the conducted research showed that using Multi-Layer Perceptron trained and tested with images pre-processed with Laplacian edge detector are achieving AUC value up to 0.99. When different image sizes are compared it can be seen that the best results are achieved if 50×50 and 100×100 images were used. [ABSTRACT FROM AUTHOR]

Computer aided diagnosis (CAD) software is not yet widely used in clinic. This paper aims to identify possible reasons why. Firstly, the technical maturity of CAD is explored through analysis of diagnostic accuracy metrics in one example application, the automated classification of Ioflupane I123 (DaTSCAN) images. Software is developed for image classification based on well- established eigenimage techniques. Using a publicly available database of images an area under the Receiver Operator Curve (AUROC) of 0.980 is achieved. Given these impressive results the main blockage to clinical adoption, both in DaTSCAN classification and potentially in other applications, is likely to relate to wider issues. These are explored with reference to the demands of the National Institute for Health and Care Excellence (NICE) evaluation processes. It is postulated that in order to enable wider adoption a greater focus on proving the safety, efficacy and cost effectiveness of CAD may be required. [ABSTRACT FROM AUTHOR]