SEARCH · Search PubMed
Search indexed PubMed citations on genomics, clinical trials, systematic reviews and public health. Explore titles, authors and supplied subject terms, then open the PubMed record.
Quote a phrase for an exact phrase match. Source license links do not imply unrestricted reuse.
This paper outlines design philosophies and methods for healthcare knowledge systems. Clinical priorities for knowledge are discussed in terms of temporal and individual needs. Book centred organisation of healthcare knowledge, which has proven effective in clinical practice, is proposed as the basis of virtual libraries available at the point of care for target groups of healthcare professionals.
The recognition of clinically significant trends in monitored signals plays an important role in many medical diagnostic applications. A template-based system technique to identify characteristic patterns in time-series data is described, based on fuzzy logic. Fuzzy set theory allows the creation of fuzzy templates from linguistic rules. The resulting fuzzy template system can accommodate multiple time signals, relative or absolute trends, and automatically generates a normalised "goodness of fit" score. The template approach was originally developed for monitoring during anaesthesia but has the potential to be useful in other domains that require temporal pattern recognition.
Estimations of the prevalence of central nervous system involvement in patients with systemic lupus erythematosus (SLE) vary from 25 to 75%. In order to assess possible deficits in memory, attention, and/or reaction time, a battery of neuropsychological tests was administered to 15 patients with SLE and to two matched groups of control subjects; eight patients on corticosteroids and 15 healthy controls. The test battery included the Multiple Choice Word Fluency Test (MWT-B), Benton Visual Memory Scale, Syndrome Short Test (SKT; attention and memory), Attention and Concentration Test (d2), Wechsler Adult Intelligence Scale (WAIS) subtests for Comprehension, Digit Span, Block Design, a Computer Controlled Reaction Time task (CCRT), and a Learning and Memory Test (LGT-3). Results revealed a statistically significant short-term memory deficit (for all six relevant subtests used) and a marked delayed simple reaction time in SLE patients as compared with scores in healthy subjects. An attention deficit as well as the expected difference between the estimated premorbid and actual level of intelligence could not be demonstrated. With three exceptions (SKT-9 figural recognition, Benton Visual Memory, and LGT-3 figural recognition), patients treated with corticosteroids did not differ from healthy controls. They also did not differ from SLE patients in any of the parameters tested. It therefore appears that the demonstrated deficit in short-term memory and reaction time in SLE patients may not only be due to the neuropsychiatric manifestation of SLE but possibly also result from medication side-effects.
DIABNET is a knowledge-based system designed to aid doctors with therapy planning in gestational diabetes. The system core is a qualitative model, implemented by a Causal Probabilistic Network, that is able to detect the insulin effectiveness on a daily basis. DIABNET analyses monitoring data and proposes quantitative changes in insulin therapy and qualitative diet modifications. This paper proposes an evaluation methodology to assess the system performance when working in a real scenario. The methodology manages the absence of a gold standard and includes: a subjective analysis based on questionnaires and an objective analysis based on a quantitative comparison of the system's and experts' proposals. The paper also shows the results of two experiments in which expert diabetologists evaluated the therapeutical advice provided by DIABNET during the follow up of 9 patients with gestational diabetes. DIABNET detected the need of a therapy modification in 92% of the cases showing its appropriateness for automatic alarm generation. Around 80% of the proposals were accepted by experts. The evaluation results are encouraging and allow characterisation of the system's performance when proposing therapy modifications. Evaluation in its turn helps to refine the knowledge managed by DIABNET and enables us to look towards the further clinical use of DIABNET as a decision tool in gestational diabetes integrated in a telemedicine service.
DIABETES is a decision-support system in the field of insulin administration. System performance evaluation is particularly difficult because of the absence of a uniform decision-making model followed by the specialists. The DELPHI method has been selected since it is appropriate for those domains where there is divergence among experts' opinions. The DELPHI approach helps a number of diabetologists arrive at a consensus and thus it facilitates performance evaluation and further knowledge acquisition. Insulin administration regimes, for 100 diabetic subjects, were proposed by DIABETES and five diabetologists (round 1). These suggestions were compiled and forwarded back to the specialists who proposed a second management approach (round 2). In each case, the experts were asked to justify their decision and comment on the suggestions of their colleagues and DIABETES. A novel scoring system for quantification of agreement was adopted. The DELPHI procedure significantly increased the agreement among the diabetologists from 67% to 84% (X2, p = 0.0001). The agreement between experts' and DIABETES recommendations was to a level of 54%. A total of 3500 comments were acquired by the experts.
Text-mining systems are indispensable tools to reduce the increasing flux of information in scientific literature to topics pertinent to a particular interest in focus. Most of the scientific literature is published as unstructured free text, complicating the development of data processing tools, which rely on structured information. To overcome the problems of free text analysis, structured, hand-curated information derived from literature is integrated in text-mining systems to improve precision and recall. In this paper several text-mining approaches are reviewed and the next step in development of text-mining systems, which is based on a concept of multiple lines of evidence, is described: results from literature analysis are combined with evidence from experiments and genome analysis to improve the accuracy of results and to generate additional knowledge beyond what is known solely from literature.
This study presents the development of a hybrid system consisting of an ensemble of Extended Kalman Filter (EKF) based Multi Layer Perceptron Network (MLPN) and a one-pass learning Fuzzy Inference System using Look-up Table Scheme for the recognition of electrocardiogram (ECG) signals. This system can distinguish various types of abnormal ECG signals such as Ventricular Premature Cycle (VPC), T wave inversion (TINV), ST segment depression (STDP), and Supraventricular Tachycardia (SVT) from normal sinus rhythm (NSR) ECG signal.
We extend the problem of association rule mining--a key data mining problem--to systems in which the database is partitioned among a very large number of computers that are dispersed over a wide area. Such computing systems include grid computing platforms, federated database systems, and peer-to-peer computing environments. The scale of these systems poses several difficulties, such as the impracticality of global communications and global synchronization, dynamic topology changes of the network, on-the-fly data updates, the need to share resources with other applications, and the frequent failure and recovery of resources. We present an algorithm by which every node in the system can reach the exact solution, as if it were given the combined database. The algorithm is entirely asynchronous, imposes very little communication overhead, transparently tolerates network topology changes and node failures, and quickly adjusts to changes in the data as they occur. Simulation of up to 10,000 nodes show that the algorithm is local: all rules, except for those whose confidence is about equal to the confidence threshold, are discovered using information gathered from a very small vicinity, whose size is independent of the size of the system.
Parallel Distributed Processing (PDP), a computational methodology with origins in Associationism, is used to provide empirical information regarding neurobiological systems. Recently, supercomputers have enabled neuroscientists to model brain behavior-relationships. An overview of supercomputer architecture demonstrates the advantages of parallel over serial processing. Histological data provide physical evidence of the parallel distributed nature of certain aspects of the human brain, as do corresponding computer simulations. Whereas sensory networks follow more sequential neural network pathways, in vivo brain imaging studies of attention and rudimentary language tasks appear to involve multiple cortical and subcortical areas. Controversy remains as to whether associative models or Artificial Intelligence symbolic models better reflect neural networks of cognitive functions; however, considerable interest has shifted towards associative models.
This paper claims for a rational treatment of patient data. It investigates data analysis with the aid of artificial neural networks. Successful example applications show that human diagnosis abilities are significantly worse than those of neural diagnosis systems. For the example of a newer architecture using RBF nets the basic functionality is explained and it is shown how human and neural expertise can be coupled. Finally, the applications and problems of this kind of systems are discussed.
In modern ultramicrotomes the thermic advance system has been replaced by a mechanical one. Earlier, conventional DC-voltage motors were used, but recently the step motor has become popular. In connection with such motors, the application of digital control elements is facilitated, thus increasing precision significantly. A further step towards improving the precision of the advance system is the application of microprocessors as intelligent and interacting control elements. The microprocessor can not only take over the function sensors, the function of regulation. This paper describes a working concept whereby the advance system does not, as usual, work freely, but in connection with a sensor which measures the advance, and first after a positive data comparison over the microprocessor, allows the cutting movement. The concept is not limited to ultramicrotomes but can also be applied to mechanical rotation microtomes.
META is a knowledge-based expert system that simulates the biotransformation of xenobiotics. It operates with the help of a dictionary (knowledge base) to seek target fragments in a compound and transform them to products. Here, a genetic algorithm is introduced to help build the knowledge base and optimize the performance of the methodology.
Percutaneous pericardial puncture is a relatively safe and effective technique in case of large pericardial effusions when practiced under echographic or radiological control. The goal of our project is to improve the performance of this technique, mainly in case of smaller and loculated effusions using an accurate guidance towards a preplanned target, based on a model of the pericardial effusion. This paper presents preclinical results of this new computer-assisted technique used to reach the pericardial cavity. The procedure is divided into 3 steps: 1. acquisition of ultrasound data, using an echocardiographic device connected to a 3-D localizer and to a computer, 2. modeling procedure to define the optimal strategy taking into account the mobility of organs on a digital model, 3. guided puncture with a localized needle to reach the predefined target using a passive guidance system. After validation on a dynamic phantom and a feasibility study on dogs, an accuracy and reliability analysis protocol was realized on pigs with experimental pericardial effusion. Feasibility of the technique is demonstrated on animal study with an accuracy of at least 2.5 mm. Further clinical investigation is in progress using a more ergonomic and less cumbersome system. This study demonstrates the feasibility of computer-assisted pericardiocentesis. Beyond the simple improvement of the current technique, this could be a new way to reach the heart or a new tool for percutaneous access and image-guided puncture of soft tissues.
MOTIVATION: High-throughput technologies create the necessity to mine large amounts of gene annotations from diverse databanks, and to integrate the resulting data. Most databanks can be interrogated only via Web, for a single gene at a time, and query results are generally available only in the HTML format. Although some databanks provide batch retrieval of data via FTP, this requires expertise and resources for locally reimplementing the databank. RESULTS: We developed MyWEST, a tool aimed at researchers without extensive informatics skills or resources, which exploits user-defined templates to easily mine selected annotations from different Web-interfaced databanks, and aggregates and structures results in an automatically updated database. Using microarray results from a model system of retinoic acid-induced differentiation, MyWEST effectively gathered relevant annotations from various biomolecular databanks, highlighted significant biological characteristics and supported a global approach to the understanding of complex cellular mechanisms. AVAILABILITY: MyWEST is freely available for non-profit use at http://www.medinfopoli.polimi.it/MyWEST/
The Institute of Medicine recently issued a landmark report on medical error.1 In the penumbra of this report, every aspect of health care is subject to new scrutiny regarding patient safety. Informatics technology can support patient safety by correcting problems inherent in older technology; however, new information technology can also contribute to new sources of error. We report here a categorization of possible errors that may arise in deploying a system designed to give guideline-based advice on prescribing drugs, an approach to anticipating these errors in an automated guideline system, and design features to minimize errors and thereby maximize patient safety. Our guideline implementation system, based on the EON architecture, provides a framework for a knowledge base that is sufficiently comprehensive to incorporate safety information, and that is easily reviewed and updated by clinician-experts.
Automated quality assessment of clinician actions and patient outcomes is a central problem in guideline- or standards-based medical care. In this paper we describe a model representation and algorithm for deriving structured quality indicators and auditing protocols from formalized specifications of guidelines used in decision support systems. We apply the model and algorithm to the assessment of physician concordance with a guideline knowledge model for hypertension used in a decision-support system. The properties of our solution include the ability to derive automatically context-specific and case-mix-adjusted quality indicators that can model global or local levels of detail about the guideline parameterized by defining the reliability of each indicator or element of the guideline.
Although many Knowledge Representation (KR) formalisms have been used to encode care guidelines, there are few direct comparisons among different formalisms. In order to compare their suitability for encoding care guidelines, three different KR formalisms were used to encode the National Cholesterol Education Panel (NCEP) guideline. PROLOG, a First Order Logic system, CLASSIC, a frame-based representation system, and CLIPS, a production rule system, were used in the comparison. All three representations allowed accurate encoding of the guideline. PROLOG produced the most compact representation, but proved the most difficult to debug. The lack of arbitrary disjunction in CLASSIC greatly increased the complexity of the encoding. Overall, the CLIPS representation was the most intuitive and easiest to use.
The wealth of physiological data made available by current medical monitoring systems can be used efficiently only if the monitoring system is capable of relieving human personnel of relatively low-level tasks by performing intelligent data interpretation, contextual analysis and advice tasks. The system described in this paper can choose the variables to which most processing time will be devoted on the basis of the evolution of the patient.