Search PubMed⌕ Search

SEARCH · Search PubMed

Results for “decision intelligence”

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.

At least 973 records · Page 54Linked to original sources
PubMed2005

Description and preliminary evaluation of a Multiagent Intelligent Dosing System (MAIDS) to manage combination insulin-oral agent therapy in type 2 diabetes.

BACKGROUND: Computer decision support systems are potentially effective methods for adjusting insulin, but current models do not take into account simultaneous changes of more than one agent. We describe the development of the Multiagent Intelligent Dosing System (MAIDS, Dimensional Dosing Systems, Wexford, PA) for predicting glycemic outcome in response to concurrent dose adjustments in oral hypoglycemic agents and insulin. METHODS: Retrospective data from a patient cohort with type 2 diabetes who had simultaneous changes in insulin and metformin were analyzed. Glycemic markers (fasting glucose, random glucose, or hemoglobin A1c) expected at the visit subsequent to dose changes were calculated using two methods: the previously reported Intelligent Dosing System (IDStrade mark, Dimensional Dosing Systems), which accounts for changes in only one agent, and the MAIDS. Expected results from both systems were correlated with levels actually observed. RESULTS: We analyzed 32 patients with 40 paired visits. For fasting glucose (n = 8 paired visits), the correlation between expected and observed values was 0.07 when using the IDS but 0.78 when using the MAIDS. For random glucose (n = 16 paired visits) the correlation between expected and observed levels was 0.49 for the IDS but 0.79 for the MAIDS. With hemoglobin A1c as the marker (n = 16 paired visits), the correlation was 0.40 when using the IDS but 0.60 with the MAIDS. CONCLUSIONS: The MAIDS allows better prediction of glycemic outcome in circumstances where both insulin and an oral hypoglycemic drug are changed concurrently. Application of the MAIDS to other clinical scenarios, such as simultaneous adjustment of insulin and carbohydrate intake, requires further study.

Algorithms↗
PubMedDate not supplied

The new cell culture smallpox vaccine should not be offered to the general population.

Cell based smallpox vaccines are to be welcomed, but any decision to vaccinate whole populations must await firstly better intelligence about the gravity of the threat from bioterrorists, including their ability to release smallpox in such a way that wide dissemination could take place; secondly evidence that vaccines grown in cell culture are protective and safe; and thirdly that the vaccines would be generally acceptable and their introduction would not compromise the rest of national immunisation programmes. Smallpox vaccination should not be offered to the general population until these uncertainties have been resolved, by which time bioterrorism might possibly have been overcome or the development of antiviral treatment might have made renewed smallpox vaccination unnecessary. Meanwhile, preparations for rapid deployment of the historically well-tried containment measures at the epicentres of any smallpox release should proceed, their effectiveness should be tested, and their adequacy kept under review.

Bioterrorism↗
PubMed1984

Multivariate statistical classification of noisy images (randomly oriented biological macromolecules).

Multivariate Statistical Analysis (MSA) methods have recently been introduced for analyzing images of biological macromolecules [Van Heel and Frank, Ultramicroscopy 6 (1981) 187]. With these techniques, the significant characteristics of each molecular image can be expressed in merely 2 to 8 factorial coordinate values rather than in the typical 64 X 64 = 4096 pixel grey values that originally described the image. This very large reduction in total amount of data facilitates the understanding of the general behavior of a set of molecular images in terms of classes or of general trends in the data set. The (artificial) intelligence of the procedure, however, lies in the decision-making or classification phase. The theory and philosophy of multivariate statistical classification are reviewed using generalized metrics. Problem-dependent classification rationales are proposed. A set of computer-generated "randomly oriented molecular images" are used to test the classification schemes. This model experiment is a step towards 3D structure analysis of macromolecules based on large numbers of (noisy) electron microscopical images of randomly oriented biological macromolecules.

Animals↗
PubMed1980

Appropriate technology: the challenge of the second generation.

Appropriate technology, defined here as a low-cost technology aimed at helping to meet the most basic needs of the world's poorest people, can only be a viable proposition if its proponents succeed in making the transition from the first to the second generation, i.e. from the small-scale experiments and pilot innovations of today, to the massive application of new devices (hardware) and new forms of organization (software). The main agents in this second generation are national planning institutions, government ministries, established research centres, development agencies, financial institutions and industral corporations. Some of the ways in which this transition can be facilitated are examined, as well as a number of specific issues such as intelligence policies in appropriate technology, the structure of decision-making mechanisms and the linkage between appropriate technology and overall development strategies.

Agriculture↗
PubMed1992

Attempts to use computers as diagnostic aids in medical decision making: a thirty-year experience.

For more than 30 years our group of physicians, statisticians, and computer scientists has worked toward developing a computer program with the capability of a trained physician to make diagnostic decisions in the relatively broad medical subspecialty of hematology. We devised and tested many programs, none of which have been sufficiently useful to warrant carrying beyond the pilot-study stage. We analyzed the reasons for this failure. Our experience confirms the great difficulty, and even the impossibility, of incorporating the complexity of human thought into a system that can be handled by a computer. We concluded that we should stop trying to make a computer act like a diagnostician and concentrate instead on ways of making computer-generated relevant information available to physicians as they make decisions.

Algorithms↗
PubMed2002

The helpful patient record system: problem oriented and knowledge based.

In contrast to existing computerized patient record systems, which merely offer static functionality for storage and presentation, a helpful patient record system is a problem-oriented, knowledge-based system which provides the clinician with situation-specific information from the patient record, relevant to the activity within the patient care process. We suggest extending the data model of current patient record systems with (1) knowledge for recognizing and interpreting care situations, (2) knowledge of how clinicians work and what information they need, and (3) means to rank information according to its relevance in a given situation. We present a framework that enables representation of three prerequisite features for a future helpful patient record system: the primary care workflow process, the problem-oriented information model, and means to identify relevant information to the care process and medical decisions.

Artificial Intelligence↗
PubMed2002

Detecting relationships between physiological variables using graphical models.

In intensive care physiological variables of the critically ill are measured and recorded in short time intervals. The proper extraction and interpretation of the information contained in this flood of information can hardly be done by experience alone. Intelligent alarm systems are needed to provide suitable bedside decision support. So far there is no commonly accepted standard for detecting the actual clinical state from the patient record. We use the statistical methodology of graphical models based on partial correlations for detecting time-varying relationships between physiological variables. Graphical models provide information on the relationships among physiological variables that is helpful e.g. for variable selection. Separate analyses for different pathophysiological states show that distinct clinical states are characterized by distinct partial correlation structures. Hence, this technique can provide new insights into physiological mechanisms.

Critical Care↗
PubMed1989

Expert systems in medicine.

The emergence of the artificial intelligence (AI) in computer technology and its application in the medical field enables the researchers to carry out such intelligent activities like image processing, medical reasoning systems, clinical decision supporting and natural language understanding, etc. A gastroenterological expert system application is briefly demonstrated in this paper. Similar expert systems can be seen to be useful in the research of gastrointestinal cytoprotection, including the plan of different compounds with cytoprotective effect, experimental and clinical medical research.

Decision Making, Computer-Assisted↗
PubMedDate not supplied

Information technology and computer-based decision support in diabetic management.

This paper describes the application of computer-based techniques within an intelligent, knowledge-based framework to the management of diabetes. The objectives are to structure data collection and storage so that the relevant patient-specific data are collected and made accessible as needed, and to provide clinical decision support on either a day-by-day or longer timescale as appropriate; these objectives relating to both hospital clinic and general practice. For longer-term management, a prototype rule set (greater than 500 rules) has been developed (coded in Sigma PROLOG), validated and tested on patient data. The data collection programs (written in SCULPTOR) to feed the ruleset have been tested in the hospital clinic and compared with the resident data collection system for usability, and impact on the running of the clinic. Links between the data collection programs and the ruleset program have been written and tested. The computer system will also incorporate a module, combining knowledge-based advisory system and glucose/insulin model as patient simulator, that can be tested as a potential decision aid for adjusting insulin dosage on a daily basis.

Data Collection↗
PubMed1999

Case-based explanation of non-case-based learning methods.

We show how to generate case-based explanations for non-case-based learning methods such as artificial neural nets or decision trees. The method uses the trained model (e.g., the neural net or the decision tree) as a distance metric to determine which cases in the training set are most similar to the case that needs to be explained. This approach is well suited to medical domains, where it is important to understand predictions made by complex machine learning models, and where training and clinical practice makes users adept at case interpretation.

Artificial Intelligence↗
PubMed1992

Expert systems and expert behavior.

Iliad 4.0 and QMR 2.03 are computer-based diagnostic knowledge bases that can play many roles in decision support and other areas of medical practice, but neither appears ready to assume the role of an expert diagnostic consultant. In contrast to human experts, these programs have problems related to recognition of their own limitations, interpretation of continuous data, recognition of dependent findings, selection of tests, and description of the impact of certain tests. Suggestions to improve these aspects of knowledge bases are offered.

Artificial Intelligence↗
PubMed1990

[Computer and acid-base disorders].

The diagnosis of acid-base disorders has been subject to computerised analysis for many years. Expert systems, an application of artificial intelligence, have been validated. They are of help to clinical decision making, enabling the different diagnostic possibilities of given acid-base and hydro-electrolytic situations to be evaluated and appropriate therapy to be instituted. Computer networks improve the transmission of laboratory results to the intensive care units and the integration of data facilitates the monitoring of biochemical tendencies. Computers can also be used for teaching acid-base physiology and pathology.

Acid-Base Imbalance↗
PubMed1996

Doctors' decision-making on giving information to cancer patients.

A major focus in the literature about doctor-patient communication is information-giving. In the case of cancer patients, one significant issue is which factors determine whether and how, general practitioners and oncologists give information to their patients. Whatever may be the content of information, the most important choice for the doctor is to give information or not. Our research group at the Department of Health Psychology has conducted investigations in order to identify the significant determinants of decisions concerning giving information to cancer patients. A sample of 60 doctors from Alicante province in Spain were asked their criteria for giving information about a cancer diagnosis. Results showed that perceived intelligence and emotional control in the patients were the best predictors of the decision by doctors to give information. Age and socio-economic status were also significantly associated with the doctors' information-giving practices. These data suggest that the criteria for giving information to cancer patients are subjective and show a strong cultural influence.

Health Knowledge, Attitudes, Practice↗
PubMed1998

The Modified Card Sorting Test: test-retest stability and relationships with demographic variables in a healthy older adult sample.

OBJECTIVES: To investigate the test-retest stability of a standardized version of Nelson's (1976) Modified Card Sorting Test (MCST) and its relationships with demographic variables in a sample of healthy older adults. DESIGN: A standard card order and administration were devised for the MCST and administered to participants at an initial assessment, and again at a second session conducted a minimum of six months later in order to examine its test-retest stability. Participants were also administered the WAIS-R at initial assessment in order to provide a measure of psychometric intelligence. METHODS: Thirty-six (24 female, 12 male) healthy older adults aged 52 to 77 years with mean education 12.42 years (SD = 3.53) completed the MCST on two occasions approximately 7.5 months (SD = 1.61) apart. Stability coefficients and test-retest differences were calculated for the range of scores. The effect of gender on MCST performance was examined. Correlations between MCST scores and age, education and WAIS-R IQs were also determined. RESULTS: Stability coefficients ranged from .26 for the percent perseverative errors measures to .49 for the failure to maintain set measure. Several measures were significantly correlated with age, education and WAIS-R IQs, although no effect of gender on MCST performance was found. CONCLUSIONS: None of the stability coefficients reached the level required for clinical decision making. The results indicate that participants' age, education, and intelligence need to be considered when interpreting MCST performance. Normative studies of MCST performance as well as further studies with patients with executive dysfunction are needed.

Adult↗
PubMed2004

A classification paradigm for distributed vertically partitioned data.

In general, pattern classification algorithms assume that all the features are available during the construction of a classifier and its subsequent use. In many practical situations, data are recorded in different servers that are geographically apart, and each server observes features of local interest. The underlying infrastructure and other logistics (such as access control) in many cases do not permit continual synchronization. Each server thus has a partial view of the data in the sense that feature subsets (not necessarily disjoint) are available at each server. In this article, we present a classification algorithm for this distributed vertically partitioned data. We assume that local classifiers can be constructed based on the local partial views of the data available at each server. These local classifiers can be any one of the many standard classifiers (e.g., neural networks, decision tree, k nearest neighbor). Often these local classifiers are constructed to support decision making at each location, and our focus is not on these individual local classifiers. Rather, our focus is constructing a classifier that can use these local classifiers to achieve an error rate that is as close as possible to that of a classifier having access to the entire feature set. We empirically demonstrate the efficacy of the proposed algorithm and also provide theoretical results quantifying the loss that results as compared to the situation where the entire feature set is available to any single classifier.

Abstracting and Indexing↗
PubMed2006

Severity of Alzheimer's disease and effect on premorbid measures of intelligence.

OBJECTIVES: To assess the robustness of the National Adult Reading Test (NART), Wechsler Test of Adult Reading (WTAR), Cambridge Contextual Reading Test (CCRT), Spot the Word (STW), and a demographic regression equation in estimating premorbid ability in people with Alzheimer's disease (AD). DESIGN: A cross-sectional multiple measures design. METHOD: Sixty-six probable AD participants were classified into stages of severity according to their Mini Mental State Examination (MMSE) score (minimal 24 to 28; mild 14 to 23). Their scores on the NART, WTAR, CCRT, STW and a demographic equation were compared with 32 healthy age matched controls. RESULTS: Significant between-group differences were found for the tests of reading ability (NART, WTAR and CCRT). The mild group made significantly more errors than the control and minimal groups. For the mild group, there was an advantage of putting the NART words into context (CCRT), but this group still made significantly more errors than the control and minimal groups. The NART was compared with the demographic estimate and there was a significant difference for the mild group with the demographic estimate providing a higher estimate. This was not the case for the control or minimal groups. There was no significant difference between the groups on the lexical decision task (STW). CONCLUSION: Reading of irregular words is compromised in AD for those with a MMSE score in the range of 14 to 23. A lexical decision task may provide a more accurate estimate of premorbid intelligence in those with mild AD. Further research is needed to provide evidence of STW's correlation with current ability.

Aged↗
PubMed2003

The knowledge modeling for chronic urticaria assessment in clinical decision support system with PDA.

The benefits of a clinical information system would be enhanced by a clinical decision support system (CDSS). We have developed urticaria diagnosis knowledge model for clinical practice. In order to construct a more accurate, evidenced-based and comprehensive knowledge base for urticaria, we arranged and integrated knowledge from literatures-based knowledge, as provided by; The Korean Academy of Asthma and Allergy [1], the American Allergy Association based on an algorithm of chronic urticaria assessment. We presented this knowledge in a Boolean cross table frame and implemented these guidelines using the developed CDSS.

Algorithms↗
PubMed1997

Induction of decision trees and Bayesian classification applied to diagnosis of sport injuries.

Machine learning techniques can be used to extract knowledge from data stored in medical databases. In our application, various machine learning algorithms were used to extract diagnostic knowledge which may be used to support the diagnosis of sport injuries. The applied methods include variants of the Assistant algorithm for top-down induction of decision trees, and variants of the Bayesian classifier. The available dataset was insufficient for reliable diagnosis of all sport injuries considered by the system. Consequently, expert-defined diagnostic rules were added and used as pre-classifiers or as generators of additional training instances for diagnoses for which only few training examples were available. Experimental results show that the classification accuracy and the explanation capability of the naive Bayesian classifier with the fuzzy discretization of numerical attributes were superior to other methods and estimated as the most appropriate for practical use.

Artificial Intelligence↗