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 253 records · Page 14Linked to original sources
PubMed2006

Dynamic reasoning to solve complex problems in activated sludge processes: a step further in decision support systems.

Decision support systems (DSS) have generated high expectations as a tool to support activated sludge operation because of their ability to represent heuristic reasoning and to handle large amounts of qualitative, uncertain and low-accuracy data. Previous applications have been satisfactory to control simple problems, when static reasoning and literature-based solutions were enough. However to face complex operational problems with biological origin and slow dynamics (e.g. solids separation problems), it is necessary to use dynamic reasoning and apply long-term control strategies, monitoring the evolution of the process and adjusting the action plan according to the feed back of the process. This paper presents a dynamic reasoning DSS to face solids separation problems in the activated sludge system. The DSS is capable of identifying the complex problem affecting the process, determining if the current situation is new or a continuation from the previous one, assessing what is the specific cause of the situation, and recommending a long-term control strategy, which is daily adjusted according to the evolution of the process.

Artificial Intelligence↗
PubMed1997

New computer-based tools for empiric antibiotic decision support.

Since 1995 we have been developing a decision-support model, called Q-ID, which uses a series of infectious disease knowledge bases to make recommendations for empirical treatment or to check the appropriateness of current antibiotic therapy. From disease manifestations and risk factors, a differential diagnosis for the patient is generated by a diagnostic medical expert system. The resulting probability of each: disease is multiplied by the expected benefit in improved mortality and morbidity from optimal antibiotic treatment of each disease. To generate empirical treatment recommendations, site-specific data on sensitivity to antibiotics of each organism is used as an estimate of the likelihood of achieving maximum benefit for each disease on the patient's differential. Combining this data with drug and patient specific factors, the model recommends the antibiotic(s) most likely to produce the optimal benefit in this patient with the least risk and expense. In this paper the model is described, excerpts from each of the knowledge bases are presented, and performance of the model in a real case is shown for illustration.

Aged↗
PubMed2005

Using a claims data-based sentinel system to improve compliance with clinical guidelines: results of a randomized prospective study.

OBJECTIVE: To demonstrate the potential effect of deploying a sentinel system that scans administrative claims information and clinical data to detect and mitigate errors in care and deviations from best medical practices. METHODS: Members (n = 39 462; age range, 12-64 years) of a midwestern managed care plan were randomly assigned to an intervention or a control group. The sentinel system was programmed with more than 1000 decision rules that were capable of generating clinical recommendations. Clinical recommendations triggered for subjects in the intervention group were relayed to treating physicians, and those for the control group were deferred to study end. RESULTS: Nine hundred eight clinical recommendations were issued to the intervention group. Among those in both groups who triggered recommendations, there were 19% fewer hospital admissions in the intervention group compared with the control group (P < .001). Charges among those whose recommendations were communicated were dollar 77.91 per member per month (pmpm) lower and paid claims were dollar 68.08 pmpm lower than among controls compared with the baseline values (P = .003 for both). Paid claims for the entire intervention group (with or without recommendations) were dollar 8.07 pmpm lower than those for the entire control group. In contrast, the intervention cost dollar 1.00 pmpm, suggesting an 8-fold return on investment. CONCLUSION: Ongoing use of a sentinel system to prompt clinically actionable, patient-specific alerts generated from administratively derived clinical data was associated with a reduction in hospitalization, medical costs, and morbidity.

Adult↗
PubMed1991

The sensitivity of medical diagnostic decision-support knowledge bases in delineating appropriate terms to document in the medical record.

A pertinent, legible and complete medical record facilitates good patient care. The recording of the symptoms, signs and lab findings which are relevant to a patient's condition contributes importantly to the medical record. The consideration and documentation of other disease states known to be related to the patient's primary illness provide further enhancement. We propose that developing sets of disease-specific core elements which a physician may want to document in the medical record can have many benefits. We hypothesize that for a given disease, terms with high importance (TI) and frequency (TF) in the DX-plain, QMR and Iliad knowledge bases (KBs) are terms which are used commonly in the medical record, and may be, in fact, terms which physicians would find useful to document. A study was undertaken to validate ten such sets of disease-specific core elements. For each of ten prevalent diseases, high TI and TF terms from the three KBs mentioned were pooled to derive the set of core elements. For each disease, all patient records (range 385 to 16,972) from a computerized ambulatory medical record database were searched to document the actual use by physicians of each of these core elements. A significant percentage (range 50 to 86%) of each set of core elements was confirmed as being used by the physicians. In addition, all medical concepts from a selection of full text records were identified, and an average of 65% of the concepts were found to be core elements.(ABSTRACT TRUNCATED AT 250 WORDS)

Artificial Intelligence↗
PubMed1996

Testing and validation of computerized decision support systems.

Systematic, through testing of decision support systems (DSSs) prior to release to general users is a critical aspect of high quality software design. Omission of this step may lead to the dangerous, and potentially fatal, condition of relying on a system with outputs of uncertain quality. Thorough testing requires a great deal of effort and is a difficult job because tools necessary to facilitate testing are not well developed. Testing is a job ill-suited to humans because it requires tireless attention to a large number of details. For these reasons, the majority of DSSs available are probably not well tested prior to release. We have successfully implemented a software design and testing plan which has helped us meet our goal of continuously improving the quality of our DSS software prior to release. While requiring large amounts of effort, we feel that the process of documenting and standardizing our testing methods are important steps toward meeting recognized national and international quality standards. Our testing methodology includes both functional and structural testing and requires input from all levels of development. Our system does not focus solely on meeting design requirements but also addresses the robustness of the system and the completeness of testing.

Artificial Intelligence↗
PubMed1998

Palomar project: predicting school renouncing dropouts, using the artificial neural networks as a support for educational policy decisions.

The "Palomar" project confronts two problem situations that are partly independent and partly connected to the Italian schooling system: unstable participation in school such as drop out and educational guidance. Our concern is that of a set of phenomena which consists of ceasing compulsory education, repetition of a year at school, school "drop outs", irregular compulsory attendance and delays in the course of studies. The "Palomar" project is designed to offer educators and administrators who want to effectively intervene with these complex problems to furnish school guidance services as an instrument able to: 1. Predict: creating a system able to predict in advance (not in a "cause-effect" way but as an approximation): a) which students are at "risk" for school destabilization or failure; b) what are the prototypical characteristics of these students; c) which students among those studied are more likely to "destabilize" or fail in school; in which course of study does each student have the greatest chance of success; d) which, among the variables studied and appropriately weighted for each student, will predict the successful grade, analyzed for each possible course of studies. 2. Optimize: selecting and focusing on a student on the basis of the information given. It is possible: a) to point out which personal factors (relational, familial, student, disciplinary, economical) need to be reinforced in order to improve the school performances of each selected student, both to prevent or limit "dropping out" desertion or failure and to raise the performances in the chosen school course as much as possible; b) on the basis of what was mentioned above, to simulate the possible support measures to increase the efficacy of the considered intervention; c) to choose for each student the appropriate intervention strategy capable of obtaining the maximum result and the maximum efficacy in the given conditions. 3. Verify: when the strategy of intervention has been decided and we proceed with its implementation, it is possible to periodically verify ("follow-up"), through subsequent administration of the form, the outcome variations elapsed in the prediction of school success or failure. This makes it possible to verify in itinere the efficacy of the interventions carried out and, if necessary, to create variations and adjustments. 4. Produce scenarios: the application field of the Prediction System with Artificial Neural Networks can also be one of a group of students, of one or more organized units (for example a class, a school, or a group of schools). In this case the Prediction System ANN using the program SCHEMA (Buscema, 1996b) is able to: a) determine intervention strategies in order to optimize and to produce the maximum results of a group of students as the one of a class; b) optimize the formative route of a whole institute in order to prevent or limit the need for school guidance.

Adolescent↗
PubMed1989

ANABEL: intelligent blood-gas analysis in the intensive care unit.

ANABEL (ANalysis of Acid-Base status by Evaluating Lisp) is a prototype medical intelligent decision-support system aiming to assist clinicians in an Intensive Care Unit environment with the interpretation of blood-gas measurements. Its architecture is based on the merging of representations for declarative (domain-descriptive) and procedural (problem-solving) medical knowledge. The system performs diagnosis in two stages (tentative and differential) by first evaluating elementary computational units of procedural knowledge (procedures) and then abstracting their symbolic outputs in generating text. Thus, a 'semantic trace' is built which reflects the system's line of reasoning in reaching its conclusion. This paper describes the design aspects, development and clinical validation of ANABEL.

Acid-Base Imbalance↗
PubMed1999

[Computed assisted voice recognition. A dream or reality in the pathologist's routine work?].

During the last 30 years the analysis of human speech with powerful computers has taken great strides; therefore, cost-effective, comfortable solutions are now available for use in professional routine work. The advantages of using voice recognition are the creation of new documentation or archives, reduced personnel costs and, last but not least, independence in cases of unforeseen notification of illness or owing to annual leave. For voice recognition systems to be used easily, a considerable amount of time must be invested for the first 3 months. Younger colleagues in particular will be more motivated to dictate more precisely and more detailed because of the introduction of voice recognition. The effects on other sectors of medical training, quality control, histology report preparation, and transmission can only be speculated.

Artificial Intelligence↗
PubMed2005

Improving the reliability of medical software by predicting the dangerous software modules.

Software reliability analysis is inevitable for modern medical systems, since a large amount of medical system functionality is now dependent on software, and software does contribute to system failures. Most software reliability models are based on software failure data collected from the project. This creates a problem for the designers since, during the early stage, software failure data are not available. However, a valuable knowledge can be learned from the analysis of previous projects and applied to the new ones. This paper presents the approach that predicts the potentially dangerous software modules under development based on the analysis of the already finished modules using the machine-learning techniques. On the basis of the prediction given by our method software designers are able to devote more testing effort to the dangerous parts of the system, which results in a more reliable medical software system.

Algorithms↗
PubMed1994

Writing Arden Syntax Medical Logic Modules.

The Arden Syntax for Medical Logic Modules is a language for encoding medical knowledge bases that consist of independent modules. The Arden Syntax has been used to generate clinical alerts, diagnostic interpretations, management messages, and screening for research studies and quality assurance. An Arden Syntax knowledge base consists of rules called Medical Logic Modules (MLMs), which are stored as simple ASCII files that can be written on any text editor. An MLM is made of slots grouped into three categories: maintenance information, library information, and the actual medical knowledge. Most MLMs are triggered by clinical events, evaluate medical criteria, and, if appropriate, perform an action such as sending a message to a health care provider. This paper provides a detailed tutorial on how to write MLMs.

Artificial Intelligence↗
PubMed1994

GAMES II Project: a general architecture for medical knowledge-based systems.

GAMES II aims at developing a comprehensive and commercially viable methodology to avoid problems ordinarily occurring in KBS development. GAMES II methodology proposes to design a KBS starting from an epistemological model of medical reasoning (the Select and Test Model). The design is viewed as a process of adding symbol level information to the epistemological model. The architectural framework provided by GAMES II integrates the use of different formalisms and techniques providing a large set of tools. The user can select the most suitable one for representing a piece of knowledge after a careful analysis of its epistemological characteristics. Special attention is devoted to the tools dealing with knowledge acquisition (both manual and automatic). A panel of practicing physicians are assessing the medical value of such a framework and its related tools by using it in a practical application.

Artificial Intelligence↗
PubMed1993

Inferential knowledge acquisition.

This paper describes the approach we are pursuing for modeling inferential processes in knowledge-based systems. It is aimed at overcoming the lack of generality affecting many of the systems described in the literature. This mainly happens since the problem-solving method adopted by those systems is too closely tied to the particular domain problem over which the method itself has been modeled. We also describe a system called M-KAT (Medical Knowledge Acquisition Tool) which is useful in simplifying the process of acquiring inferential knowledge. M-KAT relies on an epistemological model of medical reasoning which represents a generalization of most of the problem-solving methods adopted in medical knowledge-based systems. The metarules formalism has been adopted as a mean for representing inferential knowledge and making its acquisition easier, thus allowing the computational implementation of the epistemological model of medical reasoning.

Artificial Intelligence↗
PubMed2004

An evaluation of a system that recommends microarray experiments to perform to discover gene-regulation pathways.

The main topic of this paper is modeling the expected value of experimentation (EVE) for discovering causal pathways in gene expression data. By experimentation we mean both interventions (e.g., a gene knockout experiment) and observations (e.g., passively observing the expression level of a "wild-type" gene). We introduce a system called GEEVE (causal discovery in Gene Expression data using Expected Value of Experimentation), which implements expected value of experimentation in discovering causal pathways using gene expression data. GEEVE provides the following assistance, which is intended to help biologists in their quest to discover gene-regulation pathways: Recommending which experiments to perform (with a focus on "knockout" experiments) using an expected value of experimentation method. Recommending the number of measurements (observational and experimental) to include in the experimental design, again using an EVE method. Providing a Bayesian analysis that combines prior knowledge with the results of recent microarray experimental results to derive posterior probabilities of gene regulation relationships. In recommending which experiments to perform (and how many times to repeat them) the EVE approach considers the biologist's preferences for which genes to focus the discovery process. Also, since exact EVE calculations are exponential in time, GEEVE incorporates approximation methods. GEEVE is able to combine data from knockout experiments with data from wild-type experiments to suggest additional experiments to perform and then to analyze the results of those microarray experimental results. It models the possibility that unmeasured (latent) variables may be responsible for some of the statistical associations among the expression levels of the genes under study. To evaluate the GEEVE system, we used a gene expression simulator to generate data from specified models of gene regulation. The results show that the GEEVE system gives better results than two recently published approaches (1) in learning the generating models of gene regulation and (2) in recommending experiments to perform.

Animals↗
PubMed2006

The usability axiom of medical information systems.

INTRODUCTION: In this article we begin by connecting the concept of simplicity of user interfaces of information systems with that of usability, and the concept of complexity of the problem-solving in information systems with the concept of usefulness. We continue by stating "the usability axiom" of medical information technology: information systems must be, at the same time, usable and useful. We then try to show why, given existing technology, the axiom is a paradox and we continue with analysing and reformulating it several times, from more fundamental information processing perspectives. DISCUSSION: We underline the importance of the concept of representation and demonstrate the need for context-dependent representations. By means of thought experiments and examples, we advocate the need for context-dependent information processing and argue for the relevance of algorithmic information theory and case-based reasoning in this context. Further, we introduce the notion of concept spaces and offer a pragmatic perspective on context-dependent representations. We conclude that the efficient management of concept spaces may help with the solution to the medical information technology paradox. Finally, we propose a view of informatics centred on the concepts of context-dependent information processing and management of concept spaces that aligns well with existing knowledge centric definitions of informatics in general and medical informatics in particular. In effect, our view extends M. Musen's proposal and proposes a definition of Medical Informatics as context-dependent medical information processing. SUMMARY: The axiom that medical information systems must be, at the same time, useful and usable, is a paradox and its investigation by means of examples and thought experiments leads to the recognition of the crucial importance of context-dependent information processing. On the premise that context-dependent information processing equates to knowledge processing, this view defines Medical Informatics as a context-dependent medical information processing which aligns well with existing knowledge centric definitions of our field.

Algorithms↗