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 1,063 records · Page 59Linked to original sources
PubMed2004

Site-specific updating and aggregation of Bayesian belief network models for multiple experts.

A method for combining multiple expert opinions that are encoded in a Bayesian Belief Network (BBN) model is presented and applied to a problem involving the cleanup of hazardous chemicals at a site with contaminated groundwater. The method uses Bayes Rule to update each expert model with the observed evidence, then uses it again to compute posterior probability weights for each model. The weights reflect the consistency of each model with the observed evidence, allowing the aggregate model to be tailored to the particular conditions observed in the site-specific application of the risk model. The Bayesian update is easy to implement, since the likelihood for the set of evidence (observations for selected nodes of the BBN model) is readily computed by sequential execution of the BBN model. The method is demonstrated using a simple pedagogical example and subsequently applied to a groundwater contamination problem using an expert-knowledge BBN model. The BBN model in this application predicts the probability that reductive dechlorination of the contaminant trichlorethene (TCE) is occurring at a site--a critical step in the demonstration of the feasibility of monitored natural attenuation for site cleanup--given information on 14 measurable antecedent and descendant conditions. The predictions for the BBN models for 21 experts are weighted and aggregated using examples of hypothetical and actual site data. The method allows more weight for those expert models that are more reflective of the site conditions, and is shown to yield an aggregate prediction that differs from that of simple model averaging in a potentially significant manner.

Algorithms↗
PubMedDate not supplied

Plasma proteomic pattern as biomarkers for ovarian cancer.

Early detection of ovarian cancer remains a challenge. Pathologic changes within an organ might be reflected in proteomic patterns in serum or plasma. The objective of this study was to identify new plasma biomarkers in ovarian cancer patients using mass spectrometry (MS) protein profiling and artificial intelligence. The study included 35 women with ovarian cancer and 30 age-matched disease-free controls. For plasma protein signature analysis, the protein chip array surface-enhanced laser desorption/ionization (SELDI) analysis was performed. The strong anion exchange (SAX) and weak cation exchange (WCX) chips were used for analysis. After a training analysis by SAX and WCX protein chips, learning algorithm and clustering analysis was performed to reach a discriminate pattern of protein signature. SELDI mass spectroscopy was highly reproducible in detecting ovarian tumor-specific protein profiles. Four specific protein peaks were identified in plasma of women with ovarian cancer, but not in controls, with relative molecular masses of 6190.48, 5147.06, 11522.6, and 11537.7 d. Two peaks, with Mr 5295.5 and 8780.48 d, were present in plasma of control but not in women with ovarian cancer. A sensitivity of 90-96.3% and specificity of 100% for this studied cases and controls were reached. This study clearly demonstrates that the combined technology of SELDI-MS and artificial intelligence is effective in distinguishing protein expression between normal and ovary cancer plasma. The identified gained and lost protein peaks in plasma may provide as candidate proteins to be used for the detection or monitoring ovarian cancer.

Adolescent↗
PubMed1975

Interaction patterns in families of autistic, disturbed, and normal children.

Six families with autistic children were compared with six families with disturbed children and six with normal children by means of a family interaction task. No differences were found between families with autistic children and those with normal children. Families with disturbed children were found to have less agreement between father and mother than did autistic or normal families.

Adult↗
PubMed1976

Styles of decision-making and probability appraisal in selected obsessional and phobic patients.

A questionnaire was administered to obsessional and phobic patients and normal subjects. The results of this survey confirmed the prediction that a sizeable proportion of phobic patients report irrational expectations associated with their most feared situations. A group of phobics who reported irrational expectations, a group of obsessionals who reported an abnormal degree of checking behaviour and a group of normal subjects, took part in a probabilistic inference task. Several predictions about the differential performance of these groups were fulfilled. (i) Deviations from the optimal model for individual responses were greatest in the obsessional group. (ii) When Neuroticism was partialled out, the three groups differed with respect to amount of evidence required prior to a decision, the obsessional group having the highest score on this variable. (iii) The phobic group were more likely than the other two groups to make irrational event predictions.

Age Factors↗
PubMed1993

Can children withhold consent to treatment?

A dilemma exists when a doctor is faced with a child or young person who refuses medically indicated treatment. The Gillick case has been interpreted by many to mean that a child of sufficient age and intelligence could validly consent or refuse consent to treatment. Recent decisions of the Court of Appeal on a child's refusal of medical treatment have clouded the issue and undermined the spirit of the Gillick decision and the Children Act 1989. It is now the case that a child patient whose competence is in doubt will be found rational if he or she accepts the proposal to treat but may be found incompetent if he or she disagrees. Practitioners are alerted to the anomalies now exhibited by the law on the issue of children's consent and refusal. The impact of the decisions from the perspectives of medicine, ethics, and the law are examined. Practitioners should review each case of child care carefully and in cases of doubt seek legal advice.

Adolescent↗
PubMed1990

Computers in critical care: opportunities and challenges.

Treating acutely ill patients in intensive care units (ICUs) requires assimilating large amounts of patient data. The computer can help process these data and display information in easy to understand formats. Also, knowledge-based systems can provide advice in diagnosis and treatment of common disorders in the ICU. For effective use of computers, systems must be integrated into the total hospital information system and computer data must logically become the primary medical record. Standards are being developed to aid in this process. Although computers have been used in the ICU for 25 years, most hospitals still use the paper medical record. Prototype systems such as the HELP, CARE, and PDMS systems are described. They are integrated ICU systems for computerizing most of the traditional functions in the ICU. Several commercial information management products are also described along with recently developed computerized drug and fluid delivery systems. Finally, prototype knowledge-based programs are presented that provide advice to the clinician on such topics as acid-base balance, hemodynamic monitoring, and shock management.

Artificial Intelligence↗
PubMed2003

AIDA: web agents in dental treatment planning.

The objective of the AIDA project (Artificial Intelligent Dental Agents, http://aida.uni-hd.de) is the analysis of dental decision-making, the design of a computer-based decision support system, as well as the testing of the decision structure in interactions with dental experts, practicing dentists, and patients. The planning of the solution alternatives for an individual patient is based on a top-down structure for dental decision-making, aiming at a standardization of the argumentation. From a theoretical point of view, decision support can be provided only for anticipated decisions (planning). Moreover, only parts of these anticipated decisions can be supported. Accordingly, a separation of these partial aspects has to take place before one is able to build decision support systems. For prosthetic dentistry, clinicians have been shown how to use individual patient findings to sketch the possible treatment alternatives and later derive guidelines for the treatment. The planning module for fixed prostheses has already been integrated into a software agent. Planning modules for other types of prostheses are currently specified, implemented, and verified.

Decision Support Systems, Clinical↗
PubMed2005

PHSkb: a knowledgebase to support notifiable disease surveillance.

BACKGROUND: Notifiable disease surveillance in the United States is predominantly a passive process that is often limited by poor timeliness and low sensitivity. Interoperable tools are needed that interact more seamlessly with existing clinical and laboratory data to improve notifiable disease surveillance. DESCRIPTION: The Public Health Surveillance Knowledgebase (PHSkb) is a computer database designed to provide quick, easy access to domain knowledge regarding notifiable diseases and conditions in the United States. The database was developed using Protégé ontology and knowledgebase editing software. Data regarding the notifiable disease domain were collected via a comprehensive review of state health department websites and integrated with other information used to support the National Notifiable Diseases Surveillance System (NNDSS). Domain concepts were harmonized, wherever possible, to existing vocabulary standards. The knowledgebase can be used: 1) as the basis for a controlled vocabulary of reportable conditions needed for data aggregation in public health surveillance systems; 2) to provide queriable domain knowledge for public health surveillance partners; 3) to facilitate more automated case detection and surveillance decision support as a reusable component in an architecture for intelligent clinical, laboratory, and public health surveillance information systems. CONCLUSIONS: The PHSkb provides an extensible, interoperable system architecture component to support notifiable disease surveillance. Further development and testing of this resource is needed.

Communicable Diseases↗
PubMed2000

Mini-Mental State Questionnaire: problems with its use in palliative care.

The Mini-Mental State Questionnaire (MMSQ) has been established as a reliable research instrument and is recommended for the early detection of impaired mental status (Fainsinger et al, 1993). Using reflection on a clinical incident, the problems associated with the clinical application of the MMSQ that may outweigh its usefulness are identified. The patient's experience of MMSQ as routine cognitive monitoring can be distressing as the person experiences loss of cognitive ability in a visible way. This experience has a negative influence on the person's quality of life, which is contrary to the essential aim of palliative care. Research evidence suggests that the MMSQ lacks specificity (the ability to detect impaired mental status) because it is affected by pre-morbid ability and intelligence, and therefore cannot be used to assess competence in decision making. Further research on the meaning of losing cognitive ability in terminal illness and other cognitive assessment strategies is required.

Aged↗
PubMed2000

[Diagnosis of cerebellum-pontine angle tumors using artificial intelligence techniques].

We are concerned in this paper with learning classification procedures from known cases. More precisely, we provide a diagnostic model that discriminate between cerebellum-pontine angle (CPA) tumors and otorhinolaryngological (ENT) disorders. Usually, in order to distinguish between CPA tumors and ENT disorders one must perform clinical-neurological examination together with expensive radiological imagery (CT and MRI). The proposed model was obtained through artificial intelligence methods and presented a good accuracy level (88.4%) when tested against new cases, considering only clinical examination without radiological imagery results.

Artificial Intelligence↗
PubMed2005

Methodological-conceptual problems in the study of chimpanzees' folk physics: how studies with adult humans can help.

In three experiments, we examined humans' folk physics (i.e., a naturally occurring and spontaneous understanding of the physical world), using variations of problems used to study chimpanzees' folk physics. Presented with trap-tube problems in two experiments, adult humans showed an unnecessary bias to insert a stick into the end of the tube farthest from the reward to push it out the other end. When presented with trap-table problems with ineffective trapping holes, people unnecessarily avoided the side with the hole. The similarity of humans' and chimpanzees' behavior on these tasks highlights methodological and conceptual problems in studies of chimpanzees' folk physics and suggests alternative explanations for their behavior.

Adult↗
PubMed1986

Interpretive reporting to improve the effectiveness of clinical laboratory test results. An ECRI technology assessment.

Interpretive reporting encompasses a range of efforts by the clinical laboratory community to develop improved methods of transferring information from laboratories to physicians in a form that they can understand and use. The purpose of laboratory tests is to provide clinically useful information that can be used to answer a specific question for the clinician. However, growing physician reliance on laboratory and other diagnostic tests and the increased testing volumes made possible by laboratory automation have yielded some unintended negative effects. Laboratories can now provide more information than can be effectively assimilated. The resulting "information overload" can cause clinicians to misinterpret tests, ignore significant results, or fail to act appropriately when results indicate a treatable condition. Research indicates, however, that interpretive reporting improves information transfer and thus increases clinicians' understanding of the significance of laboratory test results.

Artificial Intelligence↗
PubMed1999

Intelligent systems in medical diagnosis.

From an intelligent system for a computer supported medical diagnosis it is expected to achieve high accuracy and ability to draw conclusions from a small data sets. Medical practice could takes many years to generate a large database. A new mathematical method that is able to learn on a small data set is presented.

Algorithms↗
PubMedDate not supplied

AIDA: Web agents to support dental treatment planning.

Dental treatment planning is highly dependent on the educational background and personal experience of the dentist and on the thoroughness with which findings are taken. The objective of research in the AIDA (Artificially Intelligent Dental Agents) project is therefore the analysis of dental decision making and the design of a decision-supportive software module to test the decision-making process and make it transparent for both dentists and patients. In the AIDA project (aida.uni-hd.de), an expert system has been set up to identify treatment alternatives with integrated decision rationale for experts, practicing dentists, and eventually also patients. It is based on a top-down structure for dental decision-making, which was developed to standardize argumentation. For prosthetic dentistry, how one uses individual patient findings to arrive at possible treatment alternatives was clarified in greater detail. The planning rules for fixed prostheses have already been integrated into a software agent. Other modules should soon specify and verify these suggestions in terms of further fields of dentistry (e.g., restorative dentistry). In the near future, AIDA will be able to deliver dentally-founded justifications for every individual decision.

Decision Making, Computer-Assisted↗
PubMed2002

Spinal surgery procedure discretization.

In the last decades, scientists developed analytic models of spinal surgery to assess surgical choices and instrumentation parameters. They noted the difficulty to represent the boundary conditions on their deterministic models and recognize the lack of knowledge in surgical procedures. This paper presents a formalization technique applied to spinal surgery to improve the formulation of biomechanical models. This technique consisted into two steps: knowledge extraction and knowledge representation. The protocol was established with an expert surgeon using Colorado2 instrumentation. Surgeon's knowledge acquisition has permitted to define eleven detailed independent data cards for the different steps of surgery like hook or screw insertion, rod installation, etc... The behaviour of the concerned elements on its neighbouring entity were specified using three matrices. The link between surgery and modelling becomes easier and permits to better define the boundary conditions on each entity during the simulation.

Artificial Intelligence↗