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 1,477 records · Page 82Linked to original sources
PubMed1993

Decisions about enteral tube feeding among the elderly.

OBJECTIVE: To determine choices about enteral tube feeding and factors associated with deciding to accept or forego this intervention in a group of ambulatory non-demented older individuals. DESIGN: Descriptive survey. SETTING AND PARTICIPANTS: Thirty four volunteers from a senior adult day center and 34 volunteers from the residential care section of a multilevel long-term care institution, mean age 77.8. INTERVENTION: Structured interview using a hypothetical clinical vignette in simplified language, story-book format depicting an irreversibly and severely impaired state of health. MEASUREMENT: Choice of whether to accept or forego enteral tube feeding based on the clinical vignette. RESULTS: Thirty four (50%) decided to accept and 34 (50%) chose to forego enteral tube feeding in the situation presented in the vignette. No demographic, cognitive, or affective factors were associated with the decision. Presentation of the vignette and associated questions were not anxiety-provoking or upsetting to the vast majority of participants. CONCLUSION: A hypothetical clinical vignette depicting a state of severely impaired health resulted in 34 (50%) of 68 ambulatory non-demented older individuals deciding to accept enteral tube feeding. No factors we examined were strongly associated with the decision. The vignette and discussion were not anxiety-provoking when presented in the format used in this study. Advance-directive discussions about enteral tube feeding and other health care decisions, using understandable hypothetical clinical vignettes that describe risks and benefits that might influence decisions, should be encouraged in the practice of geriatric medicine.

Advance Directives↗
PubMed1987

In re X, June 1987.

The Court ruled that it was not unlawful to terminate the defendant's pregnancy by reason only of her inability to give informed consent. She was a pregnant adult suffering from Down's syndrome and severe mental retardation. The Court held that the medical evidence showed that the abortion was in the defendant's best interest and that there was also a substantial risk that the child would be affected by Down's syndrome.

Abortion, Induced↗
PubMed2004

[Knowledge discovery in database and its application in clinical diagnosis].

Nowadays the tremendous amount of data has far exceeded our human ability for comprehension, and this has been particularly true for the medical database. However, traditional statistical techniques are no longer adequate for analyzing this vast collection of data. Knowledge discovery in database and data mining play an important role in analyzing data and uncovering important data patterns. This paper briefly presents the concepts of knowledge discovery in database and data mining, then describes the rough set theory, and gives some examples based on rough set.

Artificial Intelligence↗
PubMed1994

[Informatics education in undergraduate study at the 1st Medical School of Charles University].

History of medical informatics at the 1st Medical Faculty goes to 25 years back. Currently curriculum is divided in two parts. In the first year of studies and obligatory course of computer technique is organized including: computer functions, communications with computers, database systems and text editors. In the 4th year of studies a course in clinical informatics is realized including: principles of computer science, statistical software, artificial intelligence, computer in pedagogy, scientific information, classification in medicine, biological signal and picture analysis, hospital information systems, computer in outpatient ward, clinical decision support, computer simulation in clinical medicine, computers in pharmacology, computer in metabolic care, computers in medical devices. In this way medical students are prepared to be able to use technical means in scientific information management.

Czech Republic↗
PubMed2026

Trustworthy Agentic AI in Bioinformatics: From Workflow Automation to Traceable and Validated Biological Inference.

Agentic artificial intelligence is extending bioinformatics beyond conversational assistance by enabling systems to select tools, execute code, revise analytical plans, and interpret biological data. These capabilities may accelerate research, but they also redistribute decisions that determine whether biological conclusions are valid. We conducted a targeted, structured PubMed search in July 2026 and identified 11 peer-reviewed agentic bioinformatics systems for descriptive review based on predefined eligibility criteria for analytical decision-making, tool or code execution, iterative evaluation, or coordinated agent activity. The evidence base covered single-cell transcriptomics, microbial genomics, cancer genomics, and omics applications, together with methodological literature on reproducibility and biological validation. We examined how current systems report delegated authority, provenance, validation, evidence, abstention, and human oversight. Existing platforms implement safeguards such as sandboxed execution, restricted commands, interaction logs, evidence identifiers, automated checks, critic agents, quality scores, and expert assessment. However, published reports rarely provide a connected account linking the original biological question to samples, reference resources, analytical decisions, computational actions, statistical results, supporting evidence, validation outcomes, and final claims. We distinguish inherited bioinformatics errors, errors amplified through autonomous action, and emergent failures arising from memory, retrieval, tool interaction, or agent coordination. We further propose a multidimensional decision-rights profile, consequence-sensitive validation gates, and a claim-to-evidence provenance architecture organized through the Traceable History of Research Evidence, Agent Actions, and Decisions in Bioinformatics (THREAD-Bio) framework. Illustrative cases show that technically successful execution may still support misleading inference. Trustworthy agentic bioinformatics therefore requires claims to remain reconstructible, challengeable, validated, and proportionate to the evidence.

accountable autonomy↗
PubMed1994

Is it true that the differences in reading performance between students with and without LD cannot be explained by IQ?

This study was designed to demonstrate whether the differences in reading between students with learning disabilities (LD) and non-learning disabled students (NLD) can be explained by IQ. A sample of 133 Spanish children (85 male, 48 female) ranging in age from 8 to 13 years were classified into four groups according to IQ as measured by the Wechsler Intelligence Scale for Children-Revised (< 80; 81-90; 91-109: 110-140) and into two groups based on reading level (LD and NLD). A lexical decision task was used and we manipulated different word parameters (length, positional syllabic frequency, and familiarity) and pseudoword parameters (length and positional syllabic frequency) to study the routes used by both groups. Our findings indicate that IQ does not explain the differences between children with LD and NLD children in lexical processing. We found that the lexical and sublexical parameters have a greater influence on students with LD than NLD students, independent of IQ. In synthesis, the LD group has more difficulty in lexical processing, which is influenced by poor phonological skills.

Adolescent↗
PubMed1979

Dynamic electromyography and decision-making for surgery in the upper extremity of patients with cerebral palsy.

Seventeen children with cerebral palsy were selected for improvement in upper extremity function. Each had normal or nearly normal intelligence; each hand had good or mildly impaired sensibility; each arm had relatively good placement. Electromyograms with wire electrodes were utilized to study the patterns of activity of the planned tendon transfers. Only muscles with isolated activity in grasp were utilized to transfer in hands with weak grasp. Only muscles with isolated activity in release were utilized to transfer in hands with poor release.

Adolescent↗
PubMed1981

A method for the quantification of the decision-making process in a computer-oriented medical world.

The aim of this paper is to suggest an original approach to the decision-making process in a computer-oriented medical record, now in use on an experimental basis, at a major District Hospital in Sesto S. Giovanni, near Milano, in a general medicine department. Two types of algorithms are introduced in order to 'capture' more effectively the different steps of the decisional process on the basis of a differential diagnosis approach. The first refers to the field of symbolic reasoning, close to the area of Artificial Intelligence and uses score variables, while the other can handle qualitative expressions since it follows the fuzzy-set approach. A comparison among the performances offered by such algorithms, the physician's decision and the Bayes Rule is then carried on. Further developments should clarify the problems of parameter sensitivity as regards the successive steps to the final diagnosis. The present implementation is suitable for individual hospital departments and educational purposes.

Decision Making↗
PubMed2004

Onvergence and application of online active sampling using orthogonal pillar vectors.

The analysis of convergence and its application is shown for the Active Sampling-at-the-Boundary method applied to multidimensional space using orthogonal pillar vectors. Active learning method facilitates identifying an optimal decision boundary for pattern classification in machine learning. The result of this method is compared with the standard active learning method that uses random sampling on the decision boundary hyperplane. The comparison is done through simulation and application to the real-world data from the UCI benchmark data set. The boundary is modeled as a nonseparable linear decision hyperplane in multidimensional space with a stochastic oracle.

Algorithms↗
PubMed1996

Automated reasoning system in histopathologic diagnosis and prognosis of prostate cancer and its precursors.

OBJECTIVE: This article presents the rationale and options offered to diagnostic and prognostic decision support systems for prostate pathology by automated reasoning capabilities. METHODS: The symbolic information used in diagnostic decision-making is systematically ordered, compared, numerically assessed in its probability, and combined such that a conclusion can be drawn. The framework for the processing of such symbolic information may be an expert system, an inference network or a case-based reasoning system. Automated reasoning is implemented by the use of a rule base and information flow control modules. RESULTS: Automated reasoning allows decision support systems to follow highly adaptive decision sequences, capable of handling contradictory evidence, exceptions in diagnostic clue expression, and nonmonotonic decision-making. CONCLUSIONS: Automated reasoning capability in diagnostic and prognostic decision support systems allows highly flexible decision development, very close to human decision procedures.

Artificial Intelligence↗
PubMed2006

Childhood lead poisoning: the torturous path from science to policy.

The long history of lead poisoning provides many lessons about the process by which scientific knowledge is translated into public health policy. In the United States, lead was added to paint and to gasoline in enormous quantities long after medical evidence clearly showed that excessive lead exposure caused considerable morbidity in the population. This article discusses some of the factors that contributed to the slow pace of efforts to address this problem, including the ubiquity and magnitude of lead exposure during much of the twentieth century, which produced a distorted notion about the blood lead level that can be considered "normal"; the prevailing model of disease during this period, notably the novelty of the concept of subclinical disease; the fact that childhood lead poisoning affected mostly families that were politically and economically disenfranchised, fostering a "blame the victim" attitude; and that controlling lead exposure would have impeded efforts to achieve other desirable goals, illustrating the role that value trade-offs often play in policy decisions.

Child↗
PubMedDate not supplied

Selecting physical security equipment.

Examining the strengths and weaknesses of the various types of physical equipment currently available is the first step to intelligently selecting the equipment that will best meet your particular security needs.

Decision Making↗
PubMed2000

The use of artificial intelligence technology to predict lymph node spread in men with clinically localized prostate carcinoma.

BACKGROUND: The current study assesses artificial intelligence methods to identify prostate carcinoma patients at low risk for lymph node spread. If patients can be assigned accurately to a low risk group, unnecessary lymph node dissections can be avoided, thereby reducing morbidity and costs. METHODS: A rule-derivation technology for simple decision-tree analysis was trained and validated using patient data from a large database (4,133 patients) to derive low risk cutoff values for Gleason sum and prostate specific antigen (PSA) level. An empiric analysis was used to derive a low risk cutoff value for clinical TNM stage. These cutoff values then were applied to 2 additional, smaller databases (227 and 330 patients, respectively) from separate institutions. RESULTS: The decision-tree protocol derived cutoff values of < or = 6 for Gleason sum and < or = 10.6 ng/mL for PSA. The empiric analysis yielded a clinical TNM stage low risk cutoff value of < or = T2a. When these cutoff values were applied to the larger database, 44% of patients were classified as being at low risk for lymph node metastases (0.8% false-negative rate). When the same cutoff values were applied to the smaller databases, between 11 and 43% of patients were classified as low risk with a false-negative rate of between 0.0 and 0.7%. CONCLUSIONS: The results of the current study indicate that a population of prostate carcinoma patients at low risk for lymph node metastases can be identified accurately using a simple decision algorithm that considers preoperative PSA, Gleason sum, and clinical TNM stage. The risk of lymph node metastases in these patients is < or = 1%; therefore, pelvic lymph node dissection may be avoided safely. The implications of these findings in surgical and nonsurgical treatment are significant.

Acid Phosphatase↗
PubMed2003

Decision support systems to identify different species of malarial parasites.

In this project, medical expert systems were designed to aid technicians, students and scientists in identifying various species of malarial parasite from blood smears. The rule based system was found to intelligently ask pertinent questions to accurately and efficiently identify the species of malarial parasite. The probabilistic system provided quantitative feedback as to the likelihood of a diagnosis of a species of malaria. Medical expert systems can potentially streamline the process of malarial species identification, and can aid in training new technicians and scientists in this important skill.

Animals↗
PubMedDate not supplied

Reinforcement learning with internal expectation in the random neural networks for cascaded decisions.

The reinforcement learning scheme proposed in Halici (J. Biosystems 40 (1997) 83) for the random neural network (RNN) (Neural Computation 1 (1989) 502) is based on reward and performs well for stationary environments. However, when the environment is not stationary it suffers from getting stuck to the previously learned action and extinction is not possible. To overcome the problem, the reinforcement scheme is extended in Halici (Eur. J. Oper. Res., 126(2000) 288) by introducing a new weight update rule (E-rule) which takes into consideration the internal expectation of reinforcement. Although the E-rule is proposed for the RNN, it can be used for training learning automata or other intelligent systems based on reinforcement learning. This paper looks into the behavior of the learning scheme with internal expectation for the environments where the reinforcement is obtained after a sequence of cascaded decisions. The simulation results have shown that the RNN learns well and extinction is possible even for the cases with several decision steps and with hundreds of possible decision paths.

Computer Simulation↗