Is it time for computer-assisted decision making to improve the quality of food and nutrition services?
Explore the source record for details and available documents.
Artificial Intelligence↗
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.
Geovisualization for knowledge construction and decision support.
Explore the source record for details and available documents.
Artificial Intelligence↗
A new information processing measure for adaptive complex systems.
This paper presents an implementation-independent measure of the amount of information processing performed by (part of) an adaptive system which depends on the goal to be performed by the overall system. This new measure gives rise to a theoretical framework under which several classical supervised and unsupervised learning algorithms fall and, additionally, new efficient learning algorithms can be derived. In the context of neural networks, the framework of information theory strives to design neurally inspired structures from which complex functionality should emerge. Yet, classical measures of information have not taken an explicit account of some of the fundamental concepts in brain theory and neural computation, namely that optimal coding depends on the specific task(s) to be solved by the system and that goal orientedness also depends on extracting relevant information from the environment to be able to affect it in the desired way. We present a new information processing measure that takes into account both the extraction of relevant information and the reduction of spurious information for the task to be solved by the system. This measure is implementation-independent and therefore can be used to analyze and design different adaptive systems. Specifically, we show its application for learning perceptrons, decision trees and linear autoencoders.
Algorithms↗
Evolving rule-based systems in two medical domains using genetic programming.
OBJECTIVE: To demonstrate and compare the application of different genetic programming (GP) based intelligent methodologies for the construction of rule-based systems in two medical domains: the diagnosis of aphasia's subtypes and the classification of pap-smear examinations. MATERIAL: Past data representing (a) successful diagnosis of aphasia's subtypes from collaborating medical experts through a free interview per patient, and (b) correctly classified smears (images of cells) by cyto-technologists, previously stained using the Papanicolaou method. METHODS: Initially a hybrid approach is proposed, which combines standard genetic programming and heuristic hierarchical crisp rule-base construction. Then, genetic programming for the production of crisp rule based systems is attempted. Finally, another hybrid intelligent model is composed by a grammar driven genetic programming system for the generation of fuzzy rule-based systems. RESULTS: Results denote the effectiveness of the proposed systems, while they are also compared for their efficiency, accuracy and comprehensibility, to those of an inductive machine learning approach as well as to those of a standard genetic programming symbolic expression approach. CONCLUSION: The proposed GP-based intelligent methodologies are able to produce accurate and comprehensible results for medical experts performing competitive to other intelligent approaches. The aim of the authors was the production of accurate but also sensible decision rules that could potentially help medical doctors to extract conclusions, even at the expense of a higher classification score achievement.
Aphasia↗
Evaluation of the speech intelligibility rating (SIR) test for hearing aid comparisons.
The SIR test was created for use in hearing aid comparisons. The test protocol obtains listener judgments of the intelligibility of connected speech passages. This study was conducted to evaluate the effectiveness of the SIR test in differentiating among hearing aids. Specific research questions were (a) Is the sensitivity of the SIR test sufficient for differentiating among very similar and slightly dissimilar hearing aids? (b) Does the SIR test result in reliable hearing aid rankings? and (c) What are the effects of using shortened connected speech passages? Ten listeners with hearing impairments rated the intelligibility of both full-length and shortened SIR test passages while wearing each of four individually selected hearing aids representing three different frequency/gain prescriptions. Results suggested that the SIR test is capable of differentiating among slightly dissimilar hearing aids and that hearing aid rankings resulting from speech intelligibility ratings were reliable. The decision to use full-length or shortened SIR test passages depends on the outcome the user wishes to maximize. Under the conditions used in this study, maximum sensitivity was achieved with ratings from five shortened passages, whereas maximum reliability was obtained with three full-length passages.
Adult↗
Artificial intelligence.
Explore the source record for details and available documents.
Decision Support Techniques↗
Achieving reuse of computable guideline systems.
We describe an architecture for reusing computable guidelines and the programs used to interpret them across varied legacy clinical systems. Developed for the PRODIGY 3 project, our architecture aims to support interactive, point of care use of guidelines in primary care. Legacy medical record systems in UK primary care are diverse, using different terminologies, different data models, and varying user-interface philosophies. However, our goal is to provide common guideline knowledge bases and system components, while achieving full integration with the host medical record system, and a user interface tailored to that system. In conjunction with system suppliers, we identified areas of standardization required to achieve this goal. Firstly, standardized interfaces were created for mediation with the legacy system medical record and for act management. Secondly, a standard interface was developed for communication with the User Interface for guideline interaction. Thirdly, a terminology mapping knowledge base and system component was provided. Lastly, we developed a numeric unit conversion knowledge base and system component. The standardization of this architecture was achieved by close collaboration with existing vendors of Primary Care computing systems in the UK. The work has been verified by two suppliers successfully building and deploying systems with User Interfaces which mirror their normal look and feel, communicating fully with existing medical records, while using identical Guideline Interpreter components and knowledge bases. Encouragingly further experiments in other areas of clinical decision support have not required extension of our interfaces.
Artificial Intelligence↗
STRATEGIES OF NORMAL AND MENTALLY RETARDED CHILDREN UNDER CONDITIONS OF UNCERTAIN OUTCOME.
Explore the source record for details and available documents.
Biomedical Research↗
The reaction of adolescent offenders and nonoffenders to nonverbal emotion displays.
Adolescent male offenders and nonoffenders were compared on two tasks designed to assess reactions to the nonverbal emotion expressions of others. It was found that the offender group was less accurate in labeling another's emotion states but that this difference was apparently a function of verbal intelligence. Further, the results of the second task, a task not related to verbal intelligence, indicated that the punitive decisions of both the offender and nonoffender groups were similarly affected by the actors' nonverbal emotions. These results wree discussed as indicating that much of the social insensitivity often ascribed to delinquents may simply be a result of impoverished verbal skills among this group. A deficit in verbal skills may preclude delinquents from adequately describing their perceptions of the emotional reactions of others and it may also necessitate a nonverbal, rather than verbal, reaction to others' emotions.
Adolescent↗
On the heuristic nature of medical decision-support systems.
In the realm of medical decision-support systems, the term "heuristic systems" is often considered to be synonymous with "medical artificial intelligence systems" or with "systems employing informal model(s) of problem solving". Such a view may be inaccurate and possibly impede the conceptual development of future systems. This article examines the nature of heuristics and the levels at which heuristic solutions are introduced during system design and implementation. The authors discuss why heuristics are ubiquitous in all medical decision-support systems operating at non-trivial domains, and propose a unifying definition of heuristics that encompasses formal and ad hoc systems. System developers should be aware of the heuristic nature of all problem solving done in complex real world domains, and characterize their own use of heuristics in describing system development and implementation.
Artificial Intelligence↗
Defining medical concepts by linguistic variables with fuzzy Arden Syntax.
Diagnostic and therapeutic decisions in the domain of medicine usually depend on observed or measured data, such as observations made during an examination, or laboratory data. Furthermore, such decisions are often based on abstract domain knowledge. For decision-making, it is necessary to establish relationships between concrete data and abstract knowledge. These relationships can be defined in a formal way by fuzzy set theory. We extended the Arden Syntax for Medical Logic Systems, which can be used for decision support in the medical domain, to include concepts of fuzzy set theory. This paper presents extensions for defining linguistic variables by Arden Syntax, which can formalize different states of an abstract concept, such as different levels of blood glucose. Arden Syntax linguistic variables can be used within conditional expressions in decision rules or within fuzzy control rules for computer-aided diagnosis and therapy.
Artificial Intelligence↗
Artificial intelligence-driven advancements in agricultural biotechnology.
The need for faster and more informative data processing for better decision-making is driving the adoption of artificial intelligence (AI) in the agricultural sector. Thanks to recent advancements in computer science and the increase in computational powers of modern computers, AI is not only augmenting traditional solutions, but also helping in developing novel solutions to existing challenging matters. AI-driven models have an exceptional ability to identify patterns and combine a diverse collection of data together and make inference. The increasing pressure on farmlands posed by the growing global population and climate change is lessening growth, yield, and productivity ultimately posing risk to food security worldwide. Incorporation of AI in agriculture has the potential to drive farming efficiency to new heights. This comprehensive review critically evaluates the evolution of AI in agricultural biotechnology from a theoretical concept to a global phenomenon. A comprehensive literature search was performed using major scientific databases, including PubMed, Web of Science, Embase, Scopus, Lens and the Cochrane Library. In this review, we empirically demonstrate the fields advancement toward more capable AI systems and discuss the current applications of AI across crop improvement and precision agriculture such as crop improvement and genetic engineering, genomic selection and plant breeding, pest and disease detection, precision agriculture and smart farming, soil health and nutrient management, climate resilient crop development, livestock biotechnology, challenges and ethical considerations in AI based agricultural biotechnology. Furthermore, this review addresses the exponential growth of commercial intellectual property in the field and contrast it with academic publication outputs. Finally, we critically assess the ethical challenges impeding equitable adoption of AI including data sovereignty and digital divide, while projecting future frontiers involving quantum computing. This review will help build sustainable agricultural systems capable of adapting to climate change, contribute to the development of climate-resilient and high-yielding crops, and address global food security challenges.
Agriculture↗
Quantitative theories for clinical decision making.
Clinical work involves a great many decisions in situations characterized by uncertainty and by the need for value judgments. Formal, mostly quantitative approaches to medical decision making have been developed over the last thirty years. The best known theories are discriminant analysis or supervised pattern recognition, decision analysis and, more recently, artificial intelligence. Discriminant analysis is used for estimating diagnostic probabilities on the basis of diagnostic data. Outcome, action, state, probability, utility, and choice are the main concepts of decision analysis. Problems of diagnosis and therapy choice can be structured within the framework of decision analysis. The quality of a decision analysis largely depends on a good structuring of the problem, and on the quality of the probability and utility assessments made during the analysis. Decision analysis is basically a prescriptive theory for decision making in individual patient management. Other areas of application include basic and advanced teaching, formulation, explication and analysis of clinical problems, detection of gaps in clinical knowledge, development of clinical protocols, etc.
Decision Making↗
[A discussion of the curability of childhood epilepsies (author's transl)].
Permanent freedom from fits can be achieved in a large proportion of children with a history of epilepsy through precise individual adjustment and careful maintenance of the therapeutic regimen. A review of the cases treated at the Pediatric Clinic, out-Patient-Department for Epileptics, University of Vienna, reveals that at present about 70% of the patients have a good prognosis (the figures vary from 50 to 85%, depending on the seizure type). An important question which has received only scant attention in the literature arises in the case of patients who have remained free from epileptic fits over a period of many years, namely whether longterm antiepileptic therapy can be terminated and, if so, then when and how. Only very few studies deal specifically with this problem and even these do not provide entirely satisfactory answers to all the posed questions, not only with regard to the optimum time and mode of drug reduction, but also with regard to the principles underlying the choice of apparently suitable candidates for attempted termination of therapy. An attempt is made in this retrospective study comprising 375 patients who have been followed up over a period of at least 5 years, to throw some light on these problems. Indeed, results of statistical significance were obtained by the use of a new mathematical technique, which enables the formulation of new guiding principles in the resolution of all three above-mentioned questions. In consequence, it now appears within the power of the pediatrician to markedly reduce the risk of relapse, which in the case of childhood epilepsies, is about 20%, at present. In general, several basic principles must be adhered to. Total freedom from convulsions over an uninterrupted period of at least 3 years' duration is an absolute prerequisite for consideration of cessation of therapy. Reduction in antiepileptic drug dosage should be carried out as a stepwise procedure over a period of about 2 years. Regular clinical and EEG follow-up examinations should be performed over this period of drug reduction and for 5 years subsequently, in order to recognise and counteract promptly any early signs of possible relapse. The prerequisite convulsionfree period is raised to 4 to 5 years or even longer and the time over which therapy is tailed off increased accordingly in the presence of any of the following criteria: 1. "Endogenous" tendency to relapse, 2. persistence of paroxysmal EEG abnormalities or deterioration of the EEG during the attempt to reduce the dosage of antiepileptic drugs, 3. inveterate epilepsy. The cessation of fits and the termination of medication do not yet signify that all the after-effects of epilepsy are overcome. Social integration must also be achieved before this goal is reached. The psychopathological symptomatology of the patient plays an important role in determining the outcome, whereby the level of intelligence of the patient is the decisive factor...
Barbiturates↗
An intelligent ventilation and oxygenation management system in neonatal intensive care using fuzzy trend template fitting.
This paper describes an open loop feedback intelligent system for neonatal intensive care management. The system provides a tool enabling the user to make the final decision to accept or reject the advice given. The system collects 18 parameters from the bedside monitor and ventilator using a Medical Information Bus (MIB) system. Comparison between the system's recommendations and seven clinical users (three doctors and four nurses) actions was made during monitoring of seven neonates with gestation age of 27-31 weeks for 124.13 h (mu=17.7329, sigma=5.3843 h, range=10.40-23.85 h). The validation process compared the recommendations triggered by the system with the user feedback (agree, disagree, wait). The system made 191 recommendations in total, 33 of which (17%) were for ventilation and 158 (83%) for oxygenation. The clinician agreed with the system ventilation decisions in 30 occasions (91%) and in 148 occasions for the system oxygenation decisions (94%). The overall percentage of the agreement between the system and the clinician was 93%.
Artificial Intelligence↗
Understanding central post-stroke pain.
Almost a century ago, two French neurologists described an unusual pain syndrome following stroke. This so-called "thalamic" pain of Dejerine-Roussy exists today, affecting approximately 30,000 survivors of stroke in the United States (US) alone. Lesions involving the neospinothalamocortical tract are thought to cause thalamic pain, but the exact pathogenesis is unclear. Pharmacotherapeutic and surgical approaches offer pain relief in selected patients. Although definitive relief of central post-stroke pain (CPSP) may not be achievable for all at this time, intelligent and informed examination of the full range of options offers every sufferer a real potential for relief and mastery of pain. It is hoped that information provided herein will foster "intelligent caring" and facilitate informed decision making by consumers and caregivers alike.
Analgesics↗
Estimating the intelligibility of speakers with dysarthria.
Many speakers with dysarthria have reduced intelligibility, and improving intelligibility is often a primary intervention objective. Consequently, measurement of intelligibility provides important information that is useful for clinical decision-making. The present study compared two different measures of intelligibility obtained in audio-only and audio-visual modalities for 4 different speakers with dysarthria (2 with mild-moderate dysarthria; 2 with severe dysarthria) secondary to cerebral palsy. A total of 80 college-aged listeners provided word-by-word transcriptions and made percent estimates of intelligibility which served as dependent variables. Group results showed that transcription measures were higher than percent estimates of intelligibility overall. There was also an interaction between speakers and measures of intelligibility, indicating that the difference between transcription scores and percent estimates varied among individual speakers. Results revealed a significant main effect for presentation modality, with the audio-visual modality having slightly higher scores than the audio-only modality; however, presentation modality did not interact with speakers or with measures of intelligibility. Results suggest that standard clinical measurement of intelligibility using orthographic transcription may be more consistent than the use of more subjective percent estimates.
Adult↗
Defaults, exceptions and ambiguity in a medical knowledge representation system.
Inheritance methods for general semantic networks which allow for exceptions are essential to representing medical knowledge in forms which are familiar to doctors. Such systems give rise to the possibility of ambiguity and problems of computational efficiency. Efficient computational methods using conventional hardware for inheritance and the detection of ambiguity in general semantic networks are described. These methods have been implemented in PROLOG in a knowledge management system which is being used in the development of intelligent drug information and medical decision support systems.
Algorithms↗