SEARCH · PubMed Health

Results for “Intelligent agents”

Explore indexed PubMed citations for clinical trials, systematic reviews and public health research. Read source abstracts and follow each citation to its original PubMed record.

Quote a phrase for an exact phrase match. Source license links do not imply unrestricted reuse.

At least 901 records · Page 50Linked to original sources

PubMed2004

A novel self-organizing E-Learner community model with award and exchange mechanisms.

How to share experience and resources among learners is becoming one of the hottest topics in the field of E-Learning collaborative techniques. An intuitive way to achieve this objective is to group learners which can help each other into the same community and help them learn collaboratively. In this paper, we proposed a novel community self-organization model based on multi-agent mechanism, which can automatically group learners with similar preferences and capabilities. In particular, we proposed award and exchange schemas with evaluation and preference track records to raise the performance of this algorithm. The description of learner capability, the matchmaking process, the definition of evaluation and preference track records, the rules of award and exchange schemas and the self-organization algorithm are all discussed in this paper. Meanwhile, a prototype has been built to verify the validity and efficiency of the algorithm. Experiments based on real learner data showed that this mechanism can organize learner communities properly and efficiently; and that it has sustainable improved efficiency and scalability.

Algorithms↗

PubMed2005

Cognitive changes in children treated for acute lymphoblastic leukemia with chemotherapy only according to the Pediatric Oncology Group 9605 protocol.

The purpose of this study was to examine cognitive functioning and neuroimaging in children with leukemia treated with the Pediatric Oncology Group 9605 protocol at the Children's Hospital of Eastern Ontario. Mean age at diagnosis was 4.88 +/- 2.54 years. The mean (n = 24) Wechsler Verbal and Performance IQ fell in the low-average range (87.33 +/- 15.69 and 84.83 +/- 19.11, respectively). Mean (n = 20) Verbal and Visual Memory Indexes of 82.95 +/- 15.46 and 88.30+/- 10.80, respectively, were obtained. The proportion of scores on measures of intelligence and memory falling > 1 SD below the normative mean was substantially higher than expected. Paired t-test suggested that Wechsler Verbal IQ and memory remained stable, whereas Wechsler Performance IQ declined significantly. The results of growth curve analyses replicated these findings and suggested a significant adverse effect of cumulative dosage of intrathecal methotrexate on estimated Wechsler Performance IQ. Although only two children experienced seizures, 78% of the group showed leukoencephalopathy on at least one magnetic resonance image. Reliance on seizures as a predictor of leukoencephalopathy might underestimate the incidence of neurotoxicity.

Anti-Inflammatory Agents↗

PubMed1996

High-throughput cDNA screening utilizing a low order neural network filter.

A low order neural network-based filter was designed as a rapid screening agent for single-spanning transmembrane regions in an integrated informatics system. A rapid screening algorithm was seen as a compromise between costly structure-specific techniques and simple rules that gave a high false-positive rate for cDNA. The filter was applied to a library of 2123 anonymous cDNA sequences, which resulted in 61 detections. Evaluation of the detections with two other dissimilar computer prediction algorithms yielded strong transmembrane predictions for 15 of the detections, while 8 of the detections resulted in a definitive negative result. Homology searches performed on the sequences with detection reports yielded 13 homologs in the predicted reading frame, four of which are membrane associated.

Animals↗

PubMed1983

Do the mentally retarded suffer from affective illness?

Twenty-five published reports were reviewed regarding the occurrence of affective illness, ie, depression and mania, in mentally retarded individuals, using the DSM-III criteria to assess the validity of both diagnoses. Individuals with mental retardation (MR) were found to manifest the full range of affective disorders. Developmentally impaired social functioning and intelligence influence the clinical presentation, but not the development, of affective symptomatology. Affective disorder diagnoses can be made for patients with all levels of MR severity. In individuals with MR of mild and moderate severity, the diagnosis can be made using standard DSM-III criteria. For those with severe and profound MR, a clinically useful diagnosis can be based on changes in behavior and vegetative functioning, as well as family history of affective illness. The psychiatrically symptomatic person with MR should always be evaluated for affective symptomatology and be considered as a candidate for the full range of treatments, including psychotherapy and pharmacotherapy with antidepressants as well as lithium carbonate.

Adolescent↗

PubMed1984

Medical plan-analysis by computer: critiquing the pharmacologic management of essential hypertension.

A computer system, HT-ATTENDING, has been developed using Artificial Intelligence techniques to critique a physician's approach to the pharmacologic management of essential hypertension. HT-ATTENDING (1) assists the physician in the management of a hypertensive patient, (2) helps avoid inadvertent management errors, (3) provides information about new drugs and new treatment modalities, and (4) mentions relevant topical issues, all in the context of discussing an approach to a particular patient's care. To critique a physician's management plan effectively, HT-ATTENDING must accommodate the inherent variation of medical practice as a central part of its design. HT-ATTENDING can be thought of as an "interactive paper" which tailors its content around a proposed approach to a patient's care.

Antihypertensive Agents↗

PubMed2004

Automated segmentation of human brain MR images using a multi-agent approach.

Image interpretation consists in finding a correspondence between radiometric information and symbolic labeling with respect to specific spatial constraints. It is intrinsically a distributed process in terms of goals to be reached, zones in the image to be processed and methods to be applied. To cope the the difficulty inherent in this process, several information processing steps are required to gradually extract information. In this paper we advocate the use of situated cooperative agents as a framework for managing such steps. Dedicated agent behaviors are dynamically adapted depending on their position in the image, of their topographic relationships and of the radiometric information available. The information collected by the agents is gathered, shared via qualitative maps, or used as soon as available by acquaintances. Incremental refinement of interpretation is obtained through a coarse to fine strategy. Our work is essentially focused on radiometry-based tissue interpretation where knowledge is introduced or extracted at several levels to estimate models for tissue-intensity distribution and to cope with noise, intensity non-uniformity and partial volume effect. Several experiments on phantom and real images were performed. A complete volume can be segmented in less than 5 min with about 0.84% accuracy of the segmented reference. Comparison with other techniques demonstrates the potential interest of our approach for magnetic resonance imaging (MRI) brain scan interpretation.

Artificial Intelligence↗

PubMed2004

Bio-steps beyond Turing.

Are there 'biologically computing agents' capable to compute Turing uncomputable functions? It is perhaps tempting to dismiss this question with a negative answer. Quite the opposite, for the first time in the literature on molecular computing we contend that the answer is not theoretically negative. Our results will be formulated in the language of membrane computing (P systems). Some mathematical results presented here are interesting in themselves. In contrast with most speed-up methods which are based on non-determinism, our results rest upon some universality results proved for deterministic P systems. These results will be used for building "accelerated P systems". In contrast with the case of Turing machines, acceleration is a part of the hardware (not a quality of the environment) and it is realised either by decreasing the size of "reactors" or by speeding-up the communication channels. Consequently, two acceleration postulates of biological inspiration are introduced; each of them poses specific questions to biology. Finally, in a more speculative part of the paper, we will deal with Turing non-computability activity of the brain and possible forms of (extraterrestrial) intelligence.

Cell Membrane↗

PubMed2004

Treatment of alcohol withdrawal: chlormethiazole vs. carbamazepine and the effect on memory performance--a pilot study.

Although relatively little attention has been paid to the question how acute alcohol withdrawal might affect cognitive functions, this factor remains of particular interest because it influences psychotherapeutic treatment during detoxification. The clinical outcome and neuropsychological state of 37 inpatients with alcohol withdrawal was investigated in a randomized single-blind approach. Two different medical strategies [chlormethiazole (CMZ) vs. carbamazepine (CBZ)] in the treatment of inpatients with alcohol withdrawal syndrome were compared. Among comparable groups (related to gender, age, initial alcohol level, severity of abuses, severity of initial withdrawal symptoms such as tremor, perspiration, psychomotor agitation, hallucinations, orientation, intelligence, patient demographics), CBZ is just as potent as CMZ in therapy of withdrawal symptoms (circulatory function, vegetative function, psychomotor activity). Patients in both groups showed initial impairments in some neuropsychological tests (d2, Zahlen-Verbundings test, Beck Depression Inventory, Anxiety Sensitivity Index) with significant improvement during detoxification. Additionally, CBZ-treated patients showed significantly better verbal memory performance during the first days of treatment. Without any addictive potential, CBZ therapy could be very supportive in alcohol detoxification. In addition a higher verbal memory performance state could be favourable for a psychotherapeutic approach.

Adult↗

PubMed1998

Burns in a suicide attempt related to psychiatric side effects of interferon.

A 50-year-old woman was admitted to our critical care center after pouring lamp oil on herself and setting herself on fire. Diagnosed with chronic hepatitis, she had received interferon-alpha at another hospital. During interferon therapy she developed anxiety, irritability, sleeplessness, and depression. At our hospital she underwent fluid resuscitation according to the method of Baxter. After treatment with topical cream and ointment, she underwent skin grafting. Interferon was not given. After discharge, wound healing proved satisfactory. She was intelligent and insightful, and her mental condition remained stable with no apparent emotional problems. As she had no significant past medical or psychiatric history and no history of substance abuse, we believe that her depression was a side effect of interferon therapy. A number of reports have described depression and other psychiatric disorders associated with interferon, but none of these accounts have concerned burns sustained in suicide attempts. This case underscores the potential seriousness of adverse reactions to interferon characterized by emotional disturbance and also illustrates that physicians who treat burn patients need to have an understanding of affective disorders and unusual side effects of medication.

Antiviral Agents↗

PubMed2005

An incremental approach to genetic-algorithms-based classification.

Incremental learning has been widely addressed in the machine learning literature to cope with learning tasks where the learning environment is ever changing or training samples become available over time. However, most research work explores incremental learning with statistical algorithms or neural networks, rather than evolutionary algorithms. The work in this paper employs genetic algorithms (GAs) as basic learning algorithms for incremental learning within one or more classifier agents in a multiagent environment. Four new approaches with different initialization schemes are proposed. They keep the old solutions and use an "integration" operation to integrate them with new elements to accommodate new attributes, while biased mutation and crossover operations are adopted to further evolve a reinforced solution. The simulation results on benchmark classification data sets show that the proposed approaches can deal with the arrival of new input attributes and integrate them with the original input space. It is also shown that the proposed approaches can be successfully used for incremental learning and improve classification rates as compared to the retraining GA. Possible applications for continuous incremental training and feature selection are also discussed.

Algorithms↗

PubMed2004

The search for agents in a causal gap.

This study used a reversal experiment within a participant's frame of reference as a tool for studying human agency. Twenty-seven participants were given a sentence reading task, asked to formulate a rule for choosing which sentence to read, and instructed to fbollow and break the rule in an FBFB or BFBF sequence. Despite the difficulty they had in formulating an unambiguous rule, 23 participants both broke and followed the rule, and 20 broke it with a mutually exclusive opposite. There was evidence that a participant's genetic heritage, learning history, and rule, the experimental task, and the instructions were in no case sufficient to control the sentences he or she read. There was evidence of two causal gaps, one before and one after a participant's choice, and positive evidence of participants' systematic control over the sentences read in reversal experiments.

Cognition↗

PubMed1993

Differential diagnosis and psychopharmacology of dual disorders.

There are multiple potential interactions of substances of abuse with psychiatric illnesses. The individual agents, the stage of abuse, withdrawal, or recovery, and the patient's psychiatric illness must be considered as an integrated whole to ascertain the appropriate interventions. Polysubstance abuse can cause still more complicated interactions. Assessment of differential treatment needs for both the psychiatric illness component and the substance use disorder component permits both elements to be approached, often simultaneously, and can facilitate treatment of both. Ignoring either component can lead to inappropriate treatment or exacerbation of illness. The high rate of comorbidity of chemical dependence and other psychiatric illnesses is intriguing in light of studies that demonstrate vulnerability to drug abuse associated with specific alleles of the dopamine D2 receptor gene in some families. It is hoped that further investigations will shed light on the complex interactions and associations between chemical dependency and other psychiatric illnesses and result in new treatment strategies for both. In the past, many substance abuse treatment programs used to emphasize the complete cessation of all medications including some potentially beneficial prescription medications. This was likely because of previous excessive prescription by physicians of sedatives or benzodiazepines. Increasingly, recovery programs support intelligent, responsible use of nonaddictive psychiatric medications, and AA World Services prints a pamphlet supporting such physician-supervised use. Conversely, psychiatrists previously frequently overlooked or neglected diagnosis and treatment of chemical-dependency disorders. Greater efforts are needed to focus equal energy on diagnosis and treatment of chemical-dependency disorders in "psychiatric" populations. Many studies show that physicians neglect to collect adequate information and are not sufficiently aggressive in referring patients to chemical dependence treatment programs. By combining knowledge and appropriate therapeutic interventions from both psychiatric and addiction treatment fields, the needs of the dually diagnosed patient can be met more adequately.

Adult↗

PubMed2003

Targeted treatments for symptom domains in child and adolescent autism.

CONTEXT: The number of people with autism spectrum disorders has dramatically increased over the past decade, and problem behaviours in autism are an increasing challenge to families, schools, physicians, and other health-care professionals. Pharmacological treatments can effectively target problem behaviours associated with autism. STARTING POINT: Recently, L Namerow and colleagues (J Dev Behav Pediatr 2003; 24: 104-08) presented preliminary data in children and adolescents with autism treated with citalopram, which suggested that selective serotonin-reuptake inhibitors are useful in the reduction of symptom domains such as repetitive behaviours and mood disorders. J McCracken and colleagues (N Engl J Med 2000; 347: 314-21) showed that the atypical antipsychotic risperidone reduced serious behavioural problems, such as tantrums, aggression, or self-injury in children with autism and in children with below-average intelligence quotients. These and other studies show how developments in study design, selection of patients, and outcome measures have allowed treatment trials in autism to progress beyond anecdotal reports and case observations, and show reduction in the severity of specific symptom domains within these disorders. WHERE NEXT? In therapeutic intervention the risk of treatment toxicity must be balanced against the benefits of improved symptom severity. The newer methods enable informed decisions about which patients will benefit from which treatments. Other symptom domains within autism and effects on development need to be evaluated in adequately designed clinical trials. Future strategies include extending treatment to children as young as the preschool years.

Adolescent↗

PubMed2005

Fuzzy OLAP association rules mining-based modular reinforcement learning approach for multiagent systems.

Multiagent systems and data mining have recently attracted considerable attention in the field of computing. Reinforcement learning is the most commonly used learning process for multiagent systems. However, it still has some drawbacks, including modeling other learning agents present in the domain as part of the state of the environment, and some states are experienced much less than others, or some state-action pairs are never visited during the learning phase. Further, before completing the learning process, an agent cannot exhibit a certain behavior in some states that may be experienced sufficiently. In this study, we propose a novel multiagent learning approach to handle these problems. Our approach is based on utilizing the mining process for modular cooperative learning systems. It incorporates fuzziness and online analytical processing (OLAP) based mining to effectively process the information reported by agents. First, we describe a fuzzy data cube OLAP architecture which facilitates effective storage and processing of the state information reported by agents. This way, the action of the other agent, not even in the visual environment. of the agent under consideration, can simply be predicted by extracting online association rules, a well-known data mining technique, from the constructed data cube. Second, we present a new action selection model, which is also based on association rules mining. Finally, we generalize not sufficiently experienced states, by mining multilevel association rules from the proposed fuzzy data cube. Experimental results obtained on two different versions of a well-known pursuit domain show the robustness and effectiveness of the proposed fuzzy OLAP mining based modular learning approach. Finally, we tested the scalability of the approach presented in this paper and compared it with our previous work on modular-fuzzy Q-learning and ordinary Q-learning.

Algorithms↗

PubMed1990

Eliciting principles of hazard identification from experts.

National experts in the field of developmental toxicology were interviewed in order to elicit the principles, or rules-of-thumb, they use in determining if a compound or agent is likely to be a developmental hazard during pregnancy. Several levels of individual and cumulative consensus activity were carried out that resulted in consensus in 71 rules and partial consensus in an additional 24 rules of 145 rules initially elicited. Rules could be divided generically into those affecting the expert's confidence in a piece of scientific evidence and those determining the weight of importance of that evidence in deciding about hazard identification. Topically, the rules also divided into those about the general nature or characteristics of a compound, animal studies testing for an effect of the compound, and human reports about the presence of absence of developmental effects associated with the compound. Several conclusions about the methodology include the following: 1) expert systems must be based on the knowledge of more than one expert; 2) considerable human effort is expended in evaluating the certainty of scientific evidence before combining the evidence for problem solving; 3) how experts use evidence of different degrees of uncertainty in their decisions is a major area that is yet to be determined and that may greatly affect subsequent efforts in artificial intelligence; and 4) knowledge elicitation by interview has limitations but is a workable methodology for medical decision making.

Animal Testing Alternatives↗

PubMed2004

[A study of the effect of donepezil hydrochloride on cognitive function in patients with dementia of Alzheimer's type using WAIS-R].

The present study aimed to assess the initial effects of donepezil hydrochloride (DPZ) on various aspects of cognitive function in patients with dementia of Alzheimer's type (DAT) using the Japanese version of the Wechsler Adult Intelligence Scale-Revised (WAIS-R). DPZ was administered to 47 patients with mild-to-moderate DAT (D group). The control group comprised 61 patients who had been followed up before DPZ was released for use (C group). Both groups underwent WAIS-R testing, before and after 10 months of treatment with DPZ for group D, and at time of diagnosis of DAT and 10 months later for group C. D and C groups did not differ significantly in terms of gender ratio, years of education, age at onset of DAT, age at administration of DPZ or at diagnosis of DAT, severity of dementia, MMSE score, presence of behavioral and psychological symptoms of dementia, concomitant use of psychotropic medication, or initiation of rehabilitation. No significant differences were found between D and C groups in verbal (V), performance (P) or full-scale (F) intelligence quotient (IQ), or in six verbal subtest scores of VIQ and five performance subtest scores of PIQ on WAIS-R, before administration of DPZ or at diagnosis of DAT. For differences between each score on WAIS-R at diagnosis of DAT or before administration of DPZ and 10 months later, DPZ inhibited decreases in FIQ and in VIQ, PIQ, vocabulary, similarities, picture arrangement and object assembly subtest scores on WAIS-R. These indices are related to concept formation and abstract thinking, which form part of executive function. DPZ effectively prevented decline of cognitive function, particularly executive function, in patients with DAT.

Aged↗

PubMed2005

Mild cognitive impairment after adjuvant chemotherapy in breast cancer patients--evaluation of appropriate research design and methodology to measure symptoms.

The development of new chemotherapeutic agents and regimens has contributed to reduced risk of cancer recurrence and prolonged patient survival. However, mild cognitive impairment (MCI), also known as ''chemofog'' or ''chemobrain'' following adjuvant chemotherapy for breast cancer has been reported since the late 1980s. Unfortunately, little is known about it's mechanism, type, severity, and episode length. This article reviewed related studies on the subject, and found that chemotherapy-induced MCI appears to occur in 10-40% of patients, and memory loss and lack of concentration are the most frequent symptoms. The symptoms are apparently transient, but take at least several years to disappear. Reviewed studies show a lack of clear understanding of what causes MCI directly. There is also a lack of consistency in symptom measurement. We point to the need to conduct well-designed studies which begin with a proper hypothesis. Future research needs to be randomized and longitudinal with a base measurement point before the chemotherapy cycle starts. Future studies must adopt an effective and sensitive method to measure MCI. The latest imaging technique, positron emission tomography (PET) may be a powerful tool. Also, all confounding factors, such as age, education, intelligence quotient (IQ), fatigue and depression, hormonal therapy and other treatments should be controlled within the study design. It is hoped that the results of such future studies will allow medical professionals to contemplate effective prevention, treatment and rehabilitation for MCI.

Antineoplastic Combined Chemotherapy Protocols↗

PubMed2006

Cheminformatics analysis and learning in a data pipelining environment.

Workflow technology is being increasingly applied in discovery information to organize and analyze data. SciTegic's Pipeline Pilot is a chemically intelligent implementation of a workflow technology known as data pipelining. It allows scientists to construct and execute workflows using components that encapsulate many cheminformatics based algorithms. In this paper we review SciTegic's methodology for molecular fingerprints, molecular similarity, molecular clustering, maximal common subgraph search and Bayesian learning. Case studies are described showing the application of these methods to the analysis of discovery data such as chemical series and high throughput screening results. The paper demonstrates that the methods are well suited to a wide variety of tasks such as building and applying predictive models of screening data, identifying molecules for lead optimization and the organization of molecules into families with structural commonality.

Anti-Infective Agents↗