Search PubMed⌕ Search

SEARCH · Search PubMed

Results for “artificial 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 991 records · Page 55Linked to original sources
PubMed1989

Constraint matching as a means of designing biochemical experiments in multi-enzyme systems.

A method of qualitative analysis by constraint matching, where expectations derived from theory or from data bases are systematically compared against experimental findings, is described. This was originally developed as an artificial intelligence technique to analyze enzyme kinetic mechanism determinations. It is shown to have been used (without computer involvement) in designing experiments involving a few enzymes, and is suggested as a useful experimental design tool. The experiments in question validate the behavior of insulinoma extracts as models for pancreatic islet glycolysis, which conform to the expectations from the relevant enzyme literature. Possible generalization to other areas of biological research is suggested.

Enzymes↗
PubMed1998

Novel staging tool for localized prostate cancer: a pilot study using genetic adaptive neural networks.

PURPOSE: An estimated $1.5 billion is spent annually for direct medical expenses and an additional $2.5 billion for indirect costs for the management of prostate cancer. Today there are several procedures for staging prostate cancer, including lymph node dissection. Despite these procedures, the accuracy of predicting extracapsular disease remains low (range 37 to 63, mean 45%). Use of multiple staging procedures adds significantly to the costs of managing prostate cancer. Recently artificial intelligence based neural networks have become available for medical applications. Unlike traditional statistical methods, these networks do not assume linearity or homogeneity of variance and, thus, they are more accurate for clinical data. We applied this concept to staging localized prostate cancer and devised an algorithm that can be used for prostate cancer staging. MATERIALS AND METHODS: Our study comprised 1,200 men with clinically organ confined prostate cancer who underwent preoperative staging using serum prostate specific antigen, systematic biopsy and Gleason scoring before radical prostatectomy and lymphadenectomy. The performance of the neural network was validated for a subset of patients and network predictions were compared with actual pathological stage. Mean patient age was 62.9 years, mean serum prostate specific antigen 8.1 ng./ml. and mean biopsy Gleason 6. Of the patients 55% had organ confined disease, 27% positive margins, 8% seminal vesicle involvement and 7% lymph node disease. Of margin positive patients 30% also had seminal vesicle involvement, while of seminal vesicle positive patients 50% also had positive margins. RESULTS: The sensitivity of the network was 81 to 100%, and specificity was 72 to 75% for various predictions of margin, seminal vesicle and lymph node involvement. The negative predictive values tended to be relatively high for all 3 features (range 92 to 100%). The neural network missed only 8% of patients with margin positive disease, and 2% with lymph node and 0% with seminal vesicle involvement. CONCLUSIONS: Our study suggests that neural networks may be useful as an initial staging tool for detection of extracapsular extension in patients with clinically organ confined prostate cancer. These networks preclude unnecessary staging tests for 63% of patients with clinically organ confined prostate cancer.

Algorithms↗
PubMed2006

Neuro-fuzzy modeling: an accurate and interpretable method for predicting bladder cancer progression.

PURPOSE: New methods are required to improve the prediction of cancer progression as traditional statistical tests have limited accuracy. Accurate predictions would allow physicians to offer specific treatment according to individual patient risk. While predictive improvements are obtained using ANN, the hidden nature of these networks prevents insight and has hindered their widespread implementation. NFM is an alternate form of artificial intelligence using fuzzy logic (which is a multivalued logic which provides reasoning under uncertainty). By defuzzification the NFM rule base becomes transparent to overcome the black box nature of ANN. MATERIALS AND METHODS: Combinations of clinicopathological (tumor stage and grade, patient age, gender, and smoking status) and molecular (immunohistochemical expression of p53 and methylation status of 11 loci) data from 117 patients were used to develop and compare predictive models of tumor progression using NFM, ANN and LR. RESULTS: NFM (88% to 100% sensitivity, 97% to 100% specificity and 94% to 100% accuracy) predicted the presence and timing of cancer progression more accurately than ANN (81% to 87%, 95% to 100% and 89% to 90%, p = 0.002) and LR 3%, 61% to 72% and 47% to 53%, p = 0.00005). NFM was able to interrogate the clinicopathological and molecular data, and select the most important parameters (age, grade, stage, smoking, methylation) for progression prediction. CONCLUSIONS: Intelligent systems and molecular biomarkers improved the accuracy of cancer progression predictions. NFM appeared superior to ANN in terms of accuracy, sensitivity, specificity and transparency. The use of NFM in routine clinical practice warrants further validation.

Aged↗
PubMed2001

Noninvasive monitoring in the pediatric intensive care unit.

The best ICU monitors are physicians and nurses, who integrate all of the physiologic parameters of patients with the known pathophysiology of the disease process. Over-reliance on raw electronic data, with their inherent errors, jeopardizes the safe and efficient care of patients. Data must be interpreted in the context of the history, repetitive physical examinations, response to therapy, and a background of experience. New modalities and the application of artificial intelligence may facilitate the interpretation of data, but the role of the bedside medical practitioner remains as the heart of pediatric critical care.

Blood Gas Monitoring, Transcutaneous↗
PubMedDate not supplied

Comparative evaluation of the use of artificial neural networks for modelling the epidemiology of schistosomiasis mansoni.

There has been a marked increase in the application of approaches based on artificial intelligence (AI) in the field of computer science and medical diagnosis, but AI is still relatively unused in epidemiological settings. In this study we report results of the application of neural networks (NN; a special category of AI) to schistosomiasis. It was possible to design an NN structure which can process and fit epidemiological data collected from 251 schoolchildren in Egypt using the first year's data to predict second and third years' infection rates. Data collected over 3 years included age, gender, exposure to canal water and agricultural activities, medical history and examination, and stool and urine parasitology. Schistosoma mansoni infection rates were 50%, 78% and 66% at the baseline and the 2 follow-up periods, respectively. NN modelling was based on the standard back-propagation algorithm, in which we built a suitable configuration of the network, using the first year's data, that optimized performance. It was implemented on an IBM compatible computer using commercially available software. The performance of the NN model in the first year compared favourably with logistic regression (NN sensitivity = 83% (95% confidence interval [CI] 78-88%) and positive predictive value (PPV) = 63% (95% CI 57-69%); logistic regression sensitivity = 66% (95% CI 60%-72%) and PPV = 59% (95% CI 53%-65%). The NN model generalized the criteria for predicting infection over time better than logistic regression and showed more stability over time, as it retained its sensitivity and specificity and had better false positive and negative profiles than logistic regression. The potential of NN-based models to analyse and predict wide-scale control programme data, which are inevitably based on unstable egg excretion rates and insensitive laboratory techniques, is promising but still untapped.

Adolescent↗
PubMed1998

Static cytometry and neural networks in the discrimination of lower urinary system lesions.

OBJECTIVES: To investigate the potential of morphometry and artificial intelligence tools for the discrimination of benign and malignant lower urinary system lesions. METHODS: The study group included 50 cases of lithiasis, 61 cases of inflammation, 99 cases of benign prostatic hyperplasia, 5 cases of in situ carcinoma, 71 cases of grade I transitional cell carcinoma of the bladder (TCCB), and 184 cases of grade II and grade III TCCB. Images of voided urine smears stained by the Giemsa technique were analyzed by a custom image analysis system. The analysis gave a data set of features from 45,452 cells. A learning vector quantizer (LVQ)-type neural network (NN) was used to discriminate benign from malignant cells on the basis of the extracted morphometric and textural features. The data from 13,636 randomly selected cells were used as a training set and the data from the remaining 31,816 cells made up the test set. Similarly, in an attempt to discriminate at the patient level, 30% of the cases randomly selected were used to train an LVQ NN and the remaining 329 cases were used for the test. RESULTS: The application of the LVQ NN enabled the correct classification of 95.42% of the benign cells and 86.75% of the malignant cells, giving an overall accuracy rate of 90.63%. At the patient level, the LVQ NN enabled the correct classification of 100% of benign cases and 95.6% of malignant cases, giving an overall accuracy rate of 97.57%. CONCLUSIONS: NNs combined with image analysis offer useful information in the discrimination of benign and malignant cells and lesions of the lower urinary system.

Diagnosis, Differential↗
PubMed2000

Artificial neural network based identification of environmental bacteria by gas-chromatographic and electrophoretic data.

Chemotaxonomic identification techniques are powerful tools for environmental micro-organisms, for which poor diagnostic schemes are available. Whole cellular fatty acid methyl esters (FAME) content is a stable bacterial profile, the analysis method is rapid, cheap, simple to perform and highly automated. Whole-cell protein is an even more powerful tool because it yields information at or below the species level. The description of new species and genera and subsequent continuous rearrangement provide large amounts of data, resulting in large databases. In order to set up suitable software tools to work on such large databases artificial neural network (ANN) based programs have been used to classify and identify marine bacteria at genus and species levels, starting from the fatty acid profiles and protein profiles respectively. We analysed 50 certified strains belonging to Halomonas, Marinomonas, Marinospirillum, Oceanospirillum and Pseudoalteromonas genera. Both supervised and unsupervised ANNs provide a correct classification of the marine strains analyzed. Moreover, a set of 73 marine fresh isolates were used as an example of identification using ANNs. We propose supervised and unsupervised ANNs as a reliable tool for classification of bacteria by means of their FAME and of whole-protein analyses and as a sound basis for a comprehensive artificial intelligence based system for polyphasic taxonomy.

Bacteria↗
PubMed1997

DT-Planner: an environment for managing dynamic decision problems.

The problem of formulating plans under uncertainty and coping with dynamic decision problems is a major task of both artificial intelligence and control theory applications in medicine. In this paper we will describe a software package, called DT-Planner, designed to represent and solve dynamic decision problems that can be modelled as Markov decision processes, by exploiting a novel graphical formalism, called influence view. An influence view is a directed acyclic graph that depicts the probabilistic relationships between the problem state variables in a generic time transition; additional variables, called event variables, may be added, in order to describe the conditional independencies between state variables. By using the specified conditional independence structure, an influence view may allow a parsimonious specification of a Markov decision process. DT-Planner lets the user specify and manage models through a user-friendly graphical interface, and implements efficient for policy determination algorithms. DT-Planner is written in C with Open Interface libraries and can be obtained, for non commercial use, via anonymous ftp without charge.

Algorithms↗
PubMed1985

[Prediction of secondary structures of nucleic acids: algorithmic and physical aspects].

Prediction of secondary structures in nucleic acids requires both an adequate physical model and powerful calculation algorithms. In our approach, we cut the molecules in sections of which the contributions to the global energy are context-dependent but roughly additive. The structure of minimum energy is obtained by a tree search under constraints of binary incompatibilities. Our algorithm of the "incompatibility islets" is shown to be more powerful than the "bit parallel forward checking" algorithm, well known in Artificial Intelligence. Recurrent algorithms, proposed by other authors are even more rapid, but often miss the correct structures, for they demand a strict additivity of the energetic contributions, physically unjustified. New strategies, required to deal with molecules of more than 200 nucleotides are discussed. Our physical model has been improved by considering the special case of internal loops beginning with a G-A opposition. A bonus of 1.5 kcal. is attributed to such a feature, at each side of an internal loop. To illustrate our programs, we give the computed schemes for the 3' termini of the small subunit ribosomal RNA.

Base Sequence↗
PubMed1999

Memory retrieval as a p-adic dynamical system.

We propose a mathematical model of the memory retrieval process based on dynamical systems over a metric space of p-adic numbers representing a configuration 'space of ideas' in which two ideas are close if they have a sufficiently long common root. Our aim is to suggest a new way of conceptualizing human memory retrieval that might be useful for simulation purposes or for the construction of artificial intelligence devices, as well as for a deeper understanding of the process itself. The dynamical system is assumed to be located in a blackbox processing unit (the 'subconscious') and controlled by an interface control unit (the 'conscious') that fixes parameters in the dynamical system and starts its iteration by sending an initial generating idea to it. We show that even simple p-adic dynamical systems admit behavioral scenarios that could explain some of the essential features of the human memory retrieval process.

Humans↗
PubMed1996

Prism: a new approach to radiotherapy planning software.

PURPOSE: We describe the capabilities and performance of Prism, an innovative new radiotherapy planning system with unusual features and design. The design and implementation strategies are intended to assure high quality and clinical acceptability. The features include Artificial Intelligence tools and special support for multileaf collimator (MLC) systems. The design provides unusual flexibility of operation and ease of expansion. METHODS AND MATERIALS: We have implemented Prism, a three-dimensional (3D) radiotherapy treatment-planning system on standard commercial workstations with the widely available X window system. The design and implementation use ideas taken from recent software engineering research, for example, the use of behavioral entity-relationship modeling and the "Mediator Method" instead of ad-hoc programming. The Prism system includes the usual features of a 3D planning system, including Beam's Eye View and the ability to simulate any treatment geometry possible with any standard radiotherapy accelerator. It includes a rule-based expert system for automated generation of the planning target volume as defined in ICRU Report 50. In addition, it provides special support for planning treatments with a multileaf collimator (MLC). We also implemented a Radiotherapy Treatment Planning Tools Foundation for Prism, so that we are able to use software tools form other institutions without any source code modification. RESULTS: The Prism system has been in clinical operation at the University of Washington since July 1994 and has been installed at several other clinics. The system is run simultaneously by several users, each with their own workstation operating from a common networked database and software. In addition to the dosimetrists, the system is used by radiation oncologists to define tumor and target volumes and by radiation therapists to select treatment setups to load into a computer controlled accelerator. CONCLUSIONS: Experience with the installation and operation has shown the design to be effective as both a clinical and research tool. Integration of software tools has eased the development and significantly enhanced the clinical usability of the system. The design has been shown to be a sound basis for further innovation in radiation treatment planning software and for research in the treatment planning process.

Computer Communication Networks↗
PubMed1996

Shape recovery and volume calculation from biplane angiography in the stereotactic radiosurgical treatment of arteriovenous malformations.

PURPOSE: A model for calculating the three-dimensional volume of arteriovenous malformations from biplane angiography. METHODS AND MATERIAL: Three-dimensional (3D) volume reconstruction is easily feasible with axial, coronal, or sagittal computer tomography (CT) and nuclear magnetic resonance (NMR) scans. On the other hand, radiosurgical treatment of arteriovenous malformations (AVM) is exclusively based on two orthogonal stereotactic projections, obtained with angiographic procedures. Most commonly, AVM volumes have been calculated by assimilating the nidus volume to a prolate ellipsoid. We present an algorithm dedicated to 3D structure reconstruction starting from two orthogonal stereotactic projections. This has been achieved using a heuristic approach, which has been widely adopted in the artificial intelligence domain. RESULTS: Tests on phantom of different complexity have shown excellent results. CONCLUSION: The importance of the algorithm is considerable. As a matter of fact: (a) it allows calculations of complex structures far away from regular ellipsoid; (b) it permits shape recovery; (c) it provides AVM visualization on axial planes.

Adolescent↗
PubMed1989

Robotics in biomedical chromatography and electrophoresis.

The ideal laboratory robot can be viewed as "an indefatigable assistant capable of working continuously for 24 h a day with constant efficiency". The development of a system approaching that promise requires considerable skill and time commitment, a thorough understanding of the capabilities and limitations of the robot and its specialized modules and an intimate knowledge of the functions to be automated. The robot need not emulate every manual step. Effective substitutes for difficult steps must be devised. The future of laboratory robots depends not only on technological advances in other fields, but also on the skill and creativity of chromatographers and other scientists. The robot has been applied to automate numerous biomedical chromatography and electrophoresis methods. The quality of its data can approach, and in some cases exceed, that of manual methods. Maintaining high data quality during continuous operation requires frequent maintenance and validation. Well designed robotic systems can yield substantial increase in the laboratory productivity without a corresponding increase in manpower. They can free skilled personnel from mundane tasks and can enhance the safety of the laboratory environment. The integration of robotics, chromatography systems and laboratory information management systems permits full automation and affords opportunities for unattended method development and for future incorporation of artificial intelligence techniques and the evolution of expert systems. Finally, humanoid attributes aside, robotic utilization in the laboratory should not be an end in itself. The robot is a useful tool that should be utilized only when it is prudent and cost-effective to do so.

Chemistry, Clinical↗
PubMed1999

Automatic realignment of time-separated MR images by genetic algorithm.

A simple yet highly efficient artificial intelligence technique utilizing a genetic algorithm is used to register time-separated pairs of MRI data sets. To encourage others to try the approach, the algorithm is presented by way of a simple example to a 2-D data set; it is equally applicable to 3-D data. The technique is reliably found to reduce mismatch in images of the distal-interphalangeal joint from the order of several mm to just 200 microm (one pixel). The method and transformation are general and would be suitable for locating physical changes between any image data sets. We believe the technique to be of use in functional imaging, measurement of disease progression with time (e.g., degradation of cartilage in arthritic disease) and pre/post-surgical studies.

Algorithms↗
PubMed1997

Utility of a software assistant in critical care case review.

A computer program (the Audit Assistant) was developed to help physicians review the care of critically ill emergency department (ED) patients. The program is an example of a new class of decision aids that serves to remind physicians to consider possibilities, not an artificial intelligence program that actually attempts to simulate clinical reasoning. The goal of such programs is to enable physicians to reduce errors--in this case to enable reviewers to notice more of the errors in care in the cases they are reviewing. The objective of this study was to demonstrate on a small set of complex cases that the tested computer program enables the physician to perform a better quality review. The issue of what constitutes improved case review is addressed. In the first part of the study, reviewers reviewed two mock charts without using the Audit Assistant and then immediately reviewed the charts again with the assistance of the program. The reviews were compared. In the second part of the study, a second reviewer also compared the utility of the review of the first reviewer alone and the Audit Assistant output as an aid to review, using an additional mock chart. Six emergency physicians participated; each was a quality assurance director for the ED of one Cleveland area hospital. For the physicians reviewing without the Audit Assistant, 41% of critical actions were listed by three or four reviewers. For those using the Audit Assistant, 83% of critical actions were listed by three or four reviewers. All reviewers preferred the Audit Assistant-suggested list to the critical action list generated by a previous reviewer not using the Audit Assistant (P < .02). Use of the Audit Assistant improved the completeness and the consistency of physician review of mock charts of critically ill ED patients in a small series of cases. The critical actions added for review were important, as demonstrated by the preferential addition of critical actions chosen by other reviewers who were not using the computer program.

Critical Care↗
PubMedDate not supplied

Agent computing themes in biologically inspired models of learning and development.

After evaluating general features and attributes of the agent notion, the overlap of features in candidate (attribute) cores, and several less central features, the paper addresses agent and related theory in neuroscience, observing how agent notions have penetrated portions of this field and how the field itself emphasizes and further develops some agent themes via, e.g. schema theory, neural net-artificial intelligence (AI) comparisons, and other research. In remaining sections, models for development of memory strategies in children are presented, illustrating cooperative and competitive neural modeling agents, an active role for a "human agent in the loop," and integrating broadly-based neural network (NN) modeling with other bio-inspired models.

Aging↗
PubMed1992

A knowledge base for predicting protein localization sites in eukaryotic cells.

To automate examination of massive amounts of sequence data for biological function, it is important to computerize interpretation based on empirical knowledge of sequence-function relationships. For this purpose, we have been constructing a knowledge base by organizing various experimental and computational observations as a collection of if-then rules. Here we report an expert system, which utilizes this knowledge base, for predicting localization sites of proteins only from the information on the amino acid sequence and the source origin. We collected data for 401 eukaryotic proteins with known localization sites (subcellular and extracellular) and divided them into training data and testing data. Fourteen localization sites were distinguished for animal cells and 17 for plant cells. When sorting signals were not well characterized experimentally, various sequence features were computationally derived from the training data. It was found that 66% of the training data and 59% of the testing data were correctly predicted by our expert system. This artificial intelligence approach is powerful and flexible enough to be used in genome analyses.

Algorithms↗