SEARCH · PubMed Health

Results for “generative artificial intelligence”

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 703 records · Page 39Linked to original sources

PubMed1992

Alloplastic cranial implants made from computed tomographic scan-generated casts.

The complexity of cranioplasty increases with increased defect size. It is difficult to produce a symmetric, accurate implant presurgically or at the time of surgery when the defect is greater than 50 cm2. The procedure is also more difficult to perform when the defect is located in the temporal, infratemporal, or frontal areas. A new procedure generates a three-dimensional cast of the skull through computed tomography and computer-aided design reformation. This article describes the process of model generation and the production of a preprocessed cranial implant. To date, six cranial implants have been made with this technique. The whole head models are accurate and help the neurosurgeon-prosthodontist team in the creation of a symmetric, anatomically correct restoration. It is the technique of choice for large implants or where the cranial bones are thin. It is not necessary to augment or alter the implant during surgery. The technique reduces surgical time, and postsurgical complications have been minimal.

Artificial Intelligence↗

PubMed1996

Synthesis of an anaesthetic agent administration system using fuzzy inductive reasoning.

Control of the depth of anaesthesia is a difficult undertaking. Progress has been made during recent years by use of different methodologies and monitoring systems that suggest the safe amount of an anaesthetic drug, considering the condition of an individual patient. Despite these improvements, anaesthetists still rely heavily on personal experience when suggesting the anaesthetic dosage during surgical operations. The purposes of this paper are twofold. One is a description of the design of an anaesthetic agent control system using a qualitative modelling and simulation methodology called Fuzzy Inductive Reasoning (FIR). A comparison with a system developed for the same application using a neural network approach is also presented. The second purpose is a discussion of the problem of separating system-generic from patient-specific behaviour in the context of inductive modeling using the FIR methodology. In order to be useful, the model generated by FIR should reflect upon system-generic behavioural characteristics exclusively, while suppressing patient-specific behavioural patterns. A technique based on combining knowledge obtained from different patients is designed that makes it possible to derive a single model characterizing a specific class of similar patients undergoing similar operations, preserving the common characteristics of all these patients while filtering out the specific behavioural patterns of any one of the individual patients from whom the data were obtained.

Anesthetics↗

PubMed2006

Using MEDLINE as a knowledge source for disambiguating abbreviations and acronyms in full-text biomedical journal articles.

Biomedical abbreviations and acronyms are widely used in biomedical literature. Since many of them represent important content in biomedical literature, information retrieval and extraction benefits from identifying the meanings of those terms. On the other hand, many abbreviations and acronyms are ambiguous, it would be important to map them to their full forms, which ultimately represent the meanings of the abbreviations. In this study, we present a semi-supervised method that applies MEDLINE as a knowledge source for disambiguating abbreviations and acronyms in full-text biomedical journal articles. We first automatically generated from the MEDLINE abstracts a dictionary of abbreviation-full pairs based on a rule-based system that maps abbreviations to full forms when full forms are defined in the abstracts. We then trained on the MEDLINE abstracts and predicted the full forms of abbreviations in full-text journal articles by applying supervised machine-learning algorithms in a semi-supervised fashion. We report up to 92% prediction precision and up to 91% coverage.

Artificial Intelligence↗

PubMed2001

A knowledge-based system to aid with the clinical interpretation of complex serum protein data.

In every area of science workers are finding increasing difficulty in managing the volume of available data. In medicine, the accelerating pace has the worrisome overtones of our failing to provide up-to-date care for our patients. In other information-intensive areas, we rely heavily on software that manages much of the complexity unseen. Patient care could benefit enormously from the incorporation of "knowledge-based" programs to aid with diagnosis and management of many disorders. This article describes such a system designed to organize complex data which can be viewed as a test cluster aimed at many disorders pertinent to serum proteins. This program performs complex tasks such as reference range adjustment, ICD-9 code assignment, and searching for diagnostic "signatures", to generate clinically relevant text and simple graphics. The results have been remarkably accurate and produce repeatable results at the rate of approximately 10 cases per minute. The reluctance to embrace software assistance in laboratory medicine may have serious consequences in the short term and disastrous results within a decade. Expanding the limited algorithm described here to include more traditional chemistry testing could provide the very assistance that all in clinical care desire, a laboratory tool as powerful and adaptable as the traditional physical exam.

Artificial Intelligence↗

PubMed2006

Finding the evidence for protein-protein interactions from PubMed abstracts.

MOTIVATION: Protein-protein interactions play critical roles in biological processes, and many biologists try to find or to predict crucial information concerning these interactions. Before verifying interactions in biological laboratory work, validating them from previous research is necessary. Although many efforts have been made to create databases that store verified information in a structured form, much interaction information still remains as unstructured text. As the amount of new publications has increased rapidly, a large amount of research has sought to extract interactions from the text automatically. However, there remain various difficulties associated with the process of applying automatically generated results into manually annotated databases. For interactions that are not found in manually stored databases, researchers attempt to search for abstracts or full papers. RESULTS: As a result of a search for two proteins, PubMed frequently returns hundreds of abstracts. In this paper, a method is introduced that validates protein-protein interactions from PubMed abstracts. A query is generated from two given proteins automatically and abstracts are then collected from PubMed. Following this, target proteins and their synonyms are recognized and their interaction information is extracted from the collection. It was found that 67.37% of the interactions from DIP-PPI corpus were found from the PubMed abstracts and 87.37% of interactions were found from the given full texts. AVAILABILITY: Contact authors.

Abstracting and Indexing↗

PubMed1994

An integrated knowledge-based system to guide the physician during structured reporting.

A routinely used system for report generation, based on direct physician data entry, has been combined with a knowledge-based module. The knowledge-based system is operating in the background, and guides the user by dynamically suggesting diagnoses and generating hints regarding the actual and possible further diagnostic procedures. Hybrid technology with neural networks and rules is used. A laboratory evaluation has shown good agreement between diagnoses suggested by the system and confirmed diagnoses, with a kappa coefficient of 0.85 and an area under the ROC curve of 0.92. In a survey following a 14-day test period, physicians stated that the system was both sensible and helpful. The current application domain is ultrasound reporting.

Artificial Intelligence↗

PubMed2002

Leveraging XML-based electronic medical records to extract experiential clinical knowledge. An automated approach to generate cases for medical case-based reasoning systems.

Case-based reasoning (CBR)-driven medical diagnostic systems demand a critical mass of up-to-date diagnostic-quality cases that depict the problem-solving methodology of medical experts. In practical terms, procurement of CBR-compliant cases is quite challenging, as this requires medical experts to map their experiential knowledge to an unfamiliar computational formalism. In this paper, we propose a novel medical knowledge acquisition approach that leverages routinely generated electronic medical records (EMRs) as an alternate source for CBR-compliant cases. We present a methodology to autonomously transform XML-based EMR to specialized CBR-compliant cases for CBR-driven medical diagnostic systems. Our multi-stage methodology features: (a) collection of heterogeneous EMR from Internet-accessible EMR repositories via intelligent agents, (b) automated transformation of both the structure and content of generic EMR to specialized CBR-compliant cases, and (c) inductive estimation of the weight of each case-defining attribute. The computational implementation of our methodology is presented as case acquisition and transcription info-structure (CATI).

Artificial Intelligence↗

PubMed2004

Optimization of rifamycin B fermentation in shake flasks via a machine-learning-based approach.

Rifamycin B is an important polyketide antibiotic used in the treatment of tuberculosis and leprosy. We present results on medium optimization for Rifamycin B production via a barbital insensitive mutant strain of Amycolatopsis mediterranei S699. Machine-learning approaches such as Genetic algorithm (GA), Neighborhood analysis (NA) and Decision Tree technique (DT) were explored for optimizing the medium composition. Genetic algorithm was applied as a global search algorithm while NA was used for a guided local search and to develop medium predictors. The fermentation medium for Rifamycin B consisted of nine components. A large number of distinct medium compositions are possible by variation of concentration of each component. This presents a large combinatorial search space. Optimization was achieved within five generations via GA as well as NA. These five generations consisted of 178 shake-flask experiments, which is a small fraction of the search space. We detected multiple optima in the form of 11 distinct medium combinations. These medium combinations provided over 600% improvement in Rifamycin B productivity. Genetic algorithm performed better in optimizing fermentation medium as compared to NA. The Decision Tree technique revealed the media-media interactions qualitatively in the form of sets of rules for medium composition that give high as well as low productivity.

Actinomycetales↗

PubMed1989

Simulated evolution and artificial selection.

A highly simplified evolving system was investigated by computer simulation. The genetic complement of each simulated organism in the population was represented by a single chromosome that consisted of a string of symbols. Individual fitness was measured as the number of symbols that corresponded to a specified rule. Reproduction was simulated with a non-breeding algorithm and two variants of a breeding algorithm, and was subject to random point mutations. In each generation, selection was effected by replacing the less fit members of the population with offspring of the more fit. The size of the population and the fraction replaced, though under experimental control, were constant for each simulation run. It was found that even such a simplified system is able to mimic a variety of properties observed in natural systems. In addition, the effect of the simulation parameters on the course of fitness increase provides a basis for using a genetic algorithm as an optimization technique.

Algorithms↗

PubMed2005

Hierarchical morphological design of immunoassay technology.

The paper describes a hierarchical design approach to an immunoassay. A morphology for an immunoassay technology is considered as a basis to generate system versions. A 5-stage technology is analyzed. The problem is: Find the best composite version for each stage while taking into account requirements (criteria) at each stage and compatibility between selected design alternatives at different stages. Hierarchical solving procedure consists of two parts: (a) multicriteria ranking of alternative versions at each stage (e.g., selection of Pareto-effective local decisions), (b) composition of the selected versions into a parallel-series composite system (technology). A realistic numerical example illustrates the approach.

Artificial Intelligence↗

PubMed2000

Generalized radial basis function networks for classification and novelty detection: self-organization of optimal Bayesian decision.

By adding reverse connections from the output layer to the central layer it is shown how a generalized radial basis functions (GRBF) network can self-organize to form a Bayesian classifier, which is also capable of novelty detection. For this purpose, three stochastic sequential learning rules are introduced from biological considerations which pertain to the centers, the shapes, and the widths of the receptive fields of the neurons and allow ajoint optimization of all network parameters. The rules are shown to generate maximum-likelihood estimates of the class-conditional probability density functions of labeled data in terms of multivariate normal mixtures. Upon combination with a hierarchy of deterministic annealing procedures, which implement a multiple-scale approach, the learning process can avoid the convergence problems hampering conventional expectation-maximization algorithms. Using an example from the field of speech recognition, the stages of the learning process and the capabilities of the self-organizing GRBF classifier are illustrated.

Artificial Intelligence↗

PubMed2006

A single-lead ECG enhancement algorithm using a regularized data-driven filter.

We presented a novel way of deriving a subspace filter for enhancing a noisy electrocardiogram (ECG) signal contaminated by electromyogram (EMG). The new subspace filter was based on a multiple cycle prediction (MCP) modeling of a single-lead ECG. The adoption of an MCP model resulted in a data matrix more suitable for separating noise and signal subspaces than the linear prediction (LP) model that is implicitly assumed in many existing subspace filters. Alignment of ECG cycles of different length is required for MCP modeling and was handled by a dynamic time warping (DTW) algorithm. A run-time procedure was designed for automatically determining the signal space dimension adaptively. To validate the new filter in a quantitative way, 12 clean realistic ECG segments with different degrees of heart rate variability generated using the ECGSyn program were mixed with different realizations of EMG noise in the MIT-BIH Noise Stress Test Database and locally acquired EMG at a typical 10-dB signal-to-noise ratio. The performance of the proposed method was compared to three existing ECG enhancement algorithms and achieved encouraging results. In addition, various ECG recordings from MIT-Arrythmia database were also mixed with EMG noise and subjected to the same four filters resulting in a qualitative comparison of them.

Algorithms↗

PubMed2006

Classification of unilateral vocal fold paralysis by endoscopic digital high-speed recordings and inversion of a biomechanical model.

Hoarseness in unilateral vocal fold paralysis is mainly due to irregular vocal fold vibrations caused by asymmetries within the larynx physiology. By means of a digital high-speed camera vocal fold oscillations can be observed in real-time. It is possible to extract the irregular vocal fold oscillations from the high-speed recordings using appropriate image processing techniques. An inversion procedure is developed which adjusts the parameters of a biomechanical model of the vocal folds to reproduce the irregular vocal fold oscillations. Within the inversion procedure a first parameter approximation is achieved through a knowledge-based algorithm. The final parameter optimization is performed using a genetic algorithm. The performance of the inversion procedure is evaluated using 430 synthetically generated data sets. The evaluation results comprise an error estimation of the inversion procedure and show the reliability of the algorithm. The inversion procedure is applied to 15 healthy voice subjects and 15 subjects suffering from unilateral vocal fold paralysis. The optimized parameter sets allow a classification of pathologic and healthy vocal fold oscillations. The classification may serve as a basis for therapy selection and quantification of therapy outcome in case of unilateral vocal fold paralysis.

Algorithms↗

PubMed2004

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↗

PubMed2006

Functional verification of pulse frequency modulation-based image sensor for retinal prosthesis by in vitro electrophysiological experiments using frog retina.

The functioning of a 16 x 16 pixel pulse frequency modulation (PFM) image sensor for retinal prosthesis is verified through in vitro electrophysiological experiments using detached frog retinas. This image sensor is a prototype for demonstrating the application to in vitro electrophysiological experiments. Each pixel of the image sensor consists of a pulse generator (PFM photosensor), a stimulus circuit, and a stimulus electrode (Al bonding pad). The image sensor is fabricated using standard 0.6 microm CMOS technology. For in vitro electrophysiological experiments, a Pt/Au stacked electrode is formed on the Al bonding pad of each pixel and the entire sensor is fixed in epoxy resin. The PFM image sensor is confirmed experimentally to provide electrical stimulus to the retinal cells in a detached frog retina.

Action Potentials↗

PubMed2005

Style context with second-order statistics.

Patterns often occur as homogeneous groups or fields generated by the same source. In multisource recognition problems, such isogeny induces statistical dependencies between patterns (termed style context). We model these dependencies by second-order statistics and formulate the optimal classifier for normally distributed styles. We show that model parameters estimated only from pairs of classes suffice to train classifiers for any test field length. Although computationally expensive, the style-conscious classifier reduces the field error rate by up to 20 percent on quadruples of handwritten digits from standard NIST data sets.

Algorithms↗

PubMed2006

A Bayesian network driven approach to model the transcriptional response to nitric oxide in Saccharomyces cerevisiae.

The transcriptional response to exogenously supplied nitric oxide in Saccharomyces cerevisiae was modeled using an integrated framework of Bayesian network learning and experimental feedback. A Bayesian network learning algorithm was used to generate network models of transcriptional output, followed by model verification and revision through experimentation. Using this framework, we generated a network model of the yeast transcriptional response to nitric oxide and a panel of other environmental signals. We discovered two environmental triggers, the diauxic shift and glucose repression, that affected the observed transcriptional profile. The computational method predicted the transcriptional control of yeast flavohemoglobin YHB1 by glucose repression, which was subsequently experimentally verified. A freely available software application, ExpressionNet, was developed to derive Bayesian network models from a combination of gene expression profile clusters, genetic information and experimental conditions.

Algorithms↗

PubMed1999

Case-based explanation of non-case-based learning methods.

We show how to generate case-based explanations for non-case-based learning methods such as artificial neural nets or decision trees. The method uses the trained model (e.g., the neural net or the decision tree) as a distance metric to determine which cases in the training set are most similar to the case that needs to be explained. This approach is well suited to medical domains, where it is important to understand predictions made by complex machine learning models, and where training and clinical practice makes users adept at case interpretation.

Artificial Intelligence↗