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 775 records · Page 43Linked to original sources

PubMed2004

Deterministic design for neural network learning: an approach based on discrepancy.

The general problem of reconstructing an unknown function from a finite collection of samples is considered, in case the position of each input vector in the training set is not fixed beforehand but is part of the learning process. In particular, the consistency of the empirical risk minimization (ERM) principle is analyzed, when the points in the input space are generated by employing a purely deterministic algorithm (deterministic learning). When the output generation is not subject to noise, classical number-theoretic results, involving discrepancy and variation, enable the establishment of a sufficient condition for the consistency of the ERM principle. In addition, the adoption of low-discrepancy sequences enables the achievement of a learning rate of O(1/L), with L being the size of the training set. An extension to the noisy case is provided, which shows that the good properties of deterministic learning are preserved, if the level of noise at the output is not high. Simulation results confirm the validity of the proposed approach.

Artificial Intelligence↗

PubMed2006

Continuous-valued probabilistic behavior in a VLSI generative model.

This paper presents the VLSI implementation of the continuous restricted Boltzmann machine (CRBM), a probabilistic generative model that is able to model continuous-valued data with a simple and hardware-amenable training algorithm. The full CRBM system consists of stochastic neurons whose continuous-valued probabilistic behavior is mediated by injected noise. Integrating on-chip training circuits, the full CRBM system provides a platform for exploring computation with continuous-valued probabilistic behavior in VLSI. The VLSI CRBM's ability both to model and to regenerate continuous-valued data distributions is examined and limitations on its performance are highlighted and discussed.

Algorithms↗

PubMed2005

Clustering ensembles: models of consensus and weak partitions.

Clustering ensembles have emerged as a powerful method for improving both the robustness as well as the stability of unsupervised classification solutions. However, finding a consensus clustering from multiple partitions is a difficult problem that can be approached from graph-based, combinatorial, or statistical perspectives. This study extends previous research on clustering ensembles in several respects. First, we introduce a unified representation for multiple clusterings and formulate the corresponding categorical clustering problem. Second, we propose a probabilistic model of consensus using a finite mixture of multinomial distributions in a space of clusterings. A combined partition is found as a solution to the corresponding maximum-likelihood problem using the EM algorithm. Third, we define a new consensus function that is related to the classical intraclass variance criterion using the generalized mutual information definition. Finally, we demonstrate the efficacy of combining partitions generated by weak clustering algorithms that use data projections and random data splits. A simple explanatory model is offered for the behavior of combinations of such weak clustering components. Combination accuracy is analyzed as a function of several parameters that control the power and resolution of component partitions as well as the number of partitions. We also analyze clustering ensembles with incomplete information and the effect of missing cluster labels on the quality of overall consensus. Experimental results demonstrate the effectiveness of the proposed methods on several real-world data sets.

Algorithms↗

PubMed2026

Comparative Efficacy of Different AI Systems for Polyp Detection by Size During Colonoscopy: Systematic Review and Network Meta-Analysis.

BACKGROUND: Colorectal cancer remains a leading cause of death despite being largely preventable through polypectomy. AI systems designed to enhance polyp detection during colonoscopy have shown promise, but the extent to which they improve detection of different-sized polyps remains unclear. OBJECTIVE: This study compared the size-stratified efficacy of AI-assisted colonoscopy vs standard colonoscopy using the Hartung-Knapp-Sidik-Jonkman (HKSJ) method, and generated exploratory rankings while acknowledging all cross-platform comparisons are indirect. METHODS: This systematic review and network meta-analysis (NMA) searched PubMed, Embase, Cochrane CENTRAL, and Web of Science from inception to July 25, 2026, supplemented by citation searching. We included randomized controlled trials (RCTs) comparing AI-assisted vs standard colonoscopy in adults (≥18 years of age), reporting mean polyp detection counts stratified by size (≤5 mm, 6-9 mm, and ≥10 mm). Two reviewers screened studies, extracted data, and assessed risk of bias using the Cochrane Risk of Bias 2.0. We conducted frequentist NMA using the HKSJ method with restricted maximum likelihood estimation, calculated 95% prediction intervals (PIs), and assessed heterogeneity using I2 and τ2. Certainty of evidence was rated using the GRADE (Grading of Recommendations Assessment, Development, and Evaluation) framework. RESULTS: A total of 13 RCTs (4156 participants) compared 8 AI systems to standard colonoscopy, forming a network without direct AI comparisons. For diminutive polyps (≤5 mm), AI showed a modest advantage (standardized mean difference [SMD] 0.21, 95% CI 0.07 to 0.35, 95% PI -1.12 to 1.54), but substantial heterogeneity (I2=86.6%) and wide PI crossing the null indicated high uncertainty. EndoScreener showed the most consistent evidence (SMD 0.36, 95% CI 0.18-0.54). For small and large polyps, effects were minimal (SMD 0.02, 95% CI -0.02 to 0.06, 95% PI -0.03 to 0.07; SMD 0.01, 95% CI 0.00-0.02, 95% PI -0.01 to 0.03). GRADE certainty was very low for diminutive polyps and low for small and large polyps. Sensitivity analysis excluding Tianjin YuJin did not materially change findings. CONCLUSIONS: AI may modestly enhance diminutive polyp detection, but effects on small and large polyps are minimal, with no platform superiority. Given very low to low certainty, findings are hypothesis-generating. This exploratory NMA provides size-stratified comparisons that can inform future head-to-head trial design. Unlike prior reviews aggregating all polyp sizes, we show the overall AI benefit is driven by diminutive polyp detection, providing a framework for targeted deployment-prioritizing AI for diminutive polyp screening, with limited value for larger lesions. Head-to-head trials are urgently needed. TRIAL REGISTRATION: PROSPERO International Prospective Register of Systematic Reviews CRD420251266932; https://www.crd.york.ac.uk/PROSPERO/view/CRD420251266932.

Colonoscopy↗

PubMedDate not supplied

Locally linear embedding for dimensionality reduction in QSAR.

Current practice in Quantitative Structure Activity Relationship (QSAR) methods usually involves generating a great number of chemical descriptors and then cutting them back with variable selection techniques. Variable selection is an effective method to reduce the dimensionality but may discard some valuable information. This paper introduces Locally Linear Embedding (LLE), a local non-linear dimensionality reduction technique, that can statistically discover a low-dimensional representation of the chemical data. LLE is shown to create more stable representations than other non-linear dimensionality reduction algorithms, and to be capable of capturing non-linearity in chemical data.

Artificial Intelligence↗

PubMed1994

Writing Arden Syntax Medical Logic Modules.

The Arden Syntax for Medical Logic Modules is a language for encoding medical knowledge bases that consist of independent modules. The Arden Syntax has been used to generate clinical alerts, diagnostic interpretations, management messages, and screening for research studies and quality assurance. An Arden Syntax knowledge base consists of rules called Medical Logic Modules (MLMs), which are stored as simple ASCII files that can be written on any text editor. An MLM is made of slots grouped into three categories: maintenance information, library information, and the actual medical knowledge. Most MLMs are triggered by clinical events, evaluate medical criteria, and, if appropriate, perform an action such as sending a message to a health care provider. This paper provides a detailed tutorial on how to write MLMs.

Artificial Intelligence↗

PubMed2006

Semi-automated segmentation and visualisation of outer bone cortex from medical images.

Good segmentation of the outer bone cortex from medical images is a prerequisite for applications in the field of finite element analysis, surgical planning environments and personalised, case dependent, bone reconstruction. However, current segmentation procedures are often unsatisfactory. This study presents an automated filter procedure to generate a set of adapted contours from which a surface mesh can be deduced directly. The degree of interaction is user determined. The bone contours are extracted from the patients CT data by quick grey value segmentation. An extended filter procedure then only retains contour information representing the outer cortex as more specific internal loops and shape irregularities are removed, tailoring the image for the above-mentioned applications. The developed medical image based design methodology to convert contour sets of multiple bone types, from tibia tumour to neurocranium, is reported and discussed.

Algorithms↗

PubMedDate not supplied

Using the ID3 algorithm to find discrepant diagnoses from laboratory databases of thyroid patients.

Rare cases are a central problem when an expert system is constructed from example cases with machine learning techniques. It is difficult to make a decision support system (DSS) to cover all possible clinical cases. An inductive learning program can be used to construct an expert system for detecting cases that differ from routine cases. The ID3 algorithm and the pessimistic pruning algorithm were tested in this study: a DSS was built directly from the data of patient records. A decision tree was generated, and the cases misclassified by the decision tree as compared with the classifications of a clinician were listed on a checklist, which formed the feedback to the clinician. In clinical situations about 5-10% of functional thyroid disorders may be misclassified. At this error level, the method found over 90% of the errors with a specificity of 95%. In simple medical classification tasks this dynamic self-learning system can be used to create a DSS that can assist in the quality control of clinical decision making.

Adult↗

PubMed2006

Feature-specific structured imaging.

We present a feature-specific imaging system based on the use of structured light. Feature measurements are obtained by projecting spatially structured illumination onto an object and collecting all the reflected light onto a single photodetector. Principal component features are used to define the illumination patterns. The optimal linear minimum mean-square error (LMMSE) operator is used to generate object estimates from the measured features. We study the optimal allocation of illumination energy into each feature measurement in the presence of additive white Gaussian detector noise and optical blur. We demonstrate that this new imaging approach reduces imager complexity and provides improved image quality in high noise environments. Compared to the optimal LMMSE postprocessing of a conventional image, feature-specific structured imaging provides a 38% rms error reduction and requires 400 times fewer measurements for a noise standard deviation of sigma = 2 x 10(-3). Experimental results validate these theoretical predictions.

Algorithms↗

PubMed2004

Development of a pioneering clinical support system utilizing information technology.

Nowadays, evidence-based medicine has entered the mainstream of clinical judgement and the human genome has been completely decoded. Even the concept of individually designed medicine, that is, tailor-made medicine, is now being discussed. Due to their complexity, however, management methods for clinical information have yet to be established. We have conducted a study on a universal technique which enables one to select or produce by employing information processing technology clinical findings from various clinical information generated in vast quantity in day-to-day clinical practice, and to share such information and/or the results of analysis between two or more institutions. In this study, clinically useful findings have been successfully obtained by systematizing actual clinical information and genomic information obtained by an appropriate collecting and management method of information with due consideration to ethical issues. We report here these medical achievements as well as technological ones which will play a role in propagating such medical achievements.

Artificial Intelligence↗

PubMed2001

Building a knowledge base to support a digital library.

As part of an effort to develop a knowledge base to support searching online medical literature according to individual needs, we have studied the possibility of using the co-occurrence of MeSH terms in MEDLINE citations associated with the search strategies optimal for evidence based medicine to automated construction of a knowledge base. This study evaluates the relevance of the relationships between the semantic relationship pairs generated by the process, and the clinical validity of the semantic types involved in the process. From the semantic pairs proposed by our method, a group of clinicians judge sixty percent to be relevant. The remaining forty percent included semantic types considered unimportant by clinicians. The knowledge extraction method showed reasonable results. We believe it can be appropriate for the task of retrieving information from the medical record in order to guide users during a searching and retrieval process. Future directions include the validation of the knowledge, based on an evaluation of system performance.

Algorithms↗

PubMedDate not supplied

OCIS: 15 years' experience with patient-centered computing.

In the mid-1970s, the medical and administrative staff of the Oncology Center at Johns Hopkins Hospital recognized a need for a computer-based clinical decision-support system that organized patients' information according to the care continuum, rather than as a series of event-specific data. This is especially important in cancer patients, because of the long periods in which they receive complex medical treatment and the enormous amounts of data generated by extremely ill patients with multiple interrelated diseases. During development of the Oncology Clinical Information System (OCIS), it became apparent that administrative services, research systems, ancillary functions (such as drug and blood product ordering), and financial processes should be integrated with the basic patient-oriented database. With the structured approach used in applications development, new modules were added as the need for additional functions arose. The system has since been moved to a modern network environment with the capacity for client-server processing.

Artificial Intelligence↗

PubMed2005

An intelligent tutoring system that generates a natural language dialogue using dynamic multi-level planning.

OBJECTIVE: The objective of this research was to build an intelligent tutoring system capable of carrying on a natural language dialogue with a student who is solving a problem in physiology. Previous experiments have shown that students need practice in qualitative causal reasoning to internalize new knowledge and to apply it effectively and that they learn by putting their ideas into words. METHODS: Analysis of a corpus of 75 hour-long tutoring sessions carried on in keyboard-to-keyboard style by two professors of physiology at Rush Medical College tutoring first-year medical students provided the rules used in tutoring strategies and tactics, parsing, and text generation. The system presents the student with a perturbation to the blood pressure, asks for qualitative predictions of the changes produced in seven important cardiovascular variables, and then launches a dialogue to correct any errors and to probe for possible misconceptions. The natural language understanding component uses a cascade of finite-state machines. The generation is based on lexical functional grammar. RESULTS: Results of experiments with pretests and posttests have shown that using the system for an hour produces significant learning gains and also that even this brief use improves the student's ability to solve problems more then reading textual material on the topic. Student surveys tell us that students like the system and feel that they learn from it. The system is now in regular use in the first-year physiology course at Rush Medical College. CONCLUSION: We conclude that the CIRCSIM-Tutor system demonstrates that intelligent tutoring systems can implement effective natural language dialogue with current language technology.

Artificial Intelligence↗

PubMed2000

Enhancing the expressiveness of structured reporting systems.

The overall goal of this research is to build a structured reporting system that reduces the cost, delays, and inconvenience associated with conventional dictation and speech recognition systems. We have implemented such a structured reporting system for radiology that replaces current dictation and transcription processes by allowing radiologists and other imaging professionals to select imaging findings from a medical lexicon. The system uses an imaging-specific information model, called a "description set,' to organize selected terms in a relational database. Unique features of the knowledge representation that enhance its expressiveness include its ability to codify uncertainty about an imaging observation and to represent explicitly the logical relationships among imaging findings. In addition, the system does not require the user to fill in "blanks' in a static text template. Instead, it allows entry of terms in arbitrary order and uses automated text-generation techniques to create a text report that referring physicians are accustomed to receiving. In parallel, the system also produces a multimedia report that the referring physician can use as a quick reference. Unlike the results of conventional dictation or speech recognition, each finding is coded in a relational database for later information processing. Thus, the structured report database can be used to index images by content, to provide real-time decision support, to enhance radiologists' performance, to conduct exploratory clinical research, and to transmit imaging report data to computer-based patient record systems.

Abstracting and Indexing↗

PubMed2005

Learning from imbalanced data in surveillance of nosocomial infection.

OBJECTIVE: An important problem that arises in hospitals is the monitoring and detection of nosocomial or hospital acquired infections (NIs). This paper describes a retrospective analysis of a prevalence survey of NIs done in the Geneva University Hospital. Our goal is to identify patients with one or more NIs on the basis of clinical and other data collected during the survey. METHODS AND MATERIAL: Standard surveillance strategies are time-consuming and cannot be applied hospital-wide; alternative methods are required. In NI detection viewed as a classification task, the main difficulty resides in the significant imbalance between positive or infected (11%) and negative (89%) cases. To remedy class imbalance, we explore two distinct avenues: (1) a new re-sampling approach in which both over-sampling of rare positives and under-sampling of the noninfected majority rely on synthetic cases (prototypes) generated via class-specific sub-clustering, and (2) a support vector algorithm in which asymmetrical margins are tuned to improve recognition of rare positive cases. RESULTS AND CONCLUSION: Experiments have shown both approaches to be effective for the NI detection problem. Our novel re-sampling strategies perform remarkably better than classical random re-sampling. However, they are outperformed by asymmetrical soft margin support vector machines which attained a sensitivity rate of 92%, significantly better than the highest sensitivity (87%) obtained via prototype-based re-sampling.

Algorithms↗

PubMed1997

Automatic extraction and measurement of leukocyte motion in microvessels using spatiotemporal image analysis.

This paper describes a computer vision system for the automatic extraction and velocity measurement of moving leukocytes that adhere to microvessel walls from a sequence of images. The motion of these leukocytes can be visualized as motion along the wall contours. We use the constraint that the leukocytes move along the vessel wall contours to generate a spatiotemporal image, and the leukocyte motion is then extracted using the methods of spatiotemporal image analysis. The generated spatiotemporal image is processed by a special-purpose orientation-selective filter and a subsequent grouping process newly developed for this application. The orientation-selective filter is designed by considering the particular properties of the spatiotemporal image in this application in order to enhance only the traces of leukocytes. In the subsequent grouping process, leukocyte trace segments are selected and grouped among all the segments obtained by simple thresholding and skeletonizing operations. We show experimentally that the proposed method can stably extract leukocyte motion.

Algorithms↗

PubMed2005

Texture image retrieval using new rotated complex wavelet filters.

A new set of two-dimensional (2-D) rotated complex wavelet filters (RCWFs) are designed with complex wavelet filter coefficients, which gives texture information strongly oriented in six different directions (45 degrees apart from complex wavelet transform). The 2-D RCWFs are nonseparable and oriented, which improves characterization of oriented textures. Most texture image retrieval systems are still incapable of providing retrieval result with high retrieval accuracy and less computational complexity. To address this problem, we propose a novel approach for texture image retrieval by using a set of dual-tree rotated complex wavelet filter (DT-RCWF) and dual-tree-complex wavelet transform (DT-CWT) jointly, which obtains texture features in 12 different directions. The information provided by DT-RCWF complements the information generated by DT-CWT. Features are obtained by computing the energy and standard deviation on each subband of the decomposed image. To check the retrieval performance, texture database D1 of 1856 textures from Brodatz album and database D2 of 640 texture images from VisTex image database is created. Experimental results indicates that the proposed method improves retrieval rate from 69.61% to 77.75% on database D1, and from 64.83% to 82.81% on database D2, in comparing with traditional discrete wavelet transform based approach. The proposed method also retains comparable levels of computational complexity.

Algorithms↗

PubMed2004

The impact of tumor motion upon CT image integrity and target delineation.

Accurate planning target volume delineation is vital to the success of conformal radiation techniques such as standard three-dimensional conformal radiotherapy and intensity modulated radiation therapy. With the exception of breath-hold schemes, all current approaches acquire images while the tumor is nonstationary and, as such, are subject to the presence of motion artifacts. In lung cancer sites where tumor mobility can be significant, the detrimental effect of these motion-induced distortions on image quality and subsequently target volume delineation cannot be ignored in the pursuit of improved treatment outcomes. To investigate the fundamental nature and functional dependence of computed tomography (CT) artifacts associated with lung tumor motion, and the implications for tumor delineation, a filtered backprojection algorithm was developed in MATLAB to generate transverse CT simulation images. In addition, a three-dimensional phantom capable of mimicking the essential motions of lung tumors was constructed for experimental verification. Results show that the spatial extent of a mobile object is distorted from its true shape and location and does not accurately reflect the volume occupied during the extent of motion captured. The presence of motion also negatively impacts image intensity (density) integrity rendering accurate volume delineation highly problematic and calling into question the use of such data in CT-based heterogeneity correction algorithms for dosimetric calculation.

Algorithms↗