SEARCH · PubMed Health

Results for “Predictive Learning Models”

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 1,585 records · Page 88Linked to original sources

PubMed2006

Factorial coding of natural images: how effective are linear models in removing higher-order dependencies?

The performance of unsupervised learning models for natural images is evaluated quantitatively by means of information theory. We estimate the gain in statistical independence (the multi-information reduction) achieved with independent component analysis (ICA), principal component analysis (PCA), zero-phase whitening, and predictive coding. Predictive coding is translated into the transform coding framework, where it can be characterized by the constraint of a triangular filter matrix. A randomly sampled whitening basis and the Haar wavelet are included in the comparison as well. The comparison of all these methods is carried out for different patch sizes, ranging from 2x2 to 16x16 pixels. In spite of large differences in the shape of the basis functions, we find only small differences in the multi-information between all decorrelation transforms (5% or less) for all patch sizes. Among the second-order methods, PCA is optimal for small patch sizes and predictive coding performs best for large patch sizes. The extra gain achieved with ICA is always less than 2%. In conclusion, the edge filters found with ICA lead to only a surprisingly small improvement in terms of its actual objective.

Algorithms↗

PubMed1995

[Glossary of terms used by radiologists in image processing].

We give the definition of 166 words used in image processing. Adaptivity, aliazing, analog-digital converter, analysis, approximation, arc, artifact, artificial intelligence, attribute, autocorrelation, bandwidth, boundary, brightness, calibration, class, classification, classify, centre, cluster, coding, color, compression, contrast, connectivity, convolution, correlation, data base, decision, decomposition, deconvolution, deduction, descriptor, detection, digitization, dilation, discontinuity, discretization, discrimination, disparity, display, distance, distorsion, distribution dynamic, edge, energy, enhancement, entropy, erosion, estimation, event, extrapolation, feature, file, filter, filter floaters, fitting, Fourier transform, frequency, fusion, fuzzy, Gaussian, gradient, graph, gray level, group, growing, histogram, Hough transform, Houndsfield, image, impulse response, inertia, intensity, interpolation, interpretation, invariance, isotropy, iterative, JPEG, knowledge base, label, laplacian, learning, least squares, likelihood, matching, Markov field, mask, matching, mathematical morphology, merge (to), MIP, median, minimization, model, moiré, moment, MPEG, neural network, neuron, node, noise, norm, normal, operator, optical system, optimization, orthogonal, parametric, pattern recognition, periodicity, photometry, pixel, polygon, polynomial, prediction, pulsation, pyramidal, quantization, raster, reconstruction, recursive, region, rendering, representation space, resolution, restoration, robustness, ROC, thinning, transform, sampling, saturation, scene analysis, segmentation, separable function, sequential, smoothing, spline, split (to), shape, threshold, tree, signal, speckle, spectrum, spline, stationarity, statistical, stochastic, structuring element, support, syntaxic, synthesis, texture, truncation, variance, vision, voxel, windowing.

Diagnostic Imaging↗

PubMed2004

Children's motivation in elementary physical education: a longitudinal study.

The present study examined relationships among variables drawn from achievement goal theory and the expectancy-value model of achievement choice as well as mean level changes of these variables over time in elementary physical education. Participants (N = 207) completed questionnaires over a 2-year period: once while in the second and fourth grades and again when they were in the third and fifth grades. Results indicated that achievement goals, expectancy-related beliefs, and subjective task values were related to one another and were predictive of children's intention for future participation in physical education. Children's subjective task values of physical education decreased over time. Children in Cohort 1 (across second to third grades) generally had stronger motivation for learning in physical education than children in Cohort 2 (across fourth to fifth grades). Findings suggest the importance of integrating achievement goal theory and the expectancy-value model of achievement choice in understanding student motivation.

Child↗

PubMed2026

Natural language processing-based model to predict radiation pneumonitis in patients with locally advanced non-small cell lung cancer undergoing chemoradiotherapy: a retrospective cohort study.

BACKGROUND: Radiation pneumonitis (RP) remains a significant treatment-related toxicity in patients with unresectable, locally advanced non-small cell lung cancer (NSCLC) undergoing chemoradiotherapy (CRT). Most existing predictive models rely on static baseline demographic or dosimetry variables and lack real-time clinical applicability. We developed a novel predictive framework that integrates longitudinal symptom data extracted from clinical notes using natural language processing (NLP) with clinical and dosimetry features to improve early RP prediction. METHODS: We retrospectively identified 227 patients with locally advanced NSCLC treated with definitive CRT at a high-volume cancer center in the United States. We included all patients older than 18 years who were diagnosed between Jan 1, 2006, and Dec 31, 2022 with histologically or cytologically confirmed unresectable Stage 2 or 3 NSCLC and treated with conformal radiotherapy to a minimum dose of ≥45 Gy with or without chemotherapy. Of these, 31 RP events were identified through manual adjudication using radiologic criteria and chart review. NLP was used to extract the temporal relationship of 16 pre-specified symptoms with treatment from over 100,000 clinical notes spanning pre- and during-treatment intervals. We trained and validated machine learning models on combinations of baseline clinical data, radiation dosimetry, and NLP-derived symptom features. Model performance was evaluated using a nested cross-validation framework, with an outer cross-validation loop reserved for performance assessment and an inner cross-validation loop used for model training and integration, and summarized using area under the receiver operating characteristic curve (AUC) and partial AUC (pAUC) at high specificity thresholds. Clinical utility was evaluated using decision curve analysis (DCA). FINDINGS: The best-performing model incorporated longitudinal NLP features and achieved a median AUC of 0.759 (90% confidence interval 0.753-0.766), significantly outperforming baseline models using only dosimetry (AUC 0.613) or clinical variables (AUC 0.635). NLP-based features such as cough trajectory, shortness of breath, and wheezing were among the most important predictors. Inclusion of NLP-derived symptom data improved early identification of high-risk patients, particularly in the clinically relevant high-specificity range (pAUC 0.021 vs. 0.010 for dosimetry alone). DCA showed that the calibrated MLP model provided greater net benefit than default strategies of treating all or no patients across clinically relevant threshold possibilities. INTERPRETATION: In this early work, NLP-based extraction of longitudinal symptoms from routine clinical documentation meaningfully enhances RP prediction in patients undergoing CRT for NSCLC. This approach leverages existing electronic health record infrastructure to deliver real-time, scalable, and interpretable risk estimates, offering a pathway toward potential early intervention and personalized toxicity management. The model and DCA requires external and prospective validation before clinical deployment; as such, future work should focus on this validation and integration into clinical decision support systems. FUNDING: AstraZeneca.

Chemoradiotherapy↗

PubMed1999

The dynamics of operant conditioning.

Existing models of operant learning are relatively insensitive to historical properties of behavior and applicable to only limited data sets. This article proposes a minimal set of principles based on short-term and long-term memory mechanisms that can explain the major static and dynamic properties of operant behavior in both single-choice and multiresponse situations. The critical features of the theory are as follows: (a) The key property of conditioning is assessment of the degree of association between responses and reinforcement and between stimuli and reinforcement; (b) the contingent reinforcement is represented by learning expectancy, which is the combined prediction of response-reinforcement and stimulus-reinforcement associations; (c) the operant response is controlled by the interplay between facilitatory and suppressive variables that integrate differences between expected (long-term) and experienced (short-term) events; and (d) very-long-term effects are encoded by a consolidated memory that is sensitive to the entire reinforcement history. The model predicts the major qualitative features of operant phenomena and then suggests an experimental test of theoretical predictions about the joint effects of reinforcement probability and amount of training on operant choice. We hypothesize that the set of elementary principles that we propose may help resolve the long-standing debate about the fundamental variables controlling operant conditioning.

Animals↗

PubMed1991

Associative structure of differential inhibition: implications for models of conditioned inhibition.

Following A+/X- training (with A, X, and + being a light, tone, and footshock, respectively), rats received extinction of A and the training context, extinction of the training context alone, or no extinction. The inhibitory potential of X was then assessed with conditioned lick suppression in a neutral context using both summation and retardation tests. Extinction of the training context alone and extinction of A and the training context reduced the inhibitory potential of X appreciably and equally. Hence, what is traditionally called differential inhibition appears to depend not on the excitatory value of A but on the excitatory value of the training context. In conjunction with what is known about other inhibitory training procedures, these results suggest that a conditioned inhibitor is a stimulus that has been paired with little or no reinforcement in the presence of an accompanying stimulus that predicts greater reinforcement.

Animals↗

PubMed2000

Song replay during sleep and computational rules for sensorimotor vocal learning.

Songbirds learn a correspondence between vocal-motor output and auditory feedback during development. For neurons in a motor cortex analog of adult zebra finches, we show that the timing and structure of activity elicited by the playback of song during sleep matches activity during daytime singing. The motor activity leads syllables, and the matching sensory response depends on a sequence of typically up to three of the preceding syllables. Thus, sensorimotor correspondence is reflected in temporally precise activity patterns of single neurons that use long sensory memories to predict syllable sequences. Additionally, "spontaneous" activity of these neurons during sleep matches their sensorimotor activity, a form of song "replay." These data suggest a model whereby sensorimotor correspondences are stored during singing but do not modify behavior, and off-line comparison (e.g., during sleep) of rehearsed motor output and predicted sensory feedback is used to adaptively shape motor output.

Acoustic Stimulation↗

PubMed1999

Computational nature of human adaptive control during learning of reaching movements in force fields.

Learning to make reaching movements in force fields was used as a paradigm to explore the system architecture of the biological adaptive controller. We compared the performance of a number of candidate control systems that acted on a model of the neuromuscular system of the human arm and asked how well the dynamics of the candidate system compared with the movement characteristics of 16 subjects. We found that control via a supra-spinal system that utilized an adaptive inverse model resulted in dynamics that were similar to that observed in our subjects, but lacked essential characteristics. These characteristics pointed to a different architecture where descending commands were influenced by an adaptive forward model. However, we found that control via a forward model alone also resulted in dynamics that did not match the behavior of the human arm. We considered a third control architecture where a forward model was used in conjunction with an inverse model and found that the resulting dynamics were remarkably similar to that observed in the experimental data. The essential property of this control architecture was that it predicted a complex pattern of near-discontinuities in hand trajectory in the novel force field. A nearly identical pattern was observed in our subjects, suggesting that generation of descending motor commands was likely through a control system architecture that included both adaptive forward and inverse models. We found that as subjects learned to make reaching movements, adaptation rates for the forward and inverse models could be independently estimated and the resulting changes in performance of subjects from movement to movement could be accurately accounted for. Results suggested that the adaptation of the forward model played a dominant role in the motor learning of subjects. After a period of consolidation, the rates of adaptation in the internal models were significantly larger than those observed before the memory had consolidated. This suggested that consolidation of motor memory coincided with freeing of certain computational resources for subsequent learning.

Adaptation, Physiological↗

PubMed1993

Cell proliferation and chemical carcinogenesis: symposium overview.

Cancer, by definition, is a proliferative disease. The fundamental scientific issue explored at the international symposium "Cell Proliferation and Chemical Carcinogenesis" was the impact of chemically enhanced cell proliferation on the dynamic carcinogenic processes. This conference, held at the National Institute of Environmental Health Sciences January 14-16, 1992, provided an open forum for the exchange of new results, information, and ideas in four areas: a) general principles of cell division and carcinogenesis, b) critical evaluation of cell proliferation methodologies, c) cell proliferation and modeling of organ-specific carcinogenesis, and d) cell proliferation and human carcinogenesis. This overview summarizes key findings from that symposium. The general view expressed was that although cell proliferation is involved inextricably in the development of cancers, chemically enhanced cell division does not reliably predict carcinogenicity. Our knowledge of the multistep nature of carcinogenesis has advanced substantially during recent years; however, much still needs to be learned. A greater understanding of the cellular and molecular events in chemical carcinogenesis should improve all aspects of the overall risk assessment process, including extrapolations based on dose, species, and interindividual differences.

Animals↗

PubMed2024

Construction of a molecular diagnostic system for neurogenic rosacea by combining transcriptome sequencing and machine learning.

Patients with neurogenic rosacea (NR) frequently demonstrate pronounced neurological manifestations, often unresponsive to conventional therapeutic approaches. A molecular-level understanding and diagnosis of this patient cohort could significantly guide clinical interventions. In this study, we amalgamated our sequencing data (n = 46) with a publicly accessible database (n = 38) to perform an unsupervised cluster analysis of the integrated dataset. The eighty-four rosacea patients were partitioned into two distinct clusters. Neurovascular biomarkers were found to be elevated in cluster 1 compared to cluster 2. Pathways in cluster 1 were predominantly involved in neurotransmitter synthesis, transmission, and functionality, whereas cluster 2 pathways were centered on inflammation-related processes. Differential gene expression analysis and WGCNA were employed to delineate the characteristic gene sets of the two clusters. Subsequently, a diagnostic model was constructed from the identified gene sets using linear regression methodologies. The model's C index, comprising genes PNPLA3, CUX2, PLIN2, and HMGCR, achieved a remarkable value of 0.9683, with an area under the curve (AUC) for the training cohort's nomogram of 0.9376. Clinical characteristics from our dataset (n = 46) were assessed by three seasoned dermatologists, forming the NR validation cohort (NR, n = 18; non-neurogenic rosacea, n = 28). Upon application of our model to NR diagnosis, the model's AUC value reached 0.9023. Finally, potential therapeutic candidates for both patient groups were predicted via the Connectivity Map. In summation, this study unveiled two clusters with unique molecular phenotypes within rosacea, leading to the development of a precise diagnostic model instrumental in NR diagnosis.

Humans↗

PubMed2026

Patient-specific modeling identifies metabolic interventions for reversing glucose use reprogramming in alcohol-associated hepatitis.

Alcoholic hepatitis (AH) is an acute form of alcohol-associated liver disease with very few treatment options. Recent studies highlighted liver metabolic reprogramming in AH as an indicator of severity. We aim at identifying new intervention points to reverse liver metabolic dysregulation across varying degrees of AH. We develop 89 personalized genome-scale metabolic models by integrating a generic human cellular metabolic model with liver transcriptomics data from AH patients with varying disease severity and healthy controls. We grade the AH patients based on the model-predicted level of glycolysis reprogramming and validate the results using published metabolomics data. We test in silico gene knockdown interventions to reverse the aberrant metabolic reprogramming in AH. Knockdown of two glycolytic genes, Hkdc1 and Pkm, significantly rebalance the metabolic fluxes toward a healthy liver metabolic phenotype. We use machine learning on the glycolysis fluxes to develop a quantitative glucose use reprogramming score, which correlates with AH severity and patient-specific responses to in silico gene knockdown interventions. The score was independently validated using a published AH liver transcriptomics dataset. We propose a cellular metabolism-based therapy targeting Hkdc1 and Pkm in the glycolysis pathway as a potential treatment for reversing the aberrant glucose metabolism in AH.

Humans↗

PubMed2025

CrossAttOmics: multiomics data integration with cross-attention.

MOTIVATION: Advances in high throughput technologies enabled large access to various types of omics. Each omics provides a partial view of the underlying biological process. Integrating multiple omics layers would help have a more accurate diagnosis. However, the complexity of omics data requires approaches that can capture complex relationships. One way to accomplish this is by exploiting the known regulatory links between the different omics, which could help in constructing a better multimodal representation. RESULTS: In this article, we propose CrossAttOmics, a new deep-learning architecture based on the cross-attention mechanism for multiomics integration. Each modality is projected in a lower dimensional space with its specific encoder. Interactions between modalities with known regulatory links are computed in the feature representation space with cross-attention. The results of different experiments carried out in this article show that our model can accurately predict the types of cancer by exploiting the interactions between multiple modalities. CrossAttOmics outperforms other methods when there are few paired training examples. Our approach can be combined with attribution methods like LRP to identify which interactions are the most important. AVAILABILITY AND IMPLEMENTATION: The code is available at https://github.com/Sanofi-Public/CrossAttOmics and https://doi.org/10.5281/zenodo.15065928. TCGA data can be downloaded from the Genomic Data Commons Data Portal. CCLE data can be downloaded from the depmap portal.

Humans↗

PubMed1994

Laminar selectivity of the cholinergic suppression of synaptic transmission in rat hippocampal region CA1: computational modeling and brain slice physiology.

ACh may set the dynamics of cortical function to those appropriate for learning new information. In models of the putative associative memory function of piriform cortex, selective suppression of intrinsic but not afferent fiber synaptic transmission by ACh prevents recall of previous input from interfering with the learning of new input (Hasselmo, 1993). Selective cholinergic suppression may play a similar role in the hippocampal formation, where Schaffer collateral synapses in stratum radiatum (s. rad) may store associations between activity in region CA3 and the entorhinal cortex input to region CA1 terminating in stratum lacunosum-moleculare (s. l-m). A computational model of region CA1 predicts that for effective associative memory function of the Schaffer collaterals, cholinergic suppression of synaptic transmission should be stronger in s. rad than in s. l-m. In the hippocampal slice preparation, we tested the effect of the cholinergic agonist carbachol (0.01-500 microM) on synaptic transmission in s. rad and s. l-m. Stimulating and recording electrodes were simultaneously placed in both layers, allowing analysis of the effect of carbachol on synaptic potentials in both layers during the same perfusion in each slice. Carbachol produced a significantly stronger suppression of stimulus-evoked EPSPs in s. rad than in s. l-m at all concentrations greater than 1 microM. At 100 microM, EPSP initial slopes were suppressed by 89.1 +/- 3.0% in s. rad, but only by 40.1 +/- 4.1% in s. l-m. The muscarinic antagonist atropine (1 microM) blocked cholinergic suppression in both layers. These data support the hypothesis that synaptic modification of the Schaffer collaterals may store associations between activity in region CA3 and the afferent input to region CA1 from the entorhinal cortex. In simulations, feedback regulation of cholinergic modulation based on activity in region CA1 sets the appropriate dynamics of learning for novel associations, and recall for familiar associations.

Animals↗

PubMed2025

Deep learning guided programmable design of Escherichia coli core promoters from sequence architecture to strength control.

Core promoters are essential regulatory elements that control transcription initiation, but accurately predicting and designing their strength remains challenging due to complex sequence-function relationships and the limited generalizability of existing AI-based approaches. To address this, we developed a modular platform integrating rational library design, predictive modelling, and generative optimization into a closed-loop workflow for end-to-end core promoter engineering. Conserved and spacer region of core promoters exert distinct effects on transcriptional strength, with the former driving large-scale variation and the latter enabling finer gradation. Based on this insight, Mutation-Barcoding-Reverse Sequencing approach was used and constructed a synthetic promoter library comprising 112 955 variants with minimal redundancy and a 16 226-fold expression range. A Transformer-based model trained on this dataset achieved a Pearson correlation of 0.87 with experimentally measured promoter strengths. When combined with a conditional diffusion model, the system enabled de novo generation of promoter sequences with defined strengths, achieving a design-to-measurement correlation of 0.95 and maintaining high accuracy (R = 0.93) across varied sequence contexts. The designed promoters consistently preserved their intended strength gradients, demonstrating robust plug-and-play functionality. This work establishes a scalable and extensible platform (www.yudenglab.com) for deep learning-guided programmable design of Escherichia coli core promoters, enabling precise transcriptional control.

Promoter Regions, Genetic↗

PubMed2026

Enhanced identification of key bacterial motility genes via a cross-species genomic hybrid feature machine learning approach.

Efficient and accurate identification of functional genes is critical to biological research, yet traditional single-species approaches are often limited by low efficiency. Previously, we established a novel method for identifying key genes using cross-species protein domain features and machine learning. However, the high multiplicity of gene members associated with specific domains creates a substantial workload for subsequent experimental validation. To address this, this study proposes an enhanced approach that integrates EggNOG-based protein sequence annotation with domain analysis. Unannotated sequences are subsequently analyzed for protein domains, generating a comprehensive "direct gene annotation plus domain" hybrid feature matrix. While the hybrid matrix model yielded comparable predictive accuracy, it significantly enhanced feature resolution: the top 50 predicted features were all known motility-related genes or domains. Furthermore, among the top 100 ranked features, 58 are confirmed to be directly related to motility based on experimental evidence. Although strict genus-level control still yielded 51 confirmed features, excessive taxonomic restriction drastically reduces the number of training genomes, which may paradoxically impair identification efficiency. These results demonstrate that the new method effectively reduces the subsequent experimental workload and enables high-throughput identification of functional genes in a single analysis. With accuracy and efficiency far exceeding those of existing single-species identification methods, it provides a highly efficient solution for mining key genes underlying other complex bacterial phenotypes.

Machine Learning↗

PubMedDate not supplied

Search for predictive generic model of aqueous solubility using Bayesian neural nets.

Several predictive models of aqueous solubility have been published. They have good performances on the data sets which have been used for training the models, but usually these data sets do not contain many structures similar to the structures of interest to the drug research and their applicability in drug hunting is questionable. A very diverse data set has been gathered with compounds issued from literature reports and proprietary compounds. These compounds have been grouped in a so-called literature data set I, a proprietary data set II, and a mixed data set III formed by I and II. About 100 descriptors emphasizing surface properties were calculated for every compound. Bayesian learning of neural nets which cumulates the advantages of neural nets without having their weaknesses was used to select the most parsimonious models and train them, from I, II, and III. The models were established by either selecting the most efficient descriptors one by one using a modified Gram-Schmidt procedure (GS) or by simplifying a most complete model using automatic relevance procedure (ARD). The predictive ability of the models was accessed using validation data sets as much unrelated to the training sets as possible, using two new parameters: NDD(x,ref) the normalized smallest descriptor distance of a compound x to a reference data set and CD(x,mod) the combination of NDD(x,ref) with the dispersion of the Bayesian neural nets calculations. The results show that it is possible to obtain a generic predictive model from database I but that the diversity of database II is too restricted to give a model with good generalization ability and that the ARD method applied to the mixed database III gives the best predictive model.

Journal Article↗

PubMed2001

Learning effective amino acid interactions through iterative stochastic techniques.

The prediction of the three-dimensional structures of the native states of proteins from the sequences of their amino acids is one of the most important challenges in molecular biology. An essential task for solving this problem within coarse-grained models is the deduction of effective interaction potentials between the amino acids. Over the years, several techniques have been developed to extract potentials that are able to discriminate satisfactorily between the native and nonnative folds of a preassigned protein sequence. In general, when these potentials are used in actual dynamical folding simulations, they lead to a drift of the native structure outside the quasinative basin. In this article, we present and validate an approach to overcome this difficulty. By exploiting several numerical and analytical tools, we set up a rigorous iterative scheme to extract potentials satisfying a prerequisite of any viable potential: the stabilization of proteins within their native basin (less than 3-4 A RMSD). The scheme is flexible and is demonstrated to be applicable to a variety of parameterizations of the energy function, and it provides in each case the optimal potentials.

Amino Acids↗

PubMed1999

Learning foraging thresholds for lizards: an analysis of a simple learning algorithm

This paper gives proof of convergence for a learning algorithm that describes how anoles (lizards found in the Caribbean) learn foraging threshold distance. An anole will pursue a prey if and only if it is within this threshold of the anole's perch. The learning algorithm was proposed by Roughgarden and his colleagues. They experimentally determined that this algorithm quickly converges to the foraging threshold that is predicted by optimal foraging theory. We provide analytic confirmation that the optimal foraging behavior as predicted by Roughgarden's model can be attained by a lizard that follows this simple and zoologically plausible rule of thumb. Copyright 1999 Academic Press.

Journal Article↗