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 1,153 records · Page 64Linked to original sources

PubMed2026

Deep learning and statistical methods identify novel asthma risk variants in Europeans.

BACKGROUND: Asthma is a common heritable respiratory disorder with a complex genetic basis. Although large-scale genome-wide association studies have identified many risk loci, the full spectrum of its polygenic architecture remains to be defined. OBJECTIVE: We refined the genetic landscape of asthma in individuals of European ancestry and improve polygenic risk prediction through statistical and deep learning-based methods. METHODS: We conducted the largest genome-wide association study meta-analysis of asthma in individuals of European ancestry, combining data from the Global Biobank Meta-analysis Initiative (121,940 cases, 1,254,131 controls) and the Million Veteran Program (36,823 cases, 398,278 controls). To enhance discovery, we applied pleiotropy-informed multitrait analysis and conditional false discovery rate approaches, each incorporating eosinophil counts as a secondary trait. In parallel, we used a Transformer-based deep learning framework to further prioritize variants and improve polygenic risk prediction. RESULTS: The meta-analysis identified 69 independent genome-wide significant loci (P < 5 × 10-8) not previously reported in asthma. Multitrait analysis of genome-wide association studies, conditional false discovery rate, and deep learning approaches uncovered additional candidate loci. Functional annotation and expression quantitative trait locus mapping implicated novel genes in immune regulation, airway remodeling, and metabolic processes. Polygenic risk score models derived from deep learning-prioritized variants outperformed those based on conventional genome-wide association study and standard statistical approaches. CONCLUSIONS: Our study yields a comprehensive map of asthma-associated loci in European ancestry populations, improves genetic risk prediction, and informs future mechanistic studies.

Humans↗

PubMed2006

Modeling early recovery of physical function following hip and knee arthroplasty.

BACKGROUND: Information on early recovery after arthroplasty is needed to help benchmark progress and make appropriate decisions concerning patient rehabilitation needs. The purpose of this study was to model early recovery of physical function in patients undergoing total hip (THA) and knee (TKA) arthroplasty, using physical performance and self-report measures. METHODS: A sample of convenience of 152 subjects completed testing, of which 69 (mean age: 66.77 +/- 8.23 years) underwent THA and 83 (mean age: 60.25 +/- 11.19 years) TKA. Postoperatively, patients were treated using standardized care pathways and rehabilitation protocols. Using a repeated measures design, patients were assessed at multiple time points over the first four postoperative months. Outcome measures included the Lower Extremity Function Scale (LEFS), the physical function subscale of the Western Ontario and McMaster Universities Osteoarthritis Index (WOMAC PF), the 6 minute walk test (6 MWT), timed up and go test (TUG) and a timed stair test (ST). Average recovery curves for each of the measures were characterized using hierarchical linear modeling. Predictors of recovery were sequentially modeled after validation of the basic developmental models. RESULTS: Slopes of recovery were greater in the first 6 to 9 weeks with a second-degree polynomial growth term (weeks squared) providing a reasonable fit for the data over the study interval. Different patterns of recovery were observed between the self-report measures of physical function and the performance measures. In contrast to the models for the WOMAC PF and the LEFS, site of arthroplasty was a significant predictor (p = 0.001) in all of the physical performance measure models with the patients post TKA initially demonstrating higher function. Site of arthroplasty (p = 0.025) also predicted the rate of change for patients post THA and between 9 to 11 weeks after surgery, the THA group surpassed the function of the patients post TKA. CONCLUSION: Knowledge about the predicted growth curves will assist clinicians in referencing patient progress, and determining the critical time points for measuring change. The study has contributed further evidence to highlight the benefit of using physical performance measures to learn about the patients' actual level of disability.

Aged↗

PubMed2005

A comparison of algorithms for inference and learning in probabilistic graphical models.

Research into methods for reasoning under uncertainty is currently one of the most exciting areas of artificial intelligence, largely because it has recently become possible to record, store, and process large amounts of data. While impressive achievements have been made in pattern classification problems such as handwritten character recognition, face detection, speaker identification, and prediction of gene function, it is even more exciting that researchers are on the verge of introducing systems that can perform large-scale combinatorial analyses of data, decomposing the data into interacting components. For example, computational methods for automatic scene analysis are now emerging in the computer vision community. These methods decompose an input image into its constituent objects, lighting conditions, motion patterns, etc. Two of the main challenges are finding effective representations and models in specific applications and finding efficient algorithms for inference and learning in these models. In this paper, we advocate the use of graph-based probability models and their associated inference and learning algorithms. We review exact techniques and various approximate, computationally efficient techniques, including iterated conditional modes, the expectation maximization (EM) algorithm, Gibbs sampling, the mean field method, variational techniques, structured variational techniques and the sum-product algorithm ("loopy" belief propagation). We describe how each technique can be applied in a vision model of multiple, occluding objects and contrast the behaviors and performances of the techniques using a unifying cost function, free energy.

Algorithms↗

PubMed2006

Learning MHC I--peptide binding.

MOTIVATION AND RESULTS: Motivated by the ability of a simple threading approach to predict MHC I--peptide binding, we developed a new and improved structure-based model for which parameters can be estimated from additional sources of data about MHC-peptide binding. In addition to the known 3D structures of a small number of MHC-peptide complexes that were used in the original threading approach, we included three other sources of information on peptide-MHC binding: (1) MHC class I sequences; (2) known binding energies for a large number of MHC-peptide complexes; and (3) an even larger binary dataset that contains information about strong binders (epitopes) and non-binders (peptides that have a low affinity for a particular MHC molecule). Our model significantly outperforms the standard threading approach in binding energy prediction. In our approach, which we call adaptive double threading, the parameters of the threading model are learnable, and both MHC and peptide sequences can be threaded onto structures of other alleles. These two properties make our model appropriate for predicting binding for alleles for which very little data (if any) is available beyond just their sequence, including prediction for alleles for which 3D structures are not available. The ability of our model to generalize beyond the MHC types for which training data is available also separates our approach from epitope prediction methods which treat MHC alleles as symbolic types, rather than biological sequences. We used the trained binding energy predictor to study viral infections in 246 HIV patients from the West Australian cohort, and over 1000 sequences in HIV clade B from Los Alamos National Laboratory database, capturing the course of HIV evolution over the last 20 years. Finally, we illustrate short-, medium-, and long-term adaptation of HIV to the human immune system. AVAILABILITY: http://www.research.microsoft.com/~jojic/hlaBinding.html.

Algorithms↗

PubMed2006

ANGLE: a sequencing errors resistant program for predicting protein coding regions in unfinished cDNA.

In the process of making full-length cDNA, predicting protein coding regions helps both in the preliminary analysis of genes and in any succeeding process. However, unfinished cDNA contains artifacts including many sequencing errors, which hinder the correct evaluation of coding sequences. Especially, predictions of short sequences are difficult because they provide little information for evaluating coding potential. In this paper, we describe ANGLE, a new program for predicting coding sequences in low quality cDNA. To achieve error-tolerant prediction, ANGLE uses a machine-learning approach, which makes better expression of coding sequence maximizing the use of limited information from input sequences. Our method utilizes not only codon usage, but also protein structure information which is difficult to be used for stochastic model-based algorithms, and optimizes limited information from a short segment when deciding coding potential, with the result that predictive accuracy does not depend on the length of an input sequence. The performance of ANGLE is compared with ESTSCAN on four dataset each of them having a different error rate (one frame-shift error or one substitution error per 200-500 nucleotides) and on one dataset which has no error. ANGLE outperforms ESTSCAN by 9.26% in average Matthews's correlation coefficient on short sequence dataset (< 1000 bases). On long sequence dataset, ANGLE achieves comparable performance.

Algorithms↗

PubMed1992

Reversal of epileptic state by patterned electrical stimulation suggested by trion model calculations.

The trion model is based on the Mountcastle columnar organizational principle of cortex. A trion represents an idealized minicolumn with three levels of firing activity and is highly structured in time and in spatial connections. A network of trions has a large repertoire of quasi-stable, periodic spatial-temporal firing patterns, MPs, which can be excited and each MP can be readily enhanced by a Hebb learning rule. A particular MP present in most repertoires has all trions firing together in synchrony, which we identify as the 'Epileptic' MP (EMP). In trion model simulations, the EMP can be enhanced via the Hebb rule after electrical stimulation so that an epileptic focus with after discharge (about 3-6 Hz) is formed and spontaneous firing of the EMP occurs (as in kindling). Following this, by using a small array of closely-spaced stimulating electrodes out of phase, other MPs are enhanced via the Hebb rule eliminating the dominance of the EMP. We strongly urge that these predictions be tested in the animal models for possible clinical relevance.

Cerebral Cortex↗

PubMed2006

Dunces and da Vincis: the genetics of learning and memory in Drosophila.

Progress towards amelioration and eventual cure of human cognitive disorders requires understanding the molecular signaling mechanisms that normally govern learning and memory. The fly Drosophila melanogaster has been instrumental in the identification of molecules and signaling pathways essential for learning and memory, because genetic screens have produced mutants in these processes and the system facilitates integrated genetic, molecular, histological and behavioral analyses. We discuss the behavioral paradigms available to assess associative learning and memory in the fly, the contributions learning and memory mutants have made to our understanding of the molecular mechanisms that govern learning and memory, and predictions stemming from the nature of the affected genes. Furthermore, we consider the multiple well-established behavioral assays available and the powerful molecular genetics of the fly with regard to development of models of human cognitive disorders and their pharmacological treatment.

Animals↗

PubMed2004

Mode shifting between storage and recall based on novelty detection in oscillating hippocampal circuits.

It has been suggested that hippocampal mode shifting between a storage and a retrieval state might be under the control of acetylcholine (ACh) levels, as set by an autoregulatory hippocampo-septo-hippocampal loop. The present study investigates how such a mechanism might operate in a large-scale connectionist model of this circuitry that takes into account the major hippocampal subdivisions, oscillatory population dynamics and the time scale on which ACh exerts its effects in the hippocampus. The model assumes that hippocampal mode shifting is regulated by a novelty signal generated in the hippocampus. The simulations suggest that this signal originates in the dentate. Novel patterns presented to this structure lead to brief periods of depressed firing in the hippocampal circuitry. During these periods, an inhibitory influence of the hippocampus on the septum is lifted, leading to increased firing of cholinergic neurons. The resulting increase in ACh release in the hippocampus produces network dynamics that favor learning over retrieval. Resumption of activity in the hippocampus leads to the reinstatement of inhibition. Despite theta-locked rhythmic firing of ACh neurons in the septum, ACh modulation in the model fluctuates smoothly on a time scale of seconds. It is shown that this is compatible with the time scale on which memory processes take place. A number of strong predictions regarding memory function are derived from the model.

Acetylcholine↗

PubMed1995

A new computational model for protein folding based on atomic solvation.

A new model for calculating the solvation energy of proteins is developed and tested for its ability to identify the native conformation as the global energy minimum among a group of thousands of computationally generated compact non-native conformations for a series of globular proteins. In the model (called the WZS model), solvation preferences for a set of 17 chemically derived molecular fragments of the 20 amino acids are learned by a training algorithm based on maximizing the solvation energy difference between native and non-native conformations for a training set of proteins. The performance of the WZS model confirms the success of this learning approach; the WZS model misrecognizes (as more stable than native) only 7 of 8,200 non-native structures. Possible applications of this model to the prediction of protein structure from sequence are discussed.

Algorithms↗

PubMed1996

New approaches in molecular structure prediction.

In the past years, much effort has been put on the development of new methodologies and algorithms for the prediction of protein secondary and tertiary structures from (sequence) data; this is reviewed in detail. New approaches for these predictions such as neural network methods, genetic algorithms, machine learning, and graph theoretical methods are discussed. Secondary structure prediction algorithms were improved mostly by considering families of related proteins; however, for the reliable tertiary structure modeling of proteins, knowledge-based techniques are still preferred. Methods and examples with more or less successful results are described. Also, programs and parameterizations for energy minimisations, molecular dynamics, and electrostatic interactions have been improved, especially with respect to their former limits of applicability. Other topics discussed in this review include the use of traditional and on-line databases, the docking problem and surface properties of biomolecules, packing of protein cores, de novo design and protein engineering, prediction of membrane protein structures, the verification and reliability of model structures, and progress made with currently available software and computer hardware. In summary, the prediction of the structure, function, and other properties of a protein is still possible only within limits, but these limits continue to be moved.

Chemical Phenomena↗

PubMed2026

Automated CEAP Classification of Venous Duplex Reports Using Multimodal Artificial Intelligence.

OBJECTIVE: To develop and internally validate a prototype multimodal artificial intelligence system for automated CEAP (Clinical, Etiological, Anatomical and Pathophysiological) classification of venous duplex ultrasound (VDUS) reports, integrating natural language processing of free-text components with computer vision analysis of hand-drawn anatomical diagrams. METHODS: Single centre retrospective observational study using routinely collected clinical data. One thousand consecutive venous duplex ultrasound reports from Cambridge University Hospitals NHS Foundation Trust, UK (July 2024 - May 2025) were labelled according to the CEAP classification, excluding the Etiological component, which could not be reliably determined from duplex reports alone. Transfer learning was applied using ClinicalBERT for text and MobileNetV3 for diagrammatic data. Clinical classes were predicted from request line text. Text- and image-based pathophysiological models were developed for four anatomical territories (Great Saphenous Vein, Small Saphenous Vein, Deep system, Perforators), combined using late fusion with probability averaging. RESULTS: The clinical CEAP model achieved accuracy of 0.91, macro-F1 of 0.82, and macro-AUC of 0.98. Pathophysiological prediction varied, with text models broadly outperforming image models. Fusion yielded heterogeneous benefits, improving SSV performance but reducing Deep system accuracy. The performance of the final pathophysiological CEAP fusion models varied across anatomical territories: accuracy ranged from 0.70-0.92 and macro-AUC from 0.80-0.92. CONCLUSION: This study demonstrates the feasibility of automated CEAP classification from VDUS reports. Despite class imbalance affecting minority class predictions, the strong discriminatory performance validates this multimodal ML model for extracting clinically meaningful information from real-world data. This approach offers potential, pending external validation, to streamline vascular services through automated triage and guideline-compliant decision making.

Artificial intelligence↗

PubMed2006

Dynamic causal modeling of evoked responses in EEG and MEG.

Neuronally plausible, generative or forward models are essential for understanding how event-related fields (ERFs) and potentials (ERPs) are generated. In this paper, we present a new approach to modeling event-related responses measured with EEG or MEG. This approach uses a biologically informed model to make inferences about the underlying neuronal networks generating responses. The approach can be regarded as a neurobiologically constrained source reconstruction scheme, in which the parameters of the reconstruction have an explicit neuronal interpretation. Specifically, these parameters encode, among other things, the coupling among sources and how that coupling depends upon stimulus attributes or experimental context. The basic idea is to supplement conventional electromagnetic forward models, of how sources are expressed in measurement space, with a model of how source activity is generated by neuronal dynamics. A single inversion of this extended forward model enables inference about both the spatial deployment of sources and the underlying neuronal architecture generating them. Critically, this inference covers long-range connections among well-defined neuronal subpopulations. In a previous paper, we simulated ERPs using a hierarchical neural-mass model that embodied bottom-up, top-down and lateral connections among remote regions. In this paper, we describe a Bayesian procedure to estimate the parameters of this model using empirical data. We demonstrate this procedure by characterizing the role of changes in cortico-cortical coupling, in the genesis of ERPs. In the first experiment, ERPs recorded during the perception of faces and houses were modeled as distinct cortical sources in the ventral visual pathway. Category-selectivity, as indexed by the face-selective N170, could be explained by category-specific differences in forward connections from sensory to higher areas in the ventral stream. We were able to quantify and make inferences about these effects using conditional estimates of connectivity. This allowed us to identify where, in the processing stream, category-selectivity emerged. In the second experiment, we used an auditory oddball paradigm to show that the mismatch negativity can be explained by changes in connectivity. Specifically, using Bayesian model selection, we assessed changes in backward connections, above and beyond changes in forward connections. In accord with theoretical predictions, there was strong evidence for learning-related changes in both forward and backward coupling. These examples show that category- or context-specific coupling among cortical regions can be assessed explicitly, within a mechanistic, biologically motivated inference framework.

Auditory Pathways↗

PubMed2006

Perceptual learning with spatial uncertainties.

In perceptual learning, stimuli are usually assumed to be presented to a constant retinal location during training. However, due to tremor, drift, and microsaccades of the eyes, the same stimulus covers different retinal positions on sequential trials. Because of these variations the mathematical decision problem changes from linear to non-linear (). This non-linearity implies three predictions. First, varying the spatial position of a stimulus within a moderate range does not deteriorate perceptual learning. Second, improvement for one stimulus variant can yield negative transfer to other variants. Third, interleaved training with two stimulus variants yields no or strongly diminished learning. Using a bisection task, we found psychophysical evidence for the first and last prediction. However, no negative transfer was found as opposed to the second prediction.

Attention↗

PubMed2003

Singularities in mixture models and upper bounds of stochastic complexity.

A learning machine which is a mixture of several distributions, for example, a gaussian mixture or a mixture of experts, has a wide range of applications. However, such a machine is a non-identifiable statistical model with a lot of singularities in the parameter space, hence its generalization property is left unknown. Recently an algebraic geometrical method has been developed which enables us to treat such learning machines mathematically. Based on this method, this paper rigorously proves that a mixture learning machine has the smaller Bayesian stochastic complexity than regular statistical models. Since the generalization error of a learning machine is equal to the increase of the stochastic complexity, the result of this paper shows that the mixture model can attain the more precise prediction than regular statistical models if Bayesian estimation is applied in statistical inference.

Bayes Theorem↗

PubMed1996

Forward Models for Physiological Motor Control.

Based on theoretical and computational studies it has been suggested that the central nervous system (CNS) internally simulates the behaviour of the motor system in planning, control and learning. Such an internal "forward" model is a representation of the motor system that uses the current state of the motor system and motor command to predict the next state. We will outline the uses of such internal models for solving several fundamental computational problems in motor control and then review the evidence for their existence and use by the CNS. Finally we speculate how the location of an internal model within the CNS may be identified. Copyright 1996 Elsevier Science Ltd.

Journal Article↗

PubMed1990

The mirror effect in recognition memory: data and theory.

The mirror effect is a regularity in recognition memory that requires reexamination of current views of memory. Five experiments that further support and extended the generality of the mirror effect are reported. The first two experiments vary word frequency. The third and fourth vary both word frequency and concreteness. The fifth experiment varies word frequency, concreteness, and the subject's operations on the words. The experiments furnish data on the stability of the effect, its relation to response times, its extension to multiple mirror effects, and its extension beyond stimulus variables to operation variables. A theory of the effect and predictions that derive from the theory are presented.

Humans↗

PubMed1982

Communication development and its disorders: a psycholinguistic perspective.

There is a reciprocal relationship between the study of language disorders and research in normal language development. Recent studies in normal acquisition have led to a model of language development that includes not only linguistic achievements, but the development of social and cognitive abilities that lay the basis for the transition from prelinguistic communication to the use of conventional forms. This model has been applied to the study of developmental disorders of language learning. Such a model allows the more puzzling disorders of language development, such as childhood aphasia and primary autism, to be placed in a framework that predicts language disruption when underlying perceptual, cognitive, or social abilities are lacking. Assessment procedures that can be drawn from the model of language disorders are presented. It is argued that the study of these disabilities is important in the building of theoretical models of intact language processing that specify more precisely the contribution of underlying skills to overall functioning. Questions for future research that serve this reciprocal purpose are discussed.

Autistic Disorder↗

PubMed2005

Side-chain flexibility in protein-ligand binding: the minimal rotation hypothesis.

The goal of this work is to learn from nature about the magnitudes of side-chain motions that occur when proteins bind small organic molecules, and model these motions to improve the prediction of protein-ligand complexes. Following analysis of protein side-chain motions upon ligand binding in 63 complexes, we tested the ability of the docking tool SLIDE to model these motions without being restricted to rotameric transitions or deciding which side chains should be considered as flexible. The model tested is that side-chain conformational changes involving more atoms or larger rotations are likely to be more costly and less prevalent than small motions due to energy barriers between rotamers and the potential of large motions to cause new steric clashes. Accordingly, SLIDE adjusts the protein and ligand side groups as little as necessary to achieve steric complementarity. We tested the hypothesis that small motions are sufficient to achieve good dockings using 63 ligands and the apo structures of 20 different proteins and compared SLIDE side-chain rotations to those experimentally observed. None of these proteins undergoes major main-chain conformational change upon ligand binding, ensuring that side-chain flexibility modeling is not required to compensate for main-chain motions. Although more frugal in the number of side-chain rotations performed, this model substantially mimics the experimentally observed motions. Most side chains do not shift to a new rotamer, and small motions are both necessary and sufficient to predict the correct binding orientation and most protein-ligand interactions for the 20 proteins analyzed.

Amino Acids↗