PubMed Health⌕ Search

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 613 records · Page 34Linked to original sources
PubMed2004

Application of a prediction model for identification of individuals at diabetic risk.

As a follow-up to our preceding paper, we attempted to extract features of health risk progression for diabetes in Sequential Multi Layered Perceptron (SMLP) via inverse processing of the learned structure. The time-varying risk progress was assessed with risk trajectory and conditional mixture model. Overall risk cut along with the prediction was stable over time and high body mass index (BMI) tops the health behavioral risks predicting the onset of diabetes. For the initial prediction, high BMI (obesity), high blood pressure (BP), high cholesterol, and diet in fatty food were significant. Over time, variations in trajectory were due to changes in BMI, stress, BP, cholesterol, and fatty food intake. We tested the effectiveness of identifying prediabetics by the SMLP by applying the implemented SMLP to a test population of employees from a large manufacturing company, where an early worksite health promotion was initiated (1984). This resulted in a potential sensitivity (71.4%) although there were issues like mapping corresponding risks and large time lags. A secondary test on the similar population as in the previous paper showed a promising sensitivity (86.5%) over 3 years. When combining with targeted screening such as impaired glucose tolerance test only for those predicted to be diabetics, the presented prediction model and extracted features can be used in implementing an effective disease prevention and management program.

Diabetes Mellitus, Type 2↗
PubMed1989

The distributed representation of vestibulo-oculomotor signals by brain-stem neurons.

The vestibuloocular reflex and other oculomotor functions are subserved by populations of neurons operating in parallel. This distributed aspect of the system's organization has been largely ignored in previous block diagram models. Neurons that transmit oculomotor signals, such as those in the vestibular nucleus (VN), actually combine the different types of signals in a diverse, seemingly random way that could not be predicted from a block diagram. We used the backpropagation learning algorithm to program distributed neural-network models of the vestibulo-oculomotor system. Networks were trained to combine vestibular, pursuit and saccadic eye velocity command signals. The model neurons in these neural networks have diverse combinations of vestibulo-oculomotor signals that are qualitatively similar to those reported for actual VN neurons in the monkey. This similarity implicates a learning mechanism as an organizing influence on the vestibulo-oculomotor system and demonstrates how VN neurons can encode vestibulo-oculomotor signals in a diverse, distributed manner.

Algorithms↗
PubMed1990

Synchronous neural networks of nonlinear threshold elements with hysteresis.

We use Hoffmann's suggestion [Hoffmann, G. W. (1986) J. Theor. Biol. 122, 33-67] of hysteresis in a single neuron level and determine its consequences in a synchronous network made of such neurons. We show that the overall retrieval ability in the presence of noise and the memory capacity of the network in the present model are better than in conventional models without such hysteresis. Second-order interaction further improves the retrieval ability of the network and causes hysteresis in the retrieval-noise curve for any arbitrary width of the bistable region. The convergence rate is increased by the hysteresis at high noise levels but is reduced by the hysteresis at low noise levels. Explicit formulae are given for calculations of average final convergence and noise threshold as functions of the width of the bistable region. There is neurophysiological evidence for hysteresis in single neurons, and we propose optical implementations of the present model by using ZnSe interference filters to test the predictions of the theory.

Animals↗
PubMed2026

Advancing precision tacrolimus therapy: a systems genetics dissection in BXD platform.

BACKGROUND: Tacrolimus is a core immunosuppressant in organ transplantation, but its narrow therapeutic window and significant pharmacokinetic variability hinder precision dosing. Although CYP3A5-guided strategies have established clinical relevance for tacrolimus initial dose adjustment, they do not fully account for the marked interindividual variability in tacrolimus exposure, highlighting the need for complementary models to decode more complex genetic regulation. This study aimed to identify candidate genetic modulators of tacrolimus metabolism and develop an integrated predictive framework for individualized therapy. METHODS: Using 46 BXD recombinant inbred mouse strains, we characterized transcriptomics and machine learning, and validated key genes. We then constructed a clinical model using data from 168 renal transplant recipients. RESULTS: We identified 19 genomic loci associated with tacrolimus pharmacokinetic traits and supported DBP/CYP2A6 as candidate modulators associated with tacrolimus disposition. The clinical prediction model, incorporating these genes and clinical variables, achieved robust AUROC. CONCLUSIONS: These findings support a polygenic contribution to tacrolimus metabolism and provide an experimental and computational framework for identifying candidate modulators relevant to individualized dosing. The BXD mouse platform offers a systems-genetics approach for mechanistic discovery that may inform future translational studies on tacrolimus precision dosing.

Animals↗
PubMed2005

Building breakthrough businesses within established organizations.

Many companies assume that once they've launched a major innovation, growth will soon follow. It's not that simple. High-potential new businesses within established companies face stiff headwinds well after their inception. That's why a company's emphasis must shift: from ideas to execution and from leadership excellence to organizational excellence. The authors spent five years chronicling new businesses at the New York Times Company, Analog Devices, Corning, Hasbro, and other organizations. They found that a breakthrough new business (referred to as NewCo) rarely coexists gracefully with the established business in the company (called CoreCo). The unnatural combination creates three specific challenges--forgetting, borrowing, and learning--that NewCo must meet in order to survive and grow. NewCo must first forget some of what made CoreCo successful. NewCo and CoreCo have elemental differences, so NewCo must leave behind CoreCo's notions about what skills and competencies are most valuable. NewCo must also borrow some of CoreCo's assets--usually in one or two key areas that will give NewCo a crucial competitive advantage. Incremental cost reductions, for example, are never a sufficient justification for borrowing. Finally, NewCo must be prepared to learn some things from scratch. Because strategic experiments are highly uncertain endeavors, NewCo will face several critical unknowns. The more rapidly it can resolve those unknowns--that is, the faster it can learn--the sooner it will zero in on a winning business model or exit a hopeless situation. Managers can accelerate this learning by planning more simply and more often and by comparing predicted and actual trends.

Capital Financing↗
PubMed2005

A hybrid neural network system for prediction and recognition of promoter regions in human genome.

This paper proposes a high specificity and sensitivity algorithm called PromPredictor for recognizing promoter regions in the human genome. PromPredictor extracts compositional features and CpG islands information from genomic sequence, feeding these features as input for a hybrid neural network system (HNN) and then applies the HNN for prediction. It combines a novel promoter recognition model, coding theory, feature selection and dimensionality reduction with machine learning algorithm. Evaluation on Human chromosome 22 was approximately 66% in sensitivity and approximately 48% in specificity. Comparison with two other systems revealed that our method had superior sensitivity and specificity in predicting promoter regions. PromPredictor is written in MATLAB and requires Matlab to run. PromPredictor is freely available at http://www.whtelecom.com/Prompredictor.htm.

Computational Biology↗
PubMed1996

Parallel processing of chemical information in a local area network--II. A parallel cross-validation procedure for artificial neural networks.

This paper describes a parallel cross-validation (PCV) procedure, for testing the predictive ability of multi-layer feed-forward (MLF) neural networks models, trained by the generalized delta learning rule. The PCV program has been parallelized to operate in a local area computer network. Development and execution of the parallel application was aided by the HYDRA programming environment, which is extensively described in Part I of this paper. A brief theoretical introduction on MLF networks is given and the problems, associated with the validation of predictive abilities, will be discussed. Furthermore, this paper comprises a general outline of the PCV program. Finally, the parallel PCV application is used to validate the predictive ability of an MLF network modeling a chemical non-linear function approximation problem which is described extensively in the literature.

Artificial Intelligence↗
PubMed1979

Theories of the dorsal bundle extinction effect.

Selective destruction of the noradrenaline systems in the rat brain using the neurotoxin 6-hydroxydopamine has been found to cause resistance to extinction in a number of behavioural situations. Several theories concerning the behavioural mechanism altered by the lesion, and hence about the role of noradrenaline in normal brain functioning, are proposed and evaluated. Theories suggesting a role for noradrenaline in activity, perseveration, internal inhibition, frustrative non-reward, motivation, or secondary reinforcement, fail to explain all the available evidence and direct tests of each theory fails to support its predictions. A model which suggests that noreadrenaline is involved in attentional behaviour, specifically in filtering out or learning to ignore irrelevant environmental stimuli, is successful in explaining all available data and direct tests of the lesioned rats' attentional capacity serve to confirm many of the predictions of an attentional theory of the dorsal bundle extinction effect.

Animals↗
PubMed2004

Artificial neural networks and artificial organisms can predict Alzheimer pathology in individual patients only on the basis of cognitive and functional status.

Data from several studies have pointed out the existence of a strong correlation between Alzheimer's disease (AD) neuropathology and cognitive state. However, because of their highly complex and nonlinear relationship, it has been difficult to develop a predictive model for individual patient classification through traditional statistical approaches. When exposed to complex data sets, artificial neural networks (ANNs) can recognize patterns, learn the relationship of different variables, and address classification tasks. To predict the results of postmortem brain examinations, we applied ANNs to the Nun Study data set, a longitudinal epidemiological study, which includes annual cognitive and functional evaluation. One hundred seventeen subjects from the study participated in this analysis. We determined how demographic data and the cognitive and functional variables of each subject during the last year of her life could predict the presence of brain pathology expressed as Braak stages, neurofibrillary tangles (NFTs) and neuritic plaques (NPs) count in the neocortex and hippocampus, and brain atrophy. The result of this analysis was then compared with traditional statistical models. ANNs proved to be better predictors than Linear Discriminant Analysis in all experimentations (+ approximately 10% in overall accuracy), especially when assembled in Artificial Organisms (+ approximately 20% in overall accuracy). Demographic, cognitive, and clinical variables were better predictors of tangles count in the neocortex and in the hippocampus when compared to NPs count. These findings strengthen the hypothesis that neurofibrillary pathology may represent the major anatomic substrate of the cognitive impairment found in AD.

Alzheimer Disease↗
PubMed2025

STRUMP-I: Structure-based machine learning approach to pMHC-I binding prediction using force field energy features.

The adaptive immune system monitors cellular integrity by recognizing short peptides from intracellular proteins presented on Major Histocompatibility Complex class I (MHC-I) molecules, collectively termed peptide-MHC complexes (pMHC), enabling detection of foreign or mutated proteins. With the rising importance of immunotherapies targeting neoantigens in cancers, the ability to accurately predict which peptides will bind to the diverse population of MHC alleles is critically important. Current computational methods for pMHC-I prediction fall broadly into sequence-based methods, which rely heavily on large training datasets, and structure-based methods that leverage structural modeling and energetics of pMHC binding. While sequence-based methods have been popularly used, their performance is dependent on the size and quality of training data. On the other hands, while structure-based approaches can generalize better across diverse MHC alleles, they traditionally depend on identifying a single global minimum energy conformation, an assumption that often fails due to the inherent binding promiscuity of MHC-I molecules. To address these limitations, we developed a STRUMP-I (STRUcture-based pMHC Prediction (for class I)), a novel pMHC binding prediction tool that directly leverages a broad set of force-field-derived energy terms as machine-learning features. STRUMP-I achieves performance comparable to state-of-the-art sequence-based models while significantly outperforming them on MHC alleles with limited representation in training data. Furthermore, STRUMP-I demonstrates strong synergy when integrated with sequence-based methods, notably enhancing prediction precision. The robustness and generalizability of STRUMP-I were confirmed by evaluating its predictive performance on independent, previously unseen datasets, including an experimentally validated cancer neoantigen dataset. This combined approach advances our capability to reliably identify clinically relevant neoantigen targets. The source code and trained models are available at https://github.com/yoonjoolab/STRUMP-I.

energy optimization↗
PubMed2006

Demonstration of two novel methods for predicting functional siRNA efficiency.

BACKGROUND: siRNAs are small RNAs that serve as sequence determinants during the gene silencing process called RNA interference (RNAi). It is well know that siRNA efficiency is crucial in the RNAi pathway, and the siRNA efficiency for targeting different sites of a specific gene varies greatly. Therefore, there is high demand for reliable siRNAs prediction tools and for the design methods able to pick up high silencing potential siRNAs. RESULTS: In this paper, two systems have been established for the prediction of functional siRNAs: (1) a statistical model based on sequence information and (2) a machine learning model based on three features of siRNA sequences, namely binary description, thermodynamic profile and nucleotide composition. Both of the two methods show high performance on the two datasets we have constructed for training the model. CONCLUSION: Both of the two methods studied in this paper emphasize the importance of sequence information for the prediction of functional siRNAs. The way of denoting a bio-sequence by binary system in mathematical language might be helpful in other analysis work associated with fixed-length bio-sequence.

Algorithms↗
PubMed1999

Enhanced learning of proportional math through music training and spatial-temporal training.

It was predicted, based on a mathematical model of the cortex, that early music training would enhance spatial-temporal reasoning. We have demonstrated that preschool children given six months of piano keyboard lessons improved dramatically on spatial-temporal reasoning while children in appropriate control groups did not improve. It was then predicted that the enhanced spatial-temporal reasoning from piano keyboard training could lead to enhanced learning of specific math concepts, in particular proportional math, which is notoriously difficult to teach using the usual language-analytic methods. We report here the development of Spatial-Temporal Math Video Game software designed to teach fractions and proportional math, and its strikingly successful use in a study involving 237 second-grade children (age range six years eight months-eight years five months). Furthermore, as predicted, children given piano keyboard training along with the Math Video Game training scored significantly higher on proportional math and fractions than children given a control training along with the Math Video Game. These results were readily measured using the companion Math Video Game Evaluation Program. The training time necessary for children on the Math Video Game is very short, and they rapidly reach a high level of performance. This suggests that, as predicted, we are tapping into fundamental cortical processes of spatial-temporal reasoning. This spatial-temporal approach is easily generalized to teach other math and science concepts in a complementary manner to traditional language-analytic methods, and at a younger age. The neural mechanisms involved in thinking through fractions and proportional math during training with the Math Video Game might be investigated in EEG coherence studies along with priming by specific music.

Child↗
PubMed2026

GraphyloVar: predicting the impact of non-coding variants using a multi-species sequence model.

MOTIVATION: Understanding the functional impact of genetic variants is a key problem for precision medicine. Tools like CADD, PhyloP, and PhastCons are useful, but they often look at each position in the genome in isolation. This means they can miss important information from the evolutionary history that connects different species. In this paper, we extend our previous model, Graphylo, to predict the effects of variants. Our new model, GraphyloVar, is built to directly utilize the phylogenetic tree that relates the species. RESULTS: GraphyloVar is a deep learning model that considers both DNA sequence and evolutionary patterns from many species. It uses two main components: Graph Convolutional Networks (GCNs) to process the phylogenetic tree, and Transformer encoders to extract features from the DNA sequences. Pre-trained to predict population-level allele frequencies on the TOPMed whole-genome sequencing cohort, GraphyloVar achieves an AUROC of 0.6246 zero-shot on &#x223c;149M held-out variants, and an ensemble with CADD reaches 0.6442 (+0.020, P<10-15). Fine-tuned GraphyloVar achieves the highest AUROC across all 13 MPRA benchmark datasets. By integrating deep learning with explicit phylogenetic input, GraphyloVar offers a powerful and complementary approach to variant effect prediction that utilizes the full evolutionary history from many species to better identify and prioritize important non-coding variants. AVAILABILITY AND IMPLEMENTATION: Code and datasets are available at https://github.com/DongjoonLim/GraphyloVar under DOI: 10.5281/zenodo.20616818.

Phylogeny↗
PubMed1994

When does a different environmental context make a difference in recognition? A global activation model.

The effects on recognition of changes in environmental context between learning and test are examined. A context effect occurs when memory tests that take place in an environmental context that is different from the learning context produce consistent differences in performance. A formal model of context-dependent recognition within a global activation framework is presented. The model generates the predictions that (1) context effects will be present when items are tested in a new context that was not seen during learning and (2) context effects will be absent or very small when items are tested in a context that was experienced during learning but that differs from the context in which the test item was learned. Both predictions were verified in an experiment that varied the nature of the different-context test within subjects. Implications for research concerned with context-dependent recognition are discussed.

Adult↗
PubMed2003

Dynamic regulation of sensorimotor integration in human postural control.

Upright stance in humans is inherently unstable, requiring corrective action based on spatial-orientation information from sensory systems. One might logically predict that environments providing access to accurate orientation information from multiple sensory systems would facilitate postural stability. However, we show that, after a period in which access to accurate sensory information was reduced, the restoration of accurate information disrupted postural stability. In eyes-closed trials, proprioceptive information was altered by rotating the support surface in proportion to body sway (support surface "sway-referencing"). When the support surface returned to a level orientation, most subjects developed a transient 1-Hz body sway oscillation that differed significantly from the low-amplitude body sway typically observed during quiet stance. Additional experiments showed further enhancement of the 1-Hz oscillation when the surface transitioned from a sway-referenced to a reverse sway-referenced motion. Oscillatory behavior declined with repetition of trials, suggesting a learning effect. A simple negative feedback-control model of the postural control system predicted the occurrence of this 1-Hz oscillation in conditions where too much corrective torque is generated in proportion to body sway. Model simulations were used to distinguish between two alternative explanations for the excessive corrective torque generation. Simulation results favor an explanation based on the dynamic reweighting of sensory contributions to postural control rather than a load-compensation mechanism that scales torque in proportion to a fixed combination of sensory-orientation information.

Adaptation, Physiological↗
PubMedDate not supplied

Synaptic modifications depend on synapse location and activity: a biophysical model of STDP.

In spike-timing-dependent plasticity (STDP) the synapses are potentiated or depressed depending on the temporal order and temporal difference of the pre- and post-synaptic signals. We present a biophysical model of STDP which assumes that not only the timing, but also the shapes of these signals influence the synaptic modifications. The model is based on a Hebbian learning rule which correlates the NMDA synaptic conductance with the post-synaptic signal at synaptic location as the pre- and post-synaptic quantities. As compared to a previous paper [Saudargiene, A., Porr, B., Worgotter, F., 2004. How the shape of pre- and post-synaptic signals can influence stdp: a biophysical model. Neural Comp.], here we show that this rule reproduces the generic STDP weight change curve by using real neuronal input signals and combinations of more than two (pre- and post-synaptic) spikes. We demonstrate that the shape of the STDP curve strongly depends on the shape of the depolarising membrane potentials, which induces learning. As these potentials vary at different locations of the dendritic tree, model predicts that synaptic changes are location dependent. The model is extended to account for the patterns of more than two spikes of the pre- and post-synaptic cells. The results show that STDP weight change curve is also activity dependent.

Action Potentials↗
PubMed2005

Reasoning about conjunctive probabilistic concepts in childhood.

While adults are known to exhibit biases when making conjunctive probability judgments, little is known about childhood competencies in this area. Participants (aged between four and five years, eight and ten years, and a group of young adults) attempted to select the more likely of two events, a single event, and a conjunctive event containing, as one of its components, the single event. The problems were such that the objective probabilities of the component events were potentially available. Children in both age groups were generally successful when the single event was likely. However, when it was unlikely, a majority of children rejected it, choosing the conjunctive event instead, thereby committing the conjunction fallacy. A substantial minority of adults also committed the fallacy under equivalent conditions. It is concluded that under certain conditions children are capable of normative conjunctive judgments but that the mechanisms underpinning this capacity remain to be fully understood.

Adult↗