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 919 records · Page 51Linked to original sources

PubMed2025

Screening of the key single nucleotide polymorphisms in type 2 diabetes mellitus complicated with lower extremity arterial disease by machine learning.

OBJECTIVES: Diabetic lower extremity arterial disease (LEAD) is a manifestation of diabetic lower extremity vascular complications. This study aimed to screen the key single nucleotide polymorphism (SNP) gene signature in patients with type 2 diabetes mellitus (T2DM) and LEAD. METHODS: A total of 147 patients with T2DM complicated by LEAD and 144 patients with T2DM without LEAD were enrolled for transcriptome sequencing. The Plink software was used to preprocess the data. Five machine learning methods were adopted to build the SNP diagnosis models. The receiver operating characteristic (ROC) curve was used to quantify the predicted probabilities of the model. Gene Ontology (GO) and Kyoto Encyclopedia of Genes and Genomes (KEGG) pathway enrichment analyses were performed using the cluster Profiler package. Finally, regression statistical analysis was used to correlate the key SNPs with clinical information and biochemical indicators. RESULTS: A total of 24 SNPs were retained and 10 SNPs were risk allele genes. Nine SNPs (rs7412, rs1800629, rs699947, rs3918242, rs668, rs1800470, rs1800449, rs1800469, and rs1024611) were identified as the key SNPs sites. GO and KEGG pathway analyses revealed that these genes are mainly enriched in fluid shear stress and atherosclerosis. Finally, rs1800449 was associated with low-density lipoprotein cholesterol (LDL-C). With high density lipoprotein cholesterol (HDL-C), related site was rs1024611. The sites associated with total cholesterol (CHOL) were rs1800449 and rs7412.The site associated with apolipoprotein B (APOB) and apolipoprotein A1 (APOA1) were rs1800470 and rs1800469. CONCLUSION: This study authenticated nine SNPs for the diagnosis of T2DM patients with LEAD, which will be of great significance in the development of diagnostic molecular biomarkers for T2DM patients.

Humans↗

PubMed2007

Temporal difference modeling of the blood-oxygen level dependent response during aversive conditioning in humans: effects of dopaminergic modulation.

BACKGROUND: The prediction error (PE) hypothesized by the temporal difference model has been shown to correlate with the phasic activity of dopamine neurons during reward learning and the blood-oxygen level dependent (BOLD) response during reward and aversive conditioning tasks. We hypothesized that dopamine would modulate the PE related signal in aversive conditioning and that haloperidol would reduce PE related activity, while an acute dose of amphetamine would increase PE related activity in the ventral striatum. METHODS: Healthy participants took an acute dose of amphetamine, haloperidol, or placebo. We used functional magnetic resonance imaging (fMRI) to measure the BOLD signal while they carried out an aversive conditioning task, using cutaneous electrical stimulation as the unconditioned stimulus (US) and yellow and blue circles as conditioned stimulus (CS+ and CS-, respectively). RESULTS: Prediction error related BOLD activity was seen only in the ventral striatum in the placebo subjects. The subjects given amphetamine showed a wider network of PE related BOLD activity, including the ventral striatum, globus pallidus, putamen, insula, anterior cingulate, and substantia nigra/ventral tegmental area. Haloperidol subjects did not show PE related activity in any of these regions. CONCLUSIONS: Our results provide the first demonstration that the modulation of dopamine transmission affects both the physiological correlates and PE related BOLD activity during aversive learning.

Adolescent↗

PubMed2002

Scene segmentation by spike synchronization in reciprocally connected visual areas. I. Local effects of cortical feedback.

To investigate scene segmentation in the visual system we present a model of two reciprocally connected visual areas using spiking neurons. Area P corresponds to the orientation-selective subsystem of the primary visual cortex, while the central visual area C is modeled as associative memory representing stimulus objects according to Hebbian learning. Without feedback from area C, a single stimulus results in relatively slow and irregular activity, synchronized only for neighboring patches (slow state), while in the complete model activity is faster with an enlarged synchronization range (fast state). When presenting a superposition of several stimulus objects, scene segmentation happens on a time scale of hundreds of milliseconds by alternating epochs of the slow and fast states, where neurons representing the same object are simultaneously in the fast state. Correlation analysis reveals synchronization on different time scales as found in experiments (designated as tower, castle, and hill peaks). On the fast time scale (tower peaks, gamma frequency range), recordings from two sites coding either different or the same object lead to correlograms that are either flat or exhibit oscillatory modulations with a central peak. This is in agreement with experimental findings, whereas standard phase-coding models would predict shifted peaks in the case of different objects.

Animals↗

PubMed2006

Improving signal prediction performance of neural networks through multiresolution learning approach.

In this paper, we extend the original work on multiresolution learning for neural networks, and present new developments on the multiresolution learning paradigm. The contributions of this paper include: (1) proposing a new concept and method of adjustable neural activation functions in multiresolution learning to improve neural network learning efficacy and generalization performance for signal predictions; (2) providing new insightful explanations for the multiresolution learning paradigm from a multiresolution optimization perspective; (3) exploring underlying ideas why the multiresolution learning scheme associated with adjustable activation functions would be more appropriate for the multiresolution learning paradigm; and (4) providing rigorous validations to evaluate the multiresolution learning paradigm with adjustable activation functions and comparing it with the schemes of multiresolution learning with fixed activation functions and traditional learning. This paper presents systematically new analytical and experimental results on the multiresolution learning approach for training an individual neural network model, demonstrates our integral solution on neural network learning efficacy, and illustrates the significant improvements on neural networks' generalization performance and robustness for nonlinear signal predictions.

Algorithms↗

PubMed2004

Prediction of immediate and future rewards differentially recruits cortico-basal ganglia loops.

Evaluation of both immediate and future outcomes of one's actions is a critical requirement for intelligent behavior. Using functional magnetic resonance imaging (fMRI), we investigated brain mechanisms for reward prediction at different time scales in a Markov decision task. When human subjects learned actions on the basis of immediate rewards, significant activity was seen in the lateral orbitofrontal cortex and the striatum. When subjects learned to act in order to obtain large future rewards while incurring small immediate losses, the dorsolateral prefrontal cortex, inferior parietal cortex, dorsal raphe nucleus and cerebellum were also activated. Computational model-based regression analysis using the predicted future rewards and prediction errors estimated from subjects' performance data revealed graded maps of time scale within the insula and the striatum: ventroanterior regions were involved in predicting immediate rewards and dorsoposterior regions were involved in predicting future rewards. These results suggest differential involvement of the cortico-basal ganglia loops in reward prediction at different time scales.

Adult↗

PubMed2003

Cortical control of ocular saccades in humans: a model for motricity.

Our knowledge of the cortical control of saccadic eye movements (saccades) in humans has recently progressed mainly thanks to lesion and transcranial magnetic stimulation (TMS) studies, but also to functional imaging. It is now well-known that the frontal eye field is involved in the triggering of intentional saccades, the parietal eye field in that of reflexive saccades, the supplementary eye field (SEF) in the initiation of motor programs comprising saccades, the pre-SEF in learning of these programs, and the dorsolateral prefrontal cortex (DLPFC) in saccade inhibition, prediction and spatial working memory. Saccades may also be used as a convenient model of motricity to study general cognitive processes preparing movements, such as attention, spatial memory and motivation. Visuo-spatial attention appears to be controlled by a bilateral parieto-frontal network comprising different parts of the posterior parietal cortex and the frontal areas involved in saccade control, suggesting that visual attentional shifts and saccades are closely linked. Recently, our understanding of the cortical control of spatial memory has noticeably progressed by using the simple visuo-oculomotor model represented by the memory-guided saccade paradigm, in which a single saccade is made to the remembered position of a unique visual item presented a while before. TMS studies have determined that, after a brief stage of spatial integration in the posterior parietal cortex (inferior to 300 ms), short-term spatial memory (i.e. up to 15-20 s) is controlled by the DLPFC. Behavioral and lesion studies have shown that medium-term spatial memory (between 15-20 s and a few minutes) is specifically controlled by the parahippocampal cortex, before long-term memorization (i.e. after a few minutes) in the hippocampal formation. Lastly, it has been shown that the posterior part of the anterior cingulate cortex, called the cingulate eye field, is involved in motivation and the preparation of all intentional saccades, but not in reflexive saccades. These different but complementary study methods used in humans have thus contributed to a better understanding of both eye movement physiology and general cognitive processes preparing motricity as whole.

Cerebral Cortex↗

PubMed2025

Histology-Based Virtual RNA Inference Identifies Pathways Associated With Metastasis Risk in Colorectal Cancer.

Colorectal cancer (CRC) remains a major health concern, with >150,000 new diagnoses and >50,000 deaths annually in the United States, underscoring an urgent need for improved screening, prognostication, disease management, and therapeutic approaches. The tumor microenvironment (TME)-comprising cancerous and immune cells interacting within the tumor's spatial architecture-plays a critical role in disease progression and treatment outcomes, reinforcing its importance as a prognostic marker for metastasis and recurrence risk. However, traditional methods for TME characterization, such as bulk transcriptomics and multiplex protein assays, lack sufficient spatial resolution. Although spatial transcriptomics (ST) allows for the high-resolution mapping of whole transcriptomes at near-cellular resolution, current ST technologies (eg, Visium and Xenium) are limited by high costs, low throughput, and issues with reproducibility, preventing their widespread application in large-scale molecular epidemiology studies. In this study, we refined and implemented virtual RNA inference (VRI) to derive ST-level molecular information directly from hematoxylin and eosin (H&E)-stained tissue images. Our VRI models were trained on the largest matched CRC ST data set to date, comprising 45 patients and >300,000 Visium spots from primary tumors. Using state-of-the-art deep learning models (UNI, ResNet-50, Vision Transformer, and Vision Mamba), we achieved a median Spearman's correlation coefficient of 0.546 between predicted and measured spot-level expression. As validation, VRI-derived gene signatures linked to specific tissue regions (tumor, interface, submucosa, stroma, serosa, muscularis, and inflammation) showed strong concordance with signatures generated via direct ST, and VRI performed accurately in estimating cell-type proportions spatially from H&E slides. In an expanded CRC cohort controlling for tumor invasiveness and clinical factors, we further identified VRI-derived gene signatures significantly associated with key prognostic outcomes, including metastasis status. Although certain tumor-related pathways are not fully captured by histology alone, our findings highlight the ability of VRI to infer a wide range of "histology-associated" biological pathways at near-cellular resolution without requiring ST profiling. Future efforts will extend this framework to expand TME phenotyping from standard H&E tissue images, with the potential to accelerate translational CRC research at scale.

Humans↗

PubMed2005

A support vector machine approach to the identification of phosphorylation sites.

We describe a bioinformatics tool that can be used to predict the position of phosphorylation sites in proteins based only on sequence information. The method uses the support vector machine (SVM) statistical learning theory. The statistical models for phosphorylation by various types of kinases are built using a dataset of short (9-amino acid long) sequence fragments. The sequence segments are dissected around post-translationally modified sites of proteins that are on the current release of the Swiss-Prot database, and that were experimentally confirmed to be phosphorylated by any kinase. We represent them as vectors in a multidimensional abstract space of short sequence fragments. The prediction method is as follows. First, a given query protein sequence is dissected into overlapping short segments. All the fragments are then projected into the multidimensional space of sequence fragments via a collection of different representations. Those points are classified with pre-built statistical models (the SVM method with linear, polynomial and radial kernel functions) either as phosphorylated or inactive ones. The resulting list of plausible sites for phosphorylation by various types of kinases in the query protein is returned to the user. The efficiency of the method for each type of phosphorylation is estimated using leave-one-out tests and presented here. The sensitivities of the models can reach over 70%, depending on the type of kinase. The additional information from profile representations of short sequence fragments helps in gaining a higher degree of accuracy in some phosphorylation types. The further development of an automatic phosphorylation site annotation predictor based on our algorithm should yield a significant improvement when using statistical algorithms in order to quantify the results.

Algorithms↗

PubMed2000

Predicting ICU mortality: a comparison of stationary and nonstationary temporal models.

OBJECTIVE: This study evaluates the effectiveness of the stationarity assumption in predicting the mortality of intensive care unit (ICU) patients at the ICU discharge. DESIGN: This is a comparative study. A stationary temporal Bayesian network learned from data was compared to a set of (33) nonstationary temporal Bayesian networks learned from data. A process observed as a sequence of events is stationary if its stochastic properties stay the same when the sequence is shifted in a positive or negative direction by a constant time parameter. The temporal Bayesian networks forecast mortalities of patients, where each patient has one record per day. The predictive performance of the stationary model is compared with nonstationary models using the area under the receiver operating characteristics (ROC) curves. RESULTS: The stationary model usually performed best. However, one nonstationary model using large data sets performed significantly better than the stationary model. CONCLUSION: Results suggest that using a combination of stationary and nonstationary models may predict better than using either alone.

Artificial Intelligence↗

PubMed2004

Neural predictive error signal correlates with depressive illness severity in a game paradigm.

Considerable experimental evidence supports the existence of predictive error signals in various brain regions during associative learning in animals and humans. These regions include the prefrontal cortex, temporal lobe, cerebellum and monoamine systems. Various quantitative theories have been developed to describe behaviour during learning, including Rescorla-Wagner, Temporal Difference and Kalman filter models. These theories may also account for neural error signals. Reviews of imaging studies of depressive illness have consistently implicated the prefrontal and temporal lobes as having abnormal function, and sometimes structure, whilst the monoamine systems are directly influenced by antidepressant medication. It was hypothesised that such abnormalities may be associated with a dysfunction of associative learning that would be reflected by different predictive error signals in depressed patients when compared with healthy controls. This was tested with 30 subjects, 15 with a major depressive illness, using a gambling paradigm and fMRI. Consistent with the hypothesis, depressed patients differed from controls in having an increased error signal. Additionally, for some brain regions, the magnitude of the error signal correlated with Hamilton depression rating of illness severity. Structural equation modelling was used to investigate hypothesised change in effective connectivity between prespecified regions of interest in the limbic and paralimbic system. Again, differences were found that in some cases correlated with illness severity. These results are discussed in the context of quantitative theories of brain function, clinical features of depressive illness and treatments.

Adult↗

PubMed2022

Flnc: Machine Learning Improves the Identification of Novel Long Noncoding RNAs from Stand-Alone RNA-Seq Data.

Long noncoding RNAs (lncRNAs) play critical regulatory roles in human development and disease. Although there are over 100,000 samples with available RNA sequencing (RNA-seq) data, many lncRNAs have yet to be annotated. The conventional approach to identifying novel lncRNAs from RNA-seq data is to find transcripts without coding potential but this approach has a false discovery rate of 30-75%. Other existing methods either identify only multi-exon lncRNAs, missing single-exon lncRNAs, or require transcriptional initiation profiling data (such as H3K4me3 ChIP-seq data), which is unavailable for many samples with RNA-seq data. Because of these limitations, current methods cannot accurately identify novel lncRNAs from existing RNA-seq data. To address this problem, we have developed software, Flnc, to accurately identify both novel and annotated full-length lncRNAs, including single-exon lncRNAs, directly from RNA-seq data without requiring transcriptional initiation profiles. Flnc integrates machine learning models built by incorporating four types of features: transcript length, promoter signature, multiple exons, and genomic location. Flnc achieves state-of-the-art prediction power with an AUROC score over 0.92. Flnc significantly improves the prediction accuracy from less than 50% using the conventional approach to over 85%. Flnc is available via GitHub platform.

RNA-seq↗

PubMedDate not supplied

Cognitive correlates of anxious and depressive symptomatology: an examination of the Helplessness/Hopelessness model.

Expectancies about future life events were assessed in anxious and depressed patients to test predictions of the Helplessness/Hopelessness model of anxiety and depression (Alloy, Kelly, Mineka, & Clements, 1990). In addition to expectancies for future events, patients from affective and anxiety treatment clinics completed anxiety and depression symptom ratings and positive and negative affects scales. Findings revealed partial support for the model. Negative outcome and helplessness expectancies were related specifically to depression. Cognitions regarding future positive events were interrelated and associated with symptom measures more strongly than were cognitions regarding negative events. Additionally, positive affects was more strongly related to depression than to anxiety symptom ratings. Implications and limitations of these findings are discussed.

Adult↗

PubMed1999

The impact-acceleration model of head injury: injury severity predicts motor and cognitive performance after trauma.

This study examines neuropsychological dysfunction after varying severities of the Impact Acceleration Model of diffuse traumatic brain injury. Adult rats (340 g-400 g) were divided into five groups, and exposed to varying degrees of Impact Acceleration Injury (1 m, 2 m, 2.1 m/500 g and second insult). After injury, animals were allowed to recover; acute neurological reflexes, beam walk score, beam balance score, inclined plane score, and Morris Water Maze score were then assessed at multiple time points. Injury of all severities caused significant motor and cognitive deficits. With milder injuries these effects were transient; however, with more severe injuries no recovery in function was seen. The addition of hypoxia and hypotension made a moderate injury worse than a severe injury. The acute neurological reflexes, the beam balance test and the inclined plane test distinguished between the more severely injured groups, but were affected less by mild injury. The beam walk test was sensitive to mild injury, but appeared unable to distinguish between the severe groups. The Morris Water Maze was sensitive for all injury groups, but appeared to adopt a different response profile with secondary insult. This study has for the first time characterized the degree of motor and cognitive deficits in rodents exposed to differing severities of Impact Acceleration Injury. These data confirm that the tests considered, and the Injury Model used, provide a useful system for the consideration of potential therapies which might ameliorate neuropsychological deficits in diffuse brain injury.

Acceleration↗

PubMed1998

RESEARCH: Perceptions of Risk Associated with Use of Farm Chemicals: Implications for Conservation Initiatives

/ Data were collected from 245 farmers within the Darby Creek hydrologic unit in central Ohio to assess perceptions of risk associated with use of farm chemicals. Farmers were asked to evaluate the level of risk associated with use of agricultural chemicals for water quality, food safety, food quality, health of applicator, health of farm animals, wildlife, beneficial plants, beneficial insects, and human health. Study findings revealed that respondents perceived use of farm chemicals posed little or no threat to any of the assessed items. A composite index was formulated from the responses to the nine items and was titled Perceived Risk. Variance in the Perceived Risk index was regressed against social learning variables. The findings revealed that approximately 32% of the variance was explained by the predictive variables included in the model. It was concluded that the theoretical perspective was somewhat useful for understanding perceptions held about agricultural chemical use at the farm level. The findings are discussed in the context of future conservation and educational-information programs within the study region.KEY WORDS: Risk perception; Risk assessment; Groundwater; Pesticide contamination; Food safety; Environmental quality

Journal Article↗

PubMed2002

Spike-timing-dependent plasticity: common themes and divergent vistas.

Recent experimental observations of spike-timing-dependent synaptic plasticity (STDP) have revitalized the study of synaptic learning rules. The most surprising aspect of these experiments lies in the observation that synapses activated shortly after the occurrence of a postsynaptic spike are weakened. Thus, synaptic plasticity is sensitive to the temporal ordering of pre- and postsynaptic activation. This temporal asymmetry has been suggested to underlie a range of learning tasks. In the first part of this review we highlight some of the common themes from a range of findings in the framework of predictive coding. As an example of how this principle can be used in a learning task, we discuss a recent model of cortical map formation. In the second part of the review, we point out some of the differences in STDP models and their functional consequences. We discuss how differences in the weight-dependence, the time-constants and the non-linear properties of learning rules give rise to distinct computational functions. In light of these computational issues raised, we review current experimental findings and suggest further experiments to resolve some controversies.

Action Potentials↗

PubMed2006

Accounting for children's orthographic learning while reading text: do children self-teach?

Share's "self-teaching" model proposes that readers acquire most knowledge about the orthographic structure of words incidentally while reading independently. In the current study, the self-teaching hypothesis was tested by simulating everyday reading through the use of real words, analyzing the effects of context, and considering the independent contributions of general cognitive ability, including rapid naming ability and prior orthographic knowledge. A total of 35 first graders read short story passages in English embedded with target words representative of words likely to be known orally but not orthographically. Words were manipulated for target word spelling and contextual support. According to the self-teaching model, words correctly decoded during reading should be correlated with subsequent orthographic learning. The results of this study confirmed this prediction. Self-teaching was evidenced through significantly higher proportions of correctly identified target words across context conditions. Regression analyses showed that individual differences were related to prior orthographic knowledge and predicted students' degree and quality of orthographic learning after controlling for general decoding ability.

Child↗

PubMed2002

Latent learning, shortcuts and detours: a computational model.

Voicu and Schmajuk (Rob. Auto. Syst. 35 (2001a) 23) described a model of spatial navigation and exploration that includes an action system capable of guiding, with the help of a cognitive system, the search for specific goals as determined by a motivation system. Whereas in the original model the cognitive map stores information about the connectivity between places in the environment, in the present version the cognitive map also stores information about the paths traversed by the agent. Computer simulations show that the network correctly describes experimental results including latent learning in a maze, detours in a maze, and shortcuts in an open field. In addition, the model generates novel predictions about detours and shortcuts in an open field.

Journal Article↗

PubMed2004

Integrating four theories of adolescent smoking.

The ability of the Theory of Planned Behavior, Social Learning Theory, Social Attachment Theory, and Problem Behavior Theory to predict smoking at Grade 10 was tested against an integrated model incorporating predictors from all the theories. The integrated model also tested whether constructs from each theory contribute distinct variance to the prediction of smoking. Predictors measured at Grade 7 (in 1985) were used to model smoking 3 years later (in 1988) among 4186 youth, using logistic regression. Constructs emphasized by each theory were important, independent predictors of later smoking. The integrated model was superior to all of the theory-based models. A few predictors varied for current vs. frequent smoking outcomes. Results emphasize the need for a multifaceted approach to understanding and preventing adolescent smoking.

Adolescent↗