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 325 records · Page 18Linked to original sources

PubMedDate not supplied

Integrating behavioral theory to understand hepatitis B vaccination among men who have sex with men.

OBJECTIVE: To identify beliefs and attitudes associated with motivational readiness for vaccination against hepatitis B vaccination among at-risk men who have sex with men (MSM), using a theoretically integrated framework. METHODS: Data were collected from 358 MSM. RESULTS: MSM with increased readiness to complete the 3-dose series perceived lower practical barriers and greater benefits to vaccination, perceived higher severity of infection, and had higher self-efficacy to complete the vaccine series. CONCLUSIONS: Relationships between stages of change and theory-based constructs from the health belief model and the social learning theory follow predicted patterns suggesting that these theories may provide useful frameworks for understanding vaccination readiness and intervention strategy development among MSM.

Adolescent↗

PubMed2006

A multimarker model to predict outcome in tamoxifen-treated breast cancer patients.

PURPOSE: This study was designed to produce a model to predict outcome in tamoxifen-treated breast cancer patients based on clinicopathologic features and multiple molecular markers. EXPERIMENTAL DESIGN: This was a retrospective study of 324 stage I to III female breast cancer patients treated with tamoxifen for whom standard clinicopathologic data and tumor tissue microarrays were available. Nine molecular markers were studied by semiquantitative immunohistochemistry and/or fluorescence in situ hybridization. Cox proportional hazards analysis was used to determine the contributions of each variable to disease-specific and overall survival, and machine learning was used to produce a model to predict patient outcome. RESULTS: On a univariate basis, the following features were significantly associated with worse survival: high pathologic tumor or nodal class, histologic grade, epidermal growth factor receptor, ERBB2, MYC, or TP53; absent estrogen receptor (ER) or progesterone receptor; and low BCL2. CCND1 and CDKN1B did not reach statistical significance. On a multivariate basis, nodal class, ER, and MYC were statistically significant as independent factors for survival. However, the benefit of ER-positive status was moderated by BCL2, ERBB2, and progesterone receptor. BCL2 and TP53 also interacted as an independent risk factor. A kernel partial least squares polynomial model was developed with an area under the receiver operating characteristic curve of 0.90. CONCLUSIONS: Our data show the predictive value of BCL2, ERBB2, MYC, and TP53 in addition to the standard hormone receptors and clinicopathologic features, and they show the importance of conditional interpretation of certain molecular markers. Our multimarker predictive model performed significantly better than standard guidelines.

Aged↗

PubMedDate not supplied

Predicting mortality after coronary artery bypass surgery: what do artificial neural networks learn? The Steering Committee of the Cardiac Care Network of Ontario.

OBJECTIVE: To compare the abilities of artificial neural network and logistic regression models to predict the risk of in-hospital mortality after coronary artery bypass graft (CABG) surgery. METHODS: Neural network and logistic regression models were developed using a training set of 4,782 patients undergoing CABG surgery in Ontario, Canada, in 1991, and they were validated in two test sets of 5,309 and 5,517 patients having CABG surgery in 1992 and 1993, respectively. RESULTS: The probabilities predicted from a fully trained neural network were similar to those of a "saturated" regression model, with both models detecting all possible interactions in the training set and validating poorly in the two test sets. A second neural network was developed by cross-validating a network against a new set of data and terminating network training early to create a more generalizable model. A simple "main effects" regression model without any interaction terms was also developed. Both of these models validated well, with areas under the receiver operating characteristic curves of 0.78 and 0.77 (p > 0.10) in the 1993 test set. The predictions from the two models were very highly correlated (r=0.95). CONCLUSIONS: Artificial neural networks and logistic regression models learn similar relationships between patient characteristics and mortality after CABG surgery.

Aged↗

PubMed2003

A computational substrate for incentive salience.

Theories of dopamine function are at a crossroads. Computational models derived from single-unit recordings capture changes in dopaminergic neuron firing rate as a prediction error signal. These models employ the prediction error signal in two roles: learning to predict future rewarding events and biasing action choice. Conversely, pharmacological inhibition or lesion of dopaminergic neuron function diminishes the ability of an animal to motivate behaviors directed at acquiring rewards. These lesion experiments have raised the possibility that dopamine release encodes a measure of the incentive value of a contemplated behavioral act. The most complete psychological idea that captures this notion frames the dopamine signal as carrying 'incentive salience'. On the surface, these two competing accounts of dopamine function seem incommensurate. To the contrary, we demonstrate that both of these functions can be captured in a single computational model of the involvement of dopamine in reward prediction for the purpose of reward seeking.

Algorithms↗

PubMed1987

The combining of multiple hemispheric resources in learning-disabled and skilled readers' recall of words: a test of three information-processing models.

Three theoretical models (additive, independence, maximum rule) that characterize and predict the influence of independent hemispheric resources on learning-disabled and skilled readers' simultaneous processing were tested. Predictions related to word recall performance during simultaneous encoding conditions (dichotic listening task) were made from unilateral (dichotic listening task) presentations. The maximum rule model best characterized both ability groups in that simultaneous encoding produced no better recall than unilateral presentations. While the results support the hypothesis that both ability groups use similar processes in the combining of hemispheric resources (i.e., weak/dominant processing), ability group differences do occur in the coordination of such resources.

Cerebral Cortex↗

PubMed1997

Dynamic model of visual recognition predicts neural response properties in the visual cortex.

The responses of visual cortical neurons during fixation tasks can be significantly modulated by stimuli from beyond the classical receptive field. Modulatory effects in neural responses have also been recently reported in a task where a monkey freely views a natural scene. In this article, we describe a hierarchical network model of visual recognition that explains these experimental observations by using a form of the extended Kalman filter as given by the minimum description length (MDL) principle. The model dynamically combines input-driven bottom-up signals with expectation-driven top-down signals to predict current recognition state. Synaptic weights in the model are adapted in a Hebbian manner according to a learning rule also derived from the MDL principle. The resulting prediction-learning scheme can be viewed as implementing a form of expectation-maximization (EM) algorithm. The architecture of the model posits an active computational role of the reciprocal connections between adjoining visual cortical areas in determining neural response properties. In particular, the model demonstrates the possible role of feedback from higher cortical areas in mediating neurophysiological effects due to stimuli from beyond the classical receptive field. Simulations of the model are provided that help explain the experimental observations regarding neural responses in both free viewing and fixation conditions.

Animals↗

PubMed1994

Rule-plus-exception model of classification learning.

The authors propose a rule-plus-exception model (RULEX) of classification learning. According to RULEX, people learn to classify objects by forming simple logical rules and remembering occasional exceptions to those rules. Because the learning process in RULEX is stochastic, the model predicts that individual Ss will vary greatly in the particular rules that are formed and the exceptions that are stored. Averaged classification data are presumed to represent mixtures of these highly idiosyncratic rules and exceptions. RULEX accounts for numerous fundamental classification phenomena, including prototype and specific exemplar effects, sensitivity to correlational information, difficulty of learning linearly separable versus nonlinearly separable categories, selective attention effects, and difficulty of learning concepts with rules of differing complexity. RULEX also predicts distributions of generalization patterns observed at the individual subject level.

Adult↗

PubMed2026

PathMED: an R toolkit for single-sample molecular scoring and machine learning with omics data.

MOTIVATION: Molecular scoring is a popular approach for studying pathway-level functional alterations with omics data. Using molecular scores for tasks such as single-sample molecular characterisation, phenotype prediction or disease stratification has several advantages compared to using omics data directly. Molecular scores provide biological interpretability and are more generalisable across datasets, facilitating data integration and machine learning applications. However, numerous scoring methods are available through different software packages, and currently there is a lack of tools to easily use these scores for model training and prediction. RESULTS: We developed pathMED, an R/Bioconductor package that unifies various scoring methods in a simple framework. Furthermore, pathMED also contains a machine learning module to train and test models that use the calculated molecular scores to predict clinical outcomes. We demonstrate some of its potential applications in three use cases using public omics data. We showed the generalisability of machine learning models trained on transcriptomic scores in predicting clinical outcomes when deploying on proteomic scores. We also demonstrated the application of transcriptomics scores in predicting breast cancer treatment response and identifying pathways strongly associated to tumour biology and treatment response. Finally, we demonstrated the benefit of integrating a novel gene set dissection step into the analysis pipeline to resolve disease heterogeneity at the pathway level. AVAILABILITY: PathMED is freely available in the Bioconductor repository (https://bioconductor.org/packages/release/bioc/html/pathMED.html). Code to reproduce the analyses is publicly available at https://github.com/GENyO-BioInformatics/pathMED_article.

Software↗

PubMed2025

Proteomics-enabled learning machine algorithms enhance the prediction of cardiovascular diseases in patients with type 2 diabetes mellitus.

BACKGROUND AND AIMS: Estimating the risk of cardiovascular disease (CVD) complications in type 2 diabetes mellitus (T2DM) patients is critical in the medical decision-making process. This study aimed to use a machine learning technique combined with proteomics to develop personalized models for predicting CVD in patients with T2DM. METHODS AND RESULTS: In total, 874 patients with T2DM and 2,920 Olink proteins obtained from the UK Biobank were used in this study. Proteins were screened using Cox regression and LASSO regression. A basic model containing clinical features and a full model combining proteome and clinical features were constructed using the random survival forest algorithm. The area under the receiver operating characteristic (ROC) curve (AUC) was used to evaluate the predictive performance of the models and compare them with other CVD predictive models. Compared with the basic model, the full model performed better in predicting CVD, with time-dependent AUCs of 0.81 (3 years), 0.74 (5 years) and 0.74 (10 years) (0.77, 0.69 and 0.67). We calculated the risk scores of the Framingham, ASCVD and Score2-Diabetes models. The results revealed that the prediction performance of the full model was also better than that of the abovementioned models. In terms of differentiation accuracy, the results of the net reclassification improvement index and integrated discrimination improvement index showed that the full model can identify high-risk individuals more accurately (accuracy rate: 79% vs. 69%). CONCLUSIONS: Proteomics can be used to predict cardiovascular complications in diabetic patients. It is also necessary to consider the applicability of the model due to the limitations of the sample size and the constraints of proteomics in clinical applications.

Humans↗

PubMed2001

The quality of adolescents' friendships: associations with mothers' interpersonal relationships, attachments to parents and friends, and prosocial behaviors.

Adolescents' friendship quality and observed emotional expression with their best friends were predicted from reports of their mother's interpersonal relationships-specifically the quality of her marriage and social network. Two models explaining these relationships received support. Consistent with an Attachment Theory model, adolescents' perceptions of marital quality predicted attachment security with mother, father and friends. Security of attachment to friends in turn predicted best friendship quality, but not affective behavior with the friend. A Social Learning Theory model was also supported, in which perceptions of both marital quality and mother's social network quality predicted adolescents' prosocial behavior. Prosocial behavior in turn predicted both best friendship quality and affective behavior with the friend.

Adolescent↗

PubMed2000

An associational model of birdsong sensorimotor learning II. Temporal hierarchies and the learning of song sequence.

Understanding the neural mechanisms underlying serially ordered behavior is a fundamental problem in motor learning. We present a computational model of sensorimotor learning in songbirds that is constrained by the known functional anatomy of the song circuit. The model subsumes our companion model for learning individual song "syllables" and relies on the same underlying assumptions. The extended model addresses the problem of learning to produce syllables in the correct sequence. Central to our approach is the hypothesis that the Anterior Forebrain Pathway (AFP) produces signals related to the comparison of the bird's own vocalizations and a previously memorized "template." This "AFP comparison hypothesis" is challenged by the lack of a direct projection from the AFP to the song nucleus HVc, a candidate site for the generator of song sequence. We propose that sequence generation in HVc results from an associative chain of motor and sensory representations (motor --> sensory --> next motor. ) encoded within the two known populations of HVc projection neurons. The sensory link in the chain is provided, not by auditory feedback, but by a centrally generated efference copy that serves as an internal prediction of this feedback. The use of efference copy as a substitute for the sensory signal explains the ability of adult birds to produce normal song immediately after deafening. We also predict that the AFP guides sequence learning by biasing motor activity in nucleus RA, the premotor nucleus downstream of HVc. Associative learning then remaps the output of the HVc sequence generator. By altering the motor pathway in RA, the AFP alters the correspondence between HVc motor commands and the resulting sensory feedback and triggers renewed efference copy learning in HVc. Thus, auditory feedback-mediated efference copy learning provides an indirect pathway by which the AFP can influence sequence generation in HVc. The model makes predictions concerning the role played by specific neural populations during the sensorimotor phase of song learning and demonstrates how simple rules of associational plasticity can contribute to the learning of a complex behavior on multiple time scales.

Animals↗

PubMed2002

The effects of galanin on long-term synaptic plasticity in the CA1 area of rodent hippocampus.

Learning and memory involve complex changes in neuronal excitability including long-lasting synaptic plasticity of glutamatergic synapses. The observation that the neuropeptide galanin affects performance in a number of behavioural models predicts that galanin should affect synaptic processes underlying learning. The present study in rat and mouse hippocampal slices now demonstrates that galanin inhibits long-term potentiation induced by both tetanic and theta-burst stimulation in both apical and basal dendrites of CA1 pyramidal neurones but does not affect long-term depression. This selective effect on long-term potentiation does not appear to be mediated through inhibition of N-methyl-D-aspartate or metabotropic glutamate receptor function, but likely resides downstream of receptor activation, possibly at the level of the kinase cascade that converts short-term into long-term potentiation. Our results indicate possible mechanisms by which the neuropeptide galanin may act at the molecular level to influence learning and memory in vertebrates.

Animals↗

PubMed2025

Plasma Proteomic Profiles Predict Individual Future Osteoarthritis Risk.

OBJECTIVE: Osteoarthritis (OA) is a widespread degenerative joint disease that causes a considerable socioeconomic burden. Despite progress in genetic and environmental insights, early diagnosis is still limited by the lack of evident symptoms during the initial phases and accurate biomarkers. This study aims to identify plasma proteins associated with future risk of OA and develop a predictive model. METHODS: We conducted a large-scale proteomic analysis of 45,307 participants from the UK Biobank, excluding those with baseline OA. Plasma samples were assayed using the Olink Explore Proximity Extension Assay targeting 1,463 unique proteins. Clinical variables and OA outcomes were extracted and linked to electronic health records. A predictive model was constructed using the LightGBM machine learning method, and SHapley Additive exPlanations (SHAP) were applied to evaluate the importance of variables. RESULTS: We identified a panel of proteins significantly associated with the risk of developing OA. Notably, after adjusting for multiple confounders, collagen type IX alpha 1 chain (COL9A1) and cartilage acidic protein 1 (CRTAC1) were the most significant predictors of incident OA, with hazard ratios of 1.54 (95% confidence interval [CI] 1.48-1.61) and 1.65 (95% CI 1.54-1.78), respectively. SHAP analysis allowed a profound interpretation of the contribution of each protein and clinical variable to the model, revealing the multifactorial nature of OA risk prediction. The temporal trajectories of plasma proteins indicated that the levels of COL9A1 and CRTAC1 began to deviate from normal for more than a decade before OA onset, suggesting their potential use in early detection strategies. The predictive model, developed using the LightGBM algorithm, integrated proteins with clinical covariates and demonstrated an area under the curve (AUC) of 0.729 for 5-year OA prediction, 0.721 for 10-year prediction, and 0.723 for all incident OA. The predictive accuracy of the model was further enhanced for hip and knee OA, achieving AUCs of 0.820 and 0.803 for 5-year predictions. CONCLUSION: Our study identified the role of plasma proteomics in predicting future OA risk, which could contribute to preemptive measures. The innovative model, which integrates proteomic biomarkers with clinical data, offers a potential tool for risk assessment, potentially optimizing OA management strategies and enhancing prevention efforts.

Humans↗

PubMed2006

Analysis and prediction of helix shift errors in homology modeling.

High sequence identity between two proteins (e.g. > 60%) is a strong evidence for high structural similarity. However, internal shifts in one of the two proteins can sometimes give rise to unexpectedly high structural differences. This, in turn, causes unreliable structure predictions when two such proteins are used in homology modeling. Here, we perform a computational analysis of helix shifts and we show that their occurrence can be predicted with statistical learning methods. Our results indicate that helix shifts increase the RMS error by factor 2.6 compared to those protein pairs without a helix shift. Although helix shifts are rare (1.6% of helices and a commensurately higher number of proteins are affected), they therefore pose a significant problem for reliable structure prediction systems. In this paper, we prototype a new approach for model quality assessment and demonstrate that it can successfully warn against helix shifts. A support vector machine trained on a wide range of sequence and structure properties predicts the occurrence of helix shifts with a sensitivity of 74.2% and a specificity of 83.6%. On an equalized test dataset, this corresponds to an accuracy of 78.9%. Projected to the full dataset, it translates to an accuracy of 83.4%. Our analysis shows that helix shift detection is a valuable building block for highly reliable structure prediction systems. Furthermore, the statistical learning based approach to helix shift detection that we employ here is orthogonal to well-established model quality assessment methods (which use geometric constraint checking or mean force potentials). Therefore, a further increase of prediction accuracy is expected from the combination of these methods.

Computational Biology↗

PubMed2006

A classification-based framework for predicting and analyzing gene regulatory response.

BACKGROUND: We have recently introduced a predictive framework for studying gene transcriptional regulation in simpler organisms using a novel supervised learning algorithm called GeneClass. GeneClass is motivated by the hypothesis that in model organisms such as Saccharomyces cerevisiae, we can learn a decision rule for predicting whether a gene is up- or down-regulated in a particular microarray experiment based on the presence of binding site subsequences ("motifs") in the gene's regulatory region and the expression levels of regulators such as transcription factors in the experiment ("parents"). GeneClass formulates the learning task as a classification problem--predicting +1 and -1 labels corresponding to up- and down-regulation beyond the levels of biological and measurement noise in microarray measurements. Using the Adaboost algorithm, GeneClass learns a prediction function in the form of an alternating decision tree, a margin-based generalization of a decision tree. METHODS: In the current work, we introduce a new, robust version of the GeneClass algorithm that increases stability and computational efficiency, yielding a more scalable and reliable predictive model. The improved stability of the prediction tree enables us to introduce a detailed post-processing framework for biological interpretation, including individual and group target gene analysis to reveal condition-specific regulation programs and to suggest signaling pathways. Robust GeneClass uses a novel stabilized variant of boosting that allows a set of correlated features, rather than single features, to be included at nodes of the tree; in this way, biologically important features that are correlated with the single best feature are retained rather than decorrelated and lost in the next round of boosting. Other computational developments include fast matrix computation of the loss function for all features, allowing scalability to large datasets, and the use of abstaining weak rules, which results in a more shallow and interpretable tree. We also show how to incorporate genome-wide protein-DNA binding data from ChIP chip experiments into the GeneClass algorithm, and we use an improved noise model for gene expression data. RESULTS: Using the improved scalability of Robust GeneClass, we present larger scale experiments on a yeast environmental stress dataset, training and testing on all genes and using a comprehensive set of potential regulators. We demonstrate the improved stability of the features in the learned prediction tree, and we show the utility of the post-processing framework by analyzing two groups of genes in yeast--the protein chaperones and a set of putative targets of the Nrg1 and Nrg2 transcription factors--and suggesting novel hypotheses about their transcriptional and post-transcriptional regulation. Detailed results and Robust GeneClass source code is available for download from http://www.cs.columbia.edu/compbio/robust-geneclass.

Algorithms↗

PubMed2005

Dynamic self-efficacy and outcome expectancies: prediction of smoking lapse and relapse.

According to social learning models of drug relapse, decreases in abstinence self-efficacy (ASE) and increases in positive smoking outcome expectancies (POEs) should foreshadow lapses and relapse. In this study, the authors examined this hypothesis by using ecological momentary assessment data from 305 smokers who achieved initial abstinence from smoking and monitored their smoking and their ASE and POEs by using palmtop computers. Daily ASE and POEs predicted the occurrence of a 1st lapse on the following day. Following a lapse, variations in daily ASE predicted the onset of relapse, even after controlling for concurrent smoking. ASE and POEs generally neither mediated nor moderated each other's effects. These data emphasize the role of dynamic factors in the relapse process.

Adult↗

PubMed2026

ExoShorkie: predicting RNA-seq coverage of exogenous genomes in yeast by transfer learning.

MOTIVATION: Predicting the RNA-seq coverage of native and exogenous sequences is central to many molecular- and synthetic-biology applications. Substantial progress has been made in developing methods to predict the RNA-seq coverage of native genomic sequences, with the recently developed Shorkie achieving state-of-the-art performance in yeast. However, prediction performance of these methods over exogenous DNA is still unknown. Recent studies measured RNA-seq coverage of large exogenous genomes in yeast, providing a unique opportunity to train machine-learning models on a large exogenous sequence space and to improve both prediction performance and our understanding of regulatory mechanisms. RESULTS: We introduce ExoShorkie, a method we developed by extending Shorkie through transfer learning across multiple exogenous RNA-seq datasets. We demonstrate that ExoShorkie significantly improves prediction performance on held-out exogenous genomes and outperforms both a native-genome-trained Shorkie baseline and Yorzoi, the only competing method for predicting exogenous RNA-seq coverage in yeast, in cross-validation and in leave-one-genome-out evaluations. Furthermore, through interpretability analyses we reveal biologically meaningful regulatory motifs and distinct regulatory rules in exogenous genomes in yeast, providing new insights into transcriptional regulation. AVAILABILITY AND IMPLEMENTATION: ExoShorkie is available at https://github.com/OrensteinLab/ExoShorkie.

Genome, Fungal↗

PubMed1996

Impaired learning in mice with abnormal short-lived plasticity.

BACKGROUND: Many studies suggest that long term potentiation (LTP) has a role in learning and memory. In contrast, little is known about the function of short-lived plasticity (SLP). Modeling results suggested that SLP could be responsible for temporary memory storage, as in working memory, or that it may be involved in processing information regarding the timing of events. These models predict that abnormalities in SLP should lead to learning deficits. We tested this prediction in four lines of mutant mice with abnormal SLP, but apparently normal LTP-mice heterozygous for a alpha-calcium calmodulin kinase II mutation (alpha CaMKII +/-) have lower paired-pulse facilitation (PPF) and increased post-tetanic potentiation (PTP); mice lacking synapsin II (SyII-/-), and mice defective in both synapsin I and synapsin II (SyI/II-/-), show normal PPF but lower PTP; in contrast, mice just lacking synapsin I (SyI-/-) have increased PPF, but normal PTP. RESULTS: Our behavioral results demonstrate that alpha CaMKII +/-, SyII-/- and SyI/II-/- mutant mice, which have decreased PPF or PTP, have profound impairments in learning tasks. In contrast, behavioral analysis did not reveal learning deficits in SyI-/- mice, which have increased PPF. CONCLUSIONS: Our results are consistent with models that propose a role for SLP in learning, as mice with decreased PPF or PTP, in the absence of known LTP deficits, also show profound learning impairments. Importantly, analysis of the SyI-/- mutants demonstrated that an increase in PPF does not disrupt learning.

Animals↗