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 1,675 records · Page 93Linked to original sources

PubMed2005

Dynamic response-by-response models of matching behavior in rhesus monkeys.

We studied the choice behavior of 2 monkeys in a discrete-trial task with reinforcement contingencies similar to those Herrnstein (1961) used when he described the matching law. In each session, the monkeys experienced blocks of discrete trials at different relative-reinforcer frequencies or magnitudes with unsignalled transitions between the blocks. Steady-state data following adjustment to each transition were well characterized by the generalized matching law; response ratios undermatched reinforcer frequency ratios but matched reinforcer magnitude ratios. We modelled response-by-response behavior with linear models that used past reinforcers as well as past choices to predict the monkeys' choices on each trial. We found that more recently obtained reinforcers more strongly influenced choice behavior. Perhaps surprisingly, we also found that the monkeys' actions were influenced by the pattern of their own past choices. It was necessary to incorporate both past reinforcers and past choices in order to accurately capture steady-state behavior as well as the fluctuations during block transitions and the response-by-response patterns of behavior. Our results suggest that simple reinforcement learning models must account for the effects of past choices to accurately characterize behavior in this task, and that models with these properties provide a conceptual tool for studying how both past reinforcers and past choices are integrated by the neural systems that generate behavior.

Animals↗

PubMed2026

Machine learning approaches for cancer prognosis and diagnosis via non-coding RNA: a comprehensive review.

Non-coding RNAs (ncRNAs), once considered genomic dark matter, are now established as key regulators of gene expression with widespread roles in cellular homeostasis and disease. In cancer, ncRNA expression is frequently and systematically dysregulated, and many of these molecules circulate in stable, protected form within biofluids, offering a compelling basis for non-invasive or minimally invasive diagnostic strategies. However, their clinical translation remains substantially hindered to date due to biological complexity, technical noise, and high dimensionality inherent to ncRNA expression datasets. In this context, machine learning (ML) has emerged as a powerful analytical tool to address these challenges, enabling the identification of subtle, reproducible ncRNA signatures predictive of diverse malignancies. This review critically evaluates ML-driven frameworks for cancer diagnosis and prognosis across four ncRNA subclasses, namely miRNAs, lncRNAs, circRNAs, and piRNAs, while also acknowledging the biophysical and thermodynamic models that reinforce ncRNA bioinformatics. Despite substantial methodological progress in ML-based cancer diagnosis and prognosis, key challenges persist, including tumor biological heterogeneity, limited multicenter validation, and the lack of widely adopted standardized protocols for preprocessing, normalization, and reporting workflows. Furthermore, many current ML models lack interpretability in biological or clinical context, constraining their translational utility. By synthesizing recent advances and identifying unresolved barriers, this review charts a roadmap for developing a robust, clinically actionable ncRNA biomarker platform for cancer detection. With global cancer incidence projected to exceed 35 million annual cases by 2050, validated ncRNA-ML-driven frameworks hold potential to revolutionize early-stage detection and personalized therapeutic strategies, thereby reducing the escalating socio-economic burden of cancer worldwide.

Humans↗

PubMed2004

Prediction of the affinity of the newly synthesised azapirone derivatives for 5-HT1A receptors based on artificial neural network analysis of chromatographic retention data and calculation chemistry parameters.

The performance of artificial neural network (ANN) in predicting the affinity of a series of 65 new azapirone derivatives for rat brain serotonin 5-HT1A receptors based on high-performance liquid chromatography (HPLC) retention data and on non-empirical structural parameters of the compounds' was studied. Affinity of the agents for rat brain 5-HT1A receptors were assessed in vitro and expressed as inhibitor constant values, Ki. The retention parameters determined in 14 HPLC systems along with compounds' structural descriptors from calculation chemistry were considered in ANN analysis. Supervised method of ANN learning with back-propagation strategy was used in ANN calculations. Two models of ANN of similar architecture were designed: the first one for the data based on chromatographic retention data and the second based on structural parameters of the agents. Each ANN model was trained with the data of training set. It was next used to classify the agents from the testing set into two groups: active (Ki < 50 nM) and inactive compounds (Ki > 50 nM). A high prediction performance of both ANN models considered as regards the affinity of new azapirone derivatives for the serotonin 5-HT1A receptors was demonstrated. However, the percent of correctly classified compounds was higher in the case of the ANN processing of the non-empirical structural descriptors of azapirone derivatives. Since the ANN analysis of the retention data and of the structural parameters originating from calculation chemistry allows to segregate drug candidates according to their pharmacological properties that, in consequence, may be of help to limit the number of biological assays in the search for new drugs.

Aza Compounds↗

PubMed2005

Stress-induced enhancement of fear learning: an animal model of posttraumatic stress disorder.

Fear is an adaptive response that initiates defensive behavior to protect animals and humans from danger. However, anxiety disorders, such as Posttraumatic Stress Disorder (PTSD), can occur when fear is inappropriately regulated. Fear conditioning can be used to study aspects of PTSD, and we have developed a model in which pre-exposure to a stressor of repeated footshock enhances conditional fear responding to a single context-shock pairing. The experiments in this chapter address interpretations of this effect including generalization and summation or fear, inflation, and altered pain sensitivity. The results of these experiments lead to the conclusion that pre-exposure to shock sensitizes conditional fear responding to similar less intense stressors. This sensitization effect resists exposure therapy (extinction) and amnestic (NMDA antagonist) treatment. The pattern predicts why in PTSD patients, mild stressors cause reactions more appropriate for the original traumatic stressor and why new fears are so readily formed in these patients. This model can facilitate the study of neurobiological mechanisms underlying sensitization of responses observed in PTSD.

2-Amino-5-phosphonovalerate↗

PubMedDate not supplied

Topological shape and size of peptides: identification of potential allele specific helper T cell antigenic sites.

A database of primary sequences of 28 immunogenic peptides, known to elicit T cell response, derived from five different haplotypes was compiled to identify allele specific helper T cell antigenic sites using a rule based graph-theoretical method. The prediction was based on the identification of allele specific patterns in the form of "topological shape and size" present in the peptides. Indices computed from weighted connected graph models of amino acid side chains and peptides were used in this purpose. The system was trained by 10 Ad and 10 non-Ad restricted peptide sequences, assigned actives and inactives, respectively, chosen randomly from the database, and four Ad and four non-Ad restricted sequences were kept as test peptides. This allowed the system to learn about "topological shape and size" specific for Ad restricted peptides from the differences, if any, they had with the inactive peptides in that respect. The system made 100% correct prediction for the training set peptides and misclassified only one inactive peptide of the test set. The system also identified crucial residues for lambda repressor 12-24 and insulin A-chains. This identification also shows that activity related/crucial residues could be located at varying distances from the peptide terminals. To our knowledge, the method is unique of its kind in the literature and may find application in the rational design of synthetic vaccines and other peptides of immunological importance.

Alleles↗

PubMed1998

Broadening the Tests of Learning Models.

For many years psychological studies of the learning process have used a simulated medical diagnosis task in which symptom configurations are probabilistically related to diseases. Participants are given a set of symptoms and asked to indicate which disease is present, and feedback is given on each trial. We enrich this standard laboratory task in four different ways. First, the symptoms have four possible values (low, medium low, medium high, and high) rather than just two. Second, symptom configurations are generated from an expanded factorial design rather than a simple factorial design. Third, subjects are asked to make a continuous judgment indicating their confidence in the diagnosis, rather than simply a binary judgment. Fourth, cumulated performance scores, payoffs, and the availability of a historical summary of the outcomes are varied in order to assess how these treatments modulate performance. These enrichments provide a broader data set and more challenging tests of the models. Using 123 subjects each in 480 trials, we compare five existing learning models plus several variants, including the well-known Bayesian, fuzzy logic, connectionist, exemplar, and ALCOVE models. We find that the subjects do learn to distinguish the symptom configurations, that subjects are quite heterogeneous in their response to the task, and that only a small part of the variation across subjects arises from the differences in treatments. The most striking finding is that the model that best predicts subjects' behavior is a simple Bayesian model with a single fitted parameter for prior precision to capture individual differences. We use rolling regression techniques to elucidate the behavior of this model over time and find some evidence of over-response to current stimuli. Copyright 1998 Academic Press.

Journal Article↗

PubMed2006

Synchronizing activity of basal ganglia and pathophysiology of Parkinson's disease.

Early physiological studies emphasized changes in the discharge rate of basal ganglia in the pathophysiology of Parkinson's disease (PD), whereas recent studies stressed the role of the abnormal oscillatory activity and neuronal synchronization of pallidal cells. However, human observations cast doubt on the synchronization hypothesis since increased synchronization may be an epi-phenomenon of the tremor or of independent oscillators with similar frequency. Here, we show that modern actor/ critic models of the basal ganglia predict the emergence of synchronized activity in PD and that significant non-oscillatory and oscillatory correlations are found in MPTP primates. We conclude that the normal fluctuation of basal ganglia dopamine levels combined with local cortico-striatal learning rules lead to noncorrelated activity in the pallidum. Dopamine depletion, as in PD, results in correlated pallidal activity, and reduced information capacity. We therefore suggest that future deep brain stimulation (DBS) algorithms may be improved by desynchronizing pallidal activity.

Animals↗

PubMed2006

Encoding uncertainty in the hippocampus.

The medial temporal lobe may play a critical role in binding successive events into memory while encoding contextual information in implicit and explicit memory tasks. Information theory provides a quantitative basis to model contextual information engendered by conditional dependence between, or conditional uncertainty about, consecutive events in a sequence. We show that information theoretic indices characterizing contextual dependence within a sequential reaction time task (SRTT) predict regional responses, measured by fMRI, in areas associated with sequence learning and navigation. Specifically, activity of a distributed paralimbic system, centered on the left hippocampus, correlated selectively with predictability as measured with mutual information. This is clear evidence that the brain is sensitive to the probabilistic context in which events are encountered. This is potentially important for theories about how the brain represents uncertainty and makes perceptual inferences, particularly those based on predictive coding and hierarchical Bayes.

Adult↗

PubMed2002

Transmembrane topology of the NuoL, M and N subunits of NADH:quinone oxidoreductase and their homologues among membrane-bound hydrogenases and bona fide antiporters.

Nicotinamide adenine dinucleotide-reduced form (NADH):quinone oxidoreductase (respiratory Complex I), F420H2 oxidoreductase and complex, membrane-bound NiFe-hydrogenase contain protein subunits homologous to a certain type of bona fide antiporters. In Complex I, these polypeptides (NuoL/ND5, NuoM/ND4, NuoN/ND2) are most likely core components of the proton pumping mechanism, and it is thus important to learn more about their structure and function. In this work, we have determined the transmembrane topology of one such polypeptide, and built a 2D structural model of the protein valid for all the homologous polypeptides. The experimentally determined transmembrane topology was different from that predicted by majority vote hydrophobicity analyses of members of the superfamily. A detailed phylogenetic analysis of a large set of primary sequences shed light on the functional relatedness of these polypeptides.

Amino Acid Sequence↗

PubMedDate not supplied

Active control of spike-timing dependent synaptic plasticity in an electrosensory system.

A spike timing dependent learning rule is present at the synapse between parallel fibers and Purkinje-like medium ganglion cells in the electrosensory lobe of mormyrid electric fish. The synapse is depressed when a postsynaptic dendritic spike occurs within 50 ms of the onset of a parallel fiber excitatory postsynaptic potential, but is enhanced at all other timing relations. Operation of this learning rule results in the cancellation of predictable membrane potential changes, driving the cell towards a constant output frequency. But medium ganglion cells show a strong and predictable response to corollary discharge signals associated with the motor command that initiates the electric organ discharge. The modeling study presented here resolves this conflict by proposing an active control of dendritic spike threshold during the brief period of medium ganglion cell response.

Action Potentials↗

PubMed2002

The use of information and communication technology in veterinary education.

The internet provides new opportunities to deliver distance and e-learning to the veterinary profession both at undergraduate and postgraduate levels. There are now numerous examples of successful computer-based educational projects in UK higher education, which provide useful models for veterinary science. This will present challenges for academics who will need to adapt their teaching methodologies and students who will have to develop new ways of learning. The future of Information and Communication Technologies (ICT) in the veterinary sector is difficult to predict but it is likely to have far reaching effects on the profession.

Computer-Assisted Instruction↗

PubMed2005

Development of CYP3A4 inhibition models: comparisons of machine-learning techniques and molecular descriptors.

Computational models of cytochrome P450 3A4 inhibition were developed based on high-throughput screening data for 4470 proprietary compounds. Multiple models differentiating inhibitors (IC(50) <3 microM) and noninhibitors were generated using various machine-learning algorithms (recursive partitioning [RP], Bayesian classifier, logistic regression, k-nearest-neighbor, and support vector machine [SVM]) with structural fingerprints and topological indices. Nineteen models were evaluated by internal 10-fold cross-validation and also by an independent test set. Three most predictive models, Barnard Chemical Information (BCI)-fingerprint/SVM, MDL-keyset/SVM, and topological indices/RP, correctly classified 249, 248, and 236 compounds of 291 noninhibitors and 135, 137, and 147 compounds of 179 inhibitors in the validation set. Their overall accuracies were 82%, 82%, and 81%, respectively. Investigating applicability of the BCI/SVM model found a strong correlation between the predictive performance and the structural similarity to the training set. Using Tanimoto similarity index as a confidence measurement for the predictions, the limitation of the extrapolation was 0.7 in the case of the BCI/SVM model. Taking consensus of the 3 best models yielded a further improvement in predictive capability, kappa = 0.65 and accuracy = 83%. The consensus model could also be tuned to minimize either false positives or false negatives depending on the emphasis of the screening.

Artificial Intelligence↗

PubMed2004

The effectiveness of inhibitors in human predictive judgments depends on the strength of the positive predictor.

We tested whether the development of inhibitory strength, as measured by a summation test, is proportional to the strength of the positive cue (P) against which the inhibitory cue (I) is trained. P predicted the outcome, whereas the co-occurrence of P with I (PI) predicted no outcome. In Experiments 1, 2, and 3, we compared the latter design against a version in which P was overshadowed by another cue (X). In this design, the compound P degrees X predicted the outcome, but P degrees I degrees predicted no outcome. In all three experiments, overshadowed cue I degrees was less inhibitory than I. In Experiment 4, a P produced by fewer training trials also supported weaker inhibitory learning. Overall, the results were consistent with associative learning theories, especially Pearce's (1994) configural model. Contingency models need to make additional assumptions to accommodate this property of inhibitory learning.

Adult↗

PubMed2002

Organization of work via a natural substance: regulation of nest construction in social wasps.

In social insects, colony-level complexity emerges from simple individual-level behaviors and interactions. In the evolution of insect societies, selection has acted to promote efficiency through division of labor. Nest construction of social wasps is an excellent model system to study division of labor and the performance of a decentralized behavioral regulation. After re-examination of Jeanne's (1996) demand-driven "non-taskmates feedback" hypothesis, an alternative mechanism is suggested whereby the regulation of behavior is based on a natural substance (water) which is itself also a building material. By experimenting with a simple model system, we show that the model's predictions agree with observational data and cover a wide range of evolutionary transitions. According to the internal and external parameters, the colony builds up storage of water that is used both as regulator and building material. Through individual interactions, pulp foragers and water foragers emerge from general laborers and their ratio becomes balanced. The emergent foragers ensure both the stabilization of the quantity of stored water and the steady construction of the nest according to the given conditions. Perturbations of the system alter colony-level dynamics in a similar way as was observed in nature: water and pulp addition increase pulp arrivals and building rate; removal of pulp foragers decreases pulp input and construction rate, but not the water influx; removal of water foragers causes overcompensation of water input after a delay. After comparing the predictions of the model to natural data, assumptions found in the literature on organization of work and regulation of behavior are re-examined. A new, more parsimonious model of organization of work is proposed that may cover wide variety of cases where hormones and learning cannot be accounted for the regulation of behavior.

Animals↗

PubMed2003

A domain combination based probabilistic framework for protein-protein interaction prediction.

In this paper, we propose a probabilistic framework to predict the interaction probability of proteins. The notion of domain combination and domain combination pair is newly introduced and the prediction model in the framework takes domain combination pair as a basic unit of protein interactions to overcome the limitations of the conventional domain pair based prediction systems. The framework largely consists of prediction preparation and service stages. In the prediction preparation stage, two appearance probability matrices are constructed. Each matrix holds information on appearance frequencies of domain combination pairs in the interacting and non-interacting sets of protein pairs, respectively. Based on the appearance probability matrix, a probability equation is devised. The equation maps a protein pair to a real number in the range of 0 to 1. Two distributions of interacting and non-interacting sets of protein pairs are obtained using the equation. In the prediction service stage, the interaction probability of a protein pair is predicted using the distributions and the equation. The validity of the prediction model is evaluated for the interacting set of protein pairs in a Yeast organism and artificially generated non-interacting set of protein pairs. When 80% of the set of interacting protein pairs in DIP (Database of Interacting Proteins) is used as a learning set of interacting protein pairs, very high sensitivity (86%) and moderate specificity (56%) are achieved within our framework.

Amino Acid Sequence↗

PubMed1998

Quality of student learning and preceptor productivity in urban community health centers.

BACKGROUND AND OBJECTIVES: Clinicians in community health centers find it difficult to balance the demands of increased productivity and effective teaching. We hypothesized that precepting third-year students would decrease clinical productivity and that many elements related to the quality of the learning experience (e.g., amount of patient contact, student autonomy) would be adversely affected by pressure to see increasing numbers of patients. METHODS: Students and preceptors in a 6-week family medicine clerkship completed daily surveys that measured the presence of quantifiable elements of the ambulatory teaching experience. They also rated the overall quality of learning during each session. RESULTS: For 62 sessions for which both students and preceptors completed evaluations, students rated the overall quality of learning more highly than preceptors. For students, the elements most positively associated with quality of learning were total teaching time and the frequency with which family issues were raised. For preceptors, the elements that predicted quality of learning were the number of patients that students saw independently and total teaching time. The clinical productivity of preceptors did not differ for sessions with and without a student. CONCLUSIONS: Preceptors can be effective teachers who encourage student autonomy and who model behaviors central to family practice, without decreasing productivity.

Clinical Clerkship↗

PubMed2025

Transfer learning with multiomics integration and deep neural networks reveals drug resistance mechanisms in cancer.

Drug resistance remains one of the primary challenges in effective cancer therapy. In this study, we employed a deep neural network (DNN)-based transfer learning (TL) approach to predict drug response and uncover drug resistance mechanisms. We integrated gene expression, somatic mutation, and copy number aberration (CNA) data with drug response profiles using multi-omics integration (MI). We used the Genomics of Drug Sensitivity in Cancer (GDSC) data for training and incorporated drugs with same pathways into the training models. We then evaluated drug response predictions on independent in-vivo PDX Encyclopedia (PDX) and ex-vivo the Cancer Genome Atlas (TCGA) datasets. In addition, we conducted pathway enrichment analyses to elucidate the mechanisms underlying drug resistance for paclitaxel, 5-fluorouracil (5-FU), gemcitabine, and cetuximab. We also applied Fisher's exact test (FET) to assess potential associations between drug resistance and the presence of mutations or CNAs. Our pan-drug models outperformed other methods based on the area under the precision-recall curve (AUCPR). Our pathway enrichment analyses revealed LDHB-mediated pyruvate metabolism and FYN-mediated focal adhesion might have pivotal roles in paclitaxel resistance, while PINK1-mediated mitophagy might be critical in 5-FU resistance. In addition to transcriptional activation, FET suggested that CNAs in LDHB and PINK1 may also be associated with resistance to paclitaxel and 5-FU, respectively. Furthermore, enrichment results for paclitaxel and cetuximab indicated shared resistance mechanisms between the two drugs. Importantly, our findings are consistent with prior experimental studies, providing literature-based validation of our results. Overall, our DNN-based TL approach achieved strong predictive performance across PDX & TCGA datasets and enrichment analyses provided valuable biological insights into drug resistance mechanisms.

Humans↗

PubMed1999

The link between brain learning, attention, and consciousness.

The processes whereby our brains continue to learn about a changing world in a stable fashion throughout life are proposed to lead to conscious experiences. These processes include the learning of top-down expectations, the matching of these expectations against bottom-up data, the focusing of attention upon the expected clusters of information, and the development of resonant states between bottom-up and top-down processes as they reach an attentive consensus between what is expected and what is there in the outside world. It is suggested that all conscious states in the brain are resonant states and that these resonant states trigger learning of sensory and cognitive representations. The models which summarize these concepts are therefore called Adaptive Resonance Theory, or ART, models. Psychophysical and neurobiological data in support of ART are presented from early vision, visual object recognition, auditory streaming, variable-rate speech perception, somatosensory perception, and cognitive-emotional interactions, among others. It is noted that ART mechanisms seem to be operative at all levels of the visual system, and it is proposed how these mechanisms are realized by known laminar circuits of visual cortex. It is predicted that the same circuit realization of ART mechanisms will be found in the laminar circuits of all sensory and cognitive neocortex. Concepts and data are summarized concerning how some visual percepts may be visibly, or modally, perceived, whereas amodal percepts may be consciously recognized even though they are perceptually invisible. It is also suggested that sensory and cognitive processing in the What processing stream of the brain obey top-down matching and learning laws that are often complementary to those used for spatial and motor processing in the brain's Where processing stream. This enables our sensory and cognitive representations to maintain their stability as we learn more about the world, while allowing spatial and motor representations to forget learned maps and gains that are no longer appropriate as our bodies develop and grow from infanthood to adulthood. Procedural memories are proposed to be unconscious because the inhibitory matching process that supports these spatial and motor processes cannot lead to resonance.

Attention↗