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 451 records · Page 25Linked to original sources

PubMedDate not supplied

The relationship between reinforcement and memory: parallels in the rewarding and mnemonic effects of the neuropeptide substance P.

A theory of reinforcement is presented which accounts for the backward action of a reinforcer on operant behavior in terms of its effect on memory traces left by the operant. Several possible ways in which a reinforcer could strengthen the probability of recurrence of an operant are discussed. Predictions from the model regarding general memory-promoting effects of reinforcers presented posttrial in various learning paradigms are outlined. The theory also predicts a parallelism in reinforcing and memory-promoting effects of stimuli, including drugs. The second part of the chapter outlines experiments investigating memory modulating and reinforcing effects of the neuropeptide substance P. In general, injection of SP is positively reinforcing when injected into parts of the brain where it has been shown to facilitate learning. Peripheral injection of SP is also reinforcing at the dose known to promote passive avoidance learning when presented posttrial.

Amino Acid Sequence↗

PubMed2006

The Path-A metabolic pathway prediction web server.

Pathway Analyst (Path-A) is a publicly available web server (http://path-a.cs.ualberta.ca) that predicts metabolic pathways. It takes a FASTA format file containing a set of query protein sequences from a single organism (a partial or complete proteome) and identifies those sequences that are likely to participate in any of its supported metabolic pathways (currently 10). Path-A uses a number of machine-learning and sequence analysis techniques (e.g. SVM, BLAST and HMM) to predict pathways. Each machine-learned classifier exploits similarity between sequences in the pathways of its model organisms and sequences in the query set. It predicts the pathways that are present in the query organism and annotates each predicted reaction and catalyst, using the appropriate sequences from the query set. Path-A also provides a browsable and searchable database of the pathways for the model organisms that are used to make its predictions. Path-A's predictor sets (using different classifier technologies) have been evaluated using standard cross-validation techniques on a dataset of 10 metabolic pathways across 13 model organisms--a total of 125 organism-specific pathways. The most accurate classifier technology obtained a mean precision of 78.3% and a mean recall of 92.6% in predicting all catalyst proteins, of all reactions, in all pathways present in the dataset. Although Path-A currently only supports metabolic pathways, the underlying prediction techniques are general enough for other types of pathways. Consequently, it is our intent to extend Path-A to predict other types of pathways, including signalling pathways.

Algorithms↗

PubMed2005

Prediction of CASP6 structures using automated Robetta protocols.

The Robetta server and revised automatic protocols were used to predict structures for CASP6 targets. Robetta is a publicly available protein structure prediction server (http://robetta.bakerlab.org/ that uses the Rosetta de novo and homology modeling structure prediction methods. We incorporated some of the lessons learned in the CASP5 experiment into the server prior to participating in CASP6. We additionally tested new ideas that were amenable to full-automation with an eye toward improving the server. We find that the Robetta server shows the greatest promise for the more challenging targets. The most significant finding from CASP5, that automated protocols can be roughly comparable in ability with the better human-intervention predictors, is repeated here in CASP6.

Algorithms↗

PubMed1993

Virtual trajectory and stiffness ellipse during multijoint arm movement predicted by neural inverse models.

We predict the virtual trajectories and stiffness ellipses during multijoint arm movements by computer simulations. A two-link manipulator with four single-joint muscles and two double-joint muscles is used as a model of the human arm. Physical parameters of the model are derived from several experimental data. Among them, special emphasis is put on low values of the dynamic hand stiffness recently measured during single-joint and multijoint movements. The feedback-error-learning scheme to acquire the inverse dynamics model and the inverse statics model is utilized for this prediction. The virtual trajectories are much more complex than the actual trajectories. This indicates that planning the virtual trajectory is as difficult as solving the inverse dynamics problem for medium and fast movements, and simply falsifies the advocated computational advantage of the virtual trajectory control hypothesis. Thus, we conclude that learning inverse models is essential even in the virtual trajectory control framework. Finally, we propose a new computational model to learn the complicated shape of the virtual trajectories by integrating the virtual trajectory control and the feedback-error-learning scheme.

Arm↗

PubMed2026

A weakly supervised deep learning-based recurrence prediction and risk stratification of lung adenocarcinoma from pathology whole-slide images.

BACKGROUND: Accurate prediction of postoperative recurrence in lung adenocarcinoma (LUAD) is essential for guiding clinical decision-making and improving patient outcomes. Although various predictive models have been developed, most rely on complex genomic analyses and high-dimensional clinical data. The complexity of these approaches substantially limits their feasibility for routine clinical use. To address this clinical challenge, this study aims to predict postoperative recurrence using routinely available hematoxylin and eosin (H&E)-stained images and characterize the associated biological features. METHODS: A total of 329 patients who underwent curative resection at the First Affiliated Hospital of Wenzhou Medical University (FHWMU) were retrospectively enrolled and randomly assigned to training and internal validation cohorts in a 7:3 ratio. An independent external validation cohort comprising 70 patients from the Clinical Proteomic Tumor Analysis Consortium (CPTAC) was included. Three patch-level feature extractors (Inception_V3, ResNet18, and DenseNet121) were evaluated within a weakly supervised multiple-instance learning (MIL) framework incorporating automated region-of-interest (ROI) detection on segmented whole-slide images (WSIs). Model performance was assessed using the area under the receiver operating characteristic curve (AUC), Kaplan-Meier (KM) survival analysis, and multivariable Cox proportional hazards regression. Transcriptomic profiling and gene set enrichment analysis (GSEA) were conducted to investigate biological differences between risk groups. RESULTS: The model achieved AUCs of 0.923 in the training cohort, 0.891 in the internal validation cohort, and 0.847 in the external validation cohort. The model effectively stratified patients into high- and low-risk groups with significantly different recurrence-free survival (RFS) across all cohorts (all P < 0.001) and retained prognostic value within AJCC stages I-III. Transcriptomic analyses revealed consistent enrichment of cell cycle-related pathways and neutrophil extracellular trap (NET) formation in high-risk patients across both institutional and CPTAC cohorts, aligning with distinct biological profiles of the model-derived risk stratification. CONCLUSIONS: This weakly supervised deep learning framework enables accurate and externally validated prediction of postoperative recurrence in LUAD using routinely available histopathological images, and integration of histopathological features with molecular analyses enhances biological interpretability. This work provides a clinically accessible and cost-effective tool for postoperative risk assessment in LUAD patients.

Humans↗

PubMed2003

The intergenerational transmission of relationship violence.

This study explored the intergenerational transmission of violence in a community sample. A telephone survey of 1,249 adults in the City of Vancouver assessed family-of-origin violence (father to mother, mother to father, father to self, and mother to self), as well as physical and psychological abuse in intimate relationships. All forms of family-of-origin violence were predictive of all forms of relationship abuse, consistent with a general social learning model of relationship violence. There was no evidence of gender-specific or role-specific patterns of transmission. For example, father-to-mother violence was not specifically predictive of men's perpetration and women's victimization in adult relationships. Nor was parent-to-self violence more predictive of victimization than perpetration. The methodological and theoretical implications of these findings are discussed.

Adult↗

PubMed1996

Befloxatone, a new reversible and selective monoamine oxidase-A inhibitor. II. Pharmacological profile.

The pharmacological profile of befloxatone, a reversible, selective and competitive inhibitor of monoamine oxidase-A has been investigated in rodents. In mice, befloxatone was more active at potentiating generalized tremors induced by L-5-hydroxytryptophan (ED50, 0.21 mg/kg p.o.) than phenylethylamine-induced stereotypies (ED50, 58 mg/kg p.o.), indicating a very high in vivo selectivity for inhibition of the A form of monoamine oxidase. Befloxatone showed potent activity in behavioral models in rodents predictive of antidepressant activity (forced swimming test, learned helplessness and reserpine reversal) with minimal effective doses of 0.1 to 0.2 mg/kg p.o. In these tests, befloxatone was much more potent (10- to 500-fold) than reference antidepressant compounds (reversible and irreversible monoamine oxidase inhibitors and monoamine reuptake inhibitors). In rats, befloxatone increased rapid eye movement sleep latency and decreased rapid eye movement sleep duration, without rebound effects. Potential anxiolytic activity was observed in the elevated-plus maze test in rats (minimal effective dose, 1-2 mg/kg p.o.). Befloxatone had no effect on motor performance, did not induce sedative or stimulant activity up to doses of 200 mg/kg p.o. and was devoid of anticholinergic activity in mice. Interaction studies with p.o. dietary tyramine (12 mg/kg), carried out in freely moving rats, demonstrated that, in contrast to irreversible monoamine oxidase inhibitors, befloxatone did not potentiate the pressor effect of this amine in the range of doses which showed pharmacological activity in antidepressant behavioral models. Furthermore, of the compounds tested (moclobemide, brofaromine, nialamide and phenelzine), comparison of doses active in antidepressant models and doses potentiating the pressor effects of tyramine demonstrated that befloxatone had the best therapeutic index. The results suggest that befloxatone will show clinical antidepressant activity at low doses and will be devoid of the side effects associated with irreversible monoamine oxidase inhibitors.

Animals↗

PubMed2004

A computational framework for cortical learning.

Recent physiological findings have revealed that long-term adaptation of the synaptic strengths between cortical pyramidal neurons depends on the temporal order of presynaptic and postsynaptic spikes, which is called spike-timing-dependent plasticity (STDP) or temporally asymmetric Hebbian (TAH) learning. Here I prove by analytical means that a physiologically plausible variant of STDP adapts synaptic strengths such that the presynaptic spikes predict the postsynaptic spikes with minimal error. This prediction error model of STDP implies a mechanism for cortical memory: cortical tissue learns temporal spike patterns if these spike patterns are repeatedly elicited in a set of pyramidal neurons. The trained network finishes these patterns if their beginnings are presented, thereby recalling the memory. Implementations of the proposed algorithms may be useful for applications in voice recognition and computer vision.

Action Potentials↗

PubMed2005

Robust self-localisation and navigation based on hippocampal place cells.

A computational model of the hippocampal function in spatial learning is presented. A spatial representation is incrementally acquired during exploration. Visual and self-motion information is fed into a network of rate-coded neurons. A consistent and stable place code emerges by unsupervised Hebbian learning between place- and head direction cells. Based on this representation, goal-oriented navigation is learnt by applying a reward-based learning mechanism between the hippocampus and nucleus accumbens. The model, validated on a real and simulated robot, successfully localises itself by recalibrating its path integrator using visual input. A navigation map is learnt after about 20 trials, comparable to rats in the water maze. In contrast to previous works, this system processes realistic visual input. No compass is needed for localisation and the reward-based learning mechanism extends discrete navigation models to continuous space. The model reproduces experimental findings and suggests several neurophysiological and behavioural predictions in the rat.

Animals↗

PubMed2006

Identifying offline muscle strength profiles sufficient for short-duration FES-LCE exercise: a PAC learning model approach.

UNLABELLED: Functional electrical stimulation-induced leg cycle ergometry (FES-LCE) provides therapeutic exercise for persons with spinal cord injury (SCI). However, there exists no systematic approach to predict whether an individual has sufficient thigh muscle strength necessary for FES-LCE exercise. OBJECTIVE: To develop and test a Probably Approximately Correct (PAC) learning model as a predictor of thigh muscle strengths sufficient for short-duration FES-LCE exercise and compare the model's performance with other well-known statistical methods. METHODS: Six healthy male individuals with SCI, having age (32.0 +/- 12.5 years), height (1.8 +/- 0.04 m), and weight (79.12 +/- 10.76 kg), participated in static and dynamic experiments. During static experiments, absolute crank torque measurements were used to estimate thigh muscle strengths in response to maximum FES intensities of 70 mA, 105 mA, and 140 mA at fixed crank positions on an FES-LCE. During dynamic experiments, changes in power output measurements were used to classify rider performance as 'Fatigue' or 'No Fatigue' during short-duration FES-LCE at maximum stimulation intensities of 70 mA, 105 mA, and 140 mA and flywheel resistance levels of 0/8th, 1/8th, and 2/8th kilopounds. A Probably Approximately Correct (PAC) learning model was developed to classify static offline muscle strength observations with online rider performances. PAC's discriminatory power was compared with logistic regression (LR), Fisher's linear discriminant analysis (LDA), and an artificial neural network (ANN) model. RESULTS: PAC and ANN learning models correctly identified 100% of the training examples. PAC's average performance on the validation set was 93.1%. The ANN and LR performed comparable with 92.8% and 93.1% accuracy, respectively. The LDA method faired well on the validation set at 89.9%. CONCLUSIONS: PAC performed well in identifying muscle strengths associated with the online performance criterion. Although PAC did not perform best during cross-validation, this model has many advantages over the other methods. PAC can adapt to changes in classification schemes and is more amenable to theoretical analyses than the other methods. PAC learning has an intuitive design and may be a practical choice for classifying muscle strength profiles with well-defined performance criteria.

Adult↗

PubMed2001

Stepping out of the box: information processing in the neural networks of the basal ganglia.

The Albin-DeLong 'box and arrow' model has long been the accepted standard model for the basal ganglia network. However, advances in physiological and anatomical research have enabled a more detailed neural network approach. Recent computational models hold that the basal ganglia use reinforcement signals and local competitive learning rules to reduce the dimensionality of sparse cortical information. These models predict a steady-state situation with diminished efficacy of lateral inhibition and low synchronization. In this framework, Parkinson's disease can be characterized as a persistent state of negative reinforcement, inefficient dimensionality reduction, and abnormally synchronized basal ganglia activity.

Animals↗

PubMed1996

A computer program using BALF-analysis results as a diagnostic tool in interstitial lung diseases.

Recently, we showed that it is possible to distinguish between three common interstitial lung diseases (ILD) with similarities in clinical presentation by using a number of selected variables derived from bronchoalveolar lavage fluid (BALF) analysis. The aim of this study was to develop a more general discriminant model, based on polychotomous logistic regression analysis. The 277 patients involved in the study belonged to diagnostic groups with sarcoidosis (n = 193), extrinsic allergic alveolitis (EAA; n = 39), and idiopathic pulmonary fibrosis (IPF; n = 45). The diagnosis had been established independently of the BALF-analysis results. The variables used to discriminate among these patient groups were the yield of recovered BALF, total cell count, and percentages of alveolar macrophages, lymphocytes, neutrophils, and eosinophils. In order to test the predictive power of the logistic model, we used 128 patients having sarcoidosis (n = 91), EAA (n = 5), or IPF (n = 32) from another hospital. In this test set the agreement of predicted with actual diagnostic-group membership was the same as in the learning set in which the logistic model was fitted: 94.5% of the cases were correctly classified. A validated computer program based on the polychotomous logistic regression model can be used to predict the diagnosis for an arbitrary patient with information provided by BALF analysis, and is thought to be of diagnostic value in patients suspected of having ILD.

Adolescent↗

PubMed1993

Using neural networks to model personality development.

A neural network approach to modeling the development of personality traits through social learning is presented. From the more general model the special case of a network mapping four situation dimensions (input neurons) into seven dimensional personality traits (output neurons) is described. This network is allowed to learn with input/output sets representing conditions suspected of leading to a borderline personality disorder. The network's ability to learn these pattern pairs is demonstrated. The trained network is then presented with new input (situational) patterns and is shown to respond to these new situations with output patterns consistent with a borderline personality disorder. The neural network model is thus shown to have important advantages over other personality models in that it can predict what situations will produce shifts in personality traits, for example from active to passive. This model provides a quantitative and reproducible framework within which to discover and test theories of personality development. It is hoped that it will extend our ability to predict human behavior.

Humans↗

PubMed2000

Multi-step-ahead prediction using dynamic recurrent neural networks.

A method for the development of empirical predictive models for complex processes is presented. The models are capable of performing accurate multi-step-ahead (MS) predictions, while maintaining acceptable single-step-ahead (SS) prediction accuracy. Such predictors find applications in model predictive controllers and in fault diagnosis systems. The proposed method makes use of dynamic recurrent neural networks in the form of a nonlinear infinite impulse response (IIR) filter. A learning algorithm is presented, which is based on a dynamic gradient descent approach. The effectiveness of the method for accurate MS prediction is tested on an artificial problem and on a complex, open-loop unstable process. Comparative results are presented with polynomial Nonlinear AutoRegressive with eXogeneous (NARX) predictors, and with recurrent networks trained using teacher forcing. Validation studies indicate that excellent generalization is obtained for the range of operational dynamics studied. The research demonstrates that the proposed network architecture and the associated learning algorithm are quite effective in modeling the dynamics of complex processes and performing accurate MS predictions.

Algorithms↗

PubMed2000

A connectionist approach to making the predictability of English orthography explicit to at-risk beginning readers: evidence for alternative, effective strategies.

A case is made (and illustrated with empirical data with children) for connectionist models that are not only computationally explicit but also instructionally explicit. First-graders (N = 128) at the bottom of their classes in reading (average 11.5 percentile on nationally normed tests) participated in a 3-layer intervention. In the first layer, kept constant for all treatment groups, the alphabet principle was taught, making functional spelling units and alternations explicit. In the second layer, which varied systematically across treatment groups, children received different kinds of tutor modeling in learning a set of words of varying spelling-sound predictability, using different connections between printed and spoken words, singly or in combination. In the third layer, also kept constant, children read and discussed illustrated books. Over the 4-month, 24-lesson intervention, all 7 treatment groups in the second layer improved more in word-specific learning than a contact control group that received phonological and orthographic awareness training without explicit instruction on orthographic-phonological connections. Of these 7, only 3 kinds of explicit modeling (whole word, letter-phoneme, and combined whole word and letter-phoneme) resulted in greater transfer to untrained words than the contact control or the other 4 kinds of explicit modeling. Results are discussed in reference to the controversy over whether dual route or connectionist models best account for the acquisition of reading.

Child↗

PubMed2002

Responding under time pressure: testing two animal learning models and a model of visual categorization.

Two experiments are reported, which employed a Pavlovian eyelid conditioning procedure with human participants. The experiments tested the predictions of three models of the time-course of processing under time pressure. These were the extended generalized context model (Lamberts, 1998), and two variants of the Rescorla-Wagner model (Rescorla & Wagner, 1972), which were activated in cascade mode. Reinforcement schedules in the experiments were equivalent either to an AND rule or to an XOR rule. The time available for processing the conditioned stimulus and initiating a conditioned response was manipulated by varying the interval from the onset of the conditioned stimulus to the onset of the unconditioned stimulus. The results were in accord with the predictions of one of the two variants of the Rescorla-Wagner model.

Adult↗

PubMed2005

Possible prediction of chemoradiosensitivity of esophageal cancer by serum protein profiling.

PURPOSE: Establishment of a reliable method of predicting the efficacy of chemotherapy and radiotherapy is necessary to provide the most suitable treatment for each cancer patient. We investigated whether proteomic profiles of serum samples obtained from untreated patients were capable of being used to predict the efficacy of combined preoperative chemoradiotherapy against esophageal cancer. EXPERIMENTAL DESIGN: Proteomic spectra were obtained from a training set of 27 serum samples (15 pathologically diagnosed responders to preoperative chemoradiotherapy and 12 nonresponders) by surface-enhanced laser desorption and ionization coupled with hybrid quadrupole time-of-flight mass spectrometry. A proteomic pattern prediction model was constructed from the training set by machine learning algorithms, and it was then tested with an independent validation set consisting of serum samples from 15 esophageal cancer patients in a blinded manner. RESULTS: We selected a set of four mass peaks, at 7,420, 9,112, 17,123, and 12,867 m/z, from a total of 859 protein peaks, as perfectly distinguishing responders from nonresponders in the training set with a support vector machine algorithm. This set of peaks (i.e., the classifier) correctly diagnosed chemoradiosensitivity in 93.3% (14 of 15) of the cases in the validation set. CONCLUSIONS: Recent mass spectrometric approaches have revealed that serum contains a large volume of information that reflects the microenvironment of diseased organs. Although a multi-institutional large-scale study will be necessary to confirm each component of the classifier, there is a subtle but definite difference in serum proteomic profile between responders and nonresponders to chemoradiotherapy.

Aged↗

PubMed2003

Testing curvatures of learning functions on individual trial and block average data.

Many models offer different explanations of learning processes, some of them predicting equal learning rates between conditions. The simplest method by which to assess this equality is to evaluate the curvature parameter for each condition, followed by a statistical test. However, this approach is highly dependent on the fitting procedure, which may come with built-in biases difficult to identify. Averaging the data per block of training would help reduce the noise present in the trial data, but averaging introduces a severe distortion on the curve, which can no longer be fitted by the original function. In this article, we first demonstrate what is the distortion resulting from block averaging. The block average learning function, once known, can be used to extract parameters when the performance is averaged over blocks or sessions. The use of averages eliminates an important part of the noise present in the data and allows good recovery of the learning curve parameters. Equality of curvatures can be tested with a test of linear hypothesis. This method can be performed on trial data or block average data, but it is more powerful with block average data.

Artifacts↗