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 1,549 records · Page 86Linked to original sources

PubMed2005

A simple neural network model of the hippocampus suggesting its pathfinding role in episodic memory retrieval.

The goal of this work is to extend the theoretical understanding of the relationship between hippocampal spatial and memory functions to the level of neurophysiological mechanisms underlying spatial navigation and episodic memory retrieval. The proposed unifying theory describes both phenomena within a unique framework, as based on one and the same pathfinding function of the hippocampus. We propose a mechanism of reconstruction of the context of experience involving a search for a nearly shortest path in the space of remembered contexts. To analyze this concept in detail, we define a simple connectionist model consistent with available rodent and human neurophysiological data. Numerical study of the model begins with the spatial domain as a simple analogy for more complex phenomena. It is demonstrated how a nearly shortest path is quickly found in a familiar environment. We prove numerically that associative learning during sharp waves can account for the necessary properties of hippocampal place cells. Computational study of the model is extended to other cognitive paradigms, with the main focus on episodic memory retrieval. We show that the ability to find a correct path may be vital for successful retrieval. The model robustly exhibits the pathfinding capacity within a wide range of several factors, including its memory load (up to 30,000 abstract contexts), the number of episodes that become associated with potential target contexts, and the level of dynamical noise. We offer several testable critical predictions in both spatial and memory domains to validate the theory. Our results suggest that (1) the pathfinding function of the hippocampus, in addition to its associative and memory indexing functions, may be vital for retrieval of certain episodic memories, and (2) the hippocampal spatial navigation function could be a precursor of its memory function.

Animals↗

PubMed2006

Accurate prediction of the blood-brain partitioning of a large set of solutes using ab initio calculations and genetic neural network modeling.

A genetic algorithm-based artificial neural network model has been developed for the accurate prediction of the blood-brain barrier partitioning (in logBB scale) of chemicals. A data set of 123 logBB (115 old molecules and 8 new molecules) of a diverse set of chemicals was chosen in this study. The optimum 3D geometry of the molecules was estimated by the ab initio calculations at the level of RHF/STO-3G, and consequently, different electronic descriptors were calculated for each molecule. Indeed, logP as a measure of hydrophobicity and different topological indices were also calculated. A three-layered artificial neural network with backpropagation of an error-learning algorithm was employed to process the nonlinear relationship between the calculated descriptors and logBB data. Genetic algorithm was used as a feature selection method to select the most relevant set of descriptors as the input of the network. Modeling of the logBB data by the only quantum descriptors produced a 5:4:1 ANN structure with RMS error of validation and crossvalidation equal to 0.224 and 0.227, respectively. Better nonlinear model (RMS(V) and RMS(CV) equals to 0.097 and 0.099, respectively) was obtained by the incorporation of the logP and the principal components of the topological indices to electronic descriptors. The ultimate performances of the models were obtained by the application of the models to predict the logBB of 23 molecules that did not have contribution in the steps of model development. The best model produced RMS error of prediction 0.140, and could predict about 98% of variances in the logBB data.

Blood-Brain Barrier↗

PubMed2003

Attention and working memory: a dynamical model of neuronal activity in the prefrontal cortex.

Cognitive behaviour requires complex context-dependent mapping between sensory stimuli and actions. The same stimulus can lead to different behaviours depending on the situation, or the same behaviour may be elicited by different cueing stimuli. Neurons in the primate prefrontal cortex show task-specific firing activity during working memory delay periods. These neurons provide a neural substrate for mapping stimulus and response in a flexible, context- or rule-dependent, fashion. We describe here an integrate-and-fire network model to explain and investigate the different types of working-memory-related neuronal activity observed. The model contains different populations (or pools) of neurons (as found neurophysiologically) in attractor networks which respond in the delay period to the stimulus object, the stimulus position ('sensory pools'), to combinations of the stimulus sensory properties (e.g. the object identity or object location) and the response ('intermediate pools'), and to the response required (left or right) ('premotor pools'). The pools are arranged hierarchically, are linked by associative synaptic connections, and have global inhibition through inhibitory interneurons to implement competition. It is shown that a biasing attentional input to define the current rule applied to the intermediate pools enables the system to select the correct response in what is a biased competition model of attention. The integrate-and-fire model not only produces realistic spiking dynamicals very similar to the neuronal data but also shows how dopamine could weaken and shorten the persistent neuronal activity in the delay period; and allows us to predict more response errors when dopamine is elevated because there is less different activity in the different pools of competing neurons, resulting in more conflict.

Animals↗

PubMed1990

Detection of restenosis after successful coronary angioplasty: improved clinical decision making with use of a logistic model combining procedural and follow-up variables.

A prospective study of 111 patients who underwent repeat coronary angiography and exercise thallium-201 scintigraphy 6 +/- 2 months after complete revascularization by percutaneous transluminal coronary angioplasty was performed to assess whether clinical, procedure-related and postangioplasty exercise variables yield independent information for the prediction of angiographic restenosis after angioplasty. Complete revascularization was defined as successful angioplasty of one or more vessels that resulted in no residual coronary lesion with greater than 50% diameter stenosis. Restenosis was defined as a residual stenosis at the time of repeat angiography of greater than 50% of luminal diameter. Restenosis occurred in 40% of the patients. The 111 patients were randomly subdivided into a learning group (n = 84) and a testing group (n = 27). A logistic discriminant analysis was performed in the learning group and the logistic model was used to estimate a logistic probability of restenosis. This probability of restenosis was validated in the testing group. In the learning group of 84 patients univariate analysis of 39 factors revealed 8 factors related to restenosis: recurrence of angina (p less than 0.0001), postangioplasty abnormal finding on exercise thallium-201 scintigram (p less than 0.0001), exercise thallium-201 scintigram score (p less than 0.0001), difference between exercise and rest ST segment depression (p less than 0.001), postangioplasty exercise ST segment depression (p less than 0.001), absolute postangioplasty stenosis diameter (p less than 0.003), postangioplasty exercise work load (p less than 0.03) and postangioplasty exercise heart rate (p less than 0.05).(ABSTRACT TRUNCATED AT 250 WORDS)

Angina Pectoris↗

PubMed1999

Quantitative and qualitative analysis of type III antifreeze protein structure and function.

Some cold water marine fishes avoid cellular damage because of freezing by expressing antifreeze proteins (AFPs) that bind to ice and inhibit its growth; one such protein is the globular type III AFP from eel pout. Despite several studies, the mechanism of ice binding remains unclear because of the difficulty in modeling the AFP-ice interaction. To further explore the mechanism, we have determined the x-ray crystallographic structure of 10 type III AFP mutants and combined that information with 7 previously determined structures to mainly analyze specific AFP-ice interactions such as hydrogen bonds. Quantitative assessment of binding was performed using a neural network with properties of the structure as input and predicted antifreeze activity as output. Using the cross-validation method, a correlation coefficient of 0.60 was obtained between measured and predicted activity, indicating successful learning and good predictive power. A large loss in the predictive power of the neural network occurred after properties related to the hydrophobic surface were left out, suggesting that van der Waal's interactions make a significant contribution to ice binding. By combining the analysis of the neural network with antifreeze activity and x-ray crystallographic structures of the mutants, we extend the existing ice-binding model to a two-step process: 1) probing of the surface for the correct ice-binding plane by hydrogen-bonding side chains and 2) attractive van der Waal's interactions between the other residues of the ice-binding surface and the ice, which increases the strength of the protein-ice interaction.

Antifreeze Proteins↗

PubMed1983

Name and face matching in one or two visual fields: a test of models of hemispheric specialization.

In two experiments a name and a face (each male or female) were simultaneously flashed to either the same or opposite visual fields (left or right), for matching congruent (same sex) or incongruent (opposite sex), to test the predictions of various models of hemispheric specialization. While overall best performance occurred with a face in the left visual field (LVF) and a name in the right visual field (RVF), and worst with the opposite configuration, the general pattern of results was incompatible with either a direct access model or an activational/attentional account. The results were, however, most compatible with the predictions of a semispecialized hemispheres account, whereby cerebral asymmetries are seen as relative rather than absolute, either hemisphere being capable of processing either kind of material (verbal or visuospatial), but to different levels of efficiency. However, despite the fact that the stimulus materials had previously been shown to produce stable and consistent lateral asymmetries in the predicted directions when presented in isolation, in the composite, integrative matching task the position of the name seemed to be the major determinant of the resultant asymmetries. It would seem therefore that when such stimuli are to be cross matched, either left hemisphere (language) processes somehow dominate right hemisphere (visuospatial) processing (though not in the way that would be predicted by a simple activational/attentional account) or the left hemisphere's greater capacity predominates.

Discrimination Learning↗

PubMed2005

Validation of a histamine H3 receptor model through structure-activity relationships for classical H3 antagonists.

Histamine H(3) receptor is a G protein-coupled receptor whose activation inhibits the synthesis and release of histamine and other neurotransmitters from nerve endings and is involved in the modulation of different central nervous system functions. H(3) antagonists have been proposed for their potential usefulness in diseases characterized by impaired neurotransmission and they have demonstrated beneficial effects on learning and food intake in animal models. In the present work, a 3D model of the rat histamine H(3) receptor, built by comparative modeling from the crystallographic coordinates of bovine rhodopsin, is presented with the discussion of its ability to predict the potency of known and new H(3) antagonists. A putative binding site for classical, imidazole-derived H(3) antagonists was identified by molecular docking. Comparison with a known pharmacophore model and the binding affinity of a new rigid H(3) antagonist (compound 1, pK(i)=8.02) allowed the characterization of a binding scheme which could also account for the different affinities observed in a recently reported series of potent H(3) antagonists, characterized by a 2-aminobenzimidazole moiety. Molecular dynamics simulations were employed to assess the stability and reliability of the proposed binding mode. Two new conformationally constrained benzimidazole derivatives were prepared and their binding affinity was tested on rat brain membranes; compound 9, designed to reproduce the conformation of a known potent H(3) antagonist, showed higher potency than compound 8, as expected from the binding scheme hypothesized.

Amino Acid Sequence↗

PubMed2001

Feature subset selection by genetic algorithms and estimation of distribution algorithms. A case study in the survival of cirrhotic patients treated with TIPS.

The transjugular intrahepatic portosystemic shunt (TIPS) is an interventional treatment for cirrhotic patients with portal hypertension. In the light of our medical staff's experience, the consequences of TIPS are not homogeneous for all the patients and a subgroup dies in the first 6 months after TIPS placement. Actually, there is no risk indicator to identify this subgroup of patients before treatment. An investigation for predicting the survival of cirrhotic patients treated with TIPS is carried out using a clinical database with 107 cases and 77 attributes. Four supervised machine learning classifiers are applied to discriminate between both subgroups of patients. The application of several feature subset selection (FSS) techniques has significantly improved the predictive accuracy of these classifiers and considerably reduced the amount of attributes in the classification models. Among FSS techniques, FSS-TREE, a new randomized algorithm inspired on the new EDA (estimation of distribution algorithm) paradigm has obtained the best average accuracy results for each classifier.

Algorithms↗

PubMed2004

Confrontation naming does not add incremental diagnostic utility in MCI and Alzheimer's disease.

As the incidence of dementia increases, there is a growing need to determine the diagnostic utility of specific neuropsychological tests in the early diagnosis of Alzheimer's disease (AD). In this study, the relative utility of Boston Naming Test (BNT) in the diagnosis of AD was examined and compared to the diagnostic utility of other neuropsychological measures commonly used in the evaluation of AD. Individuals with AD (n = 306), Mild Cognitive Impairment (MCI; n = 67), and cognitively normal subjects (n = 409) with at least 2 annual evaluations were included. Logistic regression analysis suggested that initial BNT impairment is associated with increased risk of subsequent AD diagnosis. However, this risk is significantly less than that imparted by measures of delayed recall impairments. A multivariate Cox proportional hazards regression analysis suggested that BNT impairment imparted no additional risk for subsequent AD diagnosis after delayed recall impairments were included in the model. Although BNT impairment occurred in all severity groups, it was ubiquitous only in moderate to severe dementia. Collectively these results suggest that although BNT impairments become more common as AD progresses, they are neither necessary for the diagnosis of AD nor particularly useful in identifying early AD.

Aged↗

PubMed2000

Validity of measures of cognitive processes and general ability for learning and performance on highly complex computerized tutors: is the g factor of intelligence even more general?

Theoretical arguments and analyses from 2 studies provide compelling evidence that computerized measures of information-processing skills and abilities are highly useful supplements to more traditional, paper-based measures of general mental ability for predicting individuals' capacity to learn from and perform on highly challenging, multifaceted tutors. These tutors were designed to emulate learning and performance in complex, real-world settings. Hierarchical confirmatory factor analysis provided evidence that a general, higher order factor model with general ability at the apex could quite adequately and singularly account for the individual-differences data, both traditional and cognitive-process measures. Results are interpreted in light of the utility and generality of human cognitive abilities.

Cognition↗

PubMed2000

Predictors of intrinsic motivation among adolescent students in physical education.

This study examined the relationships among social factors, individual differences, intrinsic motivation, and effort and persistence in the physical education context using cognitive evaluation theory as a framework. Female (n = 201) and male (n = 206) high school students completed measures of motivational climate, teaching style, perceived competence, self-determination, goal orientations, and intrinsic motivation. Teachers rated the students on effort and persistence in the class activities. Hypothesized relationships among the variables were tested using structural equation modeling. Results revealed that perceived competence and goal orientations directly predicted intrinsic motivation and mediated the effects of motivational climate and teaching style on intrinsic motivation. Intrinsic motivation directly predicted effort and persistence. Task goal orientation mediated the effects of learning climate on perceived competence and self-determination. The strongest predictors of intrinsic motivation and effort and persistence were task goal orientation perceived competence, and learning climate.

Adolescent↗

PubMed2005

Proteomic mass spectra classification using decision tree based ensemble methods.

MOTIVATION: Modern mass spectrometry allows the determination of proteomic fingerprints of body fluids like serum, saliva or urine. These measurements can be used in many medical applications in order to diagnose the current state or predict the evolution of a disease. Recent developments in machine learning allow one to exploit such datasets, characterized by small numbers of very high-dimensional samples. RESULTS: We propose a systematic approach based on decision tree ensemble methods, which is used to automatically determine proteomic biomarkers and predictive models. The approach is validated on two datasets of surface-enhanced laser desorption/ionization time of flight measurements, for the diagnosis of rheumatoid arthritis and inflammatory bowel diseases. The results suggest that the methodology can handle a broad class of similar problems.

Algorithms↗

PubMed2026

LAMBDA: a prophage detection benchmark for genomic language models.

Transformer-based genomic sequence models represent an emerging frontier in computational biology. Yet, their embeddings have not yet shown the same level of predictive power as natural and protein language models, highlighting a gap between current implementations and theoretical promise. Existing benchmarks for DNA language models primarily focus on classifying regulatory elements in eukaryotic genomes, leaving open the fundamental question of whether these models learn sequence-level features across whole genomes. We introduce LAMBDA, a benchmark designed to rigorously evaluate genome language model embeddings through phage-bacteria sequence discrimination across four categories of increasing complexity: probing tasks, fine-tuning assessments, diagnostic tests, and genome-wide prophage detection. Our comprehensive analysis of current genomic language models provides insight into the importance of training data selection relative to model size, the need for domain-specific training, and the capabilities and limitations of genomic language models for detecting prophage sequences. This benchmark represents a challenging genomic annotation task in the bacterial domain and addresses a key computational problem with direct relevance to microbiology and medicine.

Prophages↗

PubMed2000

A computational model of information processing in the frontal cortex and basal ganglia.

Performance on the Wisconsin Card Sort Test (WCST) of patients with schizophrenia, Parkinson's disease (PD), and Huntington's disease (HD) was simulated by a neural network model constructed on principles derived from neuroanatomic loops from the frontal cortex through the basal ganglia and thalamus. The model provided a computational rationale for the empirical pattern of perseverative errors associated with frontal cortex dysfunction and random errors associated with striatal dysfunction. The model displayed perseverative errors in performance when the gain parameter of the activation function in units representing frontal cortex neurons was reduced as an analog of reduced dopamine release. Random errors occurred when the gain parameter of the activation function in units representing striatal neurons was reduced, or when the activation level was itself reduced as an analog of a striatal lesion. The model demonstrated that the perseveration of schizophrenic, Huntington's, and demented Parkinsonian patients may be principally due to ineffective inhibition of previously learned contextual rules in the frontal cortex, while the random errors of Parkinson's and Huntington's patients are more likely to be due to unsystematic errors of matching in the striatum. The model also made specific, empirically falsifiable predictions that can be used to explore the utility of these putative mechanisms of information processing in the frontal cortex and basal ganglia.

Basal Ganglia↗

PubMed2026

LAMBDA: A Prophage Detection Benchmark for Genomic Language Models.

Transformer-based genomic sequence models represent an emerging frontier in computational biology. Yet, their embeddings have not yet shown the same level of predictive power as natural and protein language models, indicating a gap between current implementations and theoretical promise. Existing benchmarks for DNA language models primarily focus on classifying regulatory elements in eukaryotic genomes, leaving open the fundamental question of whether these models learn sequence-level features across whole genomes. We introduce LAMBDA, a benchmark designed to rigorously evaluate genome language model embeddings through phage-bacteria sequence discrimination across four categories of increasing complexity: probing tasks, fine-tuning assessments, diagnostic tests, and genome-wide prophage detection. Our comprehensive analysis of current genomic language models provides novel insights into the importance of training data quality relative to model size, the need for domain-specific training, and the application of genomic language models for detecting prophage sequences. This benchmark represents a challenging genomic annotation task in the bacterial domain and addresses a key computational problem with direct relevance to microbiology and medicine.

DNA language model↗

PubMed1976

Optimizing test performance of moderately and severely mentally retarded adolescents and adults.

This study provided further evidence for the validity of a learning potential assessment procedure with institutionalized moderately and severely retarded adolescents and adults. Significant positive correlations were obtained between psychometric and learning scores, attendants' and teachers' ratings of ability, and the posttraining scores on the modified Kohs Extended Learning Potential procedure. In addition, performance on this test-train-test procedure was compared with a train-within-test format for two different tasks: training embedded within the administration of the Leiter International Performance Scale and a formboard version of Raven's Coloured Progressive Matrices. The students responded equally to the two formats. Stanford-Binet IQs were least predictive of performance on the three learning potential measures and were unrelated to teachers' and attendants' ratings of ability. The implications of these data were discussed with particular attention to the potential advantages of the train-within-test model.

Adolescent↗

PubMed2005

Discriminative components of data.

A simple probabilistic model is introduced to generalize classical linear discriminant analysis (LDA) in finding components that are informative of or relevant for data classes. The components maximize the predictability of the class distribution which is asymptotically equivalent to 1) maximizing mutual information with the classes, and 2) finding principal components in the so-called learning or Fisher metrics. The Fisher metric measures only distances that are relevant to the classes, that is, distances that cause changes in the class distribution. The components have applications in data exploration, visualization, and dimensionality reduction. In empirical experiments, the method outperformed, in addition to more classical methods, a Renyi entropy-based alternative while having essentially equivalent computational cost.

Algorithms↗

PubMed2005

Shoulder movements during the initial phase of learning manual wheelchair propulsion in able-bodied subjects.

BACKGROUND: The kinetics and kinematics of the glenohumeral joints, and shoulder muscles activities during the initial phase of learning wheelchair propulsion by individuals with paraplegia have been partially described. But no studies carry out the kinematics of the upper-limb during the learning of non-constrained open field locomotion with a wheelchair. METHODS: Ten subjects with no manual wheelchair experience propelled themselves repetitively straight ahead along an 11m linear path. Upper-limb segment orientations were measured with an electromagnetic system. Angular displacements of joints were determined using a standardized protocol [Wu, G., Van der Helm, F.C.T., Veeger, H.E.J., Makhsous, M., Van Roy, P., Anglin, C., Nagels, J., Karduna, A.R., McQuade, K., Wang, X., Wernerl, F.W., Buchholzm, B., 2005. ISB recommendation on definitions of joint coordinate systems of various joints for the reporting of human joint motion--Part II: shoulder, elbow, wrist and hand. J. Biomech. 38(5), 981-992] and a modeling method [Biryukova, E.V., Roby-Brami, A., Frolov, A.A., Mokhtari, M., 2000. Kinematics of human arm reconstructed from spatial tracking system recordings. J. Biomech. 33, 985-995]. FINDINGS: A full 3-D scapular motion description was obtained that allowed us to measure the mean amplitudes of rotation for the nine degrees of freedom of our model. The change in the propulsion pace and the repetition of trials induced a general increase of amplitudes of joint rotations that can explain the increase of velocity among trials. INTERPRETATION: We did not observe a freezing of any DOF as predicted by Bernstein's theory of motor learning, but the increase in joint movement amplitudes could correspond to his "unfreezing of DOF" stage. This non-respect of Bernstein's theory could originate in the relative simplicity of the task.

Adult↗