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 1,333 records · Page 74Linked to original sources

PubMedDate not supplied

Modeling and reinforcement of the sick role during childhood predicts adult illness behavior.

Previous studies suggest that the ways in which parents respond to children's health complaints (reinforcement) and the ways in which they cope with their own illnesses (modeling) influence the frequency of symptoms, disability days, and health care visits made by these children when they grow up. However, previous studies have not controlled for the mediating influence of stress, neuroticism, and physical examination findings. This study investigated the influence of childhood social learning on adult illness behavior in 383 women aged 20 to 40 years. Illness behavior was measured prospectively for 12 months by the frequency of symptoms, disability days, and physician visits for menstrual, bowel, and cold (upper respiratory) symptoms. Childhood reinforcement and modeling was measured retrospectively by validated questionnaires. Other independent variables were stress, neuroticism, and selected demographic variables. Multiple regression analysis was used to assess the relative contribution of each independent variable to each category of illness behavior. The principal findings were as follows. First, childhood reinforcement of menstrual illness behavior significantly predicted adult menstrual symptoms and disability days, and childhood reinforcement of cold illness behavior significantly predicted adult cold symptoms and disability days. These effects were independent of stress and neuroticism. Second, childhood reinforcement scales were useful to predict which functional disorders (dysmenorrhea or irritable bowel syndrome) these subjects had even after we controlled for stress and neuroticism.

Adaptation, Psychological↗

PubMed2004

Predicting risk sensitivity in humans and lower animals: risk as variance or coefficient of variation.

This article examines the statistical determinants of risk preference. In a meta-analysis of animal risk preference (foraging birds and insects), the coefficient of variation (CV), a measure of risk per unit of return, predicts choices far better than outcome variance, the risk measure of normative models. In a meta-analysis of human risk preference, the superiority of the CV over variance in predicting risk taking is not as strong. Two experiments show that people's risk sensitivity becomes strongly proportional to the CV when they learn about choice alternatives like other animals, by experiential sampling over time. Experience-based choices differ from choices when outcomes and probabilities are numerically described. Zipf's law as an ecological regularity and Weber's law as a psychological regularity may give rise to the CV as a measure of risk.

Animals↗

PubMed2004

Protein backbone angle prediction with machine learning approaches.

MOTIVATION: Protein backbone torsion angle prediction provides useful local structural information that goes beyond conventional three-state (alpha, beta and coil) secondary structure predictions. Accurate prediction of protein backbone torsion angles will substantially improve modeling procedures for local structures of protein sequence segments, especially in modeling loop conformations that do not form regular structures as in alpha-helices or beta-strands. RESULTS: We have devised two novel automated methods in protein backbone conformational state prediction: one method is based on support vector machines (SVMs); the other method combines a standard feed-forward back-propagation artificial neural network (NN) with a local structure-based sequence profile database (LSBSP1). Extensive benchmark experiments demonstrate that both methods have improved the prediction accuracy rate over the previously published methods for conformation state prediction when using an alphabet of three or four states. AVAILABILITY: LSBSP1 and the NN algorithm have been implemented in PrISM.1, which is available from www.columbia.edu/~ay1/. SUPPLEMENTARY INFORMATION: Supplementary data for the SVM method can be downloaded from the Website www.cs.columbia.edu/compbio/backbone.

Algorithms↗

PubMed2006

The paranoid optimist: an integrative evolutionary model of cognitive biases.

Human cognition is often biased, from judgments of the time of impact of approaching objects all the way through to estimations of social outcomes in the future. We propose these effects and a host of others may all be understood from an evolutionary psychological perspective. In this article, we elaborate error management theory (EMT; Haselton & Buss, 2000). EMT predicts that if judgments are made under uncertainty, and the costs of false positive and false negative errors have been asymmetric over evolutionary history, selection should have favored a bias toward making the least costly error. This perspective integrates a diverse array of effects under a single explanatory umbrella, and it yields new content-specific predictions.

Animals↗

PubMed1977

A new animal model for the prediction of antidepressant activity.

Animal models presently in use for the screening of potential antidepressant drugs yield numerous false positives and false negatives. In search of a more specific model, we have studied the effects of psychotropic compounds on the behavioural changes induced in rats by the removal of the olfactory bulbs. We have observed that subchronic treatment with antidepressants in general reverses the behavioural alterations displayed by bulbectomized rats in tests of conditioned behaviour. The present paper describes a brief test, the so-called anxiosoif test, which may be used to assess the effects of drugs on the behaviour of bulbectomized rats. Removal of the olfactory bulbs leads to increased water intake in the anxiosoif test and to an attenuation of avoidance when the drinking spout is electrified. This latter effect can be reversed by subchronic treatment with the antidepressant drugs amitriptyline and mianserine (Org GB 94). It is suggested that the behavior of bulbectomized rats may be used as a specific tool in the prediction of antidepressant activity of novel compounds.

Animals↗

PubMed2006

Pavlovian conditioning in Hermissenda: a circuit analysis.

An understanding of associative learning requires (1) an adequate description of the experimental conditions under which learning is produced, (2) a knowledge of what is learned or the determination of the content of learning, and (3) an explanation of how learning generates changes in behavior (Rescorla, 1980). These basic issues are being addressed at both the behavioral and cellular/molecular levels by the analysis of associative learning in animals with relatively uncomplex nervous systems. Use of Pavlovian conditioning of invertebrates as a model for associative learning has led to the identification of cellular and synaptic mechanisms underlying the formation of basic associations. However, an understanding of the associative processes that form the basis for Pavlovian conditioning requires an explanation not only of the mechanisms of temporal contiguity or predictability between the conditioned stimulus (CS) and the unconditioned stimulus (US), but also of how changes produced in the nervous system by conditioning are expressed in behavior. Studies with invertebrates have provided the opportunity to examine how associative learning is expressed in the neural circuitry that supports the generation of learned behavior.

Action Potentials↗

PubMed2026

PMGen: from peptide-MHC structure prediction to peptide generation.

MOTIVATION: Accurate structural modeling of peptide-major histocompatibility complex (pMHC) complexes is essential for structure-driven immunotherapy design, yet current prediction tools suffer from narrow class coverage, restricted peptide lengths, insufficient accuracy, and a lack of built-in structure-aware peptide sampling. Consequently, most mimotope and altered peptide ligand designs rely solely on sequence substitution, leaving spatial and biophysical insights from pMHC structures largely unexploited. RESULTS: We introduce peptide-MHC generator (PMGen), an integrated framework for structure prediction and structure-guided design of variable-length peptides across MHC Class I and II. PMGen enforces anchor constraints within AlphaFold2 through two complementary strategies, initial guess and template engineering, achieving state-of-the-art structural fidelity without model fine-tuning. On a comprehensive benchmark, PMGen outperforms all existing methods, yielding median peptide-core Cα RMSDs of 0.62 Å for MHC-I and 0.33 Å for MHC-II. We show that PMGen can recover incorrectly predicted anchor positions and that AlphaFold pLDDT scores enable sequence-independent binding-core identification. Applied to a published neoantigen/wild-type pair, PMGen accurately captures mutation-induced conformational changes. Beyond structure prediction, we show that ProteinMPNN sampling on PMGen-predicted backbones yields higher affinity peptides while preserving the parental 3D conformation. Using PMGen to generate 63 817 high-confidence pMHC structures as training data, we further improve ProteinMPNN's peptide sequence recovery from 0.14 to 0.64 on a test set of 85 unseen MHC-I alleles, highlighting the value of accurate predicted structures for downstream machine learning tasks. AVAILABILITY AND IMPLEMENTATION: PMGen is freely available at https://github.com/soedinglab/PMGen, with an interactive Colab notebook at https://colab.research.google.com/github/soedinglab/PMGen/blob/master/colab.ipynb.

Peptides↗

PubMed1984

The validity of animal models of depression.

Eighteen animal models of depression are reviewed in relation to three sets of validating criteria. Of the 18 models, five could only be assessed for predictive validity, seven could be assessed for predictive and face validity, and six could potentially have predictive, face and construct validity. Some traditional models (reserpine reversal, amphetamine potentiation) are rejected as invalid; the models with the highest overall validity are the intracranial self-stimulation, chronic stress and learned helplessness models in rats, and the primate separation model.

5-Hydroxytryptophan↗

PubMed2006

Human neocortical oscillations exhibit theta phase differences between encoding and retrieval.

We analyzed intracranial brain activity recorded from human participants during the performance of a working-memory task. We show that 6-13 Hz activity exhibits consistent phase across trials following experimental stimuli, and that this phase significantly differs between study and test stimuli. These findings suggest that oscillatory phase reflects the encoding-retrieval state of neural networks, supporting predictions of recent models of memory.[Hasselmo, M.E., Wyble, B.P., and Bodelon, C., 2002. A proposed function for hippocampal theta rhythm: Separate phases of encoding and retrieval enhance reversal of prior learning. Neural Comput. 14 793-817.; Judge, S.J., Hasselmo, M.E., 2004. Theta rhythmic stimulation of stratum lacunosum-moleculare in rat hippocampus contributes to associative LTP at a phase offset in stratum radiatum. J. Neurophys. 92 1516-1624.].

Adolescent↗

PubMed2002

Forgetting curves: implications for connectionist models.

Forgetting in long-term memory, as measured in a recall or a recognition test, is faster for items encoded more recently than for items encoded earlier. Data on forgetting curves fit a power function well. In contrast, many connectionist models predict either exponential decay or completely flat forgetting curves. This paper suggests a connectionist model to account for power-function forgetting curves by using bounded weights and by generating the learning rates from a monotonically decreasing function. The bounded weights introduce exponential forgetting in each weight and a power-function forgetting results when weights with different learning rates are averaged. It is argued that these assumptions are biologically reasonable. Therefore power-function forgetting curves are a property that may be expected from biological networks. The model has an analytic solution, which is a good approximation of a power function displaced one lag in time. This function fits better than any of the 105 suggested two-parameter forgetting-curve functions when tested on the most precise recognition memory data set collected by. Unlike the power-function normally used, the suggested function is defined at lag zero. Several functions for generating learning rates with a finite integral yield power-function forgetting curves; however, the type of function influences the rate of forgetting. It is shown that power-function forgetting curves cannot be accounted for by variability in performance between subjects because it requires a distribution of performance that is not found in empirical data. An extension of the model accounts for intersecting forgetting curves found in massed and spaced repetitions. The model can also be extended to account for a faster forgetting rate in item recognition (IR) compared to associative recognition in short but not long retention intervals.

Humans↗

PubMed2000

Large-scale predictions of secretory proteins from mammalian genomic and EST sequences.

Machine learning techniques have improved predictions of secretory proteins from protein, genomic and expressed sequence tag (EST) sequences. Artificial neural networks, physical sequence analysis using high-performance optimization, and hidden Markov models identify extremely variable signal peptides (the vehicles of protein transport across the endoplasmic reticulum membrane), transmembrane segments, and specific extracellular and intracellular domains as indicators of possible roles in the intercellular and intracellular chemical signaling pathways. The major role of peptide hormones, blood coagulation factors, carcinogenesis agents, and other secretory proteins in orchestrating multicellular life indicates pharmacological potential in the cure of major diseases and numerous biotechnological applications.

Animals↗

PubMed2002

A ligand-based approach to understanding selectivity of nuclear hormone receptors PXR, CAR, FXR, LXRalpha, and LXRbeta.

In recent years discussion of nuclear hormone receptors, transporters, and drug-metabolizing enzymes has begun to take place as our knowledge of the overlapping ligand specificity of each of these proteins has deepened. This ligand specificity is potentially valuable information for influencing future drug design, as it is important to avoid certain enzymes or transporters in order to circumvent potential drug-drug interactions. Similarly, it is critical that the induction of these same proteins via nuclear hormone receptors is avoided, as this can result in further toxicities. Using a ligand-based approach in this review we describe new and previously published computational models for PXR, CAR, FXR, LXRalpha, and LXRbeta that may help in understanding the complexity of interactions between transporters and enzymes. The value of these types of models is that they may enable us to design molecules to selectively modulate pathways for therapeutic effect and in addition predict the potential for drug interactions more reliably. Simultaneously, we might learn which came first: the transporter, the enzyme, or the nuclear hormone receptor?

Amino Acid Sequence↗

PubMed1994

A cognitive model for schizophrenia and its possible neural basis.

It is proposed that the basic disturbance in schizophrenia corresponds to a disruption of the normal relationship between stored material and current sensory input. The link between information processing disturbances and their biological bases may be facilitated by the use of paradigms derived from animal learning theory. A model for the emergence of schizophrenic symptoms is presented. The core cognitive abnormality may result from a disturbance at any point in the neural circuit involved in the prediction of subsequent sensory input.

Brain↗

PubMed2005

Learning from humans: computational modeling of face recognition.

In this paper, we propose a computational architecture of face recognition based on evidence from cognitive research. Several recent psychophysical experiments have shown that humans process faces by a combination of configural and component information. Using an appearance-based implementation of this architecture based on low-level features and their spatial relations, we were able to model aspects of human performance found in psychophysical studies. Furthermore, results from additional computational recognition experiments show that our framework is able to achieve excellent recognition performance even under large view rotations. Our interdisciplinary study is an example of how results from cognitive research can be used to construct recognition systems with increased performance. Finally, our modeling results also make new experimental predictions that will be tested in further psychophysical studies, thus effectively closing the loop between psychophysical experimentation and computational modeling.

Area Under Curve↗

PubMed2001

Burnout and engagement at work as a function of demands and control.

OBJECTIVES: The present study was designed to test the demand-control model using indicators of both health impairment and active learning or motivation. METHODS: A total of 381 insurance company employees participated in the study. Discriminant analysis was used to examine the relationship between job demands and job control on one hand and health impairment and active learning on the other. RESULTS: The amount of demands and control could be predicted on the basis of employees' perceived health impairment (exhaustion and health complaints) and active learning (engagement and commitment). Each of the four combinations of demand and control differentially affected the perception of strain or active learning. Job demands were the most clearly related to health impairment, whereas job control was the most clearly associated with active learning. CONCLUSIONS: These findings partly contradict the demand-control model, especially with respect to the validity of the interaction between demand and control. Job demands and job control seem to initiate two essentially independent processes, and this occurrence is consistent with the recently proposed job demands-resources model.

Burnout, Professional↗

PubMed2024

Blood-based DNA methylation and exposure risk scores predict PTSD with high accuracy in military and civilian cohorts.

BACKGROUND: Incorporating genomic data into risk prediction has become an increasingly useful approach for rapid identification of individuals most at risk for complex disorders such as PTSD. Our goal was to develop and validate Methylation Risk Scores (MRS) using machine learning to distinguish individuals who have PTSD from those who do not. METHODS: Elastic Net was used to develop three risk score models using a discovery dataset (n = 1226; 314 cases, 912 controls) comprised of 5 diverse cohorts with available blood-derived DNA methylation (DNAm) measured on the Illumina Epic BeadChip. The first risk score, exposure and methylation risk score (eMRS) used cumulative and childhood trauma exposure and DNAm variables; the second, methylation-only risk score (MoRS) was based solely on DNAm data; the third, methylation-only risk scores with adjusted exposure variables (MoRSAE) utilized DNAm data adjusted for the two exposure variables. The potential of these risk scores to predict future PTSD based on pre-deployment data was also assessed. External validation of risk scores was conducted in four independent cohorts. RESULTS: The eMRS model showed the highest accuracy (92%), precision (91%), recall (87%), and f1-score (89%) in classifying PTSD using 3730 features. While still highly accurate, the MoRS (accuracy = 89%) using 3728 features and MoRSAE (accuracy = 84%) using 4150 features showed a decline in classification power. eMRS significantly predicted PTSD in one of the four independent cohorts, the BEAR cohort (beta = 0.6839, p-0.003), but not in the remaining three cohorts. Pre-deployment risk scores from all models (eMRS, beta = 1.92; MoRS, beta = 1.99 and MoRSAE, beta = 1.77) displayed a significant (p < 0.001) predictive power for post-deployment PTSD. CONCLUSION: Results, especially those from the eMRS, reinforce earlier findings that methylation and trauma are interconnected and can be leveraged to increase the correct classification of those with vs. without PTSD. Moreover, our models can potentially be a valuable tool in predicting the future risk of developing PTSD. As more data become available, including additional molecular, environmental, and psychosocial factors in these scores may enhance their accuracy in predicting the condition and, relatedly, improve their performance in independent cohorts.

DNA methylation↗

PubMed2002

Cardiovascular interactions: an interactive tutorial and mathematical model.

The maintenance of an adequate cardiac output and systemic arterial blood pressure is a complex process with intricacies that are often difficult to understand. Cardiovascular Interactions is an active learning tool that demonstrates the interactions between the functions of the heart and peripheral circulation. This learning package consists of a Lab Book, a Model, and an Information file. The Lab Book is an interactive tutorial for exploring the relative influences of parameter changes on the cardiovascular system under normal, stressful, or pathophysiological conditions. The learners are guided to predict the direction and relative magnitude of changes of key variables in the cardiovascular system, evaluate the accuracy of their predictions, and describe the cause-and-effect mechanisms involved. Consequences of heart failure, hemorrhage, exercise, and changes in intrathoracic pressure can be explored. The results obtained in the Lab Book are based on a five-compartment mathematical Model, which reflects our current understanding of the basic control of the cardiovascular system. The Model was designed to be complex enough to be realistic, yet not so complex as to be overwhelming. An Information File contains definitions and descriptions of classical physiology about key concepts, including figures, and a detailed description of the Model. Hypertext tags embedded in the Lab Book are used to access the Information File. The Cardiovascular Interactions learning package was designed to run from its CD and so does not need to be installed.

CD-I↗

PubMed1998

Quantification of microbial productivity via multi-angle light scattering and supervised learning.

This article describes the use of chemometric methods for prediction of biological parameters of cell suspensions on the basis of their light scattering profiles. Laser light is directed into a vial or flow cell containing media from the suspension. The intensity of the scattered light is recorded at 18 angles. Supervised learning methods are then used to calibrate a model relating the parameter of interest to the intensity values. Using such models opens up the possibility of estimating the biological properties of fermentor broths extremely rapidly (typically every 4 sec), and, using the flow cell, without user interaction. Our work has demonstrated the usefulness of this approach for estimation of yeast cell counts over a wide range of values (10(5)-10(9) cells mL-1), although it was less successful in predicting cell viability in such suspensions.

Biotechnology↗