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 289 records · Page 16Linked to original sources

PubMedDate not supplied

Selectional constraints: an information-theoretic model and its computational realization.

A new, information-theoretic model of selectional constraints is proposed. The strategy adopted here is a minimalist one: how far can one get making as few assumptions as possible? In keeping with that strategy, the proposed model consists of only two components: first, a fairly generic taxonomic representation of concepts, and, second, a probabilistic formalization of selectional constraints defined in terms of that taxonomy, computed on the basis of simple, observable frequencies of co-occurrence between predicates and their arguments. Unlike traditional selection restrictions, the information-theoretic approach avoids empirical problems associated with definitional theories of word meaning, accommodates the observation that semantic anomaly often appears to be a matter of degree, and provides an account of how selectional constraints can be learned. A computational implementation of the model "learns" selectional constraints from collections of naturally occurring text; the predictions of the implemented model are evaluated against judgments elicited from adult subjects, and used to explore the way that arguments are syntactically realized for a class of English verbs. The paper concludes with a discussion of the role of selectional constraints in the acquisition of verb meaning.

Adult↗

PubMed1986

Validation criteria for animal models of human mental disorders: learned helplessness as a paradigm case.

Three sets of criteria are proposed for assessing animal models of human mental disorders: predictive validity (performance in the test predicts performance in the condition being modelled), face validity (phenomenological similarity) and construct validity (theoretical rationale). The problems inherent in each of these validation procedures are discussed, and their application to the learned helplessness model of depression is examined. It is concluded that whilst the model has good predictive validity, important questions about face validity remain unanswered, and construct validity has not yet been established. The distinctions between animal models and some related experimental procedures are also discussed.

Animals↗

PubMed2006

A model-based approach for mining membrane protein crystallization trials.

MOTIVATION: Membrane proteins are known to play crucial roles in various cellular functions. Information about their function can be derived from their structure, but knowledge of these proteins is limited, as their structures are difficult to obtain. Crystallization has proved to be an essential step in the determination of macromolecular structure. Unfortunately, the bottleneck is that the crystallization process is quite complex and extremely sensitive to experimental conditions, the selection of which is largely a matter of trial and error. Even under the best conditions, it can take a large amount of time, from weeks to years, to obtain diffraction-quality crystals. Other issues include the time and cost involved in taking multiple trials and the presence of very few positive samples in a wide and largely undetermined parameter space. Therefore, any help in directing scientists' attention to the hot spots in the conceptual crystallization space would lead to increased efficiency in crystallization trials. RESULTS: This work is an application case study on mining membrane protein crystallization trials to predict novel conditions that have a high likelihood of leading to crystallization. We use suitable supervised learning algorithms to model the data-space and predict a novel set of crystallization conditions. Our preliminary wet laboratory results are very encouraging and we believe this work shows great promise. We conclude with a view of the crystallization space that is based on our results, which should prove useful for future studies in this area.

Algorithms↗

PubMed2000

Disparity tuning as simulated by a neural net.

Previous research has suggested that the processing of binocular disparity in complex cells may be described with an energy formalism. The energy formalism allows for a representation of disparity by differences in the position or in the phase of monocular receptive subfields of binocular cells, or by combination of these two types. We studied the coding of disparities with an approach complementary to previous algorithmic investigations. Since realization of these representations is probably not genetically determined but learned during ontogeny, we used backpropagation networks to study which of these three possibilities were realized within neural nets. Three types of networks were trained with noise patterns in analogy to the three types of energy models. The networks learned the task and generalized to untrained correlated noise pattern input. Outputs were broadly tuned to spatial frequency and did not respond to anti-correlated noise patterns. Although the energy model was not explicitly implemented, we could analyze the outputs of the networks using predictions of the energy formalism. After learning was completed, the model neurons preferred position shifts over phase shifts in representing disparity. We discuss the general meaning of these findings and the correspondences and deviations between the energy model, V1 neurons, and our networks.

Computer Simulation↗

PubMed2025

Deep Learning on Histologic Slides Accurately Predicts Consensus Molecular Subtypes and Spatial Heterogeneity in Colon Cancer.

Colon cancer (CC) is the third most prevalent cancer type. It is highly heterogeneous, particularly in terms of molecular profiles, which have both prognostic and predictive impacts on the treatment efficacy. However, CC treatment in adjuvant situations is currently guided solely by T and N staging. In this context, consensus molecular subtypes (CMSs) were introduced to stratify patients with CC based on molecular profiles. Recent studies have shown that CMS can be heterogeneous in CC, leading to a worse prognosis. This study focused on predicting CMS and its heterogeneity in CC using deep learning on digitized hematoxylin and eosin ± saffron-stained whole-slide images. Data and whole-slide images of 1996 patients from the PETACC-8, The Cancer Genome Atlas-COAD, and PRODIGE-13 cohorts were used. The model is trained to predict a 4-dimensional CMS vector, reflecting intratumor heterogeneity (ITH). It comprises a self-supervised model for embedding image patches into vectors and a weakly supervised model predicting CMS calls. Ground-truth CMS scores are obtained with the CMSclassifier package. Interpretability analyses are performed at the slide and patch levels. For homogeneous tumors, the model trained on PETACC-8 achieves 93.0% (±1.4%) macroaverage area under the curve in internal cross-validation and 94.4% macroaverage area under the curve in external validation over PRODIGE-13, whereas the The Cancer Genome Atlas-COAD model reaches 85.4% (±3.0%) in cross-validation and 92.4% over PRODIGE-13. The trained models also provide spatial distributions of CMS across tumor slides and associate specific histologic features with each CMS. Finally, the models are able to predict ITH. The results show that a deep learning model trained on routine histology slides is capable of providing an efficient and robust method for predicting CMS and characterizing a patient's ITH, paving the way for the routine consideration of CMS/ITH in clinical decision making in the adjuvant setting.

Humans↗

PubMed2006

Frontal responses during learning predict vulnerability to the psychotogenic effects of ketamine: linking cognition, brain activity, and psychosis.

CONTEXT: Establishing a neurobiological account of delusion formation that links cognitive processes, brain activity, and symptoms is important to furthering our understanding of psychosis. OBJECTIVE: To explore a theoretical model of delusion formation that implicates prediction error-dependent associative learning processes in a pharmacological functional magnetic resonance imaging study using the psychotomimetic drug ketamine. DESIGN: Within-subject, randomized, placebo-controlled study. SETTING: Hospital-based clinical research facility, Addenbrooke's Hospital, Cambridge, England. The work was completed within the Wellcome Trust and Medical Research Council Behavioral and Clinical Neuroscience Institute, Cambridge. PARTICIPANTS: Fifteen healthy, right-handed volunteers (8 of whom were male) with a mean +/- SD age of 29 +/- 7 years and a mean +/- SD predicted full-scale IQ of 113 +/- 4 were recruited from within the local community by advertisement. INTERVENTIONS: Subjects were given low-dose ketamine (100 ng/mL of plasma) or placebo while performing a causal associative learning task during functional magnetic resonance imaging. In a separate session outside the scanner, the dose was increased (to 200 ng/mL of plasma) and subjects underwent a structured clinical interview. MAIN OUTCOME MEASURES: Brain activation, blood plasma levels of ketamine, and scores from psychiatric ratings scales (Brief Psychiatric Ratings Scale, Present State Examination, and Clinician-Administered Dissociative States Scale). RESULTS: Low-dose ketamine perturbs error-dependent learning activity in the right frontal cortex (P = .03). High-dose ketamine produces perceptual aberrations (P = .01) and delusion-like beliefs (P = .007). Critically, subjects showing the highest degree of frontal activation with placebo show the greatest occurrence of drug-induced perceptual aberrations (P = .03) and ideas or delusions of reference (P = .04). CONCLUSIONS: These findings relate aberrant prediction error-dependent associative learning to referential ideas and delusions via a perturbation of frontal cortical function. They are consistent with a model of delusion formation positing disruptions in error-dependent learning.

Adult↗

PubMed2000

Machine learning for survival analysis: a case study on recurrence of prostate cancer.

Machine learning techniques have recently received considerable attention, especially when used for the construction of prediction models from data. Despite their potential advantages over standard statistical methods, like their ability to model non-linear relationships and construct symbolic and interpretable models, their applications to survival analysis are at best rare, primarily because of the difficulty to appropriately handle censored data. In this paper we propose a schema that enables the use of classification methods--including machine learning classifiers--for survival analysis. To appropriately consider the follow-up time and censoring, we propose a technique that, for the patients for which the event did not occur and have short follow-up times, estimates their probability of event and assigns them a distribution of outcome accordingly. Since most machine learning techniques do not deal with outcome distributions, the schema is implemented using weighted examples. To show the utility of the proposed technique, we investigate a particular problem of building prognostic models for prostate cancer recurrence, where the sole prediction of the probability of event (and not its probability dependency on time) is of interest. A case study on preoperative and postoperative prostate cancer recurrence prediction shows that by incorporating this weighting technique the machine learning tools stand beside modern statistical methods and may, by inducing symbolic recurrence models, provide further insight to relationships within the modeled data.

Artificial Intelligence↗

PubMed2007

Rapid learning of syllable classes from a perceptually continuous speech stream.

To learn a language, speakers must learn its words and rules from fluent speech; in particular, they must learn dependencies among linguistic classes. We show that when familiarized with a short artificial, subliminally bracketed stream, participants can learn relations about the structure of its words, which specify the classes of syllables occurring in first and last word positions. By studying the effect of familiarization length, we compared the general predictions of associative theories of learning and those of models postulating separate mechanisms for quickly extracting the word structure and for tracking the syllable distribution in the stream. As predicted by the dual-mechanism model, the preference for structurally correct items was negatively correlated with the familiarization length. This result is difficult to explain by purely associative schemes; an extensive set of neural network simulations confirmed this difficulty. Still, we show that powerful statistical computations operating on the stream are available to our participants, as they are sensitive to co-occurrence statistics among non-adjacent syllables. We suggest that different learning mechanisms analyze speech on-line: A rapid mechanism extracting structural information about the stream, and a slower mechanism detecting statistical regularities among the items occurring in it.

Association Learning↗

PubMed2025

Automated Machine Learning Tools to Build Regression Models for Schizosaccharomyces pombe Omics Data.

Machine learning is a powerful tool for analyzing biological data and making useful predictions. The surge of biological data from high-throughput omics technologies has raised the need for modeling approaches capable of tackling such amounts of data, which is pivotal to understanding the nature of complex molecular systems. Here, we show how to construct a simple model using automated machine learning (AutoML) to predict protein abundance in Schizosaccharomyces pombe, using data obtained from codon usage bias and quantitative proteomics.

Machine Learning↗

PubMed2025

The signed two-space proximity model for learning representations in protein-protein interaction networks.

MOTIVATION: Accurately predicting complex protein-protein interactions (PPIs) is crucial for decoding biological processes, from cellular functioning to disease mechanisms. However, experimental methods for determining PPIs are computationally expensive. Thus, attention has been recently drawn to machine learning approaches. Furthermore, insufficient effort has been made toward analyzing signed PPI networks, which capture both activating (positive) and inhibitory (negative) interactions. To accurately represent biological relationships, we present the Signed Two-Space Proximity Model (S2-SPM) for signed PPI networks, which explicitly incorporates both types of interactions, reflecting the complex regulatory mechanisms within biological systems. This is achieved by leveraging two independent latent spaces to differentiate between positive and negative interactions while representing protein similarity through proximity in these spaces. Our approach also enables the identification of archetypes representing extreme protein profiles. RESULTS: S2-SPM's superior performance in predicting the presence and sign of interactions in SPPI networks is demonstrated in link prediction tasks against relevant baseline methods. Additionally, the biological prevalence of the identified archetypes is confirmed by an enrichment analysis of Gene Ontology (GO) terms, which reveals that distinct biological tasks are associated with archetypal groups formed by both interactions. This study is also validated regarding statistical significance and sensitivity analysis, providing insights into the functional roles of different interaction types. Finally, the robustness and consistency of the extracted archetype structures are confirmed using the Bayesian Normalized Mutual Information (BNMI) metric, proving the model's reliability in capturing meaningful SPPI patterns. AVAILABILITY: S2-SPM is implemented and freely available under the MIT license at https://github.com/Nicknakis/S2SPM.

Protein Interaction Mapping↗

PubMed2004

Predicting genetic regulatory response using classification.

MOTIVATION: Studying gene regulatory mechanisms in simple model organisms through analysis of high-throughput genomic data has emerged as a central problem in computational biology. Most approaches in the literature have focused either on finding a few strong regulatory patterns or on learning descriptive models from training data. However, these approaches are not yet adequate for making accurate predictions about which genes will be up- or down-regulated in new or held-out experiments. By introducing a predictive methodology for this problem, we can use powerful tools from machine learning and assess the statistical significance of our predictions. RESULTS: We present a novel classification-based method for learning to predict gene regulatory response. Our approach is motivated by the hypothesis that in simple organisms such as Saccharomyces cerevisiae, we can learn a decision rule for predicting whether a gene is up- or down-regulated in a particular experiment based on (1) the presence of binding site subsequences ('motifs') in the gene's regulatory region and (2) the expression levels of regulators such as transcription factors in the experiment ('parents'). Thus, our learning task integrates two qualitatively different data sources: genome-wide cDNA microarray data across multiple perturbation and mutant experiments along with motif profile data from regulatory sequences. We convert the regression task of predicting real-valued gene expression measurements to a classification task of predicting +1 and -1 labels, corresponding to up- and down-regulation beyond the levels of biological and measurement noise in microarray measurements. The learning algorithm employed is boosting with a margin-based generalization of decision trees, alternating decision trees. This large-margin classifier is sufficiently flexible to allow complex logical functions, yet sufficiently simple to give insight into the combinatorial mechanisms of gene regulation. We observe encouraging prediction accuracy on experiments based on the Gasch S.cerevisiae dataset, and we show that we can accurately predict up- and down-regulation on held-out experiments. We also show how to extract significant regulators, motifs and motif-regulator pairs from the learned models for various stress responses. Our method thus provides predictive hypotheses, suggests biological experiments, and provides interpretable insight into the structure of genetic regulatory networks. AVAILABILITY: The MLJava package is available upon request to the authors. Supplementary: Additional results are available from http://www.cs.columbia.edu/compbio/geneclass

Binding Sites↗

PubMed1989

Causal explanations and emotional health of women during divorce.

This study investigated (a) relationships between women's causal explanations for divorce and their present emotional health, and (b) the clinical usefulness of the Personal Stress Inventory (Ireton, 1980) as a stress assessment tool. The convenience sample consisted of 36 women ending a first marriage. Subjects were interviewed using the Tennessee Self-Concept Scale (Fitts, 1965), the Personal Stress Inventory, and a causal explanations questionnaire. Results indicated that causal explanations did predict self-esteem and emotional distress under conditions suggested by the reformulated learned helplessness model. The Personal Stress Inventory includes an emotional distress subscale that predicted self-esteem, self-perceptions of coping ability, and overall concerns about wellness/energy.

Adaptation, Psychological↗

PubMed2025

Anticancer drug response prediction integrating multi-omics pathway-based difference features and multiple deep learning techniques.

Individualized prediction of cancer drug sensitivity is of vital importance in precision medicine. While numerous predictive methodologies for cancer drug response have been proposed, the precise prediction of an individual patient's response to drug and a thorough understanding of differences in drug responses among individuals continue to pose significant challenges. This study introduced a deep learning model PASO, which integrated transformer encoder, multi-scale convolutional networks and attention mechanisms to predict the sensitivity of cell lines to anticancer drugs, based on the omics data of cell lines and the SMILES representations of drug molecules. First, we use statistical methods to compute the differences in gene expression, gene mutation, and gene copy number variations between within and outside biological pathways, and utilized these pathway difference values as cell line features, combined with the drugs' SMILES chemical structure information as inputs to the model. Then the model integrates various deep learning technologies multi-scale convolutional networks and transformer encoder to extract the properties of drug molecules from different perspectives, while an attention network is devoted to learning complex interactions between the omics features of cell lines and the aforementioned properties of drug molecules. Finally, a multilayer perceptron (MLP) outputs the final predictions of drug response. Our model exhibits higher accuracy in predicting the sensitivity to anticancer drugs comparing with other methods proposed recently. It is found that PARP inhibitors, and Topoisomerase I inhibitors were particularly sensitive to SCLC when analyzing the drug response predictions for lung cancer cell lines. Additionally, the model is capable of highlighting biological pathways related to cancer and accurately capturing critical parts of the drug's chemical structure. We also validated the model's clinical utility using clinical data from The Cancer Genome Atlas. In summary, the PASO model suggests potential as a robust support in individualized cancer treatment. Our methods are implemented in Python and are freely available from GitHub (https://github.com/queryang/PASO).

Deep Learning↗

PubMed2002

The quantitative evaluation of functional neuroimaging experiments: mutual information learning curves.

Learning curves are presented as an unbiased means for evaluating the performance of models for neuroimaging data analysis. The learning curve measures the predictive performance in terms of the generalization or prediction error as a function of the number of independent examples (e.g., subjects) used to determine the parameters in the model. Cross-validation resampling is used to obtain unbiased estimates of a generic multivariate Gaussian classifier, for training set sizes from 2 to 16 subjects. We apply the framework to four different activation experiments, in this case [(15)O]water data sets, although the framework is equally valid for multisubject fMRI studies. We demonstrate how the prediction error can be expressed as the mutual information between the scan and the scan label, measured in units of bits. The mutual information learning curve can be used to evaluate the impact of different methodological choices, e.g., classification label schemes, preprocessing choices. Another application for the learning curve is to examine the model performance using bias/variance considerations enabling the researcher to determine if the model performance is limited by statistical bias or variance. We furthermore present the sensitivity map as a general method for extracting activation maps from statistical models within the probabilistic framework and illustrate relationships between mutual information and pattern reproducibility as derived in the NPAIRS framework described in a companion paper.

Adult↗

PubMed2006

Dynamics of memory representations in networks with novelty-facilitated synaptic plasticity.

The ability to associate some stimuli while differentiating between others is an essential characteristic of biological memory. Theoretical models identify memories as attractors of neural network activity, with learning based on Hebb-like synaptic modifications. Our analysis shows that when network inputs are correlated, this mechanism results in overassociations, even up to several memories "merging" into one. To counteract this tendency, we introduce a learning mechanism that involves novelty-facilitated modifications, accentuating synaptic changes proportionally to the difference between network input and stored memories. This mechanism introduces a dependency of synaptic modifications on previously acquired memories, enabling a wide spectrum of memory associations, ranging from absolute discrimination to complete merging. The model predicts that memory representations should be sensitive to learning order, consistent with recent psychophysical studies of face recognition and electrophysiological experiments on hippocampal place cells. The proposed mechanism is compatible with a recent biological model of novelty-facilitated learning in hippocampal circuitry.

Animals↗

PubMed2000

Distance-based reconstruction of tree models for oncogenesis.

Comparative genomic hybridization (CGH) is a laboratory method to measure gains and losses in the copy number of chromosomal regions in tumor cells. It is hypothesized that certain DNA gains and losses are related to cancer progression and that the patterns of these changes are relevant to the clinical consequences of the cancer. It is therefore of interest to develop models which predict the occurrence of these events, as well as techniques for learning such models from CGH data. We continue our study of the mathematical foundations for inferring a model of tumor progression from a CGH data set that we started in Desper et al. (1999). In that paper, we proposed a class of probabilistic tree models and showed that an algorithm based on maximum-weight branching in a graph correctly infers the topology of the tree, under plausible assumptions. In this paper, we extend that work in the direction of the so-called distance-based trees, in which events are leaves of the tree, in the style of models common in phylogenetics. Then we show how to reconstruct the distance-based trees using tree-fitting algorithms developed by researchers in phylogenetics. The main advantages of the distance-based models are that 1) they represent information about co-occurrences of all pairs of events, instead of just some pairs, 2) they allow quantitative predictions about which events occur early in tumor progression, and 3) they bring into play the extensive methodology and software developed in the context of phylogenetics. We illustrate the distance-based tree method and how it complements the branching tree method, with a CGH data set for renal cancer.

Algorithms↗

PubMed2001

Seeing mum drinking a 'light' product: is social learning a stronger determinant of taste preference acquisition than caloric conditioning?

OBJECTIVE: It was examined whether caloric conditioning or social learning strategies dominate in taste preference acquisition in children. The caloric learning paradigm predicts that eating or drinking artificially sweetened products, which deliver virtually no energy, will not lead to a taste preference whereas the social learning paradigm predicts that seeing important others modelling the eating and drinking of these 'light' products will induce a preference for the taste of light products in the child. DESIGN: In a 2 x 2 between subjects factorial design, the amount of energy and social modelling was varied. SETTING: The study was undertaken at primary schools in Maastricht, The Netherlands. SUBJECTS: Forty-five children participated and six children dropped out. The 39 children who completed the study (14 boys and 25 girls) had a mean age of 67 months (range 51--81, s.d. 5.6). INTERVENTIONS: Each subject took part in nine conditioning trials with an individually selected tasting yoghurt which was not preferred very much at the pre-test. RESULTS: The children in the combined caloric and social condition showed an increase in their preference for the conditioned taste which was larger than a regression-to-the-mean effect (P=0.007), whereas children in the other groups did not. CONCLUSION: Caloric and social learning combined, ie modelling the consumption of energy-rich foods or drinks, is the best way to establish taste preferences. Children more easily learn a preference for energy-rich food that is eaten by significant others than for food that is low in energy and eaten by significant others.

Child↗

PubMed2000

Volume of focal brain lesions and hippocampal formation in relation to memory function after closed head injury in children.

OBJECTIVES: (1) A study of verbal learning and memory in children who had sustained a closed head injury (CHI) at least 3 months earlier. (2) To relate memory function to focal brain lesion and hippocampal formation volumes using morphometric analysis of MRI. METHODS: A group of 245 children who had been admitted to hospital for CHI graded by the Glasgow coma scale (GCS), including 161 patients with severe and 84 with mild CHI completed the California verbal learning test (CVLT) and underwent MRI which was analysed for focal brain lesion volume independently of memory test data. Brain MRI with 1.5 mm coronal slices obtained in subsets of 25 patients with severe and 25 patients with mild CHI were analysed for hippocampal formation volume. Interoperator reliability in morphometry was satisfactory. RESULTS: Severity of CHI and age at study significantly affected memory performance. Regression analysis showed that bifrontal, left frontal, and right frontal lesion volumes incremented prediction of various learning and memory indices after entering the GCS score and age into the model. Extrafrontal lesion volume did not contribute to predicting memory performance. CONCLUSIONS: Prefrontal lesions contribute to residual impairment of learning and memory after severe CHI in children. Although effects of CHI on hippocampal formation volume might be difficult to demonstrate in non-fatal paediatric CHI, further investigation using functional brain imaging could potentially demonstrate hippocampal dysfunction.

Adolescent↗