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 1,477 records · Page 82Linked to original sources

PubMedDate not supplied

Estimation of the aqueous solubility of organic molecules by the group contribution approach.

Several group contribution methods to estimate the aqueous solubility of organic molecules are proposed and evaluated for their ability to predict the water solubility of new molecules. The learning set consisted of 1168 organic compounds with experimental data taken from the literature after critical evaluation. The best method, based on a new fragment atom scheme, leads to a squared correlation coefficient of 0.95 and an average absolute calculation error of 0.50 log unit, which is superior to other group contribution methods currently available. One of the advantages of this model is that it has upper and lower limits so that the predicted solubilities cannot be unrealistily high or low.

Journal Article↗

PubMed2026

Unveiling tumor heterogeneity by single cell RNA-sequencing: From basic considerations to clinical applications.

Tumor heterogeneity-encompassing diverse cellular phenotypes, genomic alterations, and microenvironmental contexts-is a principal barrier to effective cancer therapy. Single-cell RNA sequencing (scRNA-seq) has transformed our ability to resolve this complexity by capturing transcriptomes at single-cell resolution. Here, we review the technical foundations required for high-quality scRNA-seq studies. We then trace the evolution of scRNA-seq platforms from manual micromanipulation to high-throughput systems, and describe the computational pipelines that enable reliable data interpretation. The application of scRNA-seq is exemplarily shown in the context of lung cancer, where single-cell profiling has revealed (i) the clonal and sub-clonal architecture of tumors, (ii) extensive remodeling of the immune microenvironment, iii) key mechanisms underlying resistance to targeted agents and immune-checkpoint blockade, and (iv) the dynamics of neo-antigen-specific T-cell responses. Integrating machine-learning techniques-such as deep-learning classifiers and graph-based models-with single-cell transcriptomic data has markedly sped up biomarker discovery, produced more accurate risk-stratification scores, and enabled the generation of patient-specific therapeutic predictions. We surveyed the major trial registry ClinicalTrials.gov and identified ∼380 ongoing or completed studies that explicitly incorporate scRNA-seq as a correlative or pharmacodynamic endpoint. Overall, the analysis shows that scRNA-seq becomes an increasingly important component of modern trials, providing high-resolution cellular and molecular readouts that complement conventional imaging and bulk-omics endpoints. While key challenges remain, ranging from costs, scalability and need for rigorous validation before routine clinical deployment, ongoing technological advances continue to expand the potential of scRNA-seq as a cornerstone of precision medicine.

Humans↗

PubMed1999

What Can Studies of Problem-Based Learning Tell Us? Synthesizing and Modeling PBL Effects on National Board of Medical Examination Performance: Hierarchical Linear Modeling Meta-Analytic Approach.

This meta-analytic study 1) examines outcomes from primary research comparing the impact of problem-based learning (PBL) and traditional curricula on medical students' National Board of Medical Examiners (NBME) I and II performance and 2) explores the use of Hierarchical Linear Modeling (HLM) in identifying study and PBL implementation characteristics that predict these outcomes. NBME I and II overall scores were used as dependent variables, with study design (randomized/non-randomized), publication year, and PBL experience (number of years since the adoption of PBL as an instructional method at the time of the reported NBME results) as explanatory variables. Initial unconditional HLM (i.e., without inclusion of potential explanatory variables) results indicated PBL curricula had: 1) a positive, albeit not statistically significant, effect on NBME II, with an average effect size of 0.16; and 2) a negative effect on NBME I, with an average effect size of -0.15. Including explanatory variables in HLM analyses explained additional variability in NBME I effect sizes, and identified study design (gamma^1 = 0.82, p = 0.01) and PBL experience (gamma^3 = 0.07, p = 0.02) as significant predictors of positive PBL effects. Publication year, in contrast, had significant negative effects (gamma^2 = -0.06, p = 0.02). This study explained variability in NBME I effect sizes and clarified the impact of PBL discerned in previous reviews. Implications for future research include the need to examine curriculum features that operationally define PBL, as well as extend the consideration of outcomes on which PBL's impact can be examined.

Journal Article↗

PubMed2002

Role of experience and oscillations in transforming a rate code into a temporal code.

In the vast majority of brain areas, the firing rates of neurons, averaged over several hundred milliseconds to several seconds, can be strongly modulated by, and provide accurate information about, properties of their inputs. This is referred to as the rate code. However, the biophysical laws of synaptic plasticity require precise timing of spikes over short timescales (<10 ms). Hence it is critical to understand the physiological mechanisms that can generate precise spike timing in vivo, and the relationship between such a temporal code and a rate code. Here we propose a mechanism by which a temporal code can be generated through an interaction between an asymmetric rate code and oscillatory inhibition. Consistent with the predictions of our model, the rate and temporal codes of hippocampal pyramidal neurons are highly correlated. Furthermore, the temporal code becomes more robust with experience. The resulting spike timing satisfies the temporal order constraints of hebbian learning. Thus, oscillations and receptive field asymmetry may have a critical role in temporal sequence learning.

Action Potentials↗

PubMed2006

Inferring causality assessments from predictive responses: cue interaction without cue competition.

The authors criticize the use of participants' predictive responses during a learning phase as a measure of causal assessments. Simulations demonstrate that a general aim to minimize error as required in the prediction task will produce results in accordance with those observed, in particular apparent cue interaction effects. It is argued that measures estimated from prediction responses do not reflect causal ratings, but are side-effects of learning explained by adaptation in strategy to changes in presented cell frequencies. The results are reinterpreted to be in line with a causal model view, not requiring dual processes or cue competition of lower level associative processes.

Association Learning↗

PubMed2005

Respiratory motion prediction by using the adaptive neuro fuzzy inference system (ANFIS).

The quality of radiation therapy delivered for treating cancer patients is related to set-up errors and organ motion. Due to the margins needed to ensure adequate target coverage, many breast cancer patients have been shown to develop late side effects such as pneumonitis and cardiac damage. Breathing-adapted radiation therapy offers the potential for precise radiation dose delivery to a moving target and thereby reduces the side effects substantially. However, the basic requirement for breathing-adapted radiation therapy is to track and predict the target as precisely as possible. Recent studies have addressed the problem of organ motion prediction by using different methods including artificial neural network and model based approaches. In this study, we propose to use a hybrid intelligent system called ANFIS (the adaptive neuro fuzzy inference system) for predicting respiratory motion in breast cancer patients. In ANFIS, we combine both the learning capabilities of a neural network and reasoning capabilities of fuzzy logic in order to give enhanced prediction capabilities, as compared to using a single methodology alone. After training ANFIS and checking for prediction accuracy on 11 breast cancer patients, it was found that the RMSE (root-mean-square error) can be reduced to sub-millimetre accuracy over a period of 20 s provided the patient is assisted with coaching. The average RMSE for the un-coached patients was 35% of the respiratory amplitude and for the coached patients 6% of the respiratory amplitude.

Algorithms↗

PubMed2005

Survival ensembles.

We propose a unified and flexible framework for ensemble learning in the presence of censoring. For right-censored data, we introduce a random forest algorithm and a generic gradient boosting algorithm for the construction of prognostic and diagnostic models. The methodology is utilized for predicting the survival time of patients suffering from acute myeloid leukemia based on clinical and genetic covariates. Furthermore, we compare the diagnostic capabilities of the proposed censored data random forest and boosting methods, applied to the recurrence-free survival time of node-positive breast cancer patients, with previously published findings.

Algorithms↗

PubMed2005

Gene expression profiles predict early relapse in ovarian cancer after platinum-paclitaxel chemotherapy.

PURPOSE: Women with advanced epithelial ovarian cancer are routinely treated with platinum-paclitaxel chemotherapy following cytoreductive surgery, yet only approximately 20% achieve long-term disease-free survival. We hypothesized that differences in gene expression before treatment could distinguish patients with short versus long time to recurrence after administration of platinum-paclitaxel combination chemotherapy. EXPERIMENTAL DESIGN: To test this hypothesis, gene expression profiling of 79 primary surgically resected tumors from women with advanced-stage, high-grade epithelial ovarian cancer was done using cDNA microarrays containing 30,721 genes. Supervised learning algorithms were applied in an effort to develop a binary classifier that could discriminate women at risk for early (< or =21 months) versus late (>21 months) relapse after initial chemotherapy. RESULTS: A 14-gene predictive model was developed using a set of training samples (n = 51) and subsequently tested using an independent set of test samples (n = 28). This model correctly predicted the outcome of 24 of the 28 test samples (86% accuracy) with 95% positive predictive value for early relapse. CONCLUSIONS: Predictive markers for early recurrence can be identified for platinum-paclitaxel combination chemotherapy in primary ovarian carcinoma. The proposed 14-gene model requires further validation.

Adult↗

PubMed1998

Using classification tree and logistic regression methods to diagnose myocardial infarction.

Early and accurate diagnosis of myocardial infarction (MI) in patients who present to the Emergency Room (ER) complaining of chest pain is an important problem in emergency medicine. A number of decision aids have been developed to assist with this problem but have not achieved general use. Machine learning techniques, including classification tree and logistic regression (LR) methods, have the potential to create simple but accurate decision aids. Both a classification tree (FT Tree) and an LR model (FT LR) have been developed to predict the probability that a patient with chest pain is having an MI based solely upon data available at time of presentation to the ER. Training data came from a data set collected in Edinburgh, Scotland. Each model was then tested on a separate Edinburgh data set, as well as on a data set from a different hospital in Sheffield, England. Previously published models, the Goldman classification tree[1] and Kennedy LR equation[2], were evaluated on the same test data sets. On the Edinburgh test set, results showed that the FT Tree, FT LR, and Kennedy LR performed equally well, with ROC curve areas of 94.04%, 94.28%, and 94.30%, respectively, while the Goldman Tree's performance was significantly poorer, with an area of 84.03%. The difference in ROC areas between the first three models and the Goldman model is significant beyond the 0.0001 level. On the Sheffield test set, results showed that the FT Tree, FT LR, and Kennedy LR ROC areas were not significantly different (p > = 0.17), while the FT Tree again outperformed the Goldman Tree (p = 0.006). Unlike previous work[3], this study indicates that classification trees, which have certain advantages over LR models, may perform as well as LR models in the diagnosis of patients with MI.

Algorithms↗

PubMed2000

Optimal amnesic probabilistic automata or how to learn and classify proteins in linear time and space.

Statistical modeling of sequences is a central paradigm of machine learning that finds multiple uses in computational molecular biology and many other domains. The probabilistic automata typically built in these contexts are subtended by uniform, fixed-memory Markov models. In practice, such automata tend to be unnecessarily bulky and computationally imposing both during their synthesis and use. Recently, D. Ron, Y. Singer, and N. Tishby built much more compact, tree-shaped variants of probabilistic automata under the assumption of an underlying Markov process of variable memory length. These variants, called Probabilistic Suffix Trees (PSTs) were subsequently adapted by G. Bejerano and G. Yona and applied successfully to learning and prediction of protein families. The process of learning the automaton from a given training set S of sequences requires theta(Ln2) worst-case time, where n is the total length of the sequences in S and L is the length of a longest substring of S to be considered for a candidate state in the automaton. Once the automaton is built, predicting the likelihood of a query sequence of m characters may cost time theta(m2) in the worst case. The main contribution of this paper is to introduce automata equivalent to PSTs but having the following properties: Learning the automaton, for any L, takes O (n) time. Prediction of a string of m symbols by the automaton takes O (m) time. Along the way, the paper presents an evolving learning scheme and addresses notions of empirical probability and related efficient computation, which is a by-product possibly of more general interest.

Algorithms↗

PubMed2005

Effects of ongoing task context and target typicality on prospective memory performance: the importance of associative cueing.

Two experiments examined whether prospective memory performance is influenced by contextual cues. In our automatic activation model, any information available at encoding and retrieval should aid recall of the prospective task. The first experiment demonstrated an effect of the ongoing task context; performance was better when information about the ongoing task present at retrieval was available at encoding. Performance was also improved by a strong association between the prospective memory target as it was presented at retrieval and the intention as it was encoded. Experiment 2 demonstrated boundary conditions of the ongoing task context effect, which implicate the association between the ongoing and prospective tasks formed at encoding as the source of the context effect. The results of this study are consistent with predictions based on automatic activation of intentions.

Adolescent↗

PubMed2006

The fear-avoidance model of chronic pain: validation and age analysis using structural equation modeling.

The cognitive-behavioral, fear-avoidance (FA) model of chronic pain (Vlaeyen JWS, Kole-Snijders AMJ, Boeren RGB, van Eek H. Fear of movement/(re)injury in chronic low back pain and its relation to behavioral performance. Pain 1995a;62:363-72) has found broad empirical support, but its multivariate, predictive relationships have not been uniformly validated. Applicability of the model across age groups of chronic pain patients has also not been tested. Goals of this study were to validate the predictive relationships of the multivariate FA model using structural equation modeling and to evaluate the factor structure of the Tampa Scale of Kinesiophobia (TSK), levels of pain-related fear, and fit of the FA model across three age groups: young (< or =40), middle-aged (41-54), and older (> or =55) adults. A heterogeneous sample of 469 chronic pain patients provided ratings of catastrophizing, pain-related fear, depression, perceived disability, and pain severity. Using a confirmatory approach, a 2-factor, 13-item structure of the TSK provided the best fit and was invariant across age groups. Older participants were found to have lower TSK fear scores than middle-aged participants for both factors (FA, Harm). A modified version of the Vlaeyen JWS, Kole-Snijders AMJ, Boeren RGB, van Eek H (Fear of movement/(re)injury in chronic low back pain and its relation to behavioral performance. Pain 1995a;62:363-72.) FA model provided a close fit to the data (chi(2)(29)=42.0, p>0.05, GFI=0.98, AGFI=0.97, CFI=0.99, RMSEA=0.031 (90% CI 0.000-0.050), p close fit=0.95). Multigroup analyses revealed significant differences in structural weights for older vs. middle-aged participants. For older chronic pain patients, a stronger mediating role for pain-related fear was supported. Results are consistent with a FA model of chronic pain, while indicating some important age group differences in this model and in levels of pain-related fear. Longitudinal testing of the multivariate model is recommended.

Adolescent↗

PubMed2007

Separate brain regions code for salience vs. valence during reward prediction in humans.

Predicting rewards and avoiding aversive conditions is essential for survival. Recent studies using computational models of reward prediction implicate the ventral striatum in appetitive rewards. Whether the same system mediates an organism's response to aversive conditions is unclear. We examined the question using fMRI blood oxygen level-dependent measurements while healthy volunteers were conditioned using appetitive and aversive stimuli. The temporal difference learning algorithm was used to estimate reward prediction error. Activations in the ventral striatum were robustly correlated with prediction error, regardless of the valence of the stimuli, suggesting that the ventral striatum processes salience prediction error. In contrast, the orbitofrontal cortex and anterior insula coded for the differential valence of appetitive/aversive stimuli. Given its location at the interface of limbic and motor regions, the ventral striatum may be critical in learning about motivationally salient stimuli, regardless of valence, and using that information to bias selection of actions.

Adult↗

PubMed2006

Predicting transmembrane beta-barrels and interstrand residue interactions from sequence.

Transmembrane beta-barrel (TMB) proteins are embedded in the outer membrane of Gram-negative bacteria, mitochondria, and chloroplasts. The cellular location and functional diversity of beta-barrel outer membrane proteins (omps) makes them an important protein class. At the present time, very few nonhomologous TMB structures have been determined by X-ray diffraction because of the experimental difficulty encountered in crystallizing transmembrane proteins. A novel method using pairwise interstrand residue statistical potentials derived from globular (nonouter membrane) proteins is introduced to predict the supersecondary structure of transmembrane beta-barrel proteins. The algorithm transFold employs a generalized hidden Markov model (i.e., multitape S-attribute grammar) to describe potential beta-barrel supersecondary structures and then computes by dynamic programming the minimum free energy beta-barrel structure. Hence, the approach can be viewed as a "wrapping" component that may capture folding processes with an initiation stage followed by progressive interaction of the sequence with the already-formed motifs. This approach differs significantly from others, which use traditional machine learning to solve this problem, because it does not require a training phase on known TMB structures and is the first to explicitly capture and predict long-range interactions. TransFold outperforms previous programs for predicting TMBs on smaller (<or=200 residues) proteins and matches their performance for straightforward recognition of longer proteins. An exception is for multimeric porins where the algorithm does perform well when an important functional motif in loops is initially identified. We verify our simulations of the folding process by comparing them with experimental data on the functional folding of TMBs. A Web server running transFold is available and outputs contact predictions and locations for sequences predicted to form TMBs.

Amino Acid Sequence↗

PubMed2005

Cell division theory and individual-based modeling of microbial lag: part I. The theory of cell division.

This series of two papers deals with the theory of cell division and its implementation in an individual-based modeling framework. In this first part, the theory of cell division is studied on an individual-based level in order to learn more about the mechanistic principles behind microbial lag phenomena. While some important literature on cell division theory dates from 30 to 40 years ago, until now it has hardly been introduced in the field of predictive microbiology. Yet, it provides a large amount of information on how cells likely respond to changing environmental conditions. On the basis of this theory, a general theory on microbial lag behavior caused by a combination of medium and/or temperature changes has been developed in this paper. The proposed theory then forms the basis for a critical evaluation of existing modeling concepts for microbial lag in predictive microbiology. First of all, a more thorough definition can be formulated to define the lag time lambda and the previously only vaguely defined physiological state of the cells in terms of mechanistically defined parameters like cell mass, RNA or protein content, specific growth rate and time to perform DNA replication and cell division. On the other hand, existing predictive models are evaluated with respect to the newly developed theory. For the model of , a certain fitting parameter can also be related to physically meaningful parameters while for the model of [Augustin, J.-C., Rosso, L., Carlier, V.A. 2000. A model describing the effect of temperature history on lag time for Listeria monocytogenes. Int. J. Food Microbiol. 57, 169-181] a new, mechanistically based, model structure is proposed. A restriction of the proposed theory is that it is only valid for situations where biomass growth responds instantly to an environment change. The authors are aware of the fact that this assumption is not generally acceptable. Lag in biomass can be caused, for example, by a delayed synthesis of some essential growth factor (e.g., enzymes). In the second part of this series of papers [Dens, E.J., Bernaerts, K., Standaert, A.R., Kreft, J.-U., Van Impe, J.F., this issue. Cell division theory and individual-based modeling of microbial lag: part II. Modeling lag phenomena induced by temperature shifts. Int. J. Food Microbiol], the theory of cell division is implemented in an individual-based simulation program and extended to account for lags in biomass growth. In conclusion, the cell division theory applied to microbial populations in dynamic medium and/or temperature conditions provides a useful framework to analyze microbial lag behavior.

Algorithms↗

PubMed2005

Linear regression models for solvent accessibility prediction in proteins.

The relative solvent accessibility (RSA) of an amino acid residue in a protein structure is a real number that represents the solvent exposed surface area of this residue in relative terms. The problem of predicting the RSA from the primary amino acid sequence can therefore be cast as a regression problem. Nevertheless, RSA prediction has so far typically been cast as a classification problem. Consequently, various machine learning techniques have been used within the classification framework to predict whether a given amino acid exceeds some (arbitrary) RSA threshold and would thus be predicted to be "exposed," as opposed to "buried." We have recently developed novel methods for RSA prediction using nonlinear regression techniques which provide accurate estimates of the real-valued RSA and outperform classification-based approaches with respect to commonly used two-class projections. However, while their performance seems to provide a significant improvement over previously published approaches, these Neural Network (NN) based methods are computationally expensive to train and involve several thousand parameters. In this work, we develop alternative regression models for RSA prediction which are computationally much less expensive, involve orders-of-magnitude fewer parameters, and are still competitive in terms of prediction quality. In particular, we investigate several regression models for RSA prediction using linear L1-support vector regression (SVR) approaches as well as standard linear least squares (LS) regression. Using rigorously derived validation sets of protein structures and extensive cross-validation analysis, we compare the performance of the SVR with that of LS regression and NN-based methods. In particular, we show that the flexibility of the SVR (as encoded by metaparameters such as the error insensitivity and the error penalization terms) can be very beneficial to optimize the prediction accuracy for buried residues. We conclude that the simple and computationally much more efficient linear SVR performs comparably to nonlinear models and thus can be used in order to facilitate further attempts to design more accurate RSA prediction methods, with applications to fold recognition and de novo protein structure prediction methods.

Amino Acids↗

PubMed1998

Analysis of a correlation-based model for the development of orientation-selective receptive fields in the visual cortex.

We analyse a model for the development of orientation-selective receptive fields of simple cells in a locally connected network of cortical neurons. The Hebbian learning rule that underlies the development is described by a linear differential equation. The structure of the emerging cortical map can be predicted by deriving the eigenfunctions corresponding to the leading eigenvalues of the associated matrix. We show that the receptive fields have the typical form of a wavelet. Mathematically, receptive fields are given by a Hermitian polynomial with Gaussian cut-off and a phase factor. Both the phase of the wavelet and the orientation are changing periodically along the surface of the cortical map as suggested by previous simulation studies and as also found in experiments. In order to get orientation-selective receptive fields, the spatial correlation function of the inputs that drive the development must have a zero crossing.

Algorithms↗

PubMed1999

Language acquisition in the absence of explicit negative evidence: how important is starting small?

It is commonly assumed that innate linguistic constraints are necessary to learn a natural language, based on the apparent lack of explicit negative evidence provided to children and on Gold's proof that, under assumptions of virtually arbitrary positive presentation, most interesting classes of languages are not learnable. However, Gold's results do not apply under the rather common assumption that language presentation may be modeled as a stochastic process. Indeed, Elman (Elman, J.L., 1993. Learning and development in neural networks: the importance of starting small. Cognition 48, 71-99) demonstrated that a simple recurrent connectionist network could learn an artificial grammar with some of the complexities of English, including embedded clauses, based on performing a word prediction task within a stochastic environment. However, the network was successful only when either embedded sentences were initially withheld and only later introduced gradually, or when the network itself was given initially limited memory which only gradually improved. This finding has been taken as support for Newport's 'less is more' proposal, that child language acquisition may be aided rather than hindered by limited cognitive resources. The current article reports on connectionist simulations which indicate, to the contrary, that starting with simplified inputs or limited memory is not necessary in training recurrent networks to learn pseudonatural languages; in fact, such restrictions hinder acquisition as the languages are made more English-like by the introduction of semantic as well as syntactic constraints. We suggest that, under a statistical model of the language environment, Gold's theorem and the possible lack of explicit negative evidence do not implicate innate, linguistic-specific mechanisms. Furthermore, our simulations indicate that special teaching methods or maturational constraints may be unnecessary in learning the structure of natural language.

Artificial Intelligence↗