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 955 records · Page 53Linked to original sources

PubMed1997

Registration of neural maps through value-dependent learning: modeling the alignment of auditory and visual maps in the barn owl's optic tectum.

In the optic tectum (OT) of the barn owl, visual and auditory maps of space are found in close alignment with each other. Experiments in which such alignment has been disrupted have shown a considerable degree of plasticity in the auditory map. The external nucleus of the inferior colliculus (ICx), an auditory center that projects massively to the tectum, is the main site of plasticity; however, it is unclear by what mechanisms the alignment between the auditory map in the ICx and the visual map in the tectum is established and maintained. In this paper, we propose that such map alignment occurs through a process of value-dependent learning. According to this paradigm, value systems, identifiable with neuromodulatory systems having diffuse projections, respond to innate or acquired salient cues and modulate changes in synaptic efficacy in many brain regions. To test the self-consistency of this proposal, we have developed a computer model of the principal neural structures involved in the process of auditory localization in the barn owl. This is complemented by simulations of aspects of the barn owl phenotype and of the experimental environment. In the model, a value system is activated whenever the owl carries out a foveation toward an auditory stimulus. A term representing the diffuse release of a neuromodulator interacts with local pre- and postsynaptic events to determine synaptic changes in the ICx. Through large-scale simulations, we have replicated a number of experimental observations on the development of spatial alignment between the auditory and visual maps during normal visual experience, after the retinal image is shifted through prismatic goggles, and after the reestablishment of normal visual input. The results suggest that value-dependent learning is sufficient to account for the registration of auditory and visual maps of space in the OT of the barn owl, and they lead to a number of experimental predictions.

Animals↗

PubMed2026

Multimodal artificial intelligence and machine learning in oncology: from data integration to precision cancer care.

Cancer remains a major global health burden, with approximately 20 million new cases and 9.7 million cancer-related deaths reported globally in 2022. While advances in radiological imaging, molecular profiling, and clinical data have enhanced the interpretation of disease progression, the availability of multiple such modalities still does not meet the needs of a large patient population. This narrative review focuses on the role of multimodal artificial intelligence and machine learning in bridging the gap in interpreting heterogeneous modalities to improve risk prediction, prognostic assessment, and treatment decision-making in precision oncology. Multimodal frameworks such as Pathomic Fusion illustrate how complementary histopathological and genomic information can be integrated for cancer diagnosis and prognostic modeling. Multimodal models have demonstrated potential in virtual biopsy, cancer screening, prognostic prediction, radiotherapy planning, intraoperative guidance, and clinical-trial design using digital twins and synthetic control arms. The major limitations of incorporating multimodal artificial intelligence and machine learning in oncology include data heterogeneity, demographic or institutional biases, and reproducibility challenges that hinder translation. Accordingly, appropriate data-governance strategies, fairness audits, and privacy-preserving approaches such as federated learning should be considered where appropriate. Future progress will depend on the development of standardized benchmarking datasets, robust external validation, seamless integration with electronic health records and picture archiving and communication systems, and the implementation of explainable, secure, and clinically validated multimodal artificial intelligence frameworks that support precision oncology in routine clinical practice.

deep learning↗

PubMedDate not supplied

Collaborative filtering on a family of biological targets.

Building a QSAR model of a new biological target for which few screening data are available is a statistical challenge. However, the new target may be part of a bigger family, for which we have more screening data. Collaborative filtering or, more generally, multi-task learning, is a machine learning approach that improves the generalization performance of an algorithm by using information from related tasks as an inductive bias. We use collaborative filtering techniques for building predictive models that link multiple targets to multiple examples. The more commonalities between the targets, the better the multi-target model that can be built. We show an example of a multi-target neural network that can use family information to produce a predictive model of an undersampled target. We evaluate JRank, a kernel-based method designed for collaborative filtering. We show their performance on compound prioritization for an HTS campaign and the underlying shared representation between targets. JRank outperformed the neural network both in the single- and multi-target models.

Ligands↗

PubMed2005

Associating unseen events: semantically mediated formation of episodic associations.

In prior work, we developed a computational model of how episodic associations between words are formed. Simulating associative learning, the model indicated that strongly associated semantically unrelated words facilitate the episodic association of other exemplars included in their semantic neighborhoods. This prediction was supported empirically by the present study. First, the incidental formation of strong associations between unrelated words, such as dog and table, improved cued recall of weak associations formed incidentally between semantic neighbors, like cat and chair. Second, deciding that two words were semantically unrelated was facilitated by forming strong associations between other words in their respective semantic neighborhoods, even if the tested pair was not presented at study. Together with the computational model, the present results demonstrate that forming episodic associations between words can implicitly mediate the association of other exemplars from the same semantic categories and reveal a mechanism by which the semantic system contributes to the formation of new episodic associations.

Adolescent↗

PubMed2006

Broadening conceptions of learning in medical education: the message from teamworking.

BACKGROUND: There is a mismatch between the broad range of learning theories offered in the wider education literature and a relatively narrow range of theories privileged in the medical education literature. The latter are usually described under the heading of 'adult learning theory'. METHODS: This paper critically addresses the limitations of the current dominant learning theories informing medical education. An argument is made that such theories, which address how an individual learns, fail to explain how learning occurs in dynamic, complex and unstable systems such as fluid clinical teams. RESULTS: Models of learning that take into account distributed knowing, learning through time as well as space, and the complexity of a learning environment including relationships between persons and artefacts, are more powerful in explaining and predicting how learning occurs in clinical teams. Learning theories may be privileged for ideological reasons, such as medicine's concern with autonomy. CONCLUSIONS: Where an increasing amount of medical education occurs in workplace contexts, sociocultural learning theories offer a best-fit exploration and explanation of such learning. We need to continue to develop testable models of learning that inform safe work practice. One type of learning theory will not inform all practice contexts and we need to think about a range of fit-for-purpose theories that are testable in practice. Exciting current developments include dynamicist models of learning drawing on complexity theory.

Cognition↗

PubMed2006

Nitric oxide regulates input specificity of long-term depression and context dependence of cerebellar learning.

Recent studies have shown that multiple internal models are acquired in the cerebellum and that these can be switched under a given context of behavior. It has been proposed that long-term depression (LTD) of parallel fiber (PF)-Purkinje cell (PC) synapses forms the cellular basis of cerebellar learning, and that the presynaptically synthesized messenger nitric oxide (NO) is a crucial "gatekeeper" for LTD. Because NO diffuses freely to neighboring synapses, this volume learning is not input-specific and brings into question the biological significance of LTD as the basic mechanism for efficient supervised learning. To better characterize the role of NO in cerebellar learning, we simulated the sequence of electrophysiological and biochemical events in PF-PC LTD by combining established simulation models of the electrophysiology, calcium dynamics, and signaling pathways of the PC. The results demonstrate that the local NO concentration is critical for induction of LTD and for its input specificity. Pre- and postsynaptic coincident firing is not sufficient for a PF-PC synapse to undergo LTD, and LTD is induced only when a sufficient amount of NO is provided by activation of the surrounding PFs. On the other hand, above-adequate levels of activity in nearby PFs cause accumulation of NO, which also allows LTD in neighboring synapses that were not directly stimulated, ruining input specificity. These findings lead us to propose the hypothesis that NO represents the relevance of a given context and enables context-dependent selection of internal models to be updated. We also predict sparse PF activity in vivo because, otherwise, input specificity would be lost.

Action Potentials↗

PubMed2006

Inferring rules of Escherichia coli translational efficiency using an artificial neural network.

Although the machinery for translation initiation in Escherichia coli is very complicated, the translational efficiency has been reported to be predictable from upstream oligonucleotide sequences. Conventional models have difficulties in their generalization ability and prediction nonlinearity and in their ability to deal with a variety of input attributions. To address these issues, we employed structural learning by artificial neural networks to infer general rules for translational efficiency. The correlation between translational activities measured by biological experiments and those predicted by our method in the test data was significant (r=0.78), and our method uncovered underlying rules of translational activities and sequence patterns from the obtained skeleton structure. The significant rules for predicting translational efficiency were (1) G- and A-rich oligonucleotide sequences, resembling the Shine-Dalgarno sequence, at positions -10 to -7; (2) first base A in the initiation codon; (3) transport/binding or amino acid metabolism gene function; (4) high binding energy between mRNA and 16S rRNA at positions -15 to -5. An additional inferred novel rule was that C at position -1 increases translational efficiency. When our model was applied to the entire genomic sequence of E. coli, translational activities of genes for metabolism and translational were significantly high.

Base Sequence↗

PubMed2025

CASTER-DTA: Equivariant Graph Neural Networks for Predicting Drug-Target Affinity.

Accurately determining the binding affinity of a ligand with a protein is important for drug design, development, and screening. With the advent of accessible protein structure prediction methods such as AlphaFold, predicted protein 3D structures are readily available; however, methods for predicting binding affinity currently do not take full advantage of 3D protein information. Here, we present CASTER-DTA (Cross-Attention with Structural Target Equivariant Representations for Drug-Target Affinity), which uses an equivariant graph neural network to learn more robust protein representations alongside a standard graph neural network to learn molecular representations to predict drug-target affinity. We augment these representations by incorporating an attention-based mechanism between protein residues and drug atoms to improve interpretability. We show that CASTER-DTA represents a state-of-the-art improvement on multiple benchmarks for predicting drug-target affinity and that it generates novel insights for several related tasks. We then apply CASTER-DTA to create a large resource of the binding affinities of every FDA-approved drug against every protein in the human proteome and make these predictions freely available for download. We also make available a web server for researchers to apply a pretrained CASTER-DTA model for predicting binding affinities between arbitrary proteins and drugs.

deep learning↗

PubMed2006

Factors influencing laparoconversions during the learning curve of laparoscopic myomectomy.

BACKGROUND: To assess the probability of conversion of a laparoscopic myomectomy to an open procedure, we only found the score developed by Dubuisson et al. (2001) based on four preoperative risk factors. Routinely this score is not appropriate, as realized by the most skilled laparoscopic surgeons. METHODS: The aim of this study was to identify the preoperative factors affecting the risk of conversion in data collected in different centers among a population of surgeons at the beginning of their experience in laparoscopic myomectomy. We collected preoperative clinical and ultrasonography data for all laparoscopic myomectomies performed in 11 hospital centers between January 1996 and December 2000. Data were available for 116 patients. Multiple logistic regression was use to develop a simple predictive model based on available preoperative risk factors of laparoconversion. RESULTS: We encountered 33 laparoconversions (28%) compared to an expected number of 7.8 using Dubuisson's score. We confirmed the importance of two of the four risk factors in Dubuisson's model: biggest myoma size at ultrasonography (increased 1 mm) (OR: 1.06) and intramural type (OR: 3.25) of the dominant myoma. However, we also identified another risk factors: surgeon's experience (OR: 0.15). Simple score was calculated and used to provide an estimated risk of conversion. CONCLUSION: Our model is a useful tool to predict laparoconversion for surgeons beginning in laparoscopic myomectomy. Ultrasound evaluation is essential before performing the procedure. Skilled surgeons in laparoscopy and in laparoscopic myomectomy must help their trainees during their learning curve in order to reduce laparoconversion rate.

Adult↗

PubMedDate not supplied

[Cognitive approach to anticipation in depression].

There is an extensive philosophical and humanistic literature concerning anticipation. Behavioural and cognitive theories have approached the concept of anticipation and have led to therapeutic solutions. The Lewinsohn model enables prediction and restoration of the activities of mastery and pleasure. The social psychology model (Bandura) forms the basis of training in assertiveness, using role-playing in order to be able to produce the relational situations which the patient will encounter. Learned helplessness for action (Seligman), teaches the reattribution of failures or successes, which leads the depressed patient to once again become involved in the action concerned. Exposure to feared situations (Marks) modifies catastrophic anticipations. The social reinforcement model (Liberman) enables prediction by functional analysis of factors involved in the persistence of problems and their modification. The mechanisms of anticipation have been reviewed since Bartlett and Ellis and up to the work of Beck. Structured patterns during existence determine thought processes in face of the circumstances which provoke them. Thus, in the opinion of the authors, our past affects our future in terms of the manner in which these patterns deal with information and determine our thoughts (cognitive events) and our vision of the future. The experimental basis of the cognitive model and the validation of these therapeutic approaches are described. The depressed patient makes negative predictions. Negative cognitions vary in conjunction with mood. Modification of these cognitions changes mood. Numerous studies are presented. They establish the effectiveness of this model, comparable to the action of antidepressant drugs and appearing to have a prolonged effect. The evaluation and cognitive treatment of anticipation are described: cognitive rating scales and analysis are proposed.(ABSTRACT TRUNCATED AT 250 WORDS)

Cognition↗

PubMed2026

Mutational signatures in blood-brain barrier: mechanisms, computational insights, and clinical applications in precision oncology.

The blood - brain barrier (BBB) plays a central role in maintaining central nervous system (CNS) homeostasis, and its disruption is a defining feature of malignant brain tumors such as glioblastoma. Emerging evidence indicates that BBB dysfunction not only alters the tumor microenvironment but also shapes the mutational processes that drive genomic instability in CNS malignancies. This review synthesizes current understanding of the biological mechanisms linking BBB breakdown with distinct mutational signatures, including those arising from oxidative stress, hypoxia-induced replication stress, lipid peroxidation, inflammation, and metabolic reprogramming. Advances in next-generation sequencing, coupled with computational tools such as non-negative matrix factorization, Bayesian modeling, and deep learning, have enabled precise extraction of these signatures and their integration with multi-omics data. Clinically, BBB-associated mutational signatures offer significant promise for therapeutic stratification, prediction of treatment response, and noninvasive monitoring through cerebrospinal fluid - derived circulating tumor DNA. Despite these advances, challenges persist due to limited tissue accessibility, low-yield CSF samples, incomplete mechanistic models, and the lack of CNS-specific analytical frameworks. A deeper understanding of BBB-driven mutational processes, supported by improved computational approaches and integrative datasets, holds potential to advance precision oncology in neuro-oncology.

Humans↗

PubMed2000

Modeling inhibitory plasticity in the electrosensory system of mormyrid electric fish.

Mathematical analyses and computer simulations are used to study the adaptation induced by plasticity at inhibitory synapses in a cerebellum-like structure, the electrosensory lateral line lobe (ELL) of mormyrid electric fish. Single-cell model results are compared with results obtained at the system level in vivo. The model of system level adaptation uses detailed temporal learning rules of plasticity at excitatory and inhibitory synapses onto Purkinje-like neurons. Synaptic plasticity in this system depends on the time difference between pre- and postsynaptic spikes. Adaptation is measured by the ability of the system to cancel a reafferent electrosensory signal by generating a negative image of the predicted signal. The effects of plasticity are tested for the relative temporal correlation between the inhibitory input and the sensory input, the gain of the sensory signal, and the presence of shunting inhibition. The model suggests that the presence of plasticity at inhibitory synapses improves the function of the system if the inhibitory inputs are temporally correlated with a predictable electrosensory signal. The functional improvements include an increased range of adaptability and a higher rate of system level adaptation. However, the presence of shunting inhibition has little effect on the dynamics of the model. The model quantifies the rate of system level adaptation and the accuracy of the negative image. We find that adaptation proceeds at a rate comparable to results obtained from experiments in vivo if the inhibitory input is correlated with electrosensory input. The mathematical analysis and computer simulations support the hypothesis that inhibitory synapses in the molecular layer of the ELL change their efficacy in response to the timing of pre- and postsynaptic spikes. Predictions include the rate of adaptation to sensory stimuli, the range of stimulus amplitudes for which adaptation is possible, the stability of stored negative images, and the timing relations of a temporal learning rule governing the inhibitory synapses. These results may be generalized to other adaptive systems in which plasticity at inhibitory synapses obeys similar learning rules.

Action Potentials↗

PubMed2001

The development of functional response units: the role of demarcating stimuli.

An experiment with rats examined the roles of demarcating stimuli and differential reinforcement probability on the development of functional response units. It examined the development of units in a probabilistic, free-operant situation in which the presence of demarcating stimuli was manipulated. In all conditions, behavior became organized into two-response sequences framed by changes in local reinforcement probability. A tone demarcating the beginning and end of contingent response sequences facilitated the development of functional response units, as in chunking, but the same units developed slowly in the absence of the tone. Complex functional response units developed even though reinforcement contigencies remained constant. These findings demonstrate that models of operant learning must include a mechanism for changing the response unit as a function of reinforcement history. Markov models may seem to be a natural technique for modeling response sequences because of their ability to predict individual responses as a function of reinforcement history; however, no class of Markov chain can incorporate changing response units in their predictions.

Animals↗

PubMed2005

Boosting alternating decision trees modeling of disease trait information.

We applied the alternating decision trees (ADTrees) method to the last 3 replicates from the Aipotu, Danacca, Karangar, and NYC populations in the Problem 2 simulated Genetic Analysis Workshop dataset. Using information from the 12 binary phenotypes and sex as input and Kofendrerd Personality Disorder disease status as the outcome of ADTrees-based classifiers, we obtained a new quantitative trait based on average prediction scores, which was then used for genome-wide quantitative trait linkage (QTL) analysis. ADTrees are machine learning methods that combine boosting and decision trees algorithms to generate smaller and easier-to-interpret classification rules. In this application, we compared four modeling strategies from the combinations of two boosting iterations (log or exponential loss functions) coupled with two choices of tree generation types (a full alternating decision tree or a classic boosting decision tree). These four different strategies were applied to the founders in each population to construct four classifiers, which were then applied to each study participant. To compute average prediction score for each subject with a specific trait profile, such a process was repeated with 10 runs of 10-fold cross validation, and standardized prediction scores obtained from the 10 runs were averaged and used in subsequent expectation-maximization Haseman-Elston QTL analyses (implemented in GENEHUNTER) with the approximate 900 SNPs in Hardy-Weinberg equilibrium provided for each population. Our QTL analyses on the basis of four models (a full alternating decision tree and a classic boosting decision tree paired with either log or exponential loss function) detected evidence for linkage (Z >or= 1.96, p < 0.01) on chromosomes 1, 3, 5, and 9. Moreover, using average iteration and abundance scores for the 12 phenotypes and sex as their relevancy measurements, we found all relevant phenotypes for all four populations except phenotype b for the Karangar population, with suggested subgroup structure consistent with latent traits used in the model. In conclusion, our findings suggest that the ADTrees method may offer a more accurate representation of the disease status that allows for better detection of linkage evidence.

Algorithms↗

PubMed2003

Optimization of neural network architecture using genetic programming improves detection and modeling of gene-gene interactions in studies of human diseases.

BACKGROUND: Appropriate definition of neural network architecture prior to data analysis is crucial for successful data mining. This can be challenging when the underlying model of the data is unknown. The goal of this study was to determine whether optimizing neural network architecture using genetic programming as a machine learning strategy would improve the ability of neural networks to model and detect nonlinear interactions among genes in studies of common human diseases. RESULTS: Using simulated data, we show that a genetic programming optimized neural network approach is able to model gene-gene interactions as well as a traditional back propagation neural network. Furthermore, the genetic programming optimized neural network is better than the traditional back propagation neural network approach in terms of predictive ability and power to detect gene-gene interactions when non-functional polymorphisms are present. CONCLUSION: This study suggests that a machine learning strategy for optimizing neural network architecture may be preferable to traditional trial-and-error approaches for the identification and characterization of gene-gene interactions in common, complex human diseases.

Algorithms↗

PubMed1994

Procedural learning and the development and stability of character.

This manuscript presents a neuropsychological model of the development and stability of human character. We define character as those things which people do routinely, automatically, and unconsciously--those which make people knowable and predictable. According to the model, the substrate of character is comprised of one's phenotypically based temperamental predispositions. This substrate is modified as a result of experience. Research has indicated the existence of multiple, relatively independent memory systems, and we are particularly interested in the distinction that has been made between declarative and procedural learning. Declarative memory involves recall of information and events, while procedural memory involves the learning of skills and other processes. In neurologically intact persons, these systems work in concert, yet they are relatively independent of one another. This model constrains the concept of character in a manner that allows researchers to address several issues, including (1) the manner in which character develops over time, (2) the mechanisms involved in the stability of character, and (3) the processes likely to be associated with character change.

Brain↗

PubMed1999

Activity-dependent regulation of receptive field properties of cat area 17 by supervised Hebbian learning.

Most algorithms currently used to model synaptic plasticity in self-organizing cortical networks suppose that the change in synaptic efficacy is governed by the same structuring factor, i.e., the temporal correlation of activity between pre- and postsynaptic neurons. Functional predictions generated by such algorithms have been tested electrophysiologically in the visual cortex of anesthetized and paralyzed cats. Supervised learning procedures were applied at the cellular level to change receptive field (RF) properties during the time of recording of an individual functionally identified cell. The protocols were devised as cellular analogs of the plasticity of RF properties, which is normally expressed during a critical period of postnatal development. We summarize here evidence demonstrating that changes in covariance between afferent input and postsynaptic response imposed during extracellular and intracellular conditioning can acutely induce selective long-lasting up- and down-regulations of visual responses. The functional properties that could be modified in 40% of cells submitted to differential pairing protocols include ocular dominance, orientation selectivity and orientation preference, interocular orientation disparity, and the relative dominance of ON and OFF responses. Since changes in RF properties can be induced in the adult as well, our findings also suggest that similar activity-dependent processes may occur during development and during active phases of learning under the supervision of behavioral attention or contextual signals. Such potential for plasticity in primary visual cortical neurons suggests the existence of a hidden connectivity expressing a wider functional competence than the one revealed at the spiking level. In particular, in the spatial domain the sensory synaptic integration field is larger than the classical discharge field. It can be shaped by supervised learning and its subthreshold extent can be unmasked by the pharmacological blockade of intracortical inhibition.

Action Potentials↗

PubMed1996

Animal models in cognitive behavioural pharmacology: an overview.

Most studies in cognitive behavioural pharmacology have used rodents as subjects and simple learning tasks. This approach is regarded as acceptable because the cognitive abilities of rats may not differ from those of non-human primates and the modelling in animals of those advanced cognitive abilities possessed by humans may be of limited utility. A strength of many existing models lies in their construct validity. However, the face, concurrent and predictive validities of many animal models are low. In part, this is due to the need to take account of species specific characteristics in experimental design. Thus, inter-species differences in learning may be explained not by differences in cognitive ability but by differences in species specific morphological, physiological and behavioural characteristics. Features of the 'ideal' animal model of human cognitive function are listed and potential strategies for future research in cognitive behavioural pharmacology assessed.

Animals↗