PubMed Health⌕ Search

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 1,423 records · Page 79Linked to original sources
PubMed2026

Decoding cancer with artificial intelligence: Transforming research, diagnosis, and therapy with future insights.

Cancer remains one of the leading global health burdens, with increasing complexity in genomic, imaging, and clinical datasets presenting significant challenges for effective management. Artificial intelligence (AI) has emerged as a powerful tool to address these challenges by enabling pattern recognition, knowledge integration, and data-driven decision-making. This review highlights recent advances in the application of AI across cancer research, diagnosis, and therapy. In research, AI accelerates drug discovery and repurposing, enhances genomic data interpretation, and facilitates biomarker identification through multi-omics integration. In diagnosis, AI has demonstrated high technical performance in radiology for lesion detection and image segmentation, in pathology for tumour grading and molecular prediction, and in liquid biopsy for non-invasive biomarker analysis. In therapy, AI supports precision medicine by predicting treatment responses, monitoring disease progression, and optimizing clinical trial design. Despite these advances, barriers such as data heterogeneity, algorithmic bias, interpretability, and regulatory challenges remain. Future directions, including explainable AI, federated learning, multimodal modelling, and digital twins, hold promise for translating AI-driven innovations into routine oncology practice. Significance Statement This review provides a timely synthesis of recent (2020-2025) advances in artificial intelligence across cancer research, diagnosis, and therapy, highlighting applications in drug discovery, genomics, multi-omics biomarker identification, and clinical decision-making. By integrating technological progress with translational and clinical relevance, this work serves as a valuable resource for bridging AI innovation with precision oncology practice. As a narrative review, the literature was identified through targeted PubMed, Scopus, and Google Scholar searches, combining terms for artificial intelligence, machine learning, and deep learning with cancer-related keywords, with priority given to peer-reviewed studies published between 2020 and 2025, seminal earlier works, and official regulatory or guideline documents. Within each domain, representative studies were selected to illustrate methodological diversity, clinical context, and current translational readiness rather than to provide exhaustive coverage of an extremely rapidly evolving field.

Artificial intelligence↗
PubMed1985

Intimacy and depression in older women.

This study examines the effects of the qualities of intimate relationships on depression in older women. The data are from a study of women over 50, randomly selected from five census tracts in Madison, Wisconsin, who were given questionnaires about depression and the quality of their intimate relationships on two occasions (summer of 1978 and summer of 1979). The results showed that some dimensions of the relationships that the women described with their most significant others predicted depression. The more depressed the women were, the more they felt that (1) the relationship was less friendly, (2) their friendly feelings were not reciprocated by the significant other, (3) their relationship was less consistent and predictable, and (4) there was less time spent with the significant other in the best state. These findings are discussed as partially consistent with Seligman's arguments on the comparability of his "learned helplessness" model and depression and with the focus of cognitive theories of Beck and others on the role of perceptions and expectations in depression.

Aged↗
PubMed2025

Decoding the Functional Interactome of Non-Model Organisms with PHILHARMONIC.

Despite the widespread availability of genome sequencing pipelines, many genes remain part of the genome's "dark matter," where existing inference tools cannot even begin to guess the biological function of their proteins from sequence alone. This challenge is especially pronounced in organisms that are highly evolutionarily distant from well-studied models, where homology-based methods break down. Here, we describe PHILHARMONIC, a computational method that combines deep learning-based de novo protein interaction network inference with robust unsupervised spectral clustering and remote homology to illuminate functional organization in any non-model organism. From only a sequenced proteome, we show PHILHARMONIC predicts protein functions, functional communities, and higher-order network structure with high accuracy. We validate its performance using experimental gene expression and pathway data in D. melanogaster, and we demonstrate its broad utility by analyzing temperature sensing and stress response pathways in the reef-building coral P. damicornis and its algal symbiont C. goreaui. PHILHARMONIC provides a general-purpose engine for functional discovery and biological hypothesis generation in non-model organisms, enabling systems-level insights across the full diversity of life.

Journal Article↗
PubMed2026

[Applications and Challenges of Deep Learning in Human Genome Research].

In recent years, the advent of high-throughput omics technologies has fueled an explosive growth in human genomic data. Uncovering the latent functions within this vast data has become a significant challenge in functional genomics research. While traditional statistical methods have proved successful for analyzing smaller-scale datasets in the past, they exhibit clear limitations in analytical efficiency and integrating multi-dimensional data, struggling to meet the escalating demands of contemporary genomic analysis. The introduction of deep learning (DL) technologies offers a novel paradigm for this field. This review systematically examines the advances in applying deep learning to human genomics research. Studies demonstrate that when ample labeled data is available, discriminative DL computational methods-such as Convolutional Neural Networks (CNNs) and Long Short-Term Memory networks (LSTMs)-achieve high accuracy and efficiency in genomic variant discovery tasks. Furthermore, generative DL methods, particularly Large Language Models (LLMs) leveraging self-supervised pre-training strategies, effectively integrate complex genomic information and exhibit superior performance in functional genomic sequence annotation and gene regulation studies. This review also explores the application of LLMs in multi-omics data integration and prediction. Looking ahead, the continued accumulation of long-read sequencing and high-dimensional data is expected to enable DL technologies to integrate increasingly complex and heterogeneous genomic information, playing an increasingly crucial role in human genomics research.

Deep Learning↗
PubMed1999

Metabolic engineering from a cybernetic perspective. 1. Theoretical preliminaries

The theoretical basis of a cybernetic metabolic network design and analysis framework, which has been subsequently successfully applied to predict system response to genetic alteration, is presented. This conceptual methodology consists of three main branches, namely, a model realization framework, a representation of genetic alteration, and lastly, a metabolic design component. These concepts are introduced as a series of postulates that describe the basic tenets of the approach. Each branch is discussed in turn, starting with the cybernetic representation of arbitrarily complex metabolic networks. A set of postulates is put forth that affords the modular construction of cybernetic models of metabolic networks using as a base a library of elementary pathways. This is followed by a discussion of the representation of genetic alterations within the cybernetic framework. It is postulated that the objective of the base network and the altered system are identical (at least on the time scale required for the organism to "learn" new objectives). This implies, with respect to resource allocation, that the base network and its genetically altered counterpart may still be treated as optimal systems; however, the set of competing physiological choices open to the altered network expands or contracts depending upon the nature of the genetic perturbation. Lastly, to add a predictive design aspect to the methodology, we present a set of postulates that outline the application of metabolic control analysis to cybernetic model systems. We postulate that sensitivity coefficients computed from a cybernetic model, although still local in scope, have the added benefit of a systematic representation of regulatory function as described by the cybernetic variables. Thus, information gained from sensitivity measurements stemming from a cybernetic model include the explicit input of metabolic regulation, a component that is lacking in a purely kinetic representation of metabolic function. The sensitivity results can then be employed to develop qualitative strategies for the rational alteration of metabolic function, which can be evaluated by simulation of an appropriately modified cybernetic model of the base network.

Journal Article↗
PubMed2006

Measuring resistance to change at the within-session level.

Resistance to change is often studied by measuring response rate in various components of a multiple schedule. Response rate in each component is normalized (that is, divided by its baseline level) and then log-transformed. Differential resistance to change is demonstrated if the normalized, log-transformed response rate in one component decreases more slowly than in another component. A problem with normalization, however, is that it can produce artifactual results if the relation between baseline level and disruption is not multiplicative. One way to address this issue is to fit specific models of disruption to untransformed response rates and evaluate whether or not a multiplicative model accounts for the data. Here we present such a test of resistance to change, using within-session response patterns in rats as a data base for fitting models of disruption. By analyzing response rate at a within-session level, we were able to confirm a central prediction of the resistance-to-change framework while discarding normalization artifacts as a plausible explanation of our results.

Animals↗
PubMed2006

Dissociable effects of the implicit and explicit memory systems on learning control of reaching.

Adaptive control of reaching depends on internal models that associate states in which the limb experienced a force perturbation with motor commands that can compensate for it. Limb state can be sensed via both vision and proprioception. However, adaptation of reaching in novel dynamics results in generalization in the intrinsic coordinates of the limb, suggesting that the proprioceptive states in which the limb was perturbed dominate representation of limb state. To test this hypothesis, we considered a task where position of the hand during a reach was correlated with patterns of force perturbation. This correlation could be sensed via vision, proprioception, or both. As predicted, when the correlations could be sensed only via proprioception, learning was significantly better as compared to when the correlations could only be sensed through vision. We found that learning with visual correlations resulted in subjects who could verbally describe the patterns of perturbations but this awareness was never observed in subjects who learned the task with only proprioceptive correlations. We manipulated the relative values of the visual and proprioceptive parameters and found that the probability of becoming aware strongly depended on the correlations that subjects could visually observe. In all conditions, aware subjects demonstrated a small but significant advantage in their ability to adapt their motor commands. Proprioceptive correlations produced an internal model that strongly influenced reaching performance yet did not lead to awareness. Visual correlations strongly increased the probability of becoming aware, yet had a much smaller but still significant effect on reaching performance. Therefore, practice resulted in acquisition of both implicit and explicit internal models.

Adaptation, Psychological↗
PubMed2000

Reward-dependent learning in neuronal networks for planning and decision making.

Neuronal network models have been proposed for the organization of evaluation and decision processes in prefrontal circuitry and their putative neuronal and molecular bases. The models all include an implementation and simulation of an elementary reward mechanism. Their central hypothesis is that tentative rules of behavior, which are coded by clusters of active neurons in prefrontal cortex, are selected or rejected based on an evaluation by this reward signal, which may be conveyed, for instance, by the mesencephalic dopaminergic neurons with which the prefrontal cortex is densely interconnected. At the molecular level, the reward signal is postulated to be a neurotransmitter such as dopamine, which exerts a global modulatory action on prefrontal synaptic efficacies, either via volume transmission or via targeted synaptic triads. Negative reinforcement has the effect of destabilizing the currently active rule-coding clusters; subsequently, spontaneous activity varies again from one cluster to another, giving the organism the chance to discover and learn a new rule. Thus, reward signals function as effective selection signals that either maintain or suppress currently active prefrontal representations as a function of their current adequacy. Simulations of this variation-selection have successfully accounted for the main features of several major tasks that depend on prefrontal cortex integrity, such as the delayed-response test, the Wisconsin card sorting test, the Tower of London test and the Stroop test. For the more complex tasks, we have found it necessary to supplement the external reward input with a second mechanism that supplies an internal reward; it consists of an auto-evaluation loop which short-circuits the reward input from the exterior. This allows for an internal evaluation of covert motor intentions without actualizing them as behaviors, by simply testing them covertly by comparison with memorized former experiences. This element of architecture gives access to enhanced rates of learning via an elementary process of internal or covert mental simulation. We have recently applied these ideas to a new model, developed with M. Kerszberg, which hypothesizes that prefrontal cortex and its reward-related connections contribute crucially to conscious effortful tasks. This model distinguishes two main computational spaces within the human brain: a unique global workspace composed of distributed and heavily interconnected neurons with long-range axons, and a set of specialized and modular perceptual, motor, memory, evaluative and attentional processors. We postulate that workspace neurons are mobilized in effortful tasks for which the specialized processors do not suffice; they selectively mobilize or suppress, through descending connections, the contribution of specific processor neurons. In the course of task performance, workspace neurons become spontaneously co-activated, forming discrete though variable spatio-temporal patterns subject to modulation by vigilance signals and to selection by reward signals. A computer simulation of the Stroop task shows workspace activation to increase during acquisition of a novel task, effortful execution, and after errors. This model makes predictions concerning the spatio-temporal activation patterns during brain imaging of cognitive tasks, particularly concerning the conditions of activation of dorsolateral prefrontal cortex and anterior cingulate, their relation to reward mechanisms, and their specific reaction during error processing.

Animals↗
PubMed2000

Learning and decay of prediction in object manipulation.

Anticipating the consequences of our own actions is a fundamental component of normal sensorimotor control and is seen, for example, during the manipulation of objects. When one hand pulls on an object held in the other hand, there is an anticipatory increase in grip force in the restraining hand that prevents the object from slipping. This anticipation is thought to rely on a forward internal model of the manipulated object and motor system, enabling the prediction of the consequences of our motor commands. Here we investigate the development of such a predictive response. Each hand held an object that was attached to its own torque motor. On each trial the subject was required to pull on the object held in the left hand and to maintain the position of the object held in the right hand. The torque motors were computer controlled so that the objects could be either "linked" so that the forces on the objects were equal and opposite, acting as though they were a single object, or "unlinked," so that they acted as two independent objects. A predictive response in the restraining hand is only necessary when the objects are linked and is unnecessary in the unlinked condition where there is no risk of the object slipping. To examine the learning and decay of predictive responses, we measured the grip force responses during unlinked trials that followed a linked trial. After a single linked trial, anticipatory grip force was quick to develop, but decayed slowly over the following unlinked trials. Varying the time between trials showed that the rate of decay depended on the number of trials since the last linked trial rather than time. Increasing the frequency of linked trials showed an increased level of subsequent grip force modulation, but did not alter the decay rate. When the torque motors simulated a linked object that did not have normal physical properties, prediction was reduced. These results show that the use of predictive responses has a different time course for learning and decay, and the response depends on experience and the physical properties of the objects.

Adult↗
PubMed1991

Prediction of clinical response in children taking methylphenidate.

Twenty-six children having Attention Deficit Hyperactivity Disorder were tested before and after treatment with methylphenidate. In addition to standardized parent and teacher rating scales, each child was assessed on a variety of psychomotor tests with an emphasis on attentional constructs. Relatively few of the performance tests, administered prior to medication, predicted clinical response to medication. However, chronological age and performance on a memory distraction task and on the Graduated Holes Task (Kløve, 1963) were moderately correlated with clinical outcome. Using stepwise multiple regression analyses to predict outcome, age and the psychomotor tasks predicted about 50% of outcome variance. There was virtually no relationship between clinical change and change on the performance tests. Findings are discussed with respect to results from previous prediction studies, theoretical models of drug response, and clinical management.

Attention↗
PubMed1999

Context-dependent recognition memory: the ICE theory.

A solution to the problem of context-dependent recognition memory is presented in terms of the item, associated context, and ensemble (ICE) theory. It is argued that different types of context effects depend on how context information is encoded at both learning and retrieval. Matching associated context in memory and a retrieval cue produces increases in both hit and false alarm rates and may not be accompanied by a change in discrimination. Integrating item and context information in an ensemble and matching ensemble information in memory and a retrieval cue produces context-dependent discrimination. Empirical support for these predictions is presented.

Adult↗
PubMed2000

Controlling activity fluctuations in large, sparsely connected random networks.

Controlling activity in recurrent neural network models of brain regions is essential both to enable effective learning and to reproduce the low activities that exist in some cortical regions such as hippocampal region CA3. Previous studies of sparse, random, recurrent networks constructed with McCulloch-Pitts neurons used probabilistic arguments to set the parameters that control activity. Here, we extend this work by adding an additional, biologically appropriate, parameter to control the magnitude and stability of activity oscillations. The new constant can be considered to be the rest conductance in a shunting model or the threshold when subtractive inhibition is used. This new parameter is critical for large networks run at low activity levels. Importantly, extreme activity fluctuations that act to turn large networks totally on or totally off can now be avoided. We also show how the size of external input activity interacts with this parameter to affect network activity. Then the model based on fixed weights is extended to estimate activities in networks with distributed weights. Because the theory provides accurate control of activity fluctuations, the approach can be used to design a predictable amount of pseudorandomness into deterministic networks. Such nonminimal fluctuations improve learning in simulations trained on the transitive inference problem.

Computer Simulation↗
PubMed2026

Fine-grained structural classification of biosynthetic gene cluster-encoded products.

MOTIVATION: Biosynthetic gene clusters (BGCs) are responsible the biosynthesis of many natural products, including a multitude of effective therapeutics and their precursors. Advances in genomic data collection as well as computational techniques have made it possible to identify BGCs at scale. However, accurately determining the types of BGC-encoded products from genomic content remains elusive. RESULTS: Here, we introduce BGC annotation tool (BGCat), a machine learning method for fine-grained structural classification of BGC-encoded products, leveraging the NPClassifier natural product nomenclature. Our method leverages a pre-trained protein language model for creating meaningful gene representations and a deep neural network for class label prediction. We show the method outperforms state-of-the-art approaches in coarse-grained product classification and is effective for detailed classification. We implement a clustering-based augmentation strategy for BGC-product relationships, addressing a crucial gap in the available datasets. We then introduce the concept of product class profiles of gene cluster families (GCFs), associating each GCF with a probabilistic distribution of product types and offering a new perspective on GCF functions. Lastly, we use BGCat to provide new product class labels for over 100k BGCs in antiSMASH DB that presently have minimal information about their products. AVAILABILITY AND IMPLEMENTATION: The source code and trained model weights are freely available at https://github.com/HassounLab/BGCat.

Multigene Family↗
PubMed1988

Social learning predictors of the avoidance of smoking relapse.

The concepts of health valuing, multidimensional locus of control, and self-efficacy were conceptualized to represent related but distinct factors which are strongly associated with health-promoting behavior. The predictive power of this model was tested by following 75 smokers quitting through formal treatment programs and 75 smokers who quit by treating themselves for three months. Discriminant Function Analysis displayed significant predictive power from the model. Self-efficacy was the strongest predictor of abstinence versus relapse, but more accurately for self-treatment than for program treatment groups. Persons attributing greater power to health professionals were more likely to relapse. Health valuing displayed a diminished return curve. Results suggest that the enhancement of self-efficacy may be the most important task of treatment.

Attitude to Health↗
PubMed1988

Brain state and plasticity: an integration of the reciprocal interaction model of sleep cycle oscillation with attentional models of hippocampal function.

The present paper relates the reciprocal interaction model for sleep cycle oscillation (McCarley and Hobson, ref. 29) to an attentional model of hippocampal function (Schmajuk and Moore, ref. 44). We consider mechanisms by which the interaction between gigantocellular tegmental field (FTG) cells and locus coeruleus (LC) activity proposed by the sleep cycle model may differentially modulate the information processing carried out in the hippocampus as described by the attentional model. Our fundamental assumption is that learning about the relevancy of different stimuli is proportional to the level of LC activation. If the environment becomes unpredictable during waking, the FTG and LC are activated and the LC facilitates hippocampal learning about stimulus relevancy. In a predictable situation during waking, FTG cells discharge rarely because no novelty is detected, and LC neurons are moderately active. If the predictable situation lasts, LC cells also decrease their activity, and a sleep period might start. At sleep onset, LC inhibition decreases and FTG activity is low leading to slow sleep. As FTG activity increases and LC activity reaches its low point, REM sleep starts. Because LC activity is low during REM sleep, values of stimulus relevancy remain unchanged. Since during sleep the threshold for external stimuli is high, only internally generated novel stimuli (subjectively perceived as dream mentation) may activate the LC. LC renewed inhibitory influence on the FTG ends REM sleep.

Animals↗
PubMed1999

Epidemiology and predictors of post-concussive syndrome after minor head injury in an emergency population.

OBJECTIVE: To determine if clinical variables or neurobehavioural test (NBT) scores obtained in the ED within 24 hours of minor head injury (MHI) predict the development of postconcussive syndrome (PCS). METHODS: Prospective, observational study of 71 MHI patients and 60 orthopaedic controls. MHI defined as loss of consciousness < 10 minutes or amnesia, GCS 15, no skull fracture or new neurologic focality on PE, and no brain injury on CT (if done). All patients received a seven part NBT battery in the ED. Telephone follow-up was done at 1, 3 and 6 months to determine if patients met the DSM IV definition of PCS. ANALYSIS: Stepwise, multivariate, logistic regression. RESULTS: Predictors of PCS at 1 month were female gender (OR = 7.8; 95% CI = 41.6, 1.98), presence of both retrograde and anterograde amnesia (OR = 0.055; CI = 0.002, 0.47), Digit Span Forward Scores (OR = 0.748; CI = 0.52, 1.03) and Hopkins Verbal Learning A scores (OR = 0.786; CI = 0.65, 0.91); at 3 months, presence of both retrograde and anterograde amnesia (OR = 0.13; CI = 0.0, 0.93), Digit Span Forward Scores (OR = 0.744; CI = 0.58, 0.94). No variables fit the model at 6 months. 92% of males scoring > 25 on Hopkins Verbal Learning A did not have PCS at 1 month, and 89% of females scoring < 9 on Digit Span Forward did have PCS at 1 month. CONCLUSIONS: Gender and two NBTs can help predict PCS after MHI.

Adult↗
PubMed1990

Structure and stimulation in the ontogeny of spoken language.

Linguistic innateness is a fundamentally physical notion, which ultimately requires independent physical evidence. For spoken language, it is relevant to consider babbling, components of which are unaffected by ambient stimulation and are predicted by models of vocal tract function. Links between babbling and speech point to innate factors in the ontogeny of spoken language and invite attention to central control mechanisms. These neural capabilities enable oral language learning by providing children with control over an initial stock of speech-like movements and by directing their attention to salient linguistic patterns. Dispositions to attend to some cues are so strong that little stimulation is required. In other cases, predispositions are weak, and acquisition requires correspondingly more experience. To understand the ontogeny of language, we need to learn which cases are which and to know how these interactions occur and change over the course of acquisition.

Animals↗