SEARCH · PubMed Health

Results for “artificial intelligence (AI)”

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 307 records · Page 17Linked to original sources

PubMed2026

Predicting cellular responses to perturbation across diverse contexts with State.

While machine learning models offer potential for predicting transcriptomic effects of perturbation, they currently struggle to generalize across cellular contexts. Here, we introduce State, a machine learning model that predicts perturbation effects while accounting for cellular heterogeneity within and across experiments. State is trained using single-cell gene expression data to predict perturbation effects across sets of cells. State improved discrimination of effects on large datasets by more than 30% and identified differentially expressed genes across genetic, signaling, and chemical perturbations with significantly improved accuracy compared with baselines. Its cell embeddings trained on observational data from 167 million cells enable the identification of strong perturbations in cellular contexts where no perturbations were observed during training. We further introduce Cell-Eval, a comprehensive evaluation framework that can be used to evaluate future models. Overall, the performance and flexibility of State set the stage for scaling the development of AI models of cell state.

Machine Learning↗

PubMed1996

Sleep classification in infants by decision tree-based neural networks.

This paper presents an AI-based approach to automatic sleep stage scoring. The system TBNN (Tree-Based Neural Network) uses a decision-tree generator to provide knowledge that defines the architecture of a backpropagation neural network, including feature selection and initialisation of the weights. The case study reports a successful application to the data from polygraphic all-night sleep of 8 babies aged 6 months. The teaching input was provided by a medical expert in accordance with the rules of Guilleminault and Souquet. The performance of TBNN is compared with 5 other methods and the results are discussed.

Artificial Intelligence↗

PubMed1989

An AI-based communication system for motor and speech disabled persons: design methodology and prototype testing.

An intelligent communication device is developed to assist the nonverbal, motor disabled in the generation of written and spoken messages. The device is centered on a knowledge base of the grammatical rules and message elements. A "belief" reasoning scheme based on both the information from external sources and the embedded knowledge is used to optimize the process of message search. The search for the message elements is conceptualized as a path search in the language graph, and a special frame architecture is used to construct and to partition the graph. Bayesian "belief" reasoning from the Dempster-Shafer theory of evidence is augmented to cope with time-varying evidence. An "information fusion" strategy is also introduced to integrate various forms of external information. Experimental testing of the prototype system is discussed.

Artificial Intelligence↗

PubMed2026

Graph neural network-based risk stratification of prostate cancer using gene expression and SHAP interpretability.

Accurate risk stratification is essential for guiding treatment decisions and preventing over treatment of prostate cancer, which remains one of the most prevalent cancers among adult men. While the Gleason score, obtained from prostate biopsies, is routinely used to assess tumor aggressiveness, the biopsy procedure carries risks such as pain, infection, and, in some cases, serious complications such as sepsis. In this study, we proposed an artificial intelligence-based framework that integrates mRNA expression profiles with functional interaction networks to classify prostate cancer patients into low-, medium-, and high-risk groups defined by Gleason scores. The pipeline comprised five steps: (1) data collection from The Cancer Genome Atlas (TCGA), (2) preprocessing of gene expression data, (3) two-stage feature selection to identify informative biomarkers, (4) risk classification using a dual-branch graph neural network (GNN) that combines gene-gene interaction graphs with sample-level expression features, and (5) model interpretation using SHAP to quantify feature contributions. Differentially expressed genes were identified in the High (ASPN, GMNN, PEBP4, C2, KNCK17), Medium (C2, IGSF1, ASPN, CDKN3, AMH), and Low (TNMD, VWA5B2, ST6GALNAC5, CYP3A5, PHGR1) risk groups, underscoring the molecular heterogeneity of disease progression. On an independent held-out test set, the model achieved AUCs of 0.86, 0.88, and 0.95 for the low-, medium-, and high-risk groups, respectively, with an overall accuracy of 80%. These results suggest that combining GNN-based modeling with explainable AI can capture both global and local molecular patterns relevant to tumor aggressiveness. However, as the model was developed and evaluated solely on the TCGA cohort, the findings should be regarded as exploratory, and external validation will be required to establish generalizability. Within these limitations, the proposed framework highlights the potential of molecular profiling and graph-based deep learning to support more precise, potentially less invasive, risk assessment and individualized treatment planning in prostate cancer.

Prostatic Neoplasms↗

PubMed2005

An artificial immune system approach with secondary response for misbehavior detection in mobile ad hoc networks.

In mobile ad hoc networks, nodes act both as terminals and information relays, and they participate in a common routing protocol, such as dynamic source routing (DSR). The network is vulnerable to routing misbehavior, due to faulty or malicious nodes. Misbehavior detection systems aim at removing this vulnerability. In this paper, we investigate the use of an artificial immune system (AIS) to detect node misbehavior in a mobile ad hoc network using DSR. The system is inspired by the natural immune system (IS) of vertebrates. Our goal is to build a system that, like its natural counterpart, automatically learns, and detects new misbehavior. We describe our solution for the classification task of the AIS; it employs negative selection and clonal selection, the algorithms for learning and adaptation used by the natural IS. We define how we map the natural IS concepts such as self, antigen, and antibody to a mobile ad hoc network and give the resulting algorithm for classifying nodes as misbehaving. We implemented the system in the network simulator Glomosim; we present detection results and discuss how the system parameters affect the performance of primary and secondary response. Further steps will extend the design by using an analogy to the innate system, danger signal, and memory cells.

Algorithms↗

PubMed2026

Data-driven approaches in green microbiology: strategies for plant growth-promoting bacteria.

Plant growth-promoting bacteria (PGPB) are gaining attention as scalable biological solutions to enhance crop productivity and resilience. However, accurately identifying and characterizing PGPB remains challenging, particularly under variable environmental conditions where microbial functions are context-dependent and shaped by complex plant-microbe interactions. Advances in high-throughput sequencing have shifted the field from culture-dependent approaches to genome-informed strategies, enabling large-scale taxonomic and functional profiling. Although trait-based databases support the prediction of plant-beneficial genes, they capture only a fraction of the underlying biological complexity and often require labor-intensive analyses. Machine learning (ML) and deep learning (DL) have emerged as powerful tools to integrate genomic, physiological, and ecological data, enabling the prioritization of candidate strains with plant growth-promoting potential. To evaluate advances in the field, we conducted a systematic review of studies integrating ML and DL with PGPB characterization, assessing algorithm selection, performance, and target plant systems. Across 248 observations, only 6.0% of studies directly addressed PGPB screening, whereas the majority (77.4%) focused on plant disease detection, revealing a substantial gap in the application of AI to beneficial microorganisms for plant growth. Convolutional neural networks (CNNs) were the most frequently applied algorithms, largely driven by image-based phenotyping tasks. Overall, the field is constrained by limited datasets, high computational demands, and challenges in modeling multispecies and host-associated interactions. We highlight the need for integrative and interpretable ML and DL frameworks that bridge genomic data and functional validation. Such approaches represent a promising path toward scalable, data-driven discovery and deployment of bioinoculants in sustainable agriculture.

Agriculture↗

PubMed1999

Prediction of blood glucose levels in diabetic patients using a hybrid AI technique.

One of the problems in the management of the diabetic patient is to balance the dose of insulin without exactly knowing how the patient's blood glucose concentration will respond. Being able to predict the blood glucose level would simplify the management. This paper describes an attempt to predict blood glucose levels using a hybrid AI technique combining the principal component method and neural networks. With this approach, no complicated models or algorithms need be considered. The results obtained from this fairly simple model show a correlation coefficient of 0.76 between the observed and the predicted values during the first 15 days of prediction. By using this technique, all the factors affecting this patient's blood glucose level are considered, since they are integrated in the data collected during this time period. It must be emphasized that the present method results in an individual model, valid for that particular patient under a limited period of time. However, the method itself has general validity, since the blood glucose variations over time have similar properties in any diabetic patient.

Algorithms↗

PubMed2025

In silico generation of synthetic cancer genomes using generative AI.

Understanding how genomic alterations drive cancer is key to advancing precision oncology. To detect these alterations, accurate algorithms are used; however, due to privacy concerns, few deeply sequenced cancer genomes can be shared, limiting benchmarking and representing a major obstacle to the improvement of analytic tools. To address this, we developed OncoGAN, a generative AI model combining adversarial networks and variational autoencoders to create realistic synthetic cancer genomes. Trained on large-scale genomic datasets, OncoGAN accurately reproduces somatic mutations, copy number alterations, and structural variants across cancer types while preserving donors' privacy. The synthetic genomes reflect tumor-specific mutational signatures and positional mutation patterns. Using DeepTumour, we validated the synthetic data's fidelity, showing high concordance between generated and predicted tumors. Moreover, augmenting the training data with synthetic genomes improved DeepTumour's accuracy, underscoring OncoGAN's potential to generate shareable datasets with known ground truths for benchmarking and enhancement of cancer genome analysis tools.

Humans↗

PubMed2000

A customisable framework for the assessment of therapies in the solution of therapy decision tasks.

In current medical research, a growing interest can be observed in the definition of a global therapy-evaluation framework which integrates considerations such as patients preferences and quality-of-life results. In this article, we propose the use of the research results in this domain as a source of knowledge in the design of support systems for therapy decision analysis, in particular with a view to application in oncology. We discuss the incorporation of these considerations in the definition of the therapy-assessment methods involved in the solution of a generic therapy decision task, described in the context of AI software development methodologies such as CommonKADS. The goal of the therapy decision task is to identify the ideal therapy, for a given patient, in accordance with a set of objectives of a diverse nature. The assessment methods applied are based either on data obtained from statistics or on the specific idiosyncrasies of each patient, as identified from their responses to a suite of psychological tests. In the analysis of the therapy decision task we emphasise the importance, from a methodological perspective, of using a rigorous approach to the modelling of domain ontologies and domain-specific data. To this aim we make extensive use of the semi-formal object oriented analysis notation UML to describe the domain level.

Artificial Intelligence↗

PubMed2001

Image understanding methods in biomedical informatics and digital imaging.

This paper will present new possibilities for the application of image recognition methods and AI application in biomedical informatics as well as semantically oriented analysis of 2D images of coronary arteries originating from coronography examinations. In particular this paper presents the possibilities for computer analysis and recognition of local stenoses of the lumen of coronary arteries via the application of syntactic methods of pattern recognition. Such stenoses are the result of the appearance of arteriosclerosis plaques, which in consequence lead to different forms of ischemic cardiovascular diseases. Such diseases may be seen in the form of stable or unstable disturbances of heart rhythm or infarction. Analysis of the correct morphology of these artery lumina is made possible with the application of syntactic analysis and pattern recognition methods, in particular with the attribute, context-free grammar of look-ahead LR(1) type.

Artificial Intelligence↗

PubMed2026

An open benchmark and language models for AI in aging biology.

Over the past two decades, human aging has been characterized across DNA methylation, transcriptomic, proteomic, and clinical modalities, yet no benchmark evaluates whether AI systems can interpret these heterogeneous data types in the context of aging biology. We introduce LongevityBench, an open suite of 17 tasks spanning five biodata domains, and use it to assess 18 frontier AI systems from six developer teams. Despite recent advances in AI, no single model dominates all tasks, with omics-based age prediction being the hardest task regardless of scale. To test whether these gaps can be closed without frontier-scale resources, we fine-tuned a family of five multitask Longevity-LLMs on domain-specific aging data. The compact (0.6B-9B parameters) Longevity-LLMs matched or exceeded far larger frontier systems on LongevityBench, showing that general-purpose language models can be adapted to structured-omics tasks. We publicly release the benchmark, models, and Longevity Claw, an agentic research interface for aging researchers.

Aging↗

PubMed1999

A study of PROforma, a development methodology for clinical procedures.

Knowledge engineering has shown that besides the general methodologies from software engineering it is useful to develop special purpose methodologies for knowledge based systems (KBS). PROforma is a newly developed methodology for a specific type of knowledge based systems. PROforma is intended for decision support systems and in particular for clinical procedures in the medical domain. This paper reports on an evaluation study of PROforma, and on the trade-off that is involved between general purpose and special purpose development methods in Knowledge Engineering and Medical AI. Our method for evaluating PROforma is based on re-engineering a realistic system in two methodologies: the new and special purpose KBS methodology PROforma and the widely accepted, and more general KBS methodology CommonKADS. The four most important results from our study are as follows. Firstly, PROforma has some strong points which are also strong related to requirements of medical reasoning. Secondly, PROforma has some weak points, but none of them are in any way related to the special purpose nature of PROforma. Thirdly, a more general method like CommonKADS works better in the analysis phase than the more special purpose method PROforma. Finally, to support a complementary use of the methodologies, we propose a mapping between their respective languages.

Artificial Intelligence↗

PubMed2025

AI-driven multi-omics modeling of myalgic encephalomyelitis/chronic fatigue syndrome.

Myalgic encephalomyelitis/chronic fatigue syndrome (ME/CFS) is a chronic illness with a multifactorial etiology and heterogeneous symptomatology, posing major challenges for diagnosis and treatment. Here we present BioMapAI, a supervised deep neural network trained on a 4-year, longitudinal, multi-omics dataset from 249 participants, which integrates gut metagenomics, plasma metabolomics, immune cell profiling, blood laboratory data and detailed clinical symptoms. By simultaneously modeling these diverse data types to predict clinical severity, BioMapAI identifies disease- and symptom-specific biomarkers and classifies ME/CFS in both held-out and independent external cohorts. Using an explainable AI approach, we construct a unique connectivity map spanning the microbiome, immune system and plasma metabolome in health and ME/CFS adjusted for age, gender and additional clinical factors. This map uncovers altered associations between microbial metabolism (for example, short-chain fatty acids, branched-chain amino acids, tryptophan, benzoate), plasma lipids and bile acids, and heightened inflammatory responses in mucosal and inflammatory T cell subsets (MAIT, γδT) secreting IFN-γ and GzA. Overall, BioMapAI provides unprecedented systems-level insights into ME/CFS, refining existing hypotheses and hypothesizing unique mechanisms-specifically, how multi-omics dynamics are associated to the disease's heterogeneous symptoms.

Humans↗

PubMed1994

Polygenic trait analysis by neural network learning.

AI techniques have been applied to the domain of DNA sequence analysis in predicting or identifying certain specialized regions, in recognizing genes, and in understanding the evolutionary relationships between sequences. This paper focuses on a kind of genetic pattern recognition, namely, the problem of identifying the gene combinations (patterns) causally related to a given trait determined by multiple genes (a so-called polygenic trait). A novel approach is presented which combines neural-network and knowledge-based techniques. The neural network is trained to predict the trait and then the knowledge embedded in the network is decoded into symbolic patterns. This hybrid approach is evaluated in the domain of identifying genes of insulin dependent diabetes mellitus. The consistency between the results with this approach and those reported in genetic literature supports the viability of this approach.

Artificial Intelligence↗

PubMed2026

AI-generated familiarity estimates are a useful new source of information about word knowledge in Simplified Chinese.

This study evaluated the usefulness of AI-generated estimates of word familiarity for predicting word difficulty in Simplified Chinese, building on previous research in alphabetic languages. We found that familiarity estimates produced using large language models (LLMs) showed moderate-to-strong correlations with human familiarity ratings. These LLM estimates were the most effective predictors of both word naming and lexical decision times, surpassing traditional metrics such as word frequency and human familiarity ratings, while the latter still provided modest, non-overlapping variance. GPT-4o with English instructions produced superior results compared to the Chinese-centered models currently available. The results imply that LLM familiarity estimates are a valuable resource for Chinese psycholinguistics, supporting work across experimental design, modeling, and norming. We release familiarity estimates for 27,624 words for unrestricted research and educational use.

Humans↗

PubMed2002

Automated assignment of NOESY NMR spectra using a knowledge based method (KNOWNOE).

Automated assignment of NOESY spectra is a prerequisite for automated structure determination of biological macromolecules. With the program KNOWNOE we present a novel, knowledge based approach to this problem. KNOWNOE is devised to work directly with the experimental spectra without interference of an expert. Besides making use of routines already implemented in AUREMOL, it contains as a central part a knowledge driven Bayesian algorithm for solving ambiguities in the NOE assignments. These ambiguities mainly arise from chemical shift degeneration which allows multiple assignments of cross peaks. Using a set of 326 protein NMR structures, statistical tables in the form of atom-pairwise volume probability distributions (VPDs) were derived. VPDs for all assignment possibilities relevant to the assignments of interproton NOEs were calculated. With these data for a given cross peak with N possible assignments Ai (i = 1,...,N) the conditional probabilities P(Ai, a/V0) can be calculated that the assignment Ai determines essentially all (a-times) of the cross peak volume V0. An assignment Ak with a probability P(Ak, a/V0) higher than 0.8 is transiently considered as unambiguously assigned. With a list of unambiguously assigned peaks a set of structures is calculated. These structures are used as input for a next cycle of iteration where a distance threshold Dmax is dynamically reduced. The program KNOWNOE was tested on NOESY spectra of a medium size protein, the cold shock protein (TmCsp) from Thermotoga maritima. The results show that a high quality structure of this protein can be obtained by automated assignment of NOESY spectra which is at least as good as the structure obtained from manual data evaluation.

Algorithms↗

PubMed2001

AI-based algorithms for protein surface comparisons.

Many current methods for protein analysis depend on the detection of similarity in either the primary sequence, or the overall tertiary structure (the Calpha atoms of the protein backbone). These common sequences or structures may imply similar functional characteristics or active properties. Active sites and ligand binding sites usually occur on or near the surface of the protein; so similarly shaped surface regions could imply similar functions. We investigate various methods for describing the shape properties of protein surfaces and for comparing them. Our current work uses algorithms from computer vision to describe the protein surfaces, and methods from graph theory to compare the surface regions. Early results indicate that we can successfully match a family of related ligand binding sites, and find their similarly shaped surface regions. This method of surface analysis could be extended to help identify unknown surface regions for possible ligand binding or active sites.

Algorithms↗

PubMed1994

Effective retrieval in Hospital Information Systems: the use of context in answering queries to Patient Discharge Summaries.

The move towards the electronic storage of medical records in Hospital Information Systems (HISs) presents significant challenges for AI retrieval techniques. In this paper, we argue that adequate information retrieval in such systems will have to rely on the exploitation of the conceptual knowledge in those records rather than superficial string searches. However, this course of action is dependent on the developments of natural language processing techniques and on retrieval systems that can exploit semantic/conceptual knowledge. We present a retrieval system, which attempts to realise the second of these developments. This system, called CONIR [developed in the context of the European Community project MENELAS (AIM 2023)] operates in the domain of Patient Discharge Summaries on coronary illness. CONIR uses flexible retrieval techniques, that exploit conceptual context information, over a database of elaborated semantic records. In the course of the paper we outline the sorts of knowledge structures that are required to do this type of retrieval and indicate how they are constructed.

Abstracting and Indexing↗