Search PubMed⌕ Search

SEARCH · Search PubMed

Results for “artificial intelligence”

Search indexed PubMed citations on genomics, clinical trials, systematic reviews and public health. Explore titles, authors and supplied subject terms, then open the PubMed record.

Quote a phrase for an exact phrase match. Source license links do not imply unrestricted reuse.

At least 775 records · Page 43Linked to original sources
PubMed2026

Precision medicine in mental health: applications, challenges, and recommendations.

Mental disorders represent a major and growing public health challenge in Europe and worldwide, characterised by marked clinical, biological, and functional heterogeneity, that limits the effectiveness of current diagnostic and therapeutic approaches. In recent years, advances in precision medicine have initiated a paradigm shift in psychiatry, offering new opportunities to improve prevention, prediction, diagnosis, treatment selection, and long-term management by integrating biological, psychological, social, and environmental information.This EPA Guidance Paper provides an overview of the current state of precision medicine in mental health and outlines its potential clinical, scientific, and policy implications. We review key advances in genomics, epigenetics, neuroimaging, transcriptomics, digital technologies, and artificial intelligence, highlighting their relevance across the full clinical pathway, from risk prediction and early detection to treatment personalisation and monitoring. We also examine major barriers to implementation, including limited biomarker validation, insufficient representativeness of research populations, ethical and regulatory challenges, data protection concerns, and inequalities in access across healthcare systems.Based on the available evidence, we propose strategic recommendations to support the responsible and equitable integration of precision approaches into mental health care in Europe. These include strengthening translational research, promoting multidisciplinary collaboration, updating regulatory and ethical frameworks, enhancing professional training, and prioritising mental health within national and European research and health agendas. By addressing these challenges, precision psychiatry has the potential to contribute to more effective, person-centred, and sustainable mental health care, while supporting innovation, reducing stigma, and improving outcomes for patients and society.

Humans↗
PubMed1986

Application of the EXPERT consultation system to accelerated laboratory testing and interpretation.

The EXPERT consultation system-building tool, a knowledge-based artificial intelligence program developed at Rutgers University, has been applied to the development of a laboratory consultation system facilitating sequential laboratory testing and interpretation. Depending on the results of a basic panel of laboratory tests, the system requests that specific secondary tests be performed. Input of these secondary findings can result in requests for tertiary testing, to complete the database necessary for interpretation. Interpretation of all results is based upon final inferences from the collected findings through a series of rules, a hierarchical network that yields an efficient production system not easily obtained through conventional programming. The rules included in this model are based upon initial results for total protein, calcium, glucose, total bilirubin, alkaline phosphatase, lactate dehydrogenase, aspartate aminotransferase, thyroxin, hemoglobin, mean corpuscular volume, and the concentrations of four drugs. Pertinent clinical history items included are jaundice, diabetes, thyroid disease, medications, and ethanol. Implementing this system in a laboratory-based accelerated testing program involving outpatients maximized the effective use of laboratory resources, eliminated useless testing, and provided the patient with low-cost laboratory information.

Adolescent↗
PubMed2003

Self-programming machines (II): Network of self-programming machines driving an Ashby homeostat.

The progress in artificial intelligence enables us to conceive adaptive systems whose characteristics are nearer and nearer to those of living beings. These characteristics though depend on ingenious choices by the designer of these systems: Initial conditions, parameters, optimisation functions, gradient and measure of fitness within the environment. Nevertheless, in living systems which are non-finalist, there are no programmers or designers to conceive of such ingenious choices. Our paper "Self-Programming Machines (I)" presents a non-finalist model since initial states and functions are randomly chosen at the beginning and once and for all. In spite of the fact that they are non-finalist, these machines always stabilise at fixed points when they are connected to an external process. This paper studies the dynamics of a mono-layered network of self-programming machines driving a real device. "the Ashby homeostat", and shows the striking properties of such networks. This system stabilises only at fixed points even if it is subjected to small perturbations or intentional breakdowns such as a reversal of power supply or disconnection of one or several motors. Real and simulated experiences are compared and theoretical results are demonstrated.

Artificial Intelligence↗
PubMed1992

Application of machine learning to a renal biopsy database.

This pilot study has applied machine learning (artificial intelligence derived qualitative analysis procedures) to yield non-invasive techniques for the assessment and interpretation of clinical and laboratory data in glomerular disease. To evaluate the appropriateness of these techniques, they were applied to subsets of a small database of 284 case histories and the resulting procedures evaluated against the remaining cases. Over such evaluations, the following average diagnostic accuracies were obtained: microscopic polyarteritis, 95.37%; minimal lesion nephrotic syndrome, 96.50%; immunoglobulin A nephropathy, 81.26%; minor changes, 93.66%; lupus nephritis, 96.27%; focal glomerulosclerosis, 92.06%; mesangial proliferative glomerulonephritis, 92.56%; and membranous nephropathy, 92.56%. Although in general the new diagnostic system is not yet as accurate as the histological evaluation of renal biopsy specimens, it shows promise of adding a further dimension to the diagnostic process. When the machine learning techniques are applied to a larger database, greater diagnostic accuracy should be obtained. It may allow accurate non-invasive diagnosis of some cases of glomerular disease without the need for renal biopsy. This may reduce both the cost and the morbidity of the investigation of glomerular disease and may be of particular value in situations where renal biopsy is considered hazardous or contraindicated.

Artificial Intelligence↗
PubMed2026

Exploring the use of machine and deep learning in genome-wide association studies: a comprehensive review.

The advent of high-throughput sequencing technologies has generated increasingly large and complex genomic datasets, necessitating analytical approaches capable of capturing high-dimensional and potentially nonlinear genetic interactions. This situation has significantly impacted the entire field of Genome-Wide Association Study (GWAS), whose primary goal is the identification of genomic traits and variants that are statistically associated with the risk of a disease. However, traditional GWAS methods may show reduced performance when applied to highly polygenic and nonlinear genetic architectures. Computational strategies from Artificial Intelligence (AI) and, in particular, from machine- and deep-learning may provide a powerful tool to overcome such limitations, especially by capturing nonlinear interactions and complex hidden regularities in large-scale data, which traditional GWAS approaches might overlook. To date, only a few approaches have been introduced and systematically assessed. In this review, we describe the main characteristics and limitations of standard statistical approaches for GWAS, the main uses of AI methods in computational genomics, and recent attempts to leverage AI strategies in GWAS. Particular attention will be devoted to key issues, such as the interpretability of methods and results, and the curse of dimensionality. More specifically, the review presents 30 methods designed to leverage AI in GWAS, as well as presenting a comprehensive set of evaluation metrics for their performance, also providing references to the most frequently used databases, and biobanks. Overall, this work may serve as a starting point for both dry- and wet-lab researchers, aiming to extract deeper insights from genomic data by moving beyond traditional linear additive assumptions, and leveraging large-scale datasets through AI-driven approaches.

Artificial intelligence↗
PubMed2026

Beyond data and technology: the need for new thinking to enable the era of precision prevention.

BACKGROUND: Global flagship initiatives increasingly advocate for proactive health maintenance to alleviate the growing burden on reactive, disease-focused healthcare systems. Precision prevention is conceived as the targeted modulation of causal pathways across the disease continuum, from latent risk and pre-disease states to clinical manifestation, surpassing conventional public health prevention strategies that prioritise managing population-level risk factors. Traditional discovery and implementation models, however, remain poorly aligned with the pace and breadth of scientific and technological advances. This review outlines key barriers to scaling precision prevention and argues for the integration of conceptual, methodological, and policy perspectives into a single implementation‑oriented framework. MAIN: Individualised risk stratification lies at the core of precision prevention. Genomics serves as a stable substrate for lifetime susceptibility assessment, while meaningful prediction in multifactorial chronic disease requires additional risk monitoring using dynamic intermediate molecular markers and high-resolution exposomic data. Machine learning and other artificial intelligence (AI) methods are increasingly helpful tools for integrating large, heterogeneous and temporally structured real-world data to generate personalised predictions of health trajectories. Trustworthy AI-enabled risk prediction or decision-support systems are expected to provide transparency about model logic, assumptions and performance. In discovery, existing diagnostic classifications and conventional case-control designs can obscure mechanistic heterogeneity. Shifting toward precision phenotyping and biologically grounded disease redefinition could reveal a new layer of molecular understanding. Evidence generation strategies that reflect the temporal change of disease, including high‑risk enrichment, surrogate endpoints, and adaptive, trajectory-based monitoring, are particularly important for common conditions with prolonged latency periods (e.g., cancer, cardiovascular disease). Features often dismissed as "noise", such as stochastic molecular variation and minimal exposures, may in fact encode meaningful individual-level signals and thus merit investigation. CONCLUSION: To shift healthcare from reactive treatment toward proactive health maintenance requires coordinated action from stakeholders to reshape the pillars of discovery, reform outcome assessments and modernise implementation strategies.

Humans↗
PubMed1993

Exploring the relationship between rationality and bounded rationality in medical knowledge-based systems.

If our goal in Artificial Intelligence in Medicine (AIM) is to engineer systems health-care providers will both use and, in the process, improve their performance, we must concentrate on the development of causal theories of knowledge and problem solving. One broad direction in pursuing this goal is understanding the relationships between existing models of rationality and bounded rationality for similar tasks. Models of rationality refer to those approaches in which the optimal properties of the models are deductively provable, i.e. in which the processing is rational. Representative models of rationality used in AIM are deductive logical models, statistical models such as Bayesian inference models, and decision-analytic models. Models of bounded rationality are those which do not guarantee such optimal properties nor yield to deductive correctness proofs. These models have their roots in cognitive psychology. In this article we show how explicating the relationship between models of rationality and bounded rationality might be done in the case of abductive tasks in medicine. This is done by positioning these modeling approaches within the same framework (an abstract computational model) and interpreting in this context both computational complexity results concerning the nature of the task and empirical results studies of human problem-solving behavior.

Artificial Intelligence↗
PubMed1988

GESA--a two-dimensional processing system using knowledge base techniques.

The successful analysis of two-dimensional (2-D) polyacrylamide electrophoresis gels demands considerable experience and understanding of the protein system under investigation as well as knowledge of the separation technique itself. The present work concerns the development of a computer system for analysing 2-D electrophoretic separations which incorporates concepts derived from artificial intelligence research such that non-experts can use the technique as a diagnostic or identification tool. Automatic analysis of 2-D gel separations has proved to be extremely difficult using statistical methods. Non-reproducibility of gel separations is also difficult to overcome using automatic systems. However, the human eye is extremely good at recognising patterns in images, and human intervention in semi-automatic computer systems can reduce the computational complexities of fully automatic systems. Moreover, the expertise and understanding of an "expert" is invaluable in reducing system complexity if it can be encapsulated satisfactorily in an expert system. The combination of user-intervention in the computer system together with the encapsulation of expert knowledge characterises the present system. The domain within which the system has been developed is that of wheat grain storage proteins (gliadins) which exhibit polymorphism to such an extent that cultivars can be uniquely identified by their gliadin patterns. The system can be adapted to other domains where a range of polymorpic protein sub-units exist. In its generalised form, the system can also be used for comparing more complex 2-D gel electrophoretic separations.

Algorithms↗
PubMed1997

A prognostic computer model to predict individual outcome in interventional cardiology. The INTERVENT Project.

It is not yet possible to predict an individual's outcome from percutaneous transluminal coronary angioplasty or alternative/adjunctive coronary interventional techniques. The purpose of the INTERVENT project is to redefine complications associated with coronary interventions, to set up a prognostic computer model to predict individual outcome and to compare the results to those of conventional statistical techniques. 2500 data items were analysed in 455 consecutive patients (mean age: 61.1 +/- 8.3 years; range 33-84 years; 80.4% male, 16.7% unstable angina, 5.1%/10.1% acute/subacute myocardial infarction) undergoing coronary interventions at three university centres. In-lab/out-of-lab complication rates were 0.4%/0.9% (death), 1.8%/0.2% (abrupt vessel closure with myocardial infarction) and 5.5%/4.0% (haemodynamic complications). Computer algorithms derived by applying techniques from artificial intelligence were able (1) to reduce the set of possible relevant risk factors from 2500 to about 40, (2) to predict individual risk with an accuracy of > 95% and (3) to explain the structural relationship between outcome and risk factors. Patient data from two centres were used to construct and test the algorithm. Data from a third centre were used to evaluate the algorithm. The most important predictors-were acute myocardial infarction, heart failure (NYHA class > II), unstable angina, complex lesions, high low density lipoprotein cholesterol and duration of coronary heart disease. Neither age nor gender impaired the percutaneous transluminal coronary angioplasty results in acute ischaemic syndromes; however, for stable angina, procedural risk increased with age. There was little risk from primary percutaneous transluminal coronary angioplasty in acute myocardial infarction in patients with NYHA heart failure classes I-II; however, the risk was high for patients in NYHA classes > II, either with or without additional thrombolysis. Alternative/adjunctive intervention techniques were no predictors for in-lab-, but were predictors for post-procedural complications.

Adult↗
PubMed2026

Beyond Earth: Recent Advancements in Microgravity Biomedical and Genetic Research in Saudi Arabia.

Microgravity research has emerged as a rapidly evolving field at the intersection of space medicine, genomics, biotechnology, and precision medicine. Exposure to the space environment induces complex physiological and molecular adaptations that affect multiple biological systems, including immune regulation, metabolism, musculoskeletal function, and gene expression. Recent advances in genomics, multi-omics technologies, artificial intelligence, and bioengineering have substantially improved our understanding of biological adaptation to spaceflight and expanded opportunities for translational biomedical research. This review summarizes recent advances in genetic and biomedical research under microgravity conditions, with particular emphasis on molecular mechanisms, omics technologies, genome editing, microbiome research, regenerative medicine, and personalized healthcare approaches. Major experimental platforms, landmark spaceflight studies, and translational applications in infectious diseases, cancer biology, aging, tissue engineering, and pharmaceutical development are discussed. The review also highlights Saudi Arabia's emerging contributions to genomic medicine and space biosciences through initiatives such as the Saudi Human Genome Program, the Saudi Pangenome Project, the Saudi Space Agency, and the BioGravity Initiative. Recent Saudi participation in human spaceflight and microgravity-associated biomedical research is discussed within the context of Vision 2030 and national investments in biotechnology and precision medicine. Collectively, advances in microgravity research are expected to contribute to the advancement of precision medicine and facilitate the development of innovative diagnostic and therapeutic strategies with significant implications for both human space exploration and terrestrial healthcare.

Humans↗
PubMed2025

AutoPVPrimer: A comprehensive AI-Enhanced pipeline for efficient plant virus primer design and assessment.

Plant viruses pose a significant threat to global agriculture and require efficient tools for their timely detection. We present AutoPVPrimer, an innovative pipeline that integrates artificial intelligence (AI) and machine learning to accelerate the development of plant virus primers. The pipeline uses Biopython to automatically retrieve different genomic sequences from the NCBI database to increase the robustness of the subsequent primer design. The design_primers_with_tuning module uses a random forest classifier that optimizes parameters and provides flexibility for different experimental conditions. Quality control measures, including the evaluation of poly-X content and melting temperature, increase primer reliability. Unique to AutoPVPrimer is the visualize_primer_dimer module, which supports the visual evaluation of primer dimers-a feature missing in other tools. Primer specificity is validated via primer BLAST, which contributes to the overall efficiency of the pipeline. AutoPVPrimer has been successfully applied to the tomato mosaic virus, proving its adaptability and efficiency. The modular design allows customization by the user and extends the applicability to different plant viruses and experimental scenarios. The pipeline represents a significant advance in primer design and provides researchers with an effective tool to accelerate molecular biology experiments. Future developments aim to extend compatibility and incorporate user feedback to consolidate AutoPVPrimer as an innovative contribution to the bioinformatics toolbox and a promising resource for the advancement of plant virology research.

DNA Primers↗
PubMed2006

Improving the efficiency of case-based reasoning to deal with activated sludge solids separation problems.

The potential of Case-Based Reasoning to use the knowledge gained from past experiences to solve problematic situations has made this Artificial Intelligence technique a useful decision support tool in different environmental domains such as wastewater treatment. Case-Based Reasoning tools automatically identify similarities between present and previous situations (cases) and reuse the experiences gained from the previous situations to solve current problems. Case retrieval can be considered to be the most important step in the process of Case-Based Reasoning. In the present study we propose incorporating a relevance network in order to increase the accuracy and the efficiency of case retrieval. The result is a context-sensitive feature-weighting methodology capable of defining the model of relationships between the different attributes or features that define the context in which Case-Based Reasoning is applied. These features affect the retrieval procedure directly. The feature's degree of relevance in the network is easily translated into a set of simple rules and applied during case retrieval, specifically during the similarity calculation. The results obtained in the present study show significant improvements in the accuracy of case retrieval. With the approach presented here experts considered more than 90% of the retrieved cases to be completely relevant according to the knowledge these cases provided for dealing with solids separation problems.

Artificial Intelligence↗
PubMed2005

The estimation of distributions and the minimum relative entropy principle.

Estimation of Distribution Algorithms (EDA) have been proposed as an extension of genetic algorithms. In this paper we explain the relationship of EDA to algorithms developed in statistics, artificial intelligence, and statistical physics. The major design issues are discussed within a general interdisciplinary framework. It is shown that maximum entropy approximations play a crucial role. All proposed algorithms try to minimize the Kullback-Leibler divergence KLD between the unknown distribution p(x) and a class q(x) of approximations. However, the Kullback-Leibler divergence is not symmetric. Approximations which suppose that the function to be optimized is additively decomposed (ADF) minimize KLD(q||p), the methods which learn the approximate model from data minimize KLD(p||q). This minimization is identical to maximizing the log-likelihood. In the paper three classes of algorithms are discussed. FDA uses the ADF to compute an approximate factorization of the unknown distribution. The factors are marginal distributions, whose values are computed from samples. The second class is represented by the Bethe-Kikuchi approach which has recently been rediscovered in statistical physics. Here the values of the marginals are computed from a difficult constrained minimization problem. The third class learns the factorization from the data. We analyze our learning algorithm LFDA in detail. It is shown that learning is faced with two problems: first, to detect the important dependencies between the variables, and second, to create an acyclic Bayesian network of bounded clique size.

Algorithms↗
PubMed1996

A computerized induction analysis of possible co-variations among different elements in human tooth enamel.

In recent decades software tools in the area of artificial intelligence have rapidly developed for use in personal computers. Interactive rule induction utilizing mathematical algorithms has become a powerful tool in data analysis and in making rules and patterns explicit. Data from a Secondary Ion Mass Spectrometry (SIMS) elemental analysis of human dental enamel were used to elucidate co-variations between certain elements. A co-variation analysis was performed employing a computerized induction analysis program, as well as a neural network program. Both analyses, confirming each other, revealed co-variations between certain elements in dental enamel in addition to exclusion of data of no importance for chosen outcomes. The results are presented in hierarchic diagrams, in which the importance for every specific element is given by its position and level in the diagram (decision tree). From the results it became evident that elements such as chlorine and sodium expressed a high co-variation level. Similarly fluorine and potassium co-varied, as well as magnesium and the trace element strontium. It was demonstrated that data from an elemental analysis could be processed by an induction analysis to reveal co-variations between certain elements in tooth enamel. The biological significance of these data is not fully understood, and further analyses in the field are needed.

Algorithms↗
PubMed2005

A comparison of algorithms for inference and learning in probabilistic graphical models.

Research into methods for reasoning under uncertainty is currently one of the most exciting areas of artificial intelligence, largely because it has recently become possible to record, store, and process large amounts of data. While impressive achievements have been made in pattern classification problems such as handwritten character recognition, face detection, speaker identification, and prediction of gene function, it is even more exciting that researchers are on the verge of introducing systems that can perform large-scale combinatorial analyses of data, decomposing the data into interacting components. For example, computational methods for automatic scene analysis are now emerging in the computer vision community. These methods decompose an input image into its constituent objects, lighting conditions, motion patterns, etc. Two of the main challenges are finding effective representations and models in specific applications and finding efficient algorithms for inference and learning in these models. In this paper, we advocate the use of graph-based probability models and their associated inference and learning algorithms. We review exact techniques and various approximate, computationally efficient techniques, including iterated conditional modes, the expectation maximization (EM) algorithm, Gibbs sampling, the mean field method, variational techniques, structured variational techniques and the sum-product algorithm ("loopy" belief propagation). We describe how each technique can be applied in a vision model of multiple, occluding objects and contrast the behaviors and performances of the techniques using a unifying cost function, free energy.

Algorithms↗
PubMed2025

Privacy-hardened and hallucination-resistant synthetic data generation with logic-solvers.

MOTIVATION: Machine-generated or synthetic data is a valuable resource for training artificial intelligence algorithms, evaluating rare workflows, and sharing data under stricter data legislations. However, current statistical and deep learning methods struggle with large data volumes, are prone to hallucinating scenarios incompatible with reality, and seldom quantify privacy meaningfully. RESULTS: Here, we introduce Genomator, a logic solving approach (SAT solving), which efficiently produces private and realistic representations of the original data. We demonstrate the method on genomic data, which arguably is the most complex and private information. We benchmark Genomator against state-of-the-art methodologies (Markov generation, Wasserstein Generative Adversarial Network and Conditional Restricted Boltzmann Machines), demonstrating a 40%-530% accuracy improvement and 57%-172% higher privacy. Genomator is also 3-100 times more efficient, making it the only tested method that scales to whole genomes. We show the universal trade-off between privacy and accuracy, and use Genomator's tuning capability to cater to all applications along the spectrum, from provable private representations of sensitive cohorts, to datasets with indistinguishable pharmacogenomic profiles. Demonstrating the production-scale generation of tuneable synthetic genomes hold great potential for balancing underrepresented populations in medical research and advancing global data exchange. AVAILABILITY AND IMPLEMENTATION: Genomator is available at https://github.com/csiro/genomator.

Algorithms↗
PubMed1996

Pattern recognition system for focal liver lesions using "crisp" and "fuzzy" classifiers.

RATIONALE AND OBJECTIVES: To determine the diagnostic performance of an artificial intelligence system for classification of focal liver lesions, in comparison to human observers. METHODS: One hundred forty-three focal hepatic lesions were evaluated with dynamic computed tomography. The study comprised 59 hemangiomas, 24 other benign lesions (focal nodular hyperplasia, adenoma), and 60 malignant liver lesions (18 primary, 42 secondary). All lesions but the hemangiomas were histologically examined by needle biopsy. For delineation of the lesion, a region of interest was defined interactively. The pattern recognition was performed in two steps with initial extraction of textural features: training of a classifier and classification of the lesions. The accuracy of classification of hepatic lesions into three groups (hemangioma, other benign processes, malignant lesions) was tested. The results were compared with those achieved by human observers using receiver operating characteristic statistical analysis. RESULTS: The accuracy (total rate of correct diagnoses) was 90.2%. False classifications were found owing to small size, weak contrast enhancement after bolus injection, respiratory movement, and atypical morphology of the lesion. The area under the receiver operating characteristic curve was not significantly different for computer and human observers. CONCLUSIONS: The system demonstrated a diagnostic accuracy comparable to human observers. Further improvement with increasing numbers of typical computed tomographic series for training of the classifier can be expected.

Adenoma↗
PubMed2005

Support vector machines for automated gait classification.

Ageing influences gait patterns causing constant threats to control of locomotor balance. Automated recognition of gait changes has many advantages including, early identification of at-risk gait and monitoring the progress of treatment outcomes. In this paper, we apply an artificial intelligence technique [support vector machines (SVM)] for the automatic recognition of young-old gait types from their respective gait-patterns. Minimum foot clearance (MFC) data of 30 young and 28 elderly participants were analyzed using a PEAK-2D motion analysis system during a 20-min continuous walk on a treadmill at self-selected walking speed. Gait features extracted from individual MFC histogram-plot and Poincaré-plot images were used to train the SVM. Cross-validation test results indicate that the generalization performance of the SVM was on average 83.3% (+/-2.9) to recognize young and elderly gait patterns, compared to a neural network's accuracy of 75.0+/-5.0%. A "hill-climbing" feature selection algorithm demonstrated that a small subset (3-5) of gait features extracted from MFC plots could differentiate the gait patterns with 90% accuracy. Performance of the gait classifier was evaluated using areas under the receiver operating characteristic plots. Improved performance of the classifier was evident when trained with reduced number of selected good features and with radial basis function kernel. These results suggest that SVMs can function as an efficient gait classifier for recognition of young and elderly gait patterns, and has the potential for wider applications in gait identification for falls-risk minimization in the elderly.

Adult↗