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 973 records · Page 54Linked to original sources
PubMed2005

Prediction of vascular tissue engineering results with artificial neural networks.

Tissue engineers are often confused on finding the most successful strategy for specific patient. In this study, we used artificial neural networks to predict the outcomes of different vascular tissue engineering strategies, thus providing advisory information for experimental designers. Over 30 variables were used as features of the tissue engineering strategies. Different architectures of artificial neural networks with back propagation algorithm were tested to obtain the best model configuration for the prediction of the tissue engineering strategies. In the computational experiments, the artificial neural networks with one and two hidden layers could, respectively, detect unsuccessful strategies with the highest predictive accuracy of 91.45 and 94.24%. In conclusion, artificial intelligence has great potential in tissue engineering decision support. It can provide accurate advisory information for tissue engineers, thus reducing failures and improving therapeutic effects.

Animals↗
PubMed2004

Quantification of human motion: gait analysis-benefits and limitations to its application to clinical problems.

The technology supporting the analysis of human motion has advanced dramatically. Past decades of locomotion research have provided us with significant knowledge about the accuracy of tests performed, the understanding of the process of human locomotion, and how clinical testing can be used to evaluate medical disorders and affect their treatment. Gait analysis is now recognized as clinically useful and financially reimbursable for some medical conditions. Yet, the routine clinical use of gait analysis has seen very limited growth. The issue of its clinical value is related to many factors, including the applicability of existing technology to addressing clinical problems; the limited use of such tests to address a wide variety of medical disorders; the manner in which gait laboratories are organized, tests are performed, and reports generated; and the clinical understanding and expectations of laboratory results. Clinical use is most hampered by the length of time and costs required for performing a study and interpreting it. A "gait" report is lengthy, its data are not well understood, and it includes a clinical interpretation, all of which do not occur with other clinical tests. Current biotechnology research is seeking to address these problems by creating techniques to capture data rapidly, accurately, and efficiently, and to interpret such data by an assortment of modeling, statistical, wave interpretation, and artificial intelligence methodologies. The success of such efforts rests on both our technical abilities and communication between engineers and clinicians.

Biomechanical Phenomena↗
PubMed2026

What's the meta now? More updates on the problems with systematic reviews.

BACKGROUND: Systematic reviews are intended to provide trustworthy evidence synthesis, yet previous iterations of this living review have identified numerous recurring problems in their conduct and reporting. This article presents the third version and second update of the living systematic review examining issues raised across the academic literature. METHODS: Using consistent eligibility criteria and methods from earlier versions, literature searches were updated to May 2025. Eligible meta-research and editorial articles describing problems with systematic reviews were analyzed to identify emerging themes. Additionally, four basic indicators of methodological quality of the included meta-research were presented across review versions. RESULTS: The update included 209 additional articles. Critically low methodological quality and absence of protocols remained among the most frequently reported issues in systematic reviews across disciplines and journals but notably in evidence underpinning clinical practice guidelines. Spin in abstracts and conflicts of interest continued to be common. Apparent improvements in reporting quality were inconsistent, with modest gains in some full-text reporting but persistent deficiencies in abstracts. Authorship diversity of systematic reviews improved in gender representation but remained geographically concentrated in high-income countries, and primary research included in reviews similarly lacked global representativeness. The issue of misalignment between systematic review evidence bases and global burden of disease bring the total number of problems with systematic reviews to 69. Emerging use of automation and artificial intelligence was variably reported. Descriptive comparison of meta-research articles over the three versions of this living review suggests a greater proportion meeting basic quality indicators in more recent updates. CONCLUSION: Across successive updates, problems with systematic reviews remain widespread and consistent rather than isolated. Incremental reporting improvements coexist with persistent concerns about transparency, bias, and representativeness. Future efforts should prioritize evaluating interventions and aligning research incentives to support genuinely trustworthy evidence synthesis.

Humans↗
PubMed2004

Analysis of nonlinear systems to estimate intraocular lens position after cataract surgery.

PURPOSE: To compare the performance of neural networks with that of linear regression to predict the postoperative effective lens position (ELP) from preoperative biometry measurements. SETTING: Departments of Ophthalmology, Medical Cybernetics and Artificial Intelligence, and Medical Physics, Medical University of Vienna, Vienna, Austria. METHODS: The neural-network-type multilayer perceptron (MLP) and a linear regression technique were used to predict ELP. Suitable MLP models and variable input combinations were selected by extended-feature subset selection. Apart from the usual preoperative biometric variables, anterior chamber depth and lens thickness were measured with partial coherence interferometry and white-to-white measurements were used as input variables. RESULTS: Prediction of ELP could be improved from a correlation coefficient (Pearson) of 0.54 for linear regression to a coefficient of 0.68 for the MLP; however, this difference was not statistically significant. CONCLUSION: The prediction of postoperative ACD with the MLP was not significantly better than the prediction using linear regression.

Adult↗
PubMed2026

National Antimicrobial Resistance Monitoring System: Three Decades of Advancing Public Health Through Integrated Surveillance of Antimicrobial Resistance.

Antimicrobial resistance (AMR) occurs when bacteria and other microorganisms adapt in ways that make medicines less effective, causing infections that are harder to treat and more likely to spread. According to the Centers for Disease Control and Prevention (CDC), AMR infections affect millions of Americans each year and contribute to thousands of deaths (CDC, 2019). After three decades of operation, the U.S. National Antimicrobial Resistance Monitoring System (NARMS) stands as a model of sustained, collaborative public health surveillance. What began in 1996 as an effort to track resistance in Salmonella and E. coli O157 has evolved into a One Health surveillance network monitoring AMR across the farm-to-fork continuum. Through a partnership among CDC, the Food and Drug Administration (FDA), the U.S. Department of Agriculture (USDA), state and local health departments, and universities, NARMS has become the backbone of foodborne AMR surveillance in the United States. The past decade has been particularly transformative. NARMS explored new sampling to include companion animals, minor livestock, aquaculture, surface water, and wildlife. Whole-genome sequencing (WGS) revolutionized the program's capabilities, enabling timely identification of emerging pathogens and revealing how resistance genes spread. Near real-time public dashboards make NARMS data accessible to researchers, clinicians, regulators, and policymakers. NARMS data shape decisions about new animal drug approvals, guide stewardship programs, and inform clinical treatment guidelines nationwide. As NARMS enters its fourth decade with a 2026-2030 strategic plan, the program will leverage artificial intelligence and metagenomics while expanding surveillance to fill remaining gaps ensuring this vital system continues to protect the food supply and both human and animal health from AMR.

Antimicrobial Resistance (AMR)↗
PubMed2026

Promises and Pitfalls of ctDNA testing in the Management of Cholangiocarcinoma.

Diagnosis and treatment of cholangiocarcinoma is often limited by the availability of tissue biopsies for genomic analysis. Liquid biopsies using blood circulating tumor DNA (ctDNA) have emerged as a valuable and non-invasive alternative to conventional testing. ctDNA analysis has advanced the treatment paradigm for cholangiocarcinoma (CCA) by identifying targetable mutations and molecular mechanisms of treatment resistance. Additionally, it has shown preliminary promise in stratifying patients for adjuvant systemic therapy and enabling earlier detection of relapse. However, current ctDNA platforms face biological and technical challenges that limit their sensitivity for certain mutation types (i.e. gene fusions and amplifications), which are commonly found in CCA. To overcome these hurdles, new sequencing techniques and analytic methods involving artificial intelligence, epigenetic profiling, and diverse reference genomes are being developed. These advanced technologies underscore the promise of ctDNA testing as an indispensable tool in the management and study of CCAs.

Cholangiocarcinoma↗
PubMed2005

Assessment of self-organizing maps to analyze sole-carbon source utilization profiles.

The use of community-level physiological profiles obtained with Biolog microplates is widely employed to consider the functional diversity of bacterial communities. Biolog produces a great amount of data which analysis has been the subject of many studies. In most cases, after some transformations, these data were investigated with classical multivariate analyses. Here we provided an alternative to this method, that is the use of an artificial intelligence technique, the Self-Organizing Maps (SOM, unsupervised neural network). We used data from a microcosm study of algae-associated bacterial communities placed in various nutritive conditions. Analyses were carried out on the net absorbances at two incubation times for each substrates and on the chemical guild categorization of the total bacterial activity. Compared to Principal Components Analysis and cluster analysis, SOM appeared as a valuable tool for community classification, and to establish clear relationships between clusters of bacterial communities and sole-carbon sources utilization. Specifically, SOM offered a clear bidimensional projection of a relatively large volume of data and were easier to interpret than plots commonly obtained with multivariate analyses. They would be recommended to pattern the temporal evolution of communities' functional diversity.

Bacteria↗
PubMed2026

Engineering extracellular vesicles for targeted siRNA delivery: Advances, therapeutic applications, and clinical translation.

Small interfering RNA (siRNA) therapeutics have emerged as a transformative approach for sequence-specific gene silencing, offering the potential to treat a broad spectrum of diseases by selectively suppressing disease-associated genes. However, the clinical translation of siRNA remains limited by rapid enzymatic degradation, poor cellular uptake, inadequate endosomal escape, and off-target effects, necessitating the development of efficient delivery systems. Extracellular vesicles (EVs) have gained considerable attention as natural nanocarriers owing to their excellent biocompatibility, low immunogenicity, intrinsic targeting capability, and ability to protect therapeutic cargo while traversing complex biological barriers. This review comprehensively discusses the biological characteristics of EVs, the molecular basis of RNA interference, and the major challenges associated with siRNA delivery [Fig. 1]. Recent advances in EV engineering, including cargo-loading strategies such as electroporation, sonication, extrusion, parent-cell engineering, and microfluidic approaches, together with surface functionalization using peptides, antibodies, aptamers, and hybrid nanoplatforms, are critically evaluated for improving targeting specificity and intracellular delivery. Furthermore, the therapeutic applications of engineered EV-mediated siRNA delivery in cancer, neurological disorders, liver diseases, cardiovascular diseases, inflammatory disorders, and infectious diseases are systematically summarized, highlighting their potential to enhance gene silencing while minimizing systemic toxicity. Current challenges related to large-scale manufacturing, cargo-loading efficiency, standardization, quality control, regulatory approval, and clinical translation are also discussed, together with emerging technologies involving synthetic biology, genome engineering, artificial intelligence, and multifunctional hybrid vesicles. Overall, engineered extracellular vesicles represent a highly versatile and biologically inspired platform for targeted siRNA delivery, providing a promising foundation for the development of next-generation precision RNA therapeutics and accelerating the clinical translation of gene-silencing strategies.

Extracellular vesicle engineering↗
PubMed2006

Goal-based action selection and utility-based action bias.

According to artificial intelligence studies, goal-based and utility-based agents can select an action to attain a desired outcome. The goal-based agent sets a specific goal regardless of its utility at first, and selects the action that leads to that goal (goal-based action selection). The utility-based agent compares the utilities of different possible outcomes, and selects the action that causes the outcome with the highest utility (utility-based action bias). The medial prefrontal cortex is involved in implementing the goal-based action selection and the striatum is involved in implementing the utility-based action bias. Goal-based action selection may be temporarily dominant over the utility-based action bias in a new environment, whereas the utility-based action bias becomes dominant after acquisition of action utilities in the environment. This transition of dominance between the two decision systems may be enhanced by a reference-point shift based on the goal-setting process during goal-based action selection.

Animals↗
PubMed2005

Fully automatic segmentation of white matter hyperintensities in MR images of the elderly.

The role of quantitative image analysis in large clinical trials is continuously increasing. Several methods are available for performing white matter hyperintensity (WMH) volume quantification. They vary in the amount of the human interaction involved. In this paper, we describe a fully automatic segmentation that was used to quantify WMHs in a large clinical trial on elderly subjects. Our segmentation method combines information from 3 different MR images: proton density (PD), T2-weighted and fluid-attenuated inversion recovery (FLAIR) images; our method uses an established artificial intelligent technique (fuzzy inference system) and does not require extensive computations. The reproducibility of the segmentation was evaluated in 9 patients who underwent scan-rescan with repositioning; an inter-class correlation coefficient (ICC) of 0.91 was obtained. The effect of differences in image resolution was tested in 44 patients, scanned with 6- and 3-mm slice thickness FLAIR images; we obtained an ICC value of 0.99. The accuracy of the segmentation was evaluated on 100 patients for whom manual delineation of WMHs was available; the obtained ICC was 0.98 and the similarity index was 0.75. Besides the fact that the approach demonstrated very high volumetric and spatial agreement with expert delineation, the software did not require more than 2 min per patient (from loading the images to saving the results) on a Pentium-4 processor (512 MB RAM).

Aged↗
PubMed2025

Comparative analysis of convolutional neural network models for the histopathological differentiation of acinic cell carcinoma and secretory carcinoma.

OBJECTIVE: Although artificial intelligence tools show promise for enhancing the diagnosis of head and neck lesions, few studies have tested these resources for the microscopic diagnosis of salivary gland tumors. Specifically, the microscopic differentiation between acinic cell carcinoma and secretory carcinoma has never been addressed in this context. Therefore, this exploratory study aimed to comparatively evaluate the feasibility of applying convolutional neural networks for the microscopic differentiation between acinic cell carcinomas and secretory carcinomas. METHODS: A cross-sectional study using whole-slide images from 46 patients with acinic cell carcinoma (n = 26) or secretory carcinoma (n = 20) was conducted. Eight CNNs (ResNet-50, InceptionV3, VGG16, Xception, MobileNet, DenseNet121, EfficientNetB0, and EfficientNetV2B0) were trained and evaluated for accuracy, sensitivity, specificity, F1-score, and AUC. Performance was measured in training, validation, and test subsets. Accuracy and loss curves were also presented. RESULTS: InceptionV3 demonstrated the best overall performance, with the lowest loss (1.39), highest accuracy (0.81), sensitivity (0.90), and F1-score (0.81). VGG16 achieved the highest AUC (0.86) and precision (0.77). DenseNet121 showed the lowest performance in terms of accuracy (0.65) and F1-Score (0.52), but the highest specificity (0.85). CONCLUSION: This proof-of-concept study suggests that convolutional neural networks may be feasible tools to support the microscopic differentiation between acinic cell carcinoma and secretory carcinoma. The performance of these models critically depends on the size of the dataset and the quality of annotations. The findings should be interpreted cautiously given the limited dataset and potential sources of bias. Further validation with larger, multicenter datasets is needed before any clinical application can be considered.

Humans↗
PubMed2025

ChemPerturb-seq screen identifies a small molecule cocktail enhancing human beta cell survival after subcutaneous transplantation.

Traditional chemical screens have focused on a single assay per screen, making them labor intensive and costly. Here, we combined a chemical screen with single-cell RNA sequencing (scRNA-seq) to perform Chemical Perturb-seq (ChemPerturb-seq), enabling a systematic analysis of the molecular changes of human beta cells upon individual small molecule treatments. Using this platform, we performed an in vivo barcoded screen and discovered a small molecule cocktail, including beta-lipotropin 61-91, insulin growth factor-1, and prostaglandin E2, with which preconditioning human beta cells and primary islets significantly enhanced function and survival when transplanted subcutaneously to female, but not to male, mice. We identified two additional molecules, serotonin and histamine, that promote islet function when transplanted subcutaneously to male mice using ChemPerturb-seq. Such small molecule cocktails could be applied to improve the current FDA-approved islet transplantation procedure. Finally, we developed an artificial intelligence (AI)-powered website, ChemPerturbDB, which provides user-friendly open access analysis of the extensive ChemPerturb-seq dataset.

Humans↗
PubMed2025

Nanobioreactor detection of space-associated hematopoietic stem and progenitor cell aging.

Human hematopoietic stem and progenitor cell (HSPC) fitness declines following exposure to stressors that reduce survival, dormancy, telomere maintenance, and self-renewal, thereby accelerating aging. While previous National Aeronautics and Space Administration (NASA) research revealed immune dysfunction in low-earth orbit (LEO), the impact of spaceflight on human HSPC aging had not been studied. To study HSPC aging, our NASA-supported Integrated Space Stem Cell Orbital Research (ISSCOR) team developed bone marrow niche nanobioreactors with lentiviral bicistronic fluorescent, ubiquitination-based cell-cycle indicator (FUCCI2BL) reporter for real-time HSPC tracking in artificial intelligence (AI)-driven CubeLabs. In month-long International Space Station (ISS) missions (SpX-24, SpX-25, SpX-26, and SpX-27) compared with ground controls, FUCCI2BL reporter, whole-genome and transcriptome sequencing, and cytokine arrays demonstrated cell-cycle, inflammatory cytokine, mitochondrial gene, human repetitive element, and apolipoprotein B mRNA editing enzyme, catalytic polypeptide-like 3 (APOBEC3) deregulation together with clonal hematopoietic mutations. Furthermore, HSPC functionally organized multi-omics aging (HSPC-FOMA) analyses revealed reduced telomere maintenance, adenosine deaminase acting on RNA1 (ADAR1) p150 self-renewal gene expression, and replating capacity indicative of space-associated HSPC aging that may limit long-duration spaceflight.

Humans↗
PubMed1996

Reducing false negatives in clinical practice: the role of neural network technology.

The fact that some cervical smears result in false-negative findings is an unavoidable and unpredictable consequence of the conventional (manual microscopic) method of screening. Errors in the detection and interpretation of abnormality are cited as leading causes of false-negative cytology findings; these are random errors that are not known to correlate with any patient risk factor, which makes the false-negative findings a "silent" threat that is difficult to prevent. Described by many as a labor-intensive procedure, the microscopic evaluation of a cervical smear involves a detailed search among hundreds of thousands of cells on each smear for a possible few that may indicate abnormality. Investigations into causes of false-negative findings preceding the discovery of high-grade lesions found that many smears had very few diagnostic cells that were often very small in size. These small cells were initially overlooked or misinterpreted and repeatedly missed on rescreening. PAPNET testing is designed to supplement conventional screening by detecting abnormal cells that initially may have been missed by microscopic examination. This interactive system uses neural networks, a type of artificial intelligence well suited for pattern recognition, to automate the arduous search for abnormality. The instrument focuses the review of suspicious cells by a trained cytologist. Clinical studies indicate that PAPNET testing is sensitive to abnormality typically missed by conventional screening and that its use as a supplemental test improves the accuracy of screening.

Cervix Uteri↗
PubMed2002

Neural networks as a prognostic tool of surgical risk in lung resections.

BACKGROUND: Assessment of surgical risk in patients undergoing pulmonary resection is a fundamental goal for thoracic surgeons. Usually used risk indices do not predict the individual outcome. Neural networks (NN) are artificial intelligence software models that have been used for estimation of several prognostic situations. METHODS: Ninety-six clinical and laboratory features from each one of 141 patients who underwent lung resection were retrospectively collected. The variables were used as input data for the software. Cases were divided into a training set (n = 113) and a test set (n = 28). Four NN models were trained using the data from the training set: (1) using all variables; (2) using only the Goldman and Torrington scores; (3) using all variables except for the two scores. A fourth NN was programmed with all variables to estimate the development of major postoperative complications. The trained NN models were tested with the test set data. RESULTS: The NN using all variables with or without the scores were able to correctly classify all 28 test cases against actual outcome. The NN using all variables also estimated major postoperative complications correctly in all 28 test cases. The NN using only two indices (Goldman and Torrington) yielded 6 of 28 errors in classification. CONCLUSIONS: These data suggest that NN can integrate results from multiple data predicting the individual outcome for patients, rather than assigning them to less-precise risk group categories.

Adolescent↗
PubMed1998

Role and use of expert systems within the clinical laboratory.

Artificial intelligence can be used, mainly in the form of knowledge based systems, for different parts of clinical laboratory activity. Most of the iterative tasks for control and validation, or for maintenance or repair of automated instruments can be assisted by specialized software. There are now specific programmes (i) for control and validation of the request, where the goal is to modify the requesting behaviour of the physician, using protocol driven requests and immediate feedback, incorporating simultaneously a check of test request redundancy, (ii) for helping in equipment trouble-shooting, (iii) for technical and biological validation because too many QC data are issued from large equipment to be checked and used properly by the technologist whilst the pathologist can be assisted for the final revision of reports and (iv) for assistance in the interpretation of laboratory reports, one of the most valuable aspects of the pathologist's participation in the patient care process.

Clinical Chemistry Tests↗
PubMed1986

In vivo probes: problems and perspectives.

Devices constructed for potential use as invasive bioprobes incorporate a selective receiving site for molecular or ionic recognition, and a transducer which is capable of translating a perturbation of physical chemistry of the determinant-site reaction (interaction) into a usable signal. Four types are envisioned--implants for general hospital use, transient-use probes to replace classical blood tests, short-term implantable probes and the long-term variety. Performance criteria are selectivity, sensitivity, fast response, site-reversible, small, rugged, inexpensive, biocompatible, calibratible, facile use by non-expert personnel and ease of telemetry. These demands, not surprisingly, create enormous challenges to the sensor specialist. With respect to biocompatibility the sensor must not be involved in infection, clot formation or antigenic response, and, furthermore, protein adsorption, etc., which can affect the sensor response should be avoided. Calibration remains a problem of monumental proportions. Many devices drift from calibrated levels even in in vitro experiments, let alone in the implanted milieu. One solution has been to carry out on-line switching between patient blood and standard solutions. However, this type of approach leaves a lot to be desired with respect to portability. Another method which is attracting increasing attention is the chemometric or artificial intelligence system involving compensation by multi-sensor array configurations. Sensitivity and limit-of-detection have attracted little research due to the overwhelming nature of other difficulties. In the present paper we evaluate a number of these technical problems and discuss the architecture of devices that are currently available. Finally, some thoughts as to priorities for re-directing sensor research in the bioprobe area are presented.

Biocompatible Materials↗
PubMed1984

A global model of the neural mechanisms responsible for visuomotor coordination in toads.

A model of how the nervous system of toads processes visual information to control motor behaviour is proposed. The problem of visuomotor coordination in toads is studied through the integration of two different approaches: a top-down approach through schema theory developed in the studies of cognitive psychology, artificial intelligence and brain theory; and a bottom-up approach through the integration of physiological, anatomical, ethological, and neural modelling. The model proposes that visual information is processed in a parallel distributed way through different brain layers whose interaction defines the proper motor response for that specific situation. It is postulated that visual processing of information is organized into main schemata, which set the goal to be attained and, depending on the specific circumstances of the animal, activates different brain layers; the main schemata may use other schemata to solve a specific subproblem to reach the schemata, and a programme of schema co-ordination. With this model we have simulated how toads plan their route to reach a prey or the route to go away form a predator, depending on the state of their three-dimensional world. The model postulates specific hypotheses that could be tested experimentally on the processing of information in the toad's nervous system.

Animals↗