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 1,333 records · Page 74Linked to original sources
PubMed2007

The dynamic lift of developmental process.

What are the essential properties of human intelligence, currently unparalleled in its power relative to other biological forms and relative to artificial forms of intelligence? We suggest that answering this question depends critically on understanding developmental process. This paper considers three principles potentially essential to building human-like intelligence: the heterogeneity of the component processes, the embedding of development in a social world, and developmental processes that change the cognitive system as a function of the history of soft-assemblies of these heterogeneous processes in specific tasks. The paper uses examples from human development and from developmental robotics to show how these processes also may underlie biological intelligence and enable us to generate more advanced forms of artificial intelligence.

Brain↗
PubMed2026

Large-scale AI analysis reveals missed opportunities in albuminuria testing and disease-modifying therapy implementation.

AIMS: Albuminuria is a key diagnostic and prognostic biomarker of chronic kidney disease (CKD), associated with adverse cardiovascular and renal outcomes. Despite guideline recommendations, urine albumin-to-creatinine ratio (UACR) testing is infrequently performed in cardiology. This study assessed the uptake of UACR testing, the estimated prevalence of undiagnosed albuminuria, and the use of disease-modifying therapies in patients with cardio-kidney-metabolic (CKM) disease. METHODS AND RESULTS: We conducted a retrospective cohort study of all adults seen at the cardiology department of a tertiary referral centre between 2019 and 2024. Data were extracted using CTcue, an AI-driven platform. Albuminuria was defined as UACR &#x2265;30 mg/g. A weighted logistic regression model estimated albuminuria prevalence in untested patients. Among 77 351 patients (44.8% female, mean age 64.4 years), only 8.9% had a recorded UACR, of whom 46.4% had albuminuria. Testing rates were low across high-risk groups: 29.9% in diabetes, 21.7% in heart failure, and 13.7% in hypertension. In untested patients, the predicted prevalence of albuminuria was 36.6%, and highest in those with eGFR <30 mL/min/1.73m2 (70.0%), heart failure (47.8%), or diabetes (46.8%). Use of disease-modifying therapies was low, even among patients with confirmed albuminuria. In patients with documented vs. predicted albuminuria, 43.0% vs. 39.1% received renin-angiotensin system inhibitors, 12.8% vs. 5.7% received SGLT2 inhibitors, and <1% in both groups received finerenone. CONCLUSION: Albuminuria is substantially underdetected in cardiology practice, possibly contributing to underuse of effective CKM therapies. Systematic UACR screening with structured treatment protocols may help close this gap and improve outcomes for patients with CKM disease.

Humans↗
PubMed2026

scBaseCount: An AI agent-curated, standardized, auto-updated single-cell data repository.

Single-cell RNA sequencing has transformed cell biology by enabling precise transcriptomic measurements of individual cells. The Sequence Read Archive (SRA) is the largest public repository of sequencing reads, yet much of it remains underutilized due to unstandardized metadata. Here, we introduce scBaseCount, a database that leverages an AI agent to automate discovery and metadata extraction and standardize data processing. Built by mining all 10x Genomics datasets, scBaseCount is the largest public repository of single-cell gene expression data, comprising over 502 million cells across 27 organisms and 75 tissues. It offers an unbiased view of the data landscape within the SRA and enables the training of more performant computational models through access to broader phenotypic diversity. Uniform processing enables measurement of both intronic and exonic reads and non-coding gene expression and improves alignment across experiments. Moreover, scBaseCount provides a blueprint for how AI can be leveraged to autonomously curate biological data repositories.

Single-Cell Analysis↗
PubMed2003

Dynamic three-dimensional echocardiography combined with semi-automated border detection offers advantages for assessment of resynchronization therapy.

Simultaneous electrical stimulation of both ventricles in patients with interventricular conduction disturbance and advanced heart failure improves hemodynamics and results in increased exercise tolerance, quality of life. We have developed a novel technique for the assessment and optimization of resynchronization therapy. Our approach is based on transthoracic dynamic three-dimensional (3D) echocardiography and allows determination of the most delayed contraction site of the left ventricle (LV) together with global LV function data. Our initial results suggest that fast reconstruction of the LV is feasible for the selection of the optimal pacing site and allows identifying LV segments with dyssynchrony.

Arrhythmias, Cardiac↗
PubMed2026

Assessing AI literacy and attitudes among medical students: implications for integration into&#xa0;healthcare practice.

PURPOSE: This study aims to assess AI literacy and attitudes among medical students and explore their implications for integrating AI into healthcare practice. DESIGN/METHODOLOGY/APPROACH: A quantitative research design was employed to comprehensively evaluate AI literacy and attitudes among 374 Lusaka Apex Medical University medical students. Data were collected from April 3, 2024, to April 30, 2024, using a closed-ended questionnaire. The questionnaire covered various aspects of AI literacy, perceived benefits of AI in healthcare, strategies for staying informed about AI, relevant AI applications for future practice, concerns related to AI algorithm training and AI-based chatbots in healthcare. FINDINGS: The study revealed varying levels of AI literacy among medical students with a basic understanding of AI principles. Perceptions regarding AI's role in healthcare varied, with recognition of key benefits such as improved diagnosis accuracy and enhanced treatment planning. Students relied predominantly on online resources to stay informed about AI. Concerns included bias reinforcement, data privacy and over-reliance on technology. ORIGINALITY/VALUE: This study contributes original insights into medical students' AI literacy and attitudes, highlighting the need for targeted educational interventions and ethical considerations in AI integration within medical education and practice.

Students, Medical↗
PubMed1999

The efficacy of physiological cost index (PCI) measurement of a subject walking with an Intelligent Prosthesis.

The Intelligent Prosthesis may enable lower limb amputees to walk faster than with conventionally damped prostheses and as a result the physical burden involved in walking could be expected to be considerably higher. The aim of this study was to investigate whether or not physiological cost index (PCI) is applicable as an indicator for monitoring the amount of exercise load involved in walking with an Intelligent Prosthesis. The method used a treadmill and monitored gas exchange, ventilation and heart rate (HR) in 6 unilateral trans-femoral amputees, ages were between 17 and 34 with an average age of 23.1. The exercise protocol was as follows: for each person speeds at 0.8 times the subject's free level walking speed, 1.0 times, 1.2 times, 1.4 times and for some 1.6 times were applied. In each case the index of correlation between PCI and oxygen uptake in response to walking speed was calculated. A significant correlation was observed between PCI and oxygen uptake in each case, which indicated a close relationship between cardiopulmonary factor and energy consumption while walking. These results suggest that PCI is of use as an indicator for ascertaining the amount of exercise load in walking with an Intelligent Prosthesis.

Adolescent↗
PubMed1997

Classification strategies for the grading of renal cell carcinomas, based on nuclear morphometry and densitometry.

The various grading systems proposed for renal cell carcinomas all suffer from problems related to inter-observer variability. Some of these grading systems are based, either partially or wholly, on morphonuclear criteria, such as nuclear size and shape, anisonucleosis, and chromatin pattern. These criteria can be quantitatively (and thus objectively) evaluated by means of the computer-assisted microscopic analysis of Feulgen-stained nuclei. In the present work, 39 quantitative variables, including two morphometric, 28 chromatin pattern-related, and nine DNA ploidy level-related, were computed for 65 renal cell carcinomas. The actual diagnostic information contributed by each variable was determined by means of multifactorial statistical analysis (discriminant analysis) and two artificial intelligence-related methods of data classification (the decision tree and production rule methods). The results show that quantitative information, as provided by the computer-assisted microscopy of Feulgen-stained nuclei and analysed by means of artificial intelligence-related methods of data classification, contributes significant diagnostic information for the grading of renal cell carcinoma, thus reducing the problem of inter-observer reproducibility.

Adult↗
PubMed1990

Nurse scheduling models: a state-of-the-art review.

Nursing salaries make up the largest single element in hospital costs. Thus, effective scheduling of nursing personnel is important in controlling health-care costs. Scheduling nurses in hospitals is a complex problem due to variability in demand and a variety of conflicting interests and objectives. This article reviews the models that have been developed for nurse scheduling, including heuristic-, optimization- and artificial intelligence-based models. The approaches and limitations of these models are discussed, and a direction for future research is identified.

Artificial Intelligence↗
PubMed2026

AI-Supported, Integrative Prediction of Postoperative Delirium: Protocol for the CONFUSED Study.

BACKGROUND: Postoperative delirium (POD) is a frequent and serious complication in older surgical patients, characterized by acute cognitive dysfunction and fluctuating levels of consciousness. POD is associated with prolonged hospitalization, long-term cognitive decline, reduced quality of life, and increased mortality. Despite its clinical relevance, the underlying pathophysiological mechanisms remain poorly understood, and reliable biomarkers for early prediction and prevention are lacking. OBJECTIVE: The CONFUSED study aims to identify molecular and clinical predictors of POD by integrating clinical data with proteomic, transcriptomic, and epigenetic analyses. The primary objective is to develop predictive models for POD using multimodal data. Secondary objectives include the identification of delirium-associated genes, proteins, and epigenetic signatures, as well as the exploration of patient subgroups at increased risk for POD. METHODS: CONFUSED is a prospective observational cohort study conducted at a German university hospital. Adult patients undergoing major surgery under general anesthesia will be enrolled until 100 cases of POD have been observed, which is expected to require a total sample size of approximately 200 to 300 patients. Blood samples are collected at 4 predefined time points: before premedication, immediately after surgery, and on postoperative days 2 and 5. Samples undergo comprehensive proteomic profiling, transcriptomic analysis using RNA microarrays, DNA methylation analysis, and genotyping of selected polymorphisms. Clinical data, including demographics, comorbidities, perioperative variables, medications, and delirium assessments using the Confusion Assessment Method (CAM) and CAM for the intensive care unit, are systematically recorded. Statistical analyses include univariate and multivariate methods, as well as machine learning approaches such as random forests and support vector machines, to identify relevant biomarkers and develop predictive models. The study protocol follows STROBE (Strengthening the Reporting of Observational Studies in Epidemiology) and TRIPOD (Transparent Reporting of a Multivariable Prediction Model for Individual Prognosis or Diagnosis) guidelines and was approved by the responsible ethics committees. RESULTS: The study was registered in the German Clinical Trials Register (DRKS00033854) on March 18, 2024. Recruitment started in January 2024 and is ongoing at the time of manuscript submission. As of now, 135 patients have been enrolled. Sample collection and laboratory analyses are ongoing. Data analysis began in January 2026, with first results anticipated in July 2026. Final data lock is anticipated after the completion of recruitment. CONCLUSIONS: By integrating multimodal molecular data with clinical parameters and applying advanced machine learning techniques, the CONFUSED study aims to improve the prediction and understanding of POD. The results are expected to support the development of personalized preventive strategies and contribute to improved perioperative care for patients at risk of POD.

Humans↗
PubMed2026

Automated Classification of Lymphoma Subtypes From Histopathological Images Using a U-Net Deep Learning Model: Comparative Evaluation Study.

BACKGROUND: Accurate classification and grading of lymphoma subtypes are essential for treatment planning. Traditional diagnostic methods face challenges of subjectivity and inefficiency, highlighting the need for automated solutions based on deep learning techniques. OBJECTIVE: This study aimed to investigate the application of deep learning technology, specifically the U-Net model, in classifying and grading lymphoma subtypes to enhance diagnostic precision and efficiency. METHODS: In this study, the U-Net model was used as the primary tool for image segmentation integrated with attention mechanisms and residual networks for feature extraction and classification. A total of 620 high-quality histopathological images representing 3 major lymphoma subtypes were collected from The Cancer Genome Atlas and the Cancer Imaging Archive. All images underwent standardized preprocessing, including Gaussian filtering for noise reduction, histogram equalization, and normalization. Data augmentation techniques such as rotation, flipping, and scaling were applied to improve the model's generalization capability. The dataset was divided into training (70%), validation (15%), and test (15%) subsets. Five-fold cross-validation was used to assess model robustness. Performance was benchmarked against mainstream convolutional neural network architectures, including fully convolutional network, SegNet, and DeepLabv3+. RESULTS: The U-Net model achieved high segmentation accuracy, effectively delineating lesion regions and improving the quality of input for classification and grading. The incorporation of attention mechanisms further improved the model's ability to extract key features, whereas the residual structure of the residual network enhanced classification accuracy for complex images. In the test set (N=1250), the proposed fusion model achieved an accuracy of 92% (1150/1250), a sensitivity of 91.04% (1138/1250), a specificity of 89.04% (1113/1250), and an F1-score of 90% (1125/1250) for the classification of the 3 lymphoma subtypes, with an area under the receiver operating characteristic curve of 0.95 (95% CI 0.93-0.97). The high sensitivity and specificity of the model indicate strong clinical applicability, particularly as an assistive diagnostic tool. CONCLUSIONS: Deep learning techniques based on the U-Net architecture offer considerable advantages in the automated classification and grading of lymphoma subtypes. The proposed model significantly improved diagnostic accuracy and accelerated pathological evaluation, providing efficient and precise support for clinical decision-making. Future work may focus on enhancing model robustness through integration with advanced algorithms and validating performance across multicenter clinical datasets. The model also holds promise for deployment in digital pathology platforms and artificial intelligence-assisted diagnostic workflows, improving screening efficiency and promoting consistency in pathological classification.

Humans↗
PubMed2025

Multi-omics technologies: Novel tools and methods for assessing nerve injury and regeneration.

Recently, with the rapid advancement of multi-omics technologies, including genomics, transcriptomics, proteomics, and metabolomics, new tools and approaches have been introduced for studying nerve injury and regeneration. This review highlights the application and progress of multi-omics in uncovering the mechanisms of nerve injury, guiding the development of regenerative strategies, and promoting clinical translation. By integrating multi-omics datasets, researchers can comprehensively track dynamic molecular changes following nerve injury, including abnormal gene expression, disrupted protein signaling, altered metabolic programs, and shifts in the immune microenvironment. Single-cell multi-omics technologies resolve cellular heterogeneity, revealing the distinct functions of neurons, glial cells, and immune cell subpopulations during the injury response. Spatially resolved transcriptomics maintain the spatial context of lesion and regeneration sites, enabling precise localization for targeted interventions. Multi-omics technologies not only identify key molecular players involved in nerve regeneration but also create opportunities for personalized medicine. Nonetheless, integrating multi-omics data poses technical challenges, including high dimensionality, batch effects, and algorithmic constraints, while ethical concerns related to stem cell therapy and gene editing require stringent oversight. To transition from structural reconstruction to functional remodeling, future research should emphasize artificial intelligence-driven data integration, organ-on-a-chip modeling, and cross-disciplinary collaboration to overcome existing technical barriers and accelerate the clinical application of neuroregenerative therapies.

artificial intelligence↗
PubMed1997

The application of computerized content analysis of speech to the diagnostic process in a psychiatric outpatient clinic.

Twenty-five new psychiatric outpatient were clinically evaluated and were routinely administered a brief psychological screening battery which included measures of symptoms, personality, and cognitive function. Included in this assessment procedure were the Gottschalk-Gleser Content Analysis Scales on which scores were derived from five-minute speech samples by means of an artificial intelligence-based computer program. Intercorrelations of these content analysis measures with scores obtained from the MMPI-2, SCL90, and other measures confirmed previously published construct validation findings. The use of this computerized content analysis procedure for initial, rapid diagnostic neuropsychiatric appraisal is supported by this research.

Adult↗
PubMed2003

Virtual patient simulator for distributed collaborative medical education.

Project TOUCH (Telehealth Outreach for Unified Community Health; http://hsc.unm.edu/touch) investigates the feasibility of using advanced technologies to enhance education in an innovative problem-based learning format currently being used in medical school curricula, applying specific clinical case models, and deploying to remote sites/workstations. The University of New Mexico's School of Medicine and the John A. Burns School of Medicine at the University of Hawai'i face similar health care challenges in providing and delivering services and training to remote and rural areas. Recognizing that health care needs are local and require local solutions, both states are committed to improving health care delivery to their unique populations by sharing information and experiences through emerging telehealth technologies by using high-performance computing and communications resources. The purpose of this study is to describe the deployment of a problem-based learning case distributed over the National Computational Science Alliance's Access Grid. Emphasis is placed on the underlying technical components of the TOUCH project, including the virtual reality development tool Flatland, the artificial intelligence-based simulation engine, the Access Grid, high-performance computing platforms, and the software that connects them all. In addition, educational and technical challenges for Project TOUCH are identified.

Artificial Intelligence↗
PubMedDate not supplied

Causal reasoning in computer programs for medical diagnosis.

Over the last decade substantial advances have been made in the use of causal pathophysiological knowledge in artificial intelligence-based programs for medical diagnosis. Various forms of causal representations have been used. They include probabilistic models, quantitative models, qualitative models, and models that describe causal relations at multiple levels of detail. This paper briefly analyses these methods using three representative systems. Outstanding problems and possible direction in further exploitation of causal reasoning for medical decision-support systems are also discussed.

Artificial Intelligence↗
PubMedDate not supplied

Intelligent Li ion battery management based on a digital signal processor for a moving actuator total artificial heart.

An intelligent Li Ion battery management (ILBM) system was developed based on a digital signal processor (DSP). Instead of using relatively complicated hardware charging control, a DSP algorithm was used, and favorable characteristics in volume, mass, and temperature increase of the implantable battery were achieved. In vitro tests were performed to evaluate the DSP based algorithm for Li Ion charging control (24 V dc motor input power 16 W, 5 L/min, 100 mmHg afterload). In this article, the first improvement was volume reduction using a Li Ion battery (3.6 V/Cell, 900 mA, seven cells: 25.2 V, 22.7 W). Its volume and mass were decreased by 40% and 50% respectively (40*55*75 mm, 189 g), compared to previously reported results, with total energy capacity increased by 110% (more than 60 min vs 25 min run time in the other battery). The second improvement includes the ILBM, which can control the performance detection for each unit cell and has a low temperature rise. The ILBM's unit cell energy detection was important because the low performance of one cell dropped to 50% of the total performance along with a 20% increase in surface temperature. All electronics for a transcutaneous energy transmission (TET), battery, and telemetry were finalized for hybridization and used for total artificial heat (TAH) implantation.

Algorithms↗
PubMed2000

A pilot study comparing the cognitive demand of walking for transfemoral amputees using the Intelligent Prosthesis with that using conventionally damped knees.

OBJECTIVE: To compare the cognitive demand of walking when using a conventional prosthesis with that using a microprocessor-controlled prosthesis. DESIGN: Ten unilateral transfemoral amputees wearing conventional pneumatic swing phase control (conventional prosthesis) prostheses walked on a treadmill which enforced a pattern of constantly varying speeds. The subjects simultaneously performed a simple or a complex distracting task. Following a period of accustomization, the subjects performed the same test wearing a prosthesis with microprocessor control of swing phase damping (the Intelligent Prosthesis). OUTCOME MEASURES: The three-dimensional trajectory (sway) of a retroreflective marker attached to the forehead was measured by a video-based motion analysis system, and used as a measure of gait quality. The ratio of the sway for the complex task over the simple task (the 'automation index') was used as a measure of the degree of automation of gait. RESULTS: No significant differences were found in the automation index between the two devices. However, the total sway for the conventional prosthesis was significantly higher. Sway during the complex distracting task was significantly higher than during the simple task. CONCLUSIONS: The microprocessor-controlled prosthesis was not found to be less cognitively demanding than a conventional prosthesis.

Adult↗