SEARCH · PubMed Health

Results for “artificial intelligence”

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 739 records · Page 41Linked to original sources

PubMed1993

SPROUT: a program for structure generation.

SPROUT is a new computer program for constrained structure generation that is designed to generate molecules for a range of applications in molecular recognition. It uses artificial intelligence techniques to moderate the combinatorial explosion that is inherent in structure generation. The program is presented here for the design of enzyme inhibitors. Structure generation is divided into two phases: (i) primary structure generation to produce molecular graphs to fit the steric constraints; and (ii) secondary structure generation which is the process of introducing appropriate functionality to the graphs to produce molecules that satisfy the secondary constraints, e.g., electrostatics and hydrophobicity. Primary structure generation has been tested on two enzyme receptor sites; the p-amidino-phenyl-pyruvate binding site of trypsin and the acetyl pepstatin binding site of HIV-1 protease. The program successfully generates structures that resemble known substrates and, more importantly, the predictive power of the program has been demonstrated by its ability to suggest novel structures.

Artificial Intelligence↗

PubMed2026

PubMind: literature-based genetic variant extraction and functional annotation using large language models.

Biomedical literature contains extensive functional knowledge on genetic variants, but much remains inaccessible in unstructured text. Existing resources such as ClinVar and HGMD remain limited by coverage, submission bias, update frequency, and sparse annotation. We develop PubMind, an artificial intelligence (AI) framework that uses large language models (LLMs) to triage and extract variant-function-disease associations and supporting evidence from biomedical text. PubMind captures single-nucleotide, copy-number, structural, and gene-fusion variants, and normalizes records to genomic and transcriptomic coordinates. Benchmarking shows >90% accuracy for variant recognition and 99% precision for disease extraction. Applied to >41 million PubMed abstracts and >5 million full-text articles, PubMind generates PubMind-DB, a database of ~1.3 million unique variants with contextual annotations, accessible via web interface and API. Only ~10% of PubMind variants overlap with ClinVar, and >80% of them show concordant pathogenicity labels. PubMind transforms unstructured biomedical text into structured genomic knowledge, advancing variant interpretation for precision medicine.

Large Language Models↗

PubMed2026

Biomarker-guided selection of intravesical therapy in high-risk non-muscle invasive bladder cancer: A contemporary review.

High-risk non-muscle invasive bladder cancer poses therapeutic challenges, with significant rates of recurrence and progression with standard intravesical bacillus Calmette-Guérin (BCG) therapy. Current surveillance strategies lack accurate risk stratification models to predict individual treatment response and personalized treatment options. Simultaneously, there are no well-validated alternatives to replace the current gold-standard approach based on clinical and pathologic features. This review examines emerging biomarkers and advanced technologies with the potential to enhance patient selection and personalize intravesical therapy in HR-NMIBC. Artificial intelligence(AI)-driven histopathologic tools, such as the computer histological AI biomarker, have demonstrated the ability to identify non-responders to standard therapy using whole-slide digital pathology images. In parallel, radiomics-enhanced imaging has shown promise in assessing tumor biology and immune microenvironment features predictive of BCG responsiveness. Liquid biopsy, especially urine tumor DNA analysis, is now available in the arsenal to detect minimal residual disease, stratify recurrence risk, and predict treatment response even before clinical or radiographic evidence of recurrence. Tissue-based genomic profiling has also revealed molecular alterations associated with treatment resistance, though additional validation is needed. Together, these next-generation biomarkers may represent a pivotal shift toward precision oncology in bladder cancer and their incorporation into NMIBC future clinical guidelines is both anticipated and necessary.

BCG-unresponsive disease↗

PubMedDate not supplied

Medical informatics and clinical decision making: the science and the pragmatics.

There are important scientific and pragmatic synergies between the medical decision making field and the emerging discipline of medical informatics. In the 1970s, the field of medicine forced clinically oriented artificial intelligence (AI) researchers to develop ways to manage explicit statements of uncertainty in expert systems. Classic probability theory was considered and discussed, but it tended to be abandoned because of complexities that limited its use. In medical AI systems, uncertainty was handled by a variety of ad hoc models that simulated probabilistic considerations. To illustrate the scientific interactions between the fields, the author describes recent work in his laboratory that has attempted to show that formal normative models based on probability and decision theory can be practically melded with AI methods to deliver effective advisory tools. In addition, the practical needs of decision makers and health policy planners are increasingly necessitating collaborative efforts to develop a computing and communications infrastructure for the decision making and informatics communities. This point is illustrated with an example drawn from outcomes management research.

Artificial Intelligence↗

PubMed1999

Estimation of latency changes and relative amplitudes in somatosensory evoked potentials using wavelets and regression.

Changes in onset latency and relative amplitudes of somatosensory evoked potentials (SEP) may be a convenient and reliable neurophysiological indicator of depth of anesthesia. However, to derive the components is very difficult mathematically and visual inspection or alternatively the peak-latency estimation is usually employed. A methodology for estimating the components was developed for both real-time and off-line applications based on the combination of the wavelet transforms (WT), geometric analysis, artificial intelligence (AI), and mathematical analysis of the first positive wave of SEPs. The WT together with AI constitutes a feature extraction engine for localizing the first positive peak and negative valley and hence relative amplitudes. The latency change between two averages is obtained by shifting one average toward another to achieve a best match along the positive inflections. The inflection, based on the peak, is modeled as a regression line and is refined using a steepness inference algorithm. Results from simulation and anesthetized rats show that it is reliable in comparison with visual inspection, robust to amplitude variation and signal distortion, and efficient in computation, and hence it is suitable for automation. Comparisons of interobserver variability and analysis of method agreement suggest that the method can be used as a substitute for estimations by visual inspection.

Algorithms↗

PubMed2026

AI-driven diagnostic and prognostic models for metabolic dysfunction-associated steatotic liver disease: insights from clinical, imaging, and multi-omics studies-a scoping review.

Metabolic dysfunction-associated steatotic liver disease (MASLD), formerly known as non-alcoholic fatty liver disease (NAFLD), is the most common chronic liver disease around the world, affecting 33.6% of the adult population (95% CI: 28.1%-39.5%; I 2 = 99.9%), or roughly one in three. The extent of the liver damage is variable, from simple steatosis to metabolic dysfunction-associated steatohepatitis (MASH, formerly NASH), cirrhosis and hepatocellular carcinoma (HCC). Early diagnosis is essential to prevent serious liver damage. Traditional diagnostic techniques such as liver biopsy, imaging, and biomarker testing are all invasive, costly, reduced sensitive to early-stage disease, and they also have variability among observers. Modern diagnostic and prognostic approaches based on the principles of Artificial Intelligence (AI) and specifically on machine learning (ML) and deep learning (DL) have enabled multimodal approaches integrating clinical, imaging and molecular data. This scoping review conducted per PRISMA-ScR guidelines, synthesizes findings from 73 studies (search window 2020-2026) across three dimensions: clinical data driven models, imaging-based classifiers (ultrasound, CT and MRI), and multi-omics (genomics, transcriptomics and proteomics) techniques. Moreover, emergence of models such as U-Net and LiverNet 2.x, classification models like DeepLiverNet and BiLSTM models, as well as transformer frameworks and the identification of biomarkers models are also described. This study also investigates challenges such as data heterogeneity, data interpretability, fairness and real-world clinical application. Finally, important areas of research opportunities and future directions are highlighted to present a developing clinically applicable, explainable and ethical AI solutions to manage MASLD.

MASLD↗

PubMed1995

[Computer-oracle-brain].

The main question of this essay is this: What can the hypotheses of Artificial Intelligence (AI) that brains work like computers contribute to the question whether neurotransplantations are permissible or not. My attitude is primarily critical. I point out that the believe that we could exchange parts of the brain like parts of a computer is erroneous. Many mathematical functions are not absolute but only relative computable. The computation of the latter is only possible by using an oracle (a stock of knowledge), which has to be implemented in the computer respectively in the brain. Hence, one should know in advance, before a transplantation is performed, in which part of the brain the oracle is located. Otherwise we would not know whether the oracle will be damaged by a neurotransplantation, and, hence, whether the persons ability to think will be changed. Of course, this is only a presupposition, not the solution of the ethical question of the legitimacy of neurotransplantations.

Artificial Intelligence↗

PubMed1999

A prognostic computer model to individually predict post-procedural complications in interventional cardiology: the INTERVENT Project.

AIMS: The purpose of this part of the INTERVENT project was (1) to redefine and individually predict post-procedural complications associated with coronary interventions, including alternative/adjunctive techniques to PTCA and (2) to employ the prognostic INTERVENT computer model to clarify the structural relationship between (pre)-procedural risk factors and post-procedural outcome. METHODS AND RESULTS: In a multicentre study, 2500 data items of 455 consecutive patients (mean age: 61.1+/-8.3 years: 33-84 years) undergoing coronary interventions at three university centres were analysed. 80.4% of the patients were male, 16.7% had unstable angina, and 5.1%/10.1% acute/subacute myocardial infarction. There were multiple or multivessel stenoses in 16.0%, vessel bending >90 degrees in 14.5%, irregular vessel contours in 65.0%, moderate calcifications in 20.9%, moderate/severe vessel tortuosity in 53.2% and a diameter stenosis of 90%-99% in 44.4% of cases. The in-lab (out-of-lab) complications were: 0.4% (0.9%) death, 1.8% (0.2%) abrupt vessel closure with myocardial infarction and 5.5% (4.0) haemodynamic disorders. CONCLUSION: Computer algorithms derived from artificial intelligence were able to predict the individual risk of these post-procedural complications with an accuracy of >95% and to explain the structural relationship between risk factors and post-procedural complications. The most important prognostic factors were: heart failure (NYHA class), use of adjunctive/alternative techniques (rotablation, atherectomy, laser), acute coronary ischaemia, pre-existent cardiac medication, stenosis length, stenosis morphology (calcification), gender, age, amount of contrast agent and smoker status. Pre-medication with aspirin or other cardiac medication had a beneficial effect. Techniques, such as laser angioplasty or atherectomy were predictors for post-procedural complications. Single predictors alone were not able to describe the individual outcome completely.

Adult↗

PubMed1997

Machine learning for the quality of life in inflammatory bowel disease.

Presence of a chronic disease influences patients' lives and reinforces demands to accept and then cope with the illness. In the case of inflammatory bowel disease, quality of life greatly differs through phases of remissions and relapses. Could the quality of life questionnaire tell the difference? In this study we are disclosing possibilities of assessing patients' perspectives by analysing analogue scale statements regarding concerns and worries related to ulcerative colitis. Some two hundred Swedish patients, 3/4 in remission and 1/4 in relapse, filled out a booklet containing 36 statements. To characterise the disease activity, we have used multivariate discrimination. To structure and describe in details paths distinguishing the remission from relapse, we have used an artificial intelligence procedure. Applications of the CART (Classification And Regression Trees) algorithm resulted in a set of classifiers which are, based on the similar subsets of significant variables, i.e. statements. Best reached classification accuracy did not exceed 80% in any case. Other classifiers namely, K-nearest-neighbour (KNN), Learning Vector Quantization (LVQ) and Back Propagation Neural Network (BPNN) confirmed that outcome. An expectation that the disease activity should clearly speak throughout the questionnaire held for a certain number of the observations such as pain and suffering, loss of bowel control, dying early, feeling alone, ability to have children, being treated as different and concerns regarding the medication. To highlight the difference of incorrect 20%, K-means clustering was performed. The results settled a basis for a hypothesis that the studied quality of life instrument captures more than the disease activity.

Algorithms↗

PubMed1989

[RGSS-IDJ and its application to cranial computed tomography].

RGSS-IDJ is developed as the Japanese version of Report Generation Support System for Imaging Diagnosis (RGSS-ID), which is a developmental computer system that applies artificial intelligence (AI) methods to a reporting system. Now RGSS-IDJ supports the report generation of cranial computed tomography. A representation scheme called Generalized Finding Representation (GFR) is proposed, to bridge the gap between natural language expressions in the radiographic report and AI methods. GRF for RGSS-IDJ is the same as for RGSS-ID. The basic style for entering the findings on the radiograph is the dialogue system with the routine of query and answering it by selecting items with a mouse. This system encodes the input findings into the network expressions, which are represented as the list form in the LISP computer language. And, it reserves them into the knowledge data base. The content of the report will be able to be utilized for various analyses within AI paradigm. The final radiographic report is made in the natural Japanese language.

Artificial Intelligence↗

PubMed2000

Hybrid optimization techniques for the workshift and rest assignment of nursing personnel.

In this paper, a detailed model and an efficient solution methodology for the monthly workshift and rest assignment of hospital nursing personnel is presented. A model that satisfies the rules of a typical hospital environment based both on published research data and on local hospital requirements is designed. A hybrid methodology that utilizes the strengths of operations research and artificial intelligence was used for the solution of the problem. In particular, an approximate integer linear programming (ILP) model is firstly solved and its solution is further improved using local search techniques. Finally, a tabu search strategy that uses as its neighborhood the solution space that the local heuristics define is presented. The use of heuristics is required because one of the main user requirements involving the user preference for specific workstretch patterns is not, for efficiency reasons, explicitly modeled in the ILP. In addition, for comparison and evaluation purposes the CLP based ILOG solver is also used to solve the same problem. The inferior computational results obtained with the ILOG solver do verify the speed and efficiency of the hybrid solution approach suggested in this paper. Extensive computational results are presented together with a detailed discussion on the quality, the computational efficiency and the operational acceptability of the solutions.

Artificial Intelligence↗

PubMed1993

[Radiological reasoning and its computer-based simulation. Reasons to use computer-based diagnostic systems developed on shells].

Research on the medical applications of artificial intelligence has increased the knowledge of logical and methodological principles of clinical reasoning. Thus, computer-based diagnostic systems are developed on the basis of progress in this field, because thorough knowledge is necessary to obtain efficient simulation. This work was aimed at analyzing the structure of medical and radiological reasoning and at discussing the modalities to simulate it with computer-based diagnostic systems. The diagnostic process includes two steps: data collection and data interpretation; radiological reasoning involves the following 5 steps: procedural, executive, observative, interpretative and communicative. Each of them needs a different approach to simulation, considering, in its development, the different characteristics of each kind of reasoning. The expert system shells on the market are necessary tools to develop expert systems, but they cannot cover the whole of processes taking place during radiological work. Therefore, a particular, radiology-aimed shell should be developed to help the radiologist.

Artificial Intelligence↗

PubMed1991

A machine learning approach to computer-aided molecular design.

Preliminary results of a machine learning application concerning computer-aided molecular design applied to drug discovery are presented. The artificial intelligence techniques of machine learning use a sample of active and inactive compounds, which is viewed as a set of positive and negative examples, to allow the induction of a molecular model characterizing the interaction between the compounds and a target molecule. The algorithm is based on a twofold phase. In the first one--the specialization step--the program identifies a number of active/inactive pairs of compounds which appear to be the most useful in order to make the learning process as effective as possible and generates a dictionary of molecular fragments, deemed to be responsible for the activity of the compounds. In the second phase--the generalization step--the fragments thus generated are combined and generalized in order to select the most plausible hypothesis with respect to the sample of compounds. A knowledge base concerning physical and chemical properties is utilized during the inductive process.

Amino Acid Sequence↗

PubMed1994

Reusable influence diagrams.

Influence Diagrams have been recognized as a suitable formalism for building probabilistic expert systems. Nevertheless, the most part of applications consists in stand-alone systems, concerning a very limited domain. On the other hand, Artificial Intelligence research has outlined Blackboard Architectures as the basis for building expert systems in which several knowledge sources, in general built with different formalisms, cooperate to the solution of a complex task. This paper addresses the use of influence diagrams as knowledge sources of such a system, and particularly faces the problem of reusing the same influence diagram in different inference phases. We will show that, specially in planning tasks, the modularity requirement of keeping the knowledge sources separated, may imply that an influence diagram must call another influence diagram to solve itself and to maintain the coherence of the whole set of decisions underlying the plan. Conditions for the correctness of this concatenation of knowledge sources will be provided, and an example from the medical domain of therapy planning for Acute Myeloid Leukemia will be shown, as an implemented prototype exploiting these ideas.

Acute Disease↗

PubMed2003

AI-guided parameter optimization in inverse treatment planning.

An artificial intelligence (AI)-guided inverse planning system was developed to optimize the combination of parameters in the objective function for intensity-modulated radiation therapy (IMRT). In this system, the empirical knowledge of inverse planning was formulated with fuzzy if-then rules, which then guide the parameter modification based on the on-line calculated dose. Three kinds of parameters (weighting factor, dose specification, and dose prescription) were automatically modified using the fuzzy inference system (FIS). The performance of the AI-guided inverse planning system (AIGIPS) was examined using the simulated and clinical examples. Preliminary results indicate that the expected dose distribution was automatically achieved using the AI-guided inverse planning system, with the complicated compromising between different parameters accomplished by the fuzzy inference technique. The AIGIPS provides a highly promising method to replace the current trial-and-error approach.

Algorithms↗

PubMed2026

AI-guided analysis of human pancreatic islet sociology reveals distinct cell compositional changes in type 1 diabetes.

Human pancreatic islets exhibit greater anatomic and cellular heterogeneity than previously appreciated, raising fundamental questions about how their composition varies with age, sex, region, and islet size and how type 1 diabetes (T1D) alters these relationships. Yet these questions remained largely unresolved due to the bottleneck of manual tissue inspection. Here, we developed an integrated artificial intelligence (AI)-guided imaging, processing, and statistical pipeline enabling unbiased, high-throughput analysis of more than 2 million candidate islets from 106 non-diabetic (ND) and T1D donors. We identified age-, region-, sex-, and islet size-dependent differences in islet distribution and composition between ND and T1D donors. Profound β-cell loss in T1D was accompanied by reciprocal α-cell expansion, whereas δ-cells and pancreatic polypeptide cells were largely resilient. Cell area and pseudotime analyses uncovered regional and age-dependent trajectories of islet remodeling across T1D progression, along with distinct patterns of cytoarchitectural reorganization of the endocrine pancreas.

Type 1 diabetes↗

PubMed2026

Integrating ex vivo platforms with AI to guide glioblastoma treatment.

PURPOSE: Ex vivo platforms can rapidly and cost-effectively screen patient-derived tumor cells or tissue. Artificial intelligence (AI) algorithms can search and identify patterns in large datasets and provide predictions. This review focuses on integrating microphysiological platforms with AI to inform physician and patient decision-making. METHODS AND RESULTS: Combining efficacy, safety, and pharmacology results from drug screens with the output of extensive AI searches can yield insights to guide physician and patient decision-making and potentially improve a patient's prognosis. We detail ex vivo platforms at different stages of development that represent the diversity of approaches: a microphysiological system and a high-throughput screen that assesses drug cytotoxicity in both bulk and drug-tolerant tumor cells. We review AI approaches that can enhance the utility of microphysiological platforms. CONCLUSION: Integrating emerging microphysiological platforms with AI is expected to significantly impact physician and patient choice of treatment.

Humans↗

PubMed2005

Vesicular roundness and compound release in PC-12 cells.

The principal goals of this study were to establish a quantitative morphological analysis of spatial and regional properties of dense core vesicles, and to use this analysis to assess whether homotypic fusion is prominent in chronically treated PC-12 cells at elevated release levels. Simple computerized image processing of electron-micrographs provided the binary images of vesicular dense cores, whilst the artificial intelligence methods were needed to determine the vesicular membranes. As in the past, the presence of large, highly irregular vesicles, provided the morphological evidence of fused vesicles, but the irregularity of vesicular shape was assessed quantitatively-from its roundness. Free space of each vesicle was determined from the distance to its nearest-neighbor, or from the size of its Voronoi polygon. Within a Voronoi polygon, each point is closer to that vesicle than to any other vesicle. Large vesicles were not less round and did not have larger free space, as expected if they result from fusion of several smaller vesicles. In conclusion, we present a novel and rigorous morphological analysis of spatial and regional properties of dense core vesicles. The results demonstrate that the homotypic fusion is not prominent in PC-12 cells, before or following a chronic treatment that enhances release.

Algorithms↗