PubMed Health⌕ Search

SEARCH · PubMed Health

Results for “Intelligent Systems”

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 37 records · Page 2Linked to original sources
PubMed1990

Relationship between carcinogenicity in rodents and the induction of sister chromatid exchanges and chromosomal aberrations in Chinese hamster ovary cells.

Two independent analyses were carried out to compare the induction of sister chromatid exchanges and of chromosomal aberrations as predictors of carcinogenicity. Using both a classical and a Bayesian approach, as well as by analysis of the structural fragments generated by CASE, an artificial intelligence system, it is included that individually neither of these tests is a satisfactory predictor of carcinogenicity. However, because the analysis revealed that each of the cytogenetic assays responds to a different set of structural features associated with carcinogenicity, it can be concluded that the assays can be included in a battery of tests to improve predictivity.

Animals↗
PubMed2026

Automated CEAP Classification of Venous Duplex Reports Using Multimodal Artificial Intelligence.

OBJECTIVE: To develop and internally validate a prototype multimodal artificial intelligence system for automated CEAP (Clinical, Etiological, Anatomical and Pathophysiological) classification of venous duplex ultrasound (VDUS) reports, integrating natural language processing of free-text components with computer vision analysis of hand-drawn anatomical diagrams. METHODS: Single centre retrospective observational study using routinely collected clinical data. One thousand consecutive venous duplex ultrasound reports from Cambridge University Hospitals NHS Foundation Trust, UK (July 2024 - May 2025) were labelled according to the CEAP classification, excluding the Etiological component, which could not be reliably determined from duplex reports alone. Transfer learning was applied using ClinicalBERT for text and MobileNetV3 for diagrammatic data. Clinical classes were predicted from request line text. Text- and image-based pathophysiological models were developed for four anatomical territories (Great Saphenous Vein, Small Saphenous Vein, Deep system, Perforators), combined using late fusion with probability averaging. RESULTS: The clinical CEAP model achieved accuracy of 0.91, macro-F1 of 0.82, and macro-AUC of 0.98. Pathophysiological prediction varied, with text models broadly outperforming image models. Fusion yielded heterogeneous benefits, improving SSV performance but reducing Deep system accuracy. The performance of the final pathophysiological CEAP fusion models varied across anatomical territories: accuracy ranged from 0.70-0.92 and macro-AUC from 0.80-0.92. CONCLUSION: This study demonstrates the feasibility of automated CEAP classification from VDUS reports. Despite class imbalance affecting minority class predictions, the strong discriminatory performance validates this multimodal ML model for extracting clinically meaningful information from real-world data. This approach offers potential, pending external validation, to streamline vascular services through automated triage and guideline-compliant decision making.

Artificial intelligence↗
PubMed1989

An analysis of pathology knowledge and decision making for the development of artificial intelligence-based consulting systems.

This paper partly addresses the question "What artificial intelligence (AI) tools are appropriate for which parts of pathology?" by analyzing the structure and components of knowledge in pathology (e.g., observations plus archival and reference data) and which aspects of that knowledge should be expressible in an AI consulting system. The different aspects of uncertainty (observational, prevalence and validity) play an important role in both human and computer-based decision-making processes, as do relationships between the components of knowledge. The design of an AI consultant system is discussed in terms of the way uncertainty is expressed and in how many parameters, the way uncertainty is propagated (Bayes, certainty factors, Dempster-Schafer, logic or Pathfinder heuristic methods), whether the system reasons from data to a conclusion or vice versa and what the aim of the system is. The suitability of an AI tool is determined by the knowable facts of the pathology subfield, by the match with its knowledge structure and by its requirements. While the success of an AI tool will partly depend on an appropriate definition of its scope, the appropriate combinatoric also depends on the expertise of the user.

Artificial Intelligence↗
PubMed1989

Artificial intelligence techniques for the control of cancer cells.

NEWCHEM, an artificial intelligence system for the control of cancer cell growth, is described. This system takes into account the most recent advances in molecular and cellular biology and in cell-drug interaction, and aims to develop optimal strategies for the selective control of cancer cell through qualitative reasoning from first principles at cellular level.

Computer Simulation↗
PubMed1989

Structure characteristics of QMSOC and the relevant operators.

This article presents a further description on the background, significance, and structure characteristics of Quantitative Medicine Simulation and Operation by Computer (QMSOC). Also some basic operators were recommended for calculations of biomedical events such as estimation of substance concentrations, exploration of etiology, evaluation of biomedical effects, etc. At last some differences of QMSOC from other artificial intelligent systems in the medical field were discussed.

Computer Simulation↗
PubMed2025

Integrating explainable artificial intelligence with multiomics systems biology and electronic health record data mining for personalized drug repurposing in Alzheimer's disease.

Alzheimer's disease (AD) is characterized by region- and patient-specific molecular heterogeneity, which hinders therapeutic design. In this study, we introduce PRISM-ML (PRecision-medicine using Interpretable Systems and Multiomics with Machine Learning), an open-source integrated analysis pipeline that combines interpretable machine learning with systems biology and electronic health records data mining to elucidate the molecular diversity of AD and predict promising drug repurposing opportunities. First, we integrated and harmonized transcriptomic (bulk RNA-seq) and genomic (genome-wide association study) data from 2105 brain samples, each with matched data from the same individual (1363 AD patients, 742 controls; 9 tissues), sourced from three independent studies. Random forest classifiers with SHapley Additive exPlanations identified patient-specific biomarkers; unsupervised clustering resolved 36 molecularly distinct subtissues (defined as clusters of samples within a brain tissue that share a specific expression pattern); and gene-gene coexpression networks prioritized 262 high-centrality bottleneck genes as putative regulators of dysregulated pathways. Next, knowledge graph-based drug repurposing predicted six Food and Drug Administration (FDA)-approved drugs that simultaneously target multiple bottleneck genes and multiple AD-relevant pathways. Notably, in a large US de-identified insurance-claims database (n&#x2009;=&#x2009;364&#xa0;733), exposure to promethazine, one of the candidate drugs, was associated with a 57%-62% lower incidence of AD versus an active antihistamine comparator (adjusted hazard ratio 0.38; inverse-probability weighted 0.43; both P&#x2009;<&#x2009;.001), providing real-world support for its repurposing potential. In summary, PRISM-ML, as an explainable multiomics analysis pipeline, is readily transferable to other complex diseases, advancing precision medicine.

Alzheimer Disease↗
PubMed1978

Uses of coronary heart attack registers.

By studying all coronary heart attacks presenting within defined communities it should be possible to avoid the distortions and omissions inherent in hospital-based case series. In practice the technique presents several problems. Measures of frequency and outcome are very sensitive to the diagnostic criteria used. Data of varying quality are mixed and specific attack rates can be calculated only for items for which the census provides a denominator. Patients presenting to different medical services have different outcomes, but probably less because of treatment than because the severity of the attack affects behaviour in it. Despite these problems, some such intelligence system is of value in any comprehensive strategy for coronary heart disease.

Adult↗
PubMedDate not supplied

Computers in oncology nursing: present use and future potential.

Computers assist oncology nurses in their roles as "care integrators" and caregivers. Computers assist nurses in their care integrator role by supporting communication with ancillary departments and by aiding in the collection, organization, and storage of data. Computers helps nurses in their role as caregivers through automated care planning, discharge planning, and patient monitoring and by tracking patients' educational, therapeutic, comfort, or other needs. Using computers, nurses can document their assessments and interventions and patient outcomes while receiving cues and reminders about policies, procedures, and standards of care. In the future, oncology nurses can expect to see computer technology in more hospitals and a host of new developments, such as more intelligent systems, nursing and medical knowledge on-line, documentation at the bedside, and use of patient data bases in education and research.

Clinical Nursing Research↗
PubMed1990

Medication monitoring in the workplace: toward improving our system of epidemiologic intelligence.

There is a great deal we do not know about the safety of pharmaceutical agents, especially regarding their safe use in the workplace. Economic and scientific imperatives can lead to a new drug's approval and marketing even though testing is limited; therefore, much of the knowledge about drug toxicities must be developed in the postapproval period, through pharmacoepidemiologic methods. The system of epidemiologic intelligence depends on spontaneous, voluntary reports of adverse drug reactions and, as applied to the work force, it is fraught with problems of ascertainment, accountability, and application. Structured epidemiologic studies of these issues have been difficult to perform because of high costs, long time frames, and methodologic problems and biases. Nevertheless, large automated data bases, with the right input, hold great promise for making it easier to accumulate and analyze the data necessary for monitoring drug safety in the workplace.

Drug Evaluation↗
PubMed1992

Intelligent alarms reduce anesthesiologist's response time to critical faults.

The proliferation of monitors and alarms in the operating room may lead to increased confusion and misdiagnosis unless the information provided is better organized. Intelligent alarm systems are being developed to organize these alarms, on the assumption that they will shorten the time anesthesiologists need to detect and correct faults. This study compared the human response time (the time between the sounding of an alarm and the resolution of a fault) when anesthesiologists used a conventional alarm system and when they used an intelligent alarm system. In a simulated operating room environment, we asked 20 anesthesiologists to resolve seven breathing circuit faults as quickly as possible. Human response time was 62% faster, decreasing from 45 to 17 s, when the intelligent alarm system was used. The standard deviations in response time were only half as large for the intelligent alarm system. It appears that the computer-based neural network in the intelligent alarm system diagnosed faults more rapidly and consistently than did the anesthesiologists. This study indicates that breathing circuit faults may be more rapidly corrected when the anesthesiologist is guided by intelligent alarms.

Anesthesiology↗
PubMed1992

Effects of the fitting parameters of a two-channel compression system on the intelligibility of speech in quiet and in noise.

These experiments were carried out to assess how accurately the gains and compression ratios in a two-channel compression system needed to be set. We used as a research tool a laboratory version of a two-channel full-dynamic-range compression system. The system was initially adjusted to suit each hearing-impaired subject according to the manufacturer's recommendations. Then, further adjustments were made to ensure that speech stimuli were both audible and comfortable over a wide range of sound levels. Finally, the settings of the gains and compression ratios were systematically varied from the adjusted values and the effects of this on the intelligibility of speech in quiet and in noise (12-talker babble, levels of 65 and 75 dB SPL) were measured. The results indicated that speech reception thresholds (SRTs) in quiet were significantly adversely affected by decreases in low-level gain. However, SRTs in noise were relatively unaffected by changes in low-level gain. An exception occurred at the higher noise level used, where increases in the low-level gains (with corresponding increases in compression ratios) had a significant adverse effect on the SRTs. It is concluded that, provided excessive low-level gains (associated with high compression ratios) are avoided, the main criteria for fitting such a system should be listening comfort (i.e. achieving an acceptable tonal balance, and avoiding uncomfortably loud sounds) and an appropriate value of the threshold for detecting speech in quiet (which should be a little below 50 dB SPL).

Acoustic Stimulation↗
PubMed2026

Artificial Intelligence in Predicting Systemic Complications From Retinal Findings: A New Frontier in Precision Medicine.

Innovations in retinal imaging technologies and growing evidence from retinal imaging of systemic and neurodegenerative diseases have begun to explore the utility of retinal imaging in diagnosing these conditions. Since the retina shares embryological origins with the central nervous system and reflects systemic microvascular characteristics, it is well positioned for noninvasive observation of patients' systemic and neural health. Moreover, accessibility of retinal imaging has improved with the increasing number of ophthalmology clinics. Rapid improvements in various deep learning (DL) tools have also catalyzed the automation of retinal imaging analysis. Systems that utilize DL for retinal imaging are being developed to assist with disease recognition, clinical judgment, and prognostic assessment of systemic health. Various imaging modalities are being integrated with existing genomic and clinical data to estimate an individual's predisposition to certain conditions. Contrary to many existing reviews, the objective of this review is to synthesize the most recent clinical and technological evidence on DL-based diagnostic systems for retinal imaging, with a focus on how different network architectures and their combinations have been developed, validated, and applied across systemic disease detection and prediction. Specifically, this review examines the datasets, model validation approaches, and automated diagnostic systems reported in recent literature. It discusses the extent to which these advancements address existing barriers toward real-time diagnostic application across clinical disciplines. Integrating retinal imaging with DL is an innovative and promising approach to precision medicine and health risk reduction.

artificial intelligence↗
PubMed1990

Cancer chronotherapy: a drug delivery challenge.

The toxicity and/or efficacy of more than twenty anticancer agents have been shown in various experimental systems to be dependent upon the circadian timing of their bolus administration or the circadian shaping of their continuous infusion. In cancer patients, the toxicity of several single agents, given either as bolus or infusion, and a growing number of drug combinations have been shown to similarly depend upon their timing. While clinical trials currently underway demonstrate that the circadian stage of drug toxicity and dose intensity each depend upon their circadian timing, definitive investigations of whether or not cancer control and patient survival are similarly dependent upon circadian treatment timing are currently under way. Both clinical trials of treatment timing and chronotherapy depend totally upon the development and use of programmable wearable and implantable, single-channel and multi-channel, open and eventually closed loop delivery systems. First generation intelligent delivery systems are currently available, work well, are economical and are destined, for economic reasons, to be more widely used. When used, each system requires temporal input, making it impossible to avoid specification of drug sequence, interval between drugs or treatment cycles and circadian treatment timing. The advent of biological therapy with cytokines and growth factors makes it likely that the precise timing of cancer therapies will be of growing importance.

Animals↗