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 1,135 records · Page 63Linked to original sources
PubMedDate not supplied

Development of proteomic patterns for detecting lung cancer.

Lung cancer is at present the number one cause of cancer death and no biomarker is available to detect early lung cancer in serum samples so far. The objective of this study is to find specific biomarkers for detection of lung cancer using Surface Enhanced Laser Desorption/Ionization (SELDI) technology. In this study, serum samples from 30 lung cancer patients and 51 age-and sex-matched healthy were analyzed by SELDI based ProteinChip reader, PBSII-C. The spectra were generated on WCX2 chips and protein peaks clustering and classification analyses were performed utilizing Biomarker Wizard and Biomarker Patterns software packages, respectively. Three protein peaks were automatically chosen for the system training and the development of a decision classification tree. The constructed model was then used to test an independent set of masked serum samples from 15 lung cancer patients and 31 healthy individuals. The analysis yielded a sensitivity of 93.3%, and a specificity of 96.7%. These results suggest that the serum is a capable resource for detection of specific lung cancer biomarkers. SELDI technique combined with an artificial intelligence classification algorithm can both facilitate the discovery of better biomarkers for lung cancer and provide a useful tool for molecular diagnosis in future.

Adenocarcinoma↗
PubMedDate not supplied

The Amsterdam Alexithymia Scale: its psychometric values and correlations with other personality traits.

BACKGROUND: This article describes the construction and validation of the Amsterdam Alexithymia Scale (AAS) and explores some of the nomological net of alexithymia. METHODS: Four correlational studies are presented. The internal structure of the AAS is explored by factor analyses on items. Correlations of the AAS with sex and (Guilford) intellectual abilities are established. Mean scores of three different professional groups are compared. Correlations between the AAS and several clinical and personality scales are determined. Students served as subjects in all studies (347<n<559). RESULTS: The 20-item AAS has a stable 5-factor structure, covering 5 defining features of alexithymia: difficulties in, respectively, experiencing emotions, fantasizing, analyzing emotions, differentiating between emotions and verbalizing emotions. The AAS showed to be reliable. The AAS scores were independent of verbal and nonverbal IQ. As expected, the AAS scores turned out to be significantly lower in a group of dramatic art students and significantly higher in a group of math and artificial intelligence students, when compared to psychology students. The AAS scores correlated negatively with extroversion, positively with social inadequacy and not with neuroticism. Finally, correlations between the AAS and the Adjective Check List scores indicated that alexithymia is associated with, respectively, a neglect of own needs and impulses, a reduced capability to understand social situations and a tendency to stick to rules rigidly, to flee into social isolation, to be submissive, to avoid commitment and to experiences of lack of personal meaning in life. CONCLUSION: The AAS is the first instrument measuring the 5 defining features of alexithymia reliably and validly.

Adult↗
PubMed2005

Prediction of pancreatic cancer by serum biomarkers using surface-enhanced laser desorption/ionization-based decision tree classification.

OBJECTIVE: In order to improve the prognosis of pancreatic cancer patients, it is crucial to explore novel tools for its early diagnosis. Here, we attempted to screen serum biomarkers to distinguish pancreatic cancer from non-cancer individuals. METHODS: 47 serum samples from pancreatic cancer patients, 39 of whom had small surgically resectable cancers, were collected before surgery, and an additional 53 serum samples from age- and sex-matched individuals without cancer were used as controls. The surface-enhanced laser desorption/ionization (SELDI) ProteinChip was applied to analyze serum protein profiling. 54 samples (27 with pancreatic cancer and 27 controls) were analyzed in the training set by a decision tree algorithm to be able to separate pancreatic cancer from controls. A double-blind test was used to determine the sensitivity and specificity of the classification model. RESULTS: A panel of six biomarkers was selected to set up a decision tree as the classification model. The model separated effectively pancreatic cancer from control samples, achieving a sensitivity of 88.9% and a specificity of 74.1%. The double-blind test challenged the model with a sensitivity of 80% and a specificity of 84.6%. CONCLUSION: The SELDI ProteinChip combined with an artificial intelligence classification algorithm shows great potential for the diagnosis of pancreatic cancer.

Adult↗
PubMed1995

A euristic approach to the volume reconstruction of arteriovenous malformations from biplane angiography.

Three-dimensional (3D) volume reconstruction is easily feasible with axial, coronal or sagittal CT and MRI scans. On the other hand, radiosurgical treatment of arteriovenous malformations (AVMs) is exclusively based on two orthogonal stereotactic projections, obtained with angiographic procedures. Most commonly AVM volumes have been calculated by assimilating the nidus volume to a prolate ellipsoid. We present an algorithm dedicated to 3D volume reconstruction starting from two stereotactic orthogonal projections. This has been achieved using a euristic approach which has been widely adopted in the artificial intelligence domain. Tests on phantoms of different complexity have shown excellent results. The importance of the algorithm is considerable. Firstly, it allows calculations of complex structures far removed from a regular ellipsoid. Secondly, it permits shape recovery. Thirdly, it provides AVM visualization on axial planes.

Algorithms↗
PubMed1994

Pathophysiologic assessment of data from a stroke data bank.

Stroke data banks have been instrumental in helping us to clarify stroke etiology and in the investigation of clinical-topographic correlations. For these purposes they have relied upon results from noninvasive vascular and cardiac methods, including extra- and transcranial Doppler sonography and echocardiography, as well as from procedures such as cranial computed tomography and magnetic resonance imaging. Conventional database concepts have also been used to assess pathophysiologic aspects of stroke. Although such applications have made important contributions in this multidiscipline area of investigation, they are limited by a lack of explicit representation of pathophysiologic knowledge for data interpretation. Recent results from artificial intelligence research suggest exciting new frontiers for medical database design with concepts stemming from second generation expert systems. We propose an extended concept for stroke data banks to include a knowledge-based system which incorporates current patient data, heuristic knowledge relating clinical features to functional impairment, and pathophysiologic models of neurological disease.

Cerebrovascular Disorders↗
PubMed1990

Expert systems as a diagnostic aid in otoneurology.

Expert systems (ES) are a new tool for information processing developed by the branch of computer science known as artificial intelligence. ES are capable of solving problems in a given domain by using the knowledge and emulating the behaviour of specialists in that field. ES can be used as powerful tools for education since they are able to justify their own conclusions and to make the underlying reasoning explicit. This paper presents 'Vertigo', an ES aimed at the classification and diagnosis of different forms of dizziness. It has been conceived mainly as a teaching tool in otoneurological departments. The rationale of this project, its development, the structure and the use of the system are described. So far, 'Vertigo' has been tested on more than 200 cases of dizziness and is presently being used by ENT residents during their otoneurology stage.

Diagnosis, Computer-Assisted↗
PubMedDate not supplied

Digital imagery/telecytology. International Academy of Cytology Task Force summary. Diagnostic Cytology Towards the 21st Century: An International Expert Conference and Tutorial.

ISSUES: Optical digital imaging and its related technologies have applications in cytopathology that encompass training and education, image analysis, diagnosis, report documentation and archiving, and telecommunications. Telecytology involves the use of telecommunications to transmit cytology images for the purposes of diagnosis, consultation or education. This working paper provides a mainly informational overview of optical digital imaging and summarizes current technologic resources and applications and some of the ethical and legal implications of the use of these new technologies in cytopathology. CONSENSUS POSITION: Computer hardware standards for optical digital imagery will continue to be driven mainly by commercial interests and nonmedical imperatives, but professional organizations can play a valuable role in developing recommendations or standards for digital image sampling, documentation, archiving, authenticity safeguards and teleconsultation protocols; in addressing patient confidentiality and ethical, legal and informed consent issues; and in providing support for quality assurance and standardization of digital image-based testing. There is some evidence that high levels of accuracy for telepathology diagnosis can be achieved using existing dynamic systems, which may also be applicable to telecytology consultation. Static systems for both telepathology and telecytology, which have the advantage of considerably lower cost, appear to have lower levels of accuracy. Laboratories that maintain digital image databases should adopt practices and protocols that ensure patient confidentiality. Individuals participating in telecommunication of digital images for diagnosis should be properly qualified, meet licensing requirements and use procedures that protect patient confidentiality. Such individuals should be cognizant of the limitations of the technology and employ quality assurance practices that ensure the validity and accuracy of each consultation. Even in an informal teleconsultation setting one should define the extent of participation and be mindful of potential malpractice liability. ONGOING ISSUES: Digital imagery applications will continue to present new opportunities and challenges. Position papers such as this are directed toward assisting the profession to stay informed and in control of these applications in the laboratory. Telecytology is an area in particular need of studies of good quality to provide data on factors affecting accuracy. New technologic approaches to addressing the issue of selective sampling in static image consultation are needed. The use of artificial intelligence software as an adjunct to enhance the accuracy and reproducibility of cytologic diagnosis of digital images in routine and consultation settings deserves to be pursued. Other telecytology-related issues that require clarification and the adoption of workable guidelines include interstate licensure and protocols to define malpractice liability.

Computer Communication Networks↗
PubMed2004

Brain-machine and brain-computer interfaces.

The idea of connecting the human brain to a computer or machine directly is not novel and its potential has been explored in science fiction. With the rapid advances in the areas of information technology, miniaturization and neurosciences there has been a surge of interest in turning fiction into reality. In this paper the authors review the current state-of-the-art of brain-computer and brain-machine interfaces including neuroprostheses. The general principles and requirements to produce a successful connection between human and artificial intelligence are outlined and the authors' preliminary experience with a prototype brain-computer interface is reported.

Animals↗
PubMed2026

State of Cardiovascular Disease and Stroke in Hispanic/Latino Adults in the United States: A Scientific Statement From the American Heart Association.

Cardiovascular disease became the leading cause of death among Hispanic individuals in the United States in 2022. Hispanic adults experience a disproportionate burden of cardiometabolic risk factors, including obesity, diabetes, and dyslipidemia. Hispanic populations are highly heterogeneous, with substantial variations in genetic ancestry and sociocultural influences that shape cardiovascular disease risk and outcomes. The "Hispanic paradox," describing lower cardiovascular disease mortality despite higher risk factor burden, is increasingly recognized as an oversimplification that does not apply uniformly across Hispanic heritage groups, sexes, or disease types. Disaggregated data reveal substantial differences in risk profiles and disease burden among Hispanic heritage groups, emphasizing the limitations of treating this population as a monolithic unit. Recent evidence demonstrates widening disparities in hypertension control, obesity, diabetes, and metabolic diseases among Hispanic populations, threatening this prior mortality advantage. Advancing cardiovascular and equitable health will require developing a deeper understanding of the unique drivers of cardiovascular disease within diverse Hispanic communities, addressing barriers such as language and insurance access, and implementing culturally tailored interventions and policies. This scientific statement summarizes current cardiovascular disease epidemiology in Hispanic populations, emphasizing heritage group variation and social and structural determinants of health, and presents strategies to improve prevention and healthcare delivery. Key priorities for advancing cardiovascular health in Hispanic adults include expanding disaggregated data collection, increasing representation in research, and ensuring equitable implementation of precision medicine approaches, including genomics, multi-omics, and artificial intelligence, while addressing environmental exposures, psychosocial stressors, and policy-related drivers of risk in order to achieve the American Heart Association's 2028 Impact Goals to advancing health and hope for everyone, everywhere.

AHA Scientific Statements↗
PubMed1997

Probabilistic independence networks for hidden Markov probability models.

Graphical techniques for modeling the dependencies of random variables have been explored in a variety of different areas, including statistics, statistical physics, artificial intelligence, speech recognition, image processing, and genetics. Formalisms for manipulating these models have been developed relatively independently in these research communities. In this paper we explore hidden Markov models (HMMs) and related structures within the general framework of probabilistic independence networks (PINs). The paper presents a self-contained review of the basic principles of PINs. It is shown that the well-known forward-backward (F-B) and Viterbi algorithms for HMMs are special cases of more general inference algorithms for arbitrary PINs. Furthermore, the existence of inference and estimation algorithms for more general graphical models provides a set of analysis tools for HMM practitioners who wish to explore a richer class of HMM structures. Examples of relatively complex models to handle sensor fusion and coarticulation in speech recognition are introduced and treated within the graphical model framework to illustrate the advantages of the general approach.

Algorithms↗
PubMed1987

The inhuman computer/the too-human psychotherapist.

There has been an understandable rejection by psychotherapists of any natural language processing (computer/human interaction by means of usual language exchange) which is intended to embrace aspects of psychotherapy. For at least twenty years therapists have experimented with computer programs for specific and general purpose with reported success. This paper describes some of the aspects of artificial intelligence used in computer-mediated or computer-assisted therapy and the utility of such efforts in general reevaluation of human-to-human psychotherapy.

Computers↗
PubMed2000

Production of diagnostic rules from a neurotologic database with decision trees.

A decision tree is an artificial intelligence program that is adaptive and is closely related to a neural network, but can handle missing or nondecisive data in decision-making. Data on patients with Meniere's disease, vestibular schwannoma, traumatic vertigo, sudden deafness, benign paroxysmal positional vertigo, and vestibular neuritis were retrieved from the database of the otoneurologic expert system ONE for the development and testing of the accuracy of decision trees in the diagnostic workup. Decision trees were constructed separately for each disease. The accuracies of the best decision trees were 94%, 95%, 99%, 99%, 100%, and 100% for the respective diseases. The most important questions concerned the presence of vertigo, hearing loss, and tinnitus; duration of vertigo; frequency of vertigo attacks; severity of rotational vertigo; onset and type of hearing loss; and occurrence of head injury in relation to the timing of onset of vertigo. Meniere's disease was the most difficult to classify correctly. The validity and structure of the decision trees are easily comprehended and can be used outside the expert system.

Databases, Factual↗
PubMed2026

Imaging and genomics in stroke.

Imaging after ischemic and hemorrhagic stroke may allow measurement of key phenotypes of injury and recovery for which targeted therapies are still lacking. Such imaging endophenotypes provide quantifiable and heritable biomarkers that can represent mechanistic aspects of disease processes better than clinical measures. Artificial intelligence is allowing extraction of these imaging biomarkers in large cohorts, which can be paired with genomic and other omics data. This will allow the evaluation of what genetic and other biologic variations impact stroke injury and recovery. Integration of these analyses with bioinformatics tools (such as Mendelian randomization and multi-trait analysis) could further dissect how stroke complications overlap with other biologic processes and how they may be causally linked to risk factors. Further work is required to confirm the translational impact of these methods in elucidating mechanisms and drug targets for stroke. However, global collaborations are accelerating analyses on large multi-ethnic stroke cohorts, with availability of imaging data facilitated by federally-funded repositories such as the Imaging Repository for the Cerebrovascular Disease Knowledge Portal (iCDKP).

Humans↗
PubMedDate not supplied

Postdoctoral training in medical informatics: a survey of National Library of Medicine-supported fellows.

The National Library of Medicine (NLM) funds training programs in medical informatics and plans to significantly increase the number of program sites in the future. The authors surveyed all NLM-funded trainees at the nine sites supported in the spring of 1988 to determine their backgrounds, current research interests, and career plans. Forty-three fellows were identified, of whom 39 returned a mailed questionnaire. All but four were physicians (89.7%), 82.1% had at least one year of postdoctoral clinical training, and 61.5% had completed a residency. Seventy-one percent of those completing residency had done so in internal medicine. The most common areas of current research were decision support/decision analysis, knowledge representation, and artificial intelligence. The overwhelming majority of the fellows planned to seek positions in a medical school on completion of their fellowships, and most preferred affiliation with a department of medical informatics or medicine.

Education, Continuing↗
PubMed1996

May we support your decision?

Expert systems to support medical decision-making have so far achieved few successes. Current technical developments, however, may overcome some of the limitations. Although there are several theoretical currents in medical artificial intelligence, there are signs of them converging. Meanwhile, decision support systems, which set themselves more modest goals than replicating or improving on clinicians' expertise, have come into routine use in places where an adequate electronic patient record exists. They may also be finding a wider role, assisting in the implementation of clinical practice guidelines. There is, however, still much uncertainty about the kinds of decision support that doctors and other health care professionals are likely to want or accept.

Bayes Theorem↗
PubMed2003

AIDA: web agents in dental treatment planning.

The objective of the AIDA project (Artificial Intelligent Dental Agents, http://aida.uni-hd.de) is the analysis of dental decision-making, the design of a computer-based decision support system, as well as the testing of the decision structure in interactions with dental experts, practicing dentists, and patients. The planning of the solution alternatives for an individual patient is based on a top-down structure for dental decision-making, aiming at a standardization of the argumentation. From a theoretical point of view, decision support can be provided only for anticipated decisions (planning). Moreover, only parts of these anticipated decisions can be supported. Accordingly, a separation of these partial aspects has to take place before one is able to build decision support systems. For prosthetic dentistry, clinicians have been shown how to use individual patient findings to sketch the possible treatment alternatives and later derive guidelines for the treatment. The planning module for fixed prostheses has already been integrated into a software agent. Planning modules for other types of prostheses are currently specified, implemented, and verified.

Decision Support Systems, Clinical↗
PubMed2026

Beyond Morphology: Reframing Lymph-Node Metastasis Prediction Through Clonal Ecology-Decades-Long Genomic Instability and Polyclonal-to-Monoclonal Transitions as the Missing Dimension in Cancer.

Recent whole-genome, lineage-tracing, single-cell, and spatial studies have reshaped our understanding of tumor evolution, revealing that cancers can arise from polyclonal populations, undergo decades-long genomic instability before clinical detection, and progress through dynamic changes in subclonal composition, cellular state, and ecological organization. These findings challenge the assumption underlying morphology-based prediction models that metastatic risk can be inferred from static histological features alone. Here, we revisit lymph-node metastasis prediction in colorectal cancer through clonal ecology, integrating computational pathology with evolutionary oncology. Drawing on the subclonal switchboard model proposed in 2012 and subsequent artificial intelligence (AI)-enabled approaches for tracking dominant and dormant subclones, we synthesize evidence that metastatic potential reflects clonal ancestry, evolutionary timing, spatial niche architecture, cellular plasticity, intercellular interactions, dormancy, and treatment-driven shifts in subclonal fitness. We define five complementary methodological pillars for operationalizing clonal ecology: single-cell transcriptomics for resolving rare subclones, evolutionary trajectories, and adaptive cell states; lineage tracing and phylogenetics for reconstructing clonal ancestry and divergence; spatial transcriptomics and genomics for mapping subclonal geography and tumor-stromal-immune interactions; longitudinal liquid biopsy surveillance for monitoring residual disease, clonal turnover, and emerging resistance; and AI-enabled multimodal integration for connecting histopathology, genomics, spatial biology, and longitudinal data into predictive ecological-state models. Multiple-instance learning and pathology foundation models provide scalable computational foundations for evolution-aware prediction. Translationally, dormant subclones represent actionable reservoirs of recurrence. A longitudinal clinical and experimental study of KMT2A-rearranged acute myeloid leukemia further supports central predictions of the subclonal switchboard framework by demonstrating treatment-associated shifts in subclonal dominance, persistence of cryptic adaptive programs, and ecological rewiring during resistance and relapse. We propose clonal ecology as a measurable dimension for extending morphology-driven prediction toward integrative models that anticipate evolutionary transitions, identify therapeutic windows, and proactively constrain adaptive tumor ecosystems before resistant or metastatic subclones achieve clinical dominance.

Humans↗
PubMed2026

Unveiling the Molecular Secrets of Seaweeds: A Comprehensive Review of Bioinformatics Applications in Algal Research.

Recent advances in high-throughput sequencing, bioinformatics, and multi-omics technologies have transformed seaweed research by overcoming long-standing challenges associated with complex genomes, diverse life cycles, and limited genomic resources. This review provides a comprehensive overview of bioinformatics approaches used to investigate seaweed genomics, transcriptomics, proteomics, metabolomics, microbiomes, and functional genomics, with emphasis on the computational tools and databases that support these analyses. Applications of bioinformatics in phylogenetics, drug discovery, microbiome characterization, and the development of biofuels, nutraceuticals, pharmaceuticals, and sustainable agriculture are also discussed. Particular attention is given to emerging strategies involving multi-omics integration, genome editing, artificial intelligence, machine learning, and synthetic biology that are reshaping seaweed research. The review further examines current challenges, including incomplete genomic resources, data standardization, and the need for experimental validation of computational predictions. Collectively, these advances highlight the growing role of bioinformatics in enabling systems-level understanding of seaweed biology and accelerating their translation into sustainable biotechnological and marine bioeconomy applications.

macroalgal genomics↗