Search PubMed⌕ Search

SEARCH · Search PubMed

Results for “computer sciences”

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 955 records · Page 53Linked to original sources
PubMed2025

Generative AI Models in Time-Varying Biomedical Data: Scoping Review.

BACKGROUND: Trajectory modeling is a long-standing challenge in the application of computational methods to health care. In the age of big data, traditional statistical and machine learning methods do not achieve satisfactory results as they often fail to capture the complex underlying distributions of multimodal health data and long-term dependencies throughout medical histories. Recent advances in generative artificial intelligence (AI) have provided powerful tools to represent complex distributions and patterns with minimal underlying assumptions, with major impact in fields such as finance and environmental sciences, prompting researchers to apply these methods for disease modeling in health care. OBJECTIVE: While AI methods have proven powerful, their application in clinical practice remains limited due to their highly complex nature. The proliferation of AI algorithms also poses a significant challenge for nondevelopers to track and incorporate these advances into clinical research and application. In this paper, we introduce basic concepts in generative AI and discuss current algorithms and how they can be applied to health care for practitioners with little background in computer science. METHODS: We surveyed peer-reviewed papers on generative AI models with specific applications to time-series health data. Our search included single- and multimodal generative AI models that operated over structured and unstructured data, physiological waveforms, medical imaging, and multi-omics data. We introduce current generative AI methods, review their applications, and discuss their limitations and future directions in each data modality. RESULTS: We followed the PRISMA-ScR (Preferred Reporting Items for Systematic Reviews and Meta-Analyses extension for Scoping Reviews) guidelines and reviewed 155 articles on generative AI applications to time-series health care data across modalities. Furthermore, we offer a systematic framework for clinicians to easily identify suitable AI methods for their data and task at hand. CONCLUSIONS: We reviewed and critiqued existing applications of generative AI to time-series health data with the aim of bridging the gap between computational methods and clinical application. We also identified the shortcomings of existing approaches and highlighted recent advances in generative AI that represent promising directions for health care modeling.

Artificial Intelligence↗
PubMed1989

[Let's study exponential function related to anesthesiology by using computer graphics--Part II: Wash-in exponential function].

The author first explained the wash-in exponential function. Then mathematically simulated changes in the concentration of inhalation anesthetic inside a breathing circle during induction of anesthesia were shown as a physical model related to anesthesiology to explain the idea of wash-in exponential function. Effect of the flow rate and concentration of anesthetic delivered to a breathing circle on the changes in the anesthetic concentration inhaled by patients was calculated and graphed by using a computer program developed for science education. The author also stressed the importance of graphic expression in understanding various physical or biophysical phenomena related to anesthesiology.

Anesthesia, Closed-Circuit↗
PubMed1991

A developed program of ionic equilibria and membrane potentials for Chinese science students.

The paper describes an interactive computer program for an IBM-compatible personal computer, which creates a convenient way of teaching Chinese students of the physiological and biological sciences about the relationship of several aspects of ionic equilibria to the generation of resting membrane potential. Students may work through this program following the scheduled lectures on those subjects. Laboratory time is also used for discussion and questions, and to present advanced examples of ionic equilibria in biological systems. The authors believe that this program will provide students with a clear understanding of the rules of ionic electricity and the generation of membrane potentials, as well as improving their problem-solving skills.

Electrolytes↗
PubMed1996

Bimodal reading: benefits of a talking computer for average and less skilled readers.

Studies have shown that when information is presented through visual and auditory channels simultaneously (i.e., bimodal presentation), speed of processing and memory recall are enhanced. The present study demonstrated the efficacy of a bimodal approach to fostering reading comprehension. Eighteen average readers (9 girls and 9 boys) and 18 less skilled readers (8 girls and 10 boys) in Grades 8 and 9 participated in the study. Students were presented with social studies and science passages via a computer. Passages were presented in three conditions: visually (on screen), auditorily (read by digitized voice), and bimodally (on screen, highlighted, while being voiced). Following each passage, students answered 10 oral-response, short-answer comprehension questions. Results indicated that less skilled readers comprehended more with bimodal versus unimodal presentations. Overall, their performance in the bimodal condition was commensurate with average readers' comprehension in the visual condition. For less skilled readers, an increase in word recognition from pre- to posttesting on word lists was found across conditions. In addition, results of a brief consumer satisfaction survey suggested that low-skilled readers felt most successful in terms of their comprehension when passages were presented bimodally. Several clinical issues involved in presenting information bimodally using computers are discussed.

Adolescent↗
PubMed2004

Looking for design in materials design.

Despite great advances in computation, materials design is still science fiction. The construction of structure-property relations on the quantum scale will turn computational empiricism into true design.

Computer Simulation↗
PubMed2005

Information-seeking behavior of nursing students and clinical nurses: implications for health sciences librarians.

OBJECTIVES: This research was conducted to provide new insights on clinical nurses' and nursing students' current use of health resources and libraries and deterrents to their retrieval of electronic clinical information, exploring implications from these findings for health sciences librarians. METHODS: Questionnaires, interviews, and observations were used to collect data from twenty-five nursing students and twenty-five clinical nurses. RESULTS: Nursing students and clinical nurses were most likely to rely on colleagues and books for medical information, while other resources they frequently cited included personal digital assistants, electronic journals and books, and drug representatives. Significantly more nursing students than clinical nurses used online databases, including CINAHL and PubMed, to locate health information, and nursing students were more likely than clinical nurses to report performing a database search at least one to five times a week. CONCLUSIONS AND RECOMMENDATIONS: Nursing students made more use of all available resources and were better trained than clinical nurses, but both groups lacked database-searching skills. Participants were eager for more patient care information, more database training, and better computer skills; therefore, health sciences librarians have the opportunity to meet the nurses' information needs and improve nurses' clinical information-seeking behavior.

Adult↗
PubMed1992

Introducing computer literacy skills for physicians.

Computers are integral to medical practice, education, and research. While medical students learn computer skills during their training, many practicing physicians do not have the same computer experience. To familiarize this group with the exciting developments in medical informatics, the Himmelfarb Health Sciences Library and Department of Computer Medicine at the George Washington University Medical Center organized a workshop "Introducing Your Office Computer!" for attending physicians. The workshop featured a short lecture/video presentation on computer applications in medicine followed by a "computer fair" of five computer applications. Eleven physicians attended the workshop. Feedback was very positive; many called later to request more detailed instructions on using the programs demonstrated. It was a valuable experience for the staff, and new bridges were built between departments and clients.

Computer User Training↗
PubMed1995

Medical image processing utilizing neural networks trained on a massively parallel computer.

While finding many applications in science, engineering, and medicine, artificial neural networks (ANNs) have typically been limited to small architectures. In this paper, we demonstrate how very large architecture neural networks can be trained for medical image processing utilizing a massively parallel, single-instruction multiple data (SIMD) computer. The two- to three-orders of magnitude improvement in processing time attainable using a parallel computer makes it practical to train very large architecture ANNs. As an example we have trained several ANNs to demonstrate the tomographic reconstruction of 64 x 64 single photon emission computed tomography (SPECT) images from 64 planar views of the images. The potential for these large architecture ANNs lies in the fact that once the neural network is properly trained on the parallel computer the corresponding interconnection weight file can be loaded on a serial computer. Subsequently, relatively fast processing of all novel images can be performed on a PC or workstation.

Computer Systems↗
PubMed1985

Assessment of metabolic bone diseases by quantitative computed tomography.

Advances in the radiologic sciences have permitted the development of numerous noninvasive techniques for measuring the mineral content of bone, with varying degrees of precision, accuracy, and sensitivity. The techniques of standard radiography, radiogrammetry, photodensitometry, Compton scattering, neutron activation analysis, single and dual photon absorptiometry, and quantitative computed tomography (QCT) are described and reviewed in depth. Results from previous cross-sectional and longitudinal QCT investigations are given. They then describe a current investigation in which they studied 269 subjects, including 173 normal women, 34 patients with hyperparathyroidism, 24 patients with steroid-induced osteoporosis, and 38 men with idiopathic osteoporosis. Spinal quantitative computed tomography, radiogrammetry, and single photon absorptiometry were performed, and a spinal fracture index was calculated on all patients. The authors found a disproportionate loss of spinal trabecular mineral compared to appendicular mineral in the men with idiopathic osteoporosis and the patients with steroid-induced osteoporosis. They observed roughly equivalent mineral loss in both the appendicular and axial regions in the hyperparathyroid patients. The appendicular cortical measurements correlated moderately well with each other but less well with spinal trabecular QCT. The spinal fracture index correlated well with QCT and less well with the appendicular measurements. Knowledge of appendicular cortical mineral status is important in its own right but is not a valid predictor of axial trabecular mineral status, which may be disproportionately decreased in certain diseases. Quantitative CT provides a reliable means of assessing the latter region of the skeleton, correlates well with the spinal fracture index (a semiquantitative measurement of end-organ failure), and offers the clinician a sensitive means of following the effects of therapy.

Aged↗