Search PubMed⌕ Search

SEARCH · Search PubMed

Results for “Intelligent Systems”

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 379 records · Page 21Linked to original sources
PubMed1997

Neural networks in neurotologic expert systems.

Artificial intelligence donates new possibilities to neurotologic research. Neural networks are a computer-based reasoning method which can be applied in expert systems created for clinical decision support. Neural networks have been used in medical imaging, in medical signal processing and to analyze both clinical and laboratory data. Principally, neural networks simulate the function of the brain. They have to be taught to make correct decisions from the input data. This learning process can be either supervised or unsupervised. The decision making is based on mathematical transformations and it occurs on a hidden level. Calculations are made on parallel manner and the decision making simulates pattern recognition method. Neural networks suit well in medical problems which cannot be defined in simple rules. A drawback of neural networks is that the decisions are irrational and cannot be motivated to the user. Another problem is neural networks' difficulty to handle incomplete input data, i.e., how to define some default or expected values for unknown input parameters. In a complex medical area, which would require multilayered neural networks, the neural networks require a large amount of solved cases for the learning process. In our experience neural networks seem not suitable for diagnosing vertigo and a better choice would be either case-based reasoning or possibly genetic algorithms or a combination of these.

Diagnosis, Computer-Assisted↗
PubMed2006

A novel two-dimensional echocardiographic image analysis system using artificial intelligence-learned pattern recognition for rapid automated ejection fraction.

OBJECTIVES: We sought to test the hypothesis that a novel 2-dimensional echocardiographic image analysis system using artificial intelligence-learned pattern recognition can rapidly and reproducibly calculate ejection fraction (EF). BACKGROUND: Echocardiographic EF by manual tracing is time consuming, and visual assessment is inherently subjective. METHODS: We studied 218 patients (72 female), including 165 with abnormal left ventricular (LV) function. Auto EF incorporated a database trained on >10,000 human EF tracings to automatically locate and track the LV endocardium from routine grayscale digital cineloops and calculate EF in 15 s. Auto EF results were independently compared with manually traced biplane Simpson's rule, visual EF, and magnetic resonance imaging (MRI) in a subset. RESULTS: Auto EF was possible in 200 (92%) of consecutive patients, of which 77% were completely automated and 23% required manual editing. Auto EF correlated well with manual EF (r = 0.98; 6% limits of agreement) and required less time per patient (48 +/- 26 s vs. 102 +/- 21 s; p < 0.01). Auto EF correlated well with visual EF by expert readers (r = 0.96; p < 0.001), but interobserver variability was greater (3.4 +/- 2.9% vs. 9.8 +/- 5.7%, respectively; p < 0.001). Visual EF was less accurate by novice readers (r = 0.82; 19% limits of agreement) and improved with trainee-operated Auto EF (r = 0.96; 7% limits of agreement). Auto EF also correlated with MRI EF (n = 21) (r = 0.95; 12% limits of agreement), but underestimated absolute volumes (r = 0.95; bias of -36 +/- 27 ml overall). CONCLUSIONS: Auto EF can automatically calculate EF similarly to results by manual biplane Simpson's rule and MRI, with less variability than visual EF, and has clinical potential.

Aged↗
PubMed1997

Artificial intelligence elements in multimedia system for surgery.

The paper presents a concept of a computer system designed to assist a surgeon's work both before and during a surgical operation. The aim of multimedia in the system is to ensure comfort in communication between an operating surgeon and his assistants. The elements of artificial intelligence, on the other hand, are to assist the surgeon in taking optimal decisions in difficult and untypical situations.

Artificial Intelligence↗
PubMed2004

Wearable textile biofeedback systems: are they too intelligent for the wearer?

The Intelligent Knee Sleeve is a device capable of providing immediate audible feedback to the wearer pertaining to knee flexion angle during human movement. The Intelligent Knee Sleeve was used in a landing training program to determine whether providing subjects with this form of feedback was able to effect a change in knee flexion angle during dynamic landing tasks. Preliminary results suggest that the feedback modality is effective in correcting landing technique. However, advancements in the Intelligent Knee Sleeve design would produce a more robust system leading to more effective biofeedback for the athlete.

Adult↗
PubMed1995

MONI: an intelligent database and monitoring system for surveillance of nosocomial infections.

Recording, recognition, and prevention of nosocomial infections are the primary responsibilities of the hospital infection control unit. To perform these tasks, this unit needs information from diverse sources--the patient's symptoms and signs, microbiological and virological test results, and information regarding antibiotics and treatment come from different levels of healthcare delivery. Because of the large amount of data (e.g., about 300 microbiological requests daily) a computer system is required to store this information and to provide a means for subsequent evaluation. MONI (Monitoring of nosocomial infections) is an intelligent database and monitoring system for surveillance and detection of nosocomial infections. Data can be entered into the system manually as well as transferred automatically from external information systems. The central feature of the system is the automatic detection of and calling attention to conditions that may be a detriment to patient recovery, such as possible hospital-acquired infections, risk factors, diseases to be reported, etc. By using this system, we seek to reduce the frequency of infection and the frequency of nosocomial deaths by improving the quality of patient treatment, shortening the length of stay in a hospital, and the use of fewer and/or cheaper antibiotics. MONI provides a means to access relevant medical data (names of infectious agents, antibiotics, department names, monitoring rules, etc.) from a library. This library can be updated or otherwise modified, even during use. An infection control team using this system can customize it to suit the demands of that particular unit. Automatic data transfer from external information systems is made possible by tables that translate between different code systems. The system also offers flexibility; the program can be configured to adapt it for use in other hospitals and institutions. The core element of MONI is the monitoring module, which is implemented as a layer between data input and the database. Upon data acquisition, the system checks the input against several monitoring tools and alerts the user to matches, which may indicate an infection risk. Processing of a rule may be deferred, depending on complexity of the rule and the actual and estimated workload of the system. Examples of the monitoring guidelines are: (1) suspicion of nosocomial infection; (2) infection at a normally sterile site; (3) infection due to bacteria with unusual antibiotic sensitivity patterns; (4) lab report indicates that patient is treated with ineffective antibiotic; (5) possible choice for less expensive antibiotic; (6) infection which is required to be reported to state and/or health authorities; (7) patients receiving prophylactic antibiotics longer than medically indicated; and (8) infections of two or more patients in different wards with the same bacteria (cf. Evans 85). The MONI system was developed at one of the largest hospitals in Europe, the Vienna General Hospital (2,200 beds). This facility serves as the teaching hospital of the University of Vienna Medical School. The size of the hospital and the large amount of data made it necessary to introduce such a system into clinical routine. MONI was programmed in C and C++ with a state-of-the-art graphical user interface (Presentation Manager, Workplace Shell) for OS/2. IBM Database 2 for OS/2 (dB 2/2) was used in constructing the database. The layer between the database and the monitoring application is driven by the multitasking and interprocess communication abilities of OS/2. A pen-based support system that assists in mobile data acquisition is currently under development.

Anti-Bacterial Agents↗
PubMedDate not supplied

Development of an expert system for haemodynamic monitoring: computerized symbolization of on-line monitoring data.

The development of intelligent alarm systems for intensive care benefits from the transformation of data from a quantitative to a qualitative mode. We constructed a computerized algorithm for the symbolization of on-line monitoring data of heart rate, systemic arterial, pulmonary arterial and central venous pressures, as well as central and peripheral temperatures. We tested the ability of the algorithm to symbolize the levels of the parameters and to detect significant long-term trends in ten adult patients admitted to the intensive care unit after cardiac surgery. The estimations of an experienced clinician were taken as the 'gold standard'. The symbolization of the levels of the monitored parameters was in agreement with the clinician in 99.4% of the estimations. The algorithm detected 93.0% of the trends correctly and also estimated their reliability. The clinician considered its estimations to be accurate in 96.2% of cases. On the other hand, the clinician considered unreliable 2.4% of all the trends detected and classified as reliable by the algorithm. The computerized algorithm for the symbolization of real-time monitoring data performed efficiently enough for its further use in expert systems for intelligent monitoring.

Algorithms↗
PubMed2026

AI-driven CRISPR screening: optimizing gene editing through automation and intelligent decision support.

BACKGROUND: CRISPR-based genetic screening has become a central methodology in functional genomics, enabling systematic interrogation of gene function, genetic interactions and context-dependent vulnerabilities at scale. However, the rapid expansion of screening modalities-including multi-condition designs, combinatorial perturbations, in vivo applications and single-cell readouts-has exposed fundamental limitations of heuristic-driven experimental design and post hoc statistical analysis. MAIN BODY: This Review synthesizes how artificial intelligence is reshaping CRISPR screening by introducing predictive, adaptive and system-level intelligence across the experimental lifecycle. We organize recent advances into two tightly coupled modules. First, machine learning and deep learning (ML/DL) methods optimize experimental design by learning context-dependent perturbation behavior, anticipating confounding effects and enabling iterative, information-efficient screening strategies. Second, large language model-agent (LLM-agent) systems complement these advances by externalizing scientific reasoning, integrating biological knowledge at scale and coordinating analysis and decision-making in human-in-the-loop workflows. CONCLUSIONS: Together, ML/DL and LLM-agent approaches reframe CRISPR screening from a static analytical pipeline into an intelligent experimental system, with important implications for robustness, scalability and biological discovery.

Artificial Intelligence↗
PubMed1996

Cross-scale information processing in evolution, development and intelligence.

Biological systems are treated as percolation networks in which processes at all scales participate. Macroscopic inputs are transduced to microphysical events through an interleaved hierarchy of structures and processes and microphysical events are amplified to control macroscopic structures and functions. Integrity and adaptation are achieved through self-consistency dynamics operating at all levels of organization. The unmanifest structure of the vacuum plays a vital role in these dynamics.

Biological Evolution↗
PubMed2005

The systemic theory of living systems and relevance to CAM: the theory (Part III).

Western medical science lacks a solid philosophical and theoretical approach to disease cognition and therapeutics. My first two articles provided a framework for a humane medicine based on Modern Biophysics. Its precepts encompass modern therapeutics and CAM. Modern Biophysics and its concepts are presently missing in medicine, whether orthodox or CAM, albeit they probably provide the long sought explanation that bridges the abyss between East and West. Key points that differentiate Systemic from other systems' approaches are 'Intelligence', 'Energy' and the objective 'to survive'. The General System Theory (GST) took a forward step by proposing a departure from the mechanistic biological concept-of analyzing parts and processes in isolation-and brought us towards an organismic model. GST examines the system's components and results of their interaction. However, GST still does not go far enough. GST assumes 'Self-Organization' as a spontaneous phenomenon, ignoring a causative entity or central controller to all systems: Intelligence. It also neglects 'Survive' as the directional motivation common to any living system, and scarcely assigns 'Energy' its true inherent value. These three parameters, Intelligence, Energy and Survive, are vital variables to be considered, in our human quest, if we are to achieve a unified theory of life.

Journal Article↗
PubMed2000

Intelligent database generated occupational questionnaire system.

Obtaining an adequate occupational history requires special expertise to "ask the right questions" that are relevant to a particular patient's specific health conditions and potential exposures. This article describes a way to systematically accomplish this by means of a computer system that can overcome limited availability of necessary clinical occupational health expertise. The Intelligent Questionnaire system is a computer-based system for generating case-specific questionnaires about the influence of work on respiratory disease. Intelligent Questionnaire includes three databases: Questions, Responses, and Calls (clues to identify questions). The Questionnaire also arranges questions in a logical manner and provides a customized data entry screen for each subject. This approach provides primary practitioners with expertise on a case-by-case basis. It also facilitates occupational health surveillance because it allows acquiring detailed case-specific information in a systematic fashion. A computer-based system can facilitate obtaining occupational histories with high specificity and consistency without depending on general availability of a human occupational health clinical expertise.

Artificial Intelligence↗
PubMed1989

Decision analysis: a framework for critical care decision assistance.

The ultimate goal of medical computer systems is to help clinicians make good decisions. Such systems must be based on sound principles. Decision analysis is a 25-year-old discipline that provides the needed rigorous foundation for decision assistance. Decision analysis comprises the philosophy, procedures, and tools that can correct the flaws in existing critical care decision-making practice. Intelligent decision systems--computer-based systems that automate decision analysis--make it practical to apply decision analysis to critical care. Orchestra is a pilot intelligent decision system (now under development) that coordinates the efforts of the critical care specialist, the bedside physician, and the bedside nurse in building decision models that can provide recommendations and insight for ventilator management decisions. Decision analysis delivered by intelligent decision systems has great potential for improving critical care decision-making.

Algorithms↗
PubMed1987

Modeling and artificial intelligence approaches to enzyme systems.

Modeling is a means of formulating and testing complex hypotheses. Useful modeling is now possible with biological laboratory microcomputers with which experimenters feel comfortable. Artificial intelligence (AI) is sufficiently similar to modeling that AI techniques, now becoming usable on microcomputers, are applicable to modeling. Microcomputer and AI applications to physiological system studies with multienzyme models and with kinetic models of isolated enzymes are described. Using an IBM PC microcomputer, we have been able to fit kinetic enzyme models; to extend this process to design kinetic experiments by determining the optimal conditions; and to construct an enzyme (hexokinase) kinetics data base. We have also used a PC to do most of the constructing of complex multienzyme models, initially with small simple BASIC programs; alternative methods with standard spreadsheet or data base programs have been defined. Formulating and solving differential equations in appropriate representational languages, and sensitivity analysis, are soon likely to be feasible with PCs. Much of the modeling process can be stated in terms of AI expert systems, using sets of rules for fitting and evaluating models and designing further experiments. AI techniques also permit critiquing and evaluating the data, experiments, and hypotheses being modeled, and can be extended to supervise the calculations involved.

Artificial Intelligence↗
PubMed1992

On a common structure of intelligence in biological and technical systems.

This is a survey of the general structure of an electronic computer-implemented, operation-oriented system, designed by the authors, which uses artificial intelligence mechanisms and is intended for the control of technical objects that function both in predictable and random environments. The system is based on processing knowledge, which is stored in a hierarchically arranged Knowledge Bank, and program mechanisms for adapting to and interacting with the External and Internal Worlds. The system has distributed program mechanisms, which are 'designed' with a constant structure. It is independent of the purpose and environment of the system operation and the specific features of the controlled object. None of the program mechanisms are concentrated in any program module. They are distributed in many modules, and therefore there is no single module responsible for the execution of a particular external function. The system is structured into separate program modules by internal procedures. The conceptual organisation of the Knowledge Base presupposes that the framework is structured according to functional, semantic and tier indications, i.e. the structured description of knowledge, by the system, of the external environment and its possible behaviour in it. The possibility of multiple use of the same elements of the lower tiers of the Knowledge Base by higher-tier elements makes the proposed Knowledge Base very efficient. If the cerebrum is considered at a structural level, there appears to be an amazing similarity between the structure and the mechanisms of the above system and the structure of the cerebral cortex, as suggested previously by Edelman and Mountcastle. Each mechanism of the cerebral cortex structure has a structural analogue in the described system.(ABSTRACT TRUNCATED AT 250 WORDS)

Algorithms↗
PubMed1998

Female voice communications in high level aircraft cockpit noises--part II: vocoder and automatic speech recognition systems.

BACKGROUND: The intelligibility of female and male speech is equivalent under most ordinary living conditions. However, due to small differences between their acoustic speech signals, called speech spectra, one can be more or less intelligible than the other in certain situations such as high levels of noise. Anecdotal information, supported by some empirical observations, suggests that some of the high intensity noise spectra of military aircraft cockpits may degrade the intelligibility of female speech more than that of male speech. METHODS: In an applied research study, the intelligibility of female and male speech was measured in several high level aircraft cockpit noise conditions experienced in military aviation. RESULTS: In Part I, (Nixon CW, et al. Aviat Space Environ Med 1998; 69:675-83) female speech intelligibility measured in the spectra and levels of aircraft cockpit noises and with noise-canceling microphones was lower than that of the male speech in all conditions. However, the differences were small and only those at some of the highest noise levels were significant. Although speech intelligibility of both genders was acceptable during normal cruise noises, improvements are required in most of the highest levels of noise created during maximum aircraft operating conditions. These results are discussed in a Part I technical report. This Part II report examines the intelligibility in the same aircraft cockpit noises of vocoded female and male speech and the accuracy with which female and male speech in some of the cockpit noises were understood by automatic speech recognition systems. The intelligibility of vocoded female speech was generally the same as that of vocoded male speech. No significant differences were measured between the recognition accuracy of male and female speech by the automatic speech recognition systems. The intelligibility of female and male speech was equivalent for these conditions.

Adult↗
PubMed2026

Improving insurance deduction identification: a hybrid artificial intelligence model using machine learning and expert systems.

PURPOSE: Financial challenges in healthcare systems worldwide, especially in low- and middle-income countries like Iran, have increased hospitals' reliance on insurance reimbursements. Unrecognized insurance deductions often cause severe financial shortages, making efficient deduction management crucial. This study aimed to design a hybrid intelligent system for identifying and predicting insurance deductions by combining machine learning and expert system frameworks. DESIGN/METHODOLOGY/APPROACH: A mixed-methods design was applied in four stages. First, a scoping review identified the causes and patterns of insurance deductions. Second, interviews with 15 insurance experts produced a validated checklist and a dataset from inpatient billing records. Third, using the CRISP-DM methodology, machine learning algorithms were developed and tested in SPSS Modeler alongside a fuzzy expert system developed in MATLAB. Finally, the model was validated using the holdout method. FINDINGS: Four categories of deduction drivers were identified: service provision, registration errors, document submission issues, and revenue conversion processes. The CHAID decision tree outperformed other algorithms with a 99% precision rate and the lowest Mean Absolute Error (9.43). A brief assessment of potential overfitting was conducted to ensure that the CHAID model's high accuracy was interpreted cautiously and supported by the validation results. The fuzzy expert system with validated rules was adaptable for deduction classification, especially for cases unsuitable for quantitative modeling. ORIGINALITY/VALUE: The hybrid model improves detection and prevention of deductions, offering actionable insights for hospital administrators, insurers, and policymakers. Its implementation can enhance hospital information systems, streamline claims processing, and optimize revenue management amid financial constraints.

Machine Learning↗
PubMed2005

A Bayesian approach to generating tutorial hints in a collaborative medical problem-based learning system.

OBJECTIVES: Today a great many medical schools have turned to a problem-based learning (PBL) approach to teaching. While PBL has many strengths, effective PBL requires the tutor to provide a high degree of personal attention to the students, which is difficult in the current academic environment of increasing demands on faculty time. This paper describes intelligent tutoring in a collaborative medical tutor for PBL. The main contribution of our work is the development of representational techniques and algorithms for generating tutoring hints in PBL group problem solving, as well as the implementation of these techniques in a collaborative intelligent tutoring system, COMET. The system combines concepts from computer-supported collaborative learning with those from intelligent tutoring systems. METHODS AND MATERIALS: The system uses Bayesian networks to model individual student clinical reasoning, as well as that of the group. The prototype system incorporates substantial domain knowledge in the areas of head injury, stroke and heart attack. Tutoring in PBL is particularly challenging since the tutor should provide as little guidance as possible while at the same time not allowing the students to get lost. From studies of PBL sessions at a local medical school, we have identified and implemented eight commonly used hinting strategies. In order to evaluate the appropriateness and quality of the hints generated by our system, we compared the tutoring hints generated by COMET with those of experienced human tutors. We also compared the focus of group activity chosen by COMET with that chosen by human tutors. RESULTS: On average, 74.17% of the human tutors used the same hint as COMET. The most similar human tutor agreed with COMET 83% of the time and the least similar tutor agreed 62% of the time. Our results show that COMET's hints agree with the hints of the majority of the human tutors with a high degree of statistical agreement (McNemar test, p=0.652, kappa=0.773). The focus of group activity chosen by COMET agrees with that chosen by the majority of the human tutors with a high degree of statistical agreement (McNemar test, p=0.774, kappa=0.823). CONCLUSION: Bayesian network clinical reasoning models can be combined with generic tutoring strategies to successfully emulate human tutor hints in group medical PBL.

Artificial Intelligence↗
PubMed1996

An expert diagnostic system based on neural networks and image analysis techniques in the field of automated cytogenetics.

In this study, we introduce an expert system for intelligent chromosome recognition and classification based on artificial neural networks (ANN) and features obtained by automated image analysis techniques. A microscope equipped with a CCTV camera, integrated with an IBM-PC compatible computer environment including a frame grabber, is used for image data acquisition. Features of the chromosomes are obtained directly from the digital chromosome images. Two new algorithms for automated object detection and object skeletonizing constitute the basis of the feature extraction phase which constructs the components of the input vector to the ANN part of the system. This first version of our intelligent diagnostic system uses a trained unsupervised neural network structure and an original rule-based classification algorithm to find a karyotyped form of randomly distributed chromosomes over a complete metaphase. We investigate the effects of network parameters on the classification performance and discuss the adaptability and flexibility of the neural system in order to reach a structure giving an output including information about both structural and numerical abnormalities. Moreover, the classification performances of neural and rule-based system are compared for each class of chromosome.

Algorithms↗