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 973 records · Page 54Linked to original sources
PubMedDate not supplied

Defaults, exceptions and ambiguity in a medical knowledge representation system.

Inheritance methods for general semantic networks which allow for exceptions are essential to representing medical knowledge in forms which are familiar to doctors. Such systems give rise to the possibility of ambiguity and problems of computational efficiency. Efficient computational methods using conventional hardware for inheritance and the detection of ambiguity in general semantic networks are described. These methods have been implemented in PROLOG in a knowledge management system which is being used in the development of intelligent drug information and medical decision support systems.

Algorithms↗
PubMed1996

On the interpretation of certainty factors in expert systems.

Despite the strong theoretical foundation the Bayesian probabilistic approach to model uncertainty in medicine meets many difficulties at the implementation step. One of these difficulties is related to a large amount of conditional probabilities to be assessed and in many cases this task was recognised to be practically insoluble. The MYCIN certainty factors model is a widely distributed pragmatical approach for modeling reasoning under uncertainty that substantially simplifies the problem, at the sacrifice of theoretical soundness. One can determine certainty factors as a function of prior and posterior probability. However, this approach is only consistent with the modularity axiom for certainty factors for tree-structure inference networks, which is rarely true for practical applications. In this paper we abandon the requirement of a direct probabilistic interpretation of certainty factors and build a model of propagation of uncertainty in terms of absolute belief and belief updates. We describe our model for propagating uncertainty in terms of matrix multiplication with specifically defined addition and multiplication which correspond to parallel and sequential combinations of certainty factors. It is possible to define these operations in such a manner that they form a field, and therefore to obtain some useful properties. Finally we present a method of determining certainty factors from statistical data using nonlinear regression and illustrate it with a leukemia diagnostics problem.

Artificial Intelligence↗
PubMed1997

Genetic algorithm based system for patient scheduling in highly constrained situations.

In medicine and health care there are a lot of situations when patients have to be scheduled on different devices and/or with different physicians or therapists. It may concern preventive examinations, laboratory tests or convalescent therapies, therefore we are always looking for an optimal schedule that would result in finishing all the activities scheduled as soon as possible, with the least patient waiting time and maximum device utilization. Since patient scheduling is a highly complex problem, it is impossible to make a qualitative schedule by hand or even with exact heuristic methods. Therefore we developed a powerful automated scheduling method for highly constrained situations based on genetic algorithms and machine learning. In this paper we present the method, together with the whole process of schedule generation, the important parameters to direct the evolution and how the algorithm is guaranteed to produce only feasible solutions, not breaking any of the required constraints. We applied the described method to a problem of scheduling patients with different therapy needs to a limited number of therapeutic devices, but the algorithm can be easily modified for use in similar situations. The results are quite encouraging and since all the solutions are feasible, the method can be easily incorporated into an interactive user interface, which can be of major importance when scheduling patients, and human resources in general, is considered.

Algorithms↗
PubMed2004

Surveillance for progressive intellectual and neurological deterioration in the Canadian paediatric population.

OBJECTIVES: To conduct active surveillance of the Canadian paediatric population for children who have a progressive intellectual and neurological deterioration to detect the occurrence of cases of Creutzfeldt-Jakob disease or variant Creutzfeldt-Jakob disease. CASE DEFINITION: Any child who is less than or equal to 18 years of age, who had a progressive loss of already attained intellectual/developmental abilities and development of abnormal neurological signs of greater than three months duration was eligible for inclusion. DURATION: July 1999 to July 2001. METHOD: Enhanced active surveillance system for progressive intellectual and neurological deterioration was implemented to detect, prospectively, among the Canadian paediatric population. Each month, all paediatricians and paediatric neurologists in Canada were mailed a reporting form. All reported cases were reviewed by the principal investigator who classified the cases into one of four predetermined categories. Cases where there was evidence of neurological and intellectual regression without known cause were reviewed by a panel. Reported cases were reviewed for the possibility of classic or variant Creutzfeldt-Jakob disease. RESULTS: Over 2200 physicians took part in this program. There was more than an 80% monthly return rate of the initial report form. Ninety-nine possible cases of progressive neurological and intellectual deterioration were reported. Sixty cases were classified as having a progressive neurological syndrome associated with intellectual deterioration. Fourteen cases were duplicates. One case of Creutzfeldt-Jacob disorder was found but no cases of the variant form of Creutzfeldt-Jacob disorder. Fifteen cases were felt not to meet the above-mentioned entry criteria.

Adolescent↗
PubMed1992

Acquisition of ICU data: concepts and demands.

As the issue of data overload is a problem in critical care today, it is of utmost importance to improve acquisition, storage, integration, and presentation of medical data, which appears only feasible with the help of bedside computers. The data originates from four major sources: (1) the bedside medical devices, (2) the local area network (LAN) of the ICU, (3) the hospital information system (HIS) and (4) manual input. All sources differ markedly in quality and quantity of data and in the demands of the interfaces between source of data and patient database. The demands for data acquisition from bedside medical devices, ICU-LAN and HIS concentrate on technical problems, such as computational power, storage capacity, real-time processing, interfacing with different devices and networks and the unmistakable assignment of data to the individual patient. The main problem of manual data acquisition is the definition and configuration of the user interface that must allow the inexperienced user to interact with the computer intuitively. Emphasis must be put on the construction of a pleasant, logical and easy-to-handle graphical user interface (GUI). Short response times will require high graphical processing capacity. Moreover, high computational resources are necessary in the future for additional interfacing devices such as speech recognition and 3D-GUI. Therefore, in an ICU environment the demands for computational power are enormous. These problems are complicated by the urgent need for friendly and easy-to-handle user interfaces. Both facts place ICU bedside computing at the vanguard of present and future workstation development leaving no room for solutions based on traditional concepts of personal computers.(ABSTRACT TRUNCATED AT 250 WORDS)

Artificial Intelligence↗
PubMed2006

Prediction of heterogeneity in intelligence and adult prognosis by genetic polymorphisms in the dopamine system among children with attention-deficit/hyperactivity disorder: evidence from 2 birth cohorts.

CONTEXT: The study and treatment of psychiatric disorders is made difficult by the fact that patients with identical symptoms often differ markedly in their clinical features and presumably in their etiology. A principal aim of genetic research is to provide new information that can resolve such clinical heterogeneity and that can be incorporated into diagnostic practice. OBJECTIVE: To test the hypothesis that the DRD4 seven-repeat allele and DAT1 ten-repeat allele would prove useful in identifying a subset of children with attention-deficit/hyperactivity disorder (ADHD) who have compromised intellectual functions. DESIGN: Longitudinal epidemiologic investigation of 2 independent birth cohorts. SETTING: Britain and New Zealand. PARTICIPANTS: The first cohort was born in Britain in 1994-1995 and includes 2232 children; the second cohort was born in New Zealand in 1972-1973 and includes 1037 children. MAIN OUTCOME MEASURES: Evaluation of ADHD, IQ, and adult psychosocial adjustment. RESULTS: We present replicated evidence that polymorphisms in the DRD4 and DAT1 genes were associated with variation in intellectual functioning among children diagnosed as having ADHD, apart from severity of their symptoms. We further show longitudinal evidence that these polymorphisms predicted which children with ADHD were at greatest risk for poor adult prognosis. CONCLUSION: The findings indicate that genetic information of this nature may prove useful for etiology-based psychiatric nosologies.

Adolescent↗
PubMed1980

Intellectual, school and occupational performance in patients with idiopathic hypothalamo-pituitary hypothyroidism and primary hypothyroidism.

Intelligence quotient (IQ), school and professional performance were reviewed in 33 patients with idiopathic hypothalamo-pituitary hypothyroidism. Diagnosis was based on low T4 values and clinical signs. All were treated with growth hormone (HGH). In some, hypothyroidism became manifest only after HGH therapy. Birth history revealed breech delivery in 24 and perinatal asphyxia in 15 of them. Thyroid treatment was started at a mean age of 9.8 (range 4-18 years). The mean IQ was 103.4 +/- 16.7 (SD). 9 patients had IQs below 90, 8 of them were born by breech delivery, 3 had severe perinatal asphyxia, one recurrent symptomatic hypoglycemia, and one a micropenis. Of those patients who have reached the respective age, 7 attended college, 3 university, and 9 had skilled professions. Only 7 required special education. For comparison, 52 patients with primary hypothyroidism were studied. Their mean IQ was with 89.3 +/- 18.1 (SD) significantly lower (p < 0.001) than the mean IQ of patients with hypothalamo-pituitary hypothyroidism. The best IQ (96.8 +/- 16.9) was attained when thyroid treatment was started before the age of 4 months, the lowest IQ (78.2 +/- 19.2) was found in the group of patients in whom thyroid substitution was initiated between 5 and 12 months. Patients who were treated after one year of age, had a mean IQ of 90.0 +/- 15.7. This group includes patients with ectopic thyroid glands or acquired hypothyroidism such as Hashimoto's thyroiditis.

Adolescent↗
PubMed1998

Automatic classification of transiently evoked otoacoustic emissions using an artificial neural network.

The increasing use of transiently evoked otoacoustic emissions (TEOAE) in large neonatal hearing screening programmes makes a standardized method of response classification desirable. Until now methods have been either subjective or based on arbitrary response characteristics. This study takes an expert system approach to standardize the subjective judgements of an experienced scorer. The method that is developed comprises three stages. First, it transforms TEOAEs from waveforms in the time domain into a simplified parameter set. Second, the parameter set is classified by an artificial neural network that has been taught on a large database TEOAE waveforms and corresponding expert scores. Third, additional fuzzy logic rules automatically detect probable artefacts in the waveforms and synchronized spontaneous emission components. In this way, the knowledge of the experienced scorer is encapsulated in the expert system software and thereafter can be accessed by non-experts. Teaching and evaluation of the neural network was based on TEOAEs from a database totalling 2190 neonatal hearing screening tests. The database was divided into learning and test groups with 820 and 1370 waveforms respectively. From each recorded waveform a set of 12 parameters was calculated, representing signal static and dynamic properties. The artifical network was taught with parameter sets of only the learning groups. Reproduction of the human scorer classification by the neural net in the learning group showed a sensitivity for detecting screen fails of 99.3% (299 from 301 failed results on subjective scoring) and a specificity for detecting screen passes of 81.1% (421 of 519 pass results). To quantify the post hoc performance of the net (generalization), the test group was then presented to the network input. Sensitivity was 99.4% (474 from 477) and specificity was 87.3% (780 from 893). To check the efficiency of the classification method, a second learning group was selected out of the previous test group, and the previous learning group was used as the test group. Repeating learning and test procedures yielded 99.3% sensitivity and 80.7% specificity for reproduction, and 99.4% sensitivity and 86.7% specificity for generalization. In all respects, performance was better than for a previously optimized method based simply on cross-correlation between replicate non-linear waveforms. It is concluded that classification methods based on neural networks show promise for application to large neonatal screening programmes utilizing TEOAEs.

Artificial Intelligence↗
PubMedDate not supplied

Semi-automated entry of clinical temporal-abstraction knowledge.

OBJECTIVES: The authors discuss the usability of an automated tool that supports entry, by clinical experts, of the knowledge necessary for forming high-level concepts and patterns from raw time-oriented clinical data. DESIGN: Based on their previous work on the RESUME system for forming high-level concepts from raw time-oriented clinical data, the authors designed a graphical knowledge acquisition (KA) tool that acquires the knowledge required by RESUME. This tool was designed using Protégé, a general framework and set of tools for the construction of knowledge-based systems. The usability of the KA tool was evaluated by three expert physicians and three knowledge engineers in three domains-the monitoring of children's growth, the care of patients with diabetes, and protocol-based care in oncology and in experimental therapy for AIDS. The study evaluated the usability of the KA tool for the entry of previously elicited knowledge. MEASUREMENTS: The authors recorded the time required to understand the methodology and the KA tool and to enter the knowledge; they examined the subjects' qualitative comments; and they compared the output abstractions with benchmark abstractions computed from the same data and a version of the same knowledge entered manually by RESUME experts. RESULTS: Understanding RESUME required 6 to 20 hours (median, 15 to 20 hours); learning to use the KA tool required 2 to 6 hours (median, 3 to 4 hours). Entry times for physicians varied by domain-2 to 20 hours for growth monitoring (median, 3 hours), 6 and 12 hours for diabetes care, and 5 to 60 hours for protocol-based care (median, 10 hours). An increase in speed of up to 25 times (median, 3 times) was demonstrated for all participants when the KA process was repeated. On their first attempt at using the tool to enter the knowledge, the knowledge engineers recorded entry times similar to those of the expert physicians' second attempt at entering the same knowledge. In all cases RESUME, using knowledge entered by means of the KA tool, generated abstractions that were almost identical to those generated using the same knowledge entered manually. CONCLUSION: The authors demonstrate that the KA tool is usable and effective for expert physicians and knowledge engineers to enter clinical temporal-abstraction knowledge and that the resulting knowledge bases are as valid as those produced by manual entry.

Acquired Immunodeficiency Syndrome↗
PubMed2026

Artificial intelligence-assisted histopathological diagnosis of endocervical gastric-type adenocarcinoma: a multicenter model development and validation study.

Endocervical gastric-type adenocarcinoma (GAS) is one of the most aggressive subtypes of cervical cancer and is frequently underdiagnosed due to morphological ambiguity, leading to delayed diagnosis. Despite the availability of molecular and genomic assays, their high cost, complexity, and limited reproducibility restrict clinical use. This study therefore proposes a highly sensitive artificial intelligence (AI)-assisted diagnostic system for GAS based exclusively on H&E-stained histopathological images. We included 309 slides from 96 GAS cases collected at Peking University Third Hospital from January 2018 to January 2025, representing the largest GAS cohort reported to date for AI research. In addition, we incorporated other morphologically analogous diseases, encompassing a total of 1,320 slides sourced from four categories: normal cervical mucosa (NORM), benign endocervical lesion entities (BELE), HPV-associated adenocarcinoma (HPVA), and endometrioid carcinoma with mucinous differentiation (ECMD). We developed GASPath, based on a novel multiple instance learning framework that efficiently captures fine-grained morphological variations from H&E-stained images. Beyond internal validation, GASPath was evaluated across 12 independent retrospective cohorts and further subjected to large-scale real-world validation on more than 7,000 samples from March 2024 to April 2025. Across three stages, GASPath demonstrated high performance. In internal validation (Stage I), it achieved an accuracy of 0.980 (95% CI 0.977-0.983) and an ROC-AUC of 0.995 (95% CI 0.994-0.997). In external validation (Stage II), the sensitivity reached 0.902 and improved to 0.968 with proposed strategies. For biopsy samples, GASPath achieved an ROC-AUC of 0.990 (95% CI 0.984-0.997). In large-scale real-world deployment (Stage III, n&#x2009;=&#x2009;7,056), GASPath achieved a balanced accuracy of 0.953, with 100% sensitivity for GAS (45/45 cases correctly identified). The heatmaps highlight morphological features of GAS that are easily underestimated, such as irregular, angulated glands, subtle loss of nuclear polarity, and mild cytologic atypia, which show substantial morphological overlap with other diagnostic categories. GASPath enables high-sensitivity detection of GAS in routine H&E-stained slides, obviating the need for extensive auxiliary testing while preventing underdiagnosis and misdiagnosis. This advancement addresses a critical gap by streamlining diagnostic workflows without compromising accuracy. Its implementation could enable cost-effective, scalable AI-assisted diagnostics, potentially transforming the early detection and management of this aggressive cancer subtype.

Female↗
PubMedDate not supplied

Intelligence quotient in childhood acute lymphoblastic leukemia after prophylactic treatment in central nervous system with 18 Gy cranial irradiation and intrathecal methotrexate.

The purpose of this study is to evaluate whether central nervous system prophylactic treatment (CNSP) with cranial irradiation therapy (CrRT) 18 Gy and intrathecal methotrexate would decline the intelligence quotient (IQ) scores of children with acute lymphoblastic leukemia (ALL). In protocol TCL 842, children with ALL received CrRT 18 Gy in 12 fractions, and 5 concomitant doses of intrathecal methotrexate 15 mg/m2/dose with 15 mg as the maximum, for CNSP after remission achieved. The first IQ test was performed immediately after CNSP. Those who had no CNS relapse for more than 5 years after CNSP had a second IQ test. For children between 3 and 6 years old, the Stanford-Binet (S-B) IV test was used, and for older children, the Wechsler Intelligence Scale for Children-Revised (WISC-R) was used. Fourteen consecutive children at our hospital were enrolled. There were 7 boys and 7 girls. The age at diagnosis ranged from 3 to 9 years old. Two of them were in the high-risk group, eight in the intermediate-risk group, and four in the standard-risk group. The IQ scores of all patients fell within the average range. In the first IQ tests, the mean IQ score was 104.29 (range 83-124, S.D. 14.55). In the second IQ tests, the mean IQ score was 100.93 (range 85-128, S.D. 11.57). Statistically, there was no significant difference between the first and second IQ scores (paired t-test, two-tailed P = 0.4232; one-tailed P = 0.2116). Our findings suggested that CNSP used in protocol TCL 842 did not reduce IQ scores of children with ALL 5 years after CNSP.

Adolescent↗
PubMed1989

Neurologic status and intracranial hemorrhage in very-low-birth-weight preterm infants. Outcome at 1 year and 5 years.

Twenty-six very-low-birth-weight preterm infants with and without intracranial hemorrhage (ICH) were followed up prospectively from birth to school age to determine the relationship between ICH and subsequent neurologic and cognitive outcomes. All children had sequential cranial ultrasound examinations at birth and neurologic assessments at 3-month intervals during the first year, at 1 year of age, and at 5 to 6 years; psychometric assessments were done at 5 to 6 years. Seventeen children had no ICH, 3 had grade 1 ICH, 1 had grade 3 ICH, and 5 had grade 4 ICH. The 1-year Amiel-Tison neurologic assessment in 25 infants demonstrated that 14 were normal, 3 were suspect, and 8 were abnormal. By 5 to 6 years of age, 5 of 8 children neurologically abnormal at 1 year remained abnormal, 2 of 3 children neurologically suspect at 1 year remained suspect; while 9 of 15 children neurologically normal at 1 year remained normal, the remaining 6 had become suspect. The predominant neurologic abnormality at 5 to 6 years was subtle neurologic dysfunctioning. The Wechsler Preschool and Primary Scale of Intelligence at 5 to 6 years revealed a mean group IQ score of 92.1. The Beery Visual Motor Integration Test results demonstrated that 18 of 26 children had mild to severe visual motor perceptual difficulties. Severe ICH (grades 3 and 4) correlated with abnormal neurologic performances at 1 and 5 to 6 years. Mild ICH (grade 1) and no ICH did not correlate with any one of the 1-year neurologic classifications. The 1-year status correlated with the 5- to 6-year neurologic outcome best for children who were either neurologically suspect or abnormal at age 1 year. The 1-year neurologic score did not correlate with 5- to 6-year IQ and Beery Visual Motor Integration Test scores.

Cerebral Hemorrhage↗
PubMed1986

NPPD (spy dust) is predicted to be a mutagen.

With the aid of CASE, the Computer Automated Structure Evaluation system, a new artificial intelligence procedure to study structure-activity relationships and a data base consisting of 233 monocyclic nitroarenes, it is predicted that 5-(4-nitrophenyl)-2,4-pentadienal will be mutagenic for Salmonella typhimurium but that the activity will be very low.

Computers↗
PubMed1989

Conformational analysis of blood group A-active glycosphingolipids using HSEA-calculations. The possible significance of the core oligosaccharide chain for the presentation and recognition of the A-determinant.

Conformational analysis of four different A-active glycosphingolipids, A types 1-4, was carried out using HSEA-calculations with the GESA-program. In their minimum energy conformations the oligosaccharide chains are more or less curved; in particular the type 3 and 4 have a strongly bent shape. When the carbohydrate structures are linked to ceramide, using the conformational features predominantly observed in crystal structures of membrane lipids, rather drastic differences in the orientation of the oligosaccharide chains are obtained. For the type 1 glycosphingolipid the model study indicates that the A-determinant extends almost perpendicularly to the membrane plane whereas for type 2, 3 and 4 the terminal part of the oligosaccharide chains is more parallel to the membrane. The fucose branch on type 3 and type 4 thereby appears directed towards the environment whereas for type 2 it would face the membrane. Due to restrictions imposed by the membrane layer this core specific orientation is largely preserved even if the flexibility of the saccharide-ceramide linkage is taken into account. Hydrophilic and hydrophobic sites on the surface of the different oligosaccharide chains in their minimum energy conformation were located using the GRID-program. It is suggested that the core-dependent presentation of the A-determinant might explain the chain type specificity observed for different monoclonal anti-A antibodies. The results further suggest that assay systems ensuring a membrane-like presentation of the glycolipid antigen should be used in studies of glycolipid/protein interactions.

ABO Blood-Group System↗