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 793 records · Page 44Linked to original sources
PubMed2026

Open and sustainable AI: challenges, opportunities and the road ahead in the life sciences.

Artificial intelligence (AI) has seen transformative breakthroughs in the life sciences, expanding possibilities to interpret biological information at an unprecedented capacity. To maximize return on growing investments and accelerate progress, it is urgent to address long-standing research challenges arising from the rapid adoption of AI methods. We review the erosion of trust in AI outputs driven by poor reusability and reproducibility, and highlight their impact on environmental sustainability. Furthermore, we discuss the fragmented components of the AI ecosystem and lack of guiding pathways to support open and sustainable AI model development. In response, this Perspective introduces practical open and sustainable AI recommendations mapped to over 300 ecosystem components and provides guiding implementation pathways. Our work connects researchers with relevant AI resources, facilitating the implementation of sustainable, reusable and reproducible AI. Built upon community consensus and aligned to existing efforts, these outputs will aid future policy development and structured pathways for guiding AI implementation.

Artificial Intelligence↗
PubMed2004

A bridged diagnostic method for the monitoring of polymorphic discrete-event systems.

Diagnosis of discrete-event systems (DESs) is a challenging problem that has been tackled both by automatic control and artificial intelligence communities. The relevant approaches share similarities, including modeling by automata, compositional modeling, and model-based reasoning. This paper aims to bridge two complementary approaches from these communities, namely, the diagnoser approach and the active system approach, respectively. The more significant shortcomings of such approaches are, on the one side, the need for the generation of the global system model and, on the other, the lack of monitoring capabilities. The former makes the application of the diagnoser approach prohibitive in real contexts, where the system model is too large to be generated, even offline. The latter requires the completion of the system observation before starting the diagnostic task, thereby, making the monitoring of the system. impossible. The bridged diagnostic method subsumes, to a large extent on the peculiarities of the two approaches and is capable of coping with an extended class of DESs that integrate both synchronous and asynchronous behavior. The bridge is built by extending the active system approach by means of several enhanced techniques, which eventually, allow the efficient monitoring of polymorphic DESs. Upon the occurrence of each system message, two pieces of diagnostic information are generated, namely, the snapshot and historic diagnostic sets. While the former accounts for the faults pertinent to the newly generated message only, the latter is based on the whole sequence of messages yielded by the system during operation.

Algorithms↗
PubMed1997

Application of genetic search in derivation of matrix models of peptide binding to MHC molecules.

T cells of the vertebrate immune system recognise peptides bound by major histocompatibility complex (MHC) molecules on the surface of host cells. Peptide binding to MHC molecules is necessary for immune recognition, but only a subset of peptides are capable of binding to a particular MHC molecule. Common amino acid patterns (binding motifs) have been observed in sets of peptides that bind to specific MHC molecules. Recently, matrix models for peptide/MHC interaction have been reported. These encode the rules of peptide/ MHC interactions for an individual MHC molecule as a 20 x 9 matrix where the contribution to binding of each amino acid at each position within a 9-mer peptide is quantified. The artificial intelligence techniques of genetic search and machine learning have proved to be very useful in the area of biological sequence analysis. The availability of peptide/MHC binding data can facilitate derivation of binding matrices using machine learning techniques. We performed a simulation study to determine the minimum number of peptide samples required to derive matrices, given the pre-defined accuracy of the matrix model. The matrices were derived using a genetic search. In addition, matrices for peptide binding to the human class I MHC molecules, HLA-B35 and -A24, were derived, validated by independent experimental data and compared to previously-reported matrices. The results indicate that at least 150 peptide samples are required to derive matrices of acceptable accuracy. This result is based on a maximum noise content of 5%, the availability of precise affinity measurements and that acceptable accuracy is determined by an area under the Relative Operating Characteristic curve (Aroc) of > 0.8. More than 600 peptide samples are required to derive matrices of excellent accuracy (Aroc > 0.9). Finally, we derived a human HLA-B27 binding matrix using a genetic search and 404 experimentally-tested peptides, and estimated its accuracy at Aroc > 0.88. The results of this study are expected to be of practical interest to immunologists for efficient identification of peptides as candidates for immunotherapy.

Amino Acid Sequence↗
PubMed2026

Precision periodontology in clinical practice: bridging omics and clinical decision-making.

BACKGROUND: Precision periodontology integrates molecular diagnostics, genomics, and advanced imaging into clinical decision-making. Despite major advances in microbiome characterisation, host genetics, and inflammatory biomarkers, their translation into routine care remains limited. OBJECTIVES: To critically appraise current evidence on microbiome-based profiling, genetic and epigenetic markers, host-response biomarkers, and three-dimensional imaging in periodontology, and to propose a conceptual decision-support framework linking diagnostic outputs to potential therapeutic actions and future implementation research. MATERIALS AND METHODS: A narrative review searching PubMed/MEDLINE, Scopus, Embase, and the Cochrane Library (2010-2025) using terms related to precision periodontology, subgingival microbiome, periodontitis genetics and epigenetics, salivary and GCF biomarkers, aMMP-8, CBCT, risk assessment, and artificial intelligence. Priority was given to meta-analyses, systematic reviews, longitudinal studies, and guideline documents. RESULTS: Microbiological testing has defined but narrow indications; single-SNP genotyping has not demonstrated clinical utility commensurate with cost; aMMP-8 point-of-care testing is among the most extensively investigated host-response tools and may have adjunctive value in selected monitoring and peri-implant scenarios; however, current evidence remains insufficient to support routine diagnostic implementation. CBCT may directly influence surgical decision-making through defect morphology characterisation. AI-based models show promise but lack prospective clinical validation. These conclusions are consistent with the 20th EFP Workshop Consensus Report. CONCLUSIONS: Precision periodontology currently operates in addition to, rather than in replacement of, conventional staging and grading. We propose a conceptual decision-threshold framework for the selective consideration of molecular and advanced imaging tools when their additive contribution may meaningfully inform management. This framework should be regarded as a research-oriented decision-support model rather than a validated clinical algorithm. CLINICAL RELEVANCE: Clinicians are provided with a structured, evidence-based framework that identifies specific clinical scenarios where molecular diagnostics, host-response biomarkers, and three-dimensional imaging may meaningfully modify periodontal treatment decisions, supporting the operationalisation of precision approaches in daily practice.

Humans↗
PubMed1994

An evaluation of expert human and automated Abbreviated Injury Scale and ICD-9-CM injury coding.

Two hundred ninety-five injury descriptions from 135 consecutive patients treated at a level-I trauma center were coded by three human coders (H1, H2, H3) and by TRI-CODE (T), a PC-based artificial intelligence software program. Two study coders are nationally recognized experts who teach AIS coding for its developers (the Association for the Advancement of Automotive Medicine); the third has 5 years experience in ICD and AIS coding. A "correct coding" (CC) was established for the study injury descriptions. Coding results were obtained for each coder relative to the CC. The correct ICD codes were selected in 96% of cases for H2, 92% for H1, 91% for T, and 86% for H3. The three human coders agreed on 222 (75%) injuries. The correct 7 digit AIS codes (six identifying digits and the severity digit) were selected in 93% of cases for H2, 87% for T, 77% for H3, and 73% for H1. The correct AIS severity codes (seventh digit only) were selected in 98.3% of cases for H2, 96.3% for T, 93.9% for H3, and 90.8% for H1. On the basis of the weighted kappa statistic TRI-CODE had excellent agreement with the correct coding (CC) of AIS severities. Each human coder had excellent agreement with CC and with TRI-CODE. Coders H1 and H2 were in excellent agreement. Coder H3 was in good agreement with H1 and H2. However, errors among the human coders often occur for different codes, accentuating the variability.(ABSTRACT TRUNCATED AT 250 WORDS)

Abbreviated Injury Scale↗
PubMedDate not supplied

An expert system for the diagnosis of epilepsy: results of a clinical trial.

BACKGROUND: Artificial intelligence is an area where computer systems are used to solve real-life problems that require expert human intelligence. Expert systems serve as an effective alternative to supplement the dearth of human experts in a narrow domain of applications. We developed an expert system named SEIZ using DIAGNOS (an expert system shell for diagnostic applications) for the diagnosis and management of epilepsy. METHODS: A clinical trial was done to test the reliability of SEIZ. The clinical and demographic data from the medical records of 50 patients with epilepsy who attended an epilepsy clinic were provided to the expert system. The system-generated diagnosis was compared with the clinical diagnosis. RESULTS: The seizure types and epileptic syndromes for the 50 patients included generalized -tonic-clonic seizure (14), absence (4), complex partial seizure (18), simple partial seizure (4), juvenile myoclonic epilepsy (5) and other epileptic syndromes (3). There were two cases of hysterical conversion reaction. There was concordance in the diagnosis between the expert system and clinician in 47 cases (94%). The overall sensitivity was 94% and the specificity was 100% for absence, generalized tonic-clonic seizures, simple partial seizures and juvenile myoclonic epilepsy; 94% for complex partial seizures and 98% for hysterical conversion reaction. CONCLUSION: This expert system could generate reliable diagnoses for patients with epilepsy. Such a system may be useful for a doctor in a remote or peripheral area where an expert on epilepsy is not available.

Adult↗
PubMed2026

AI proteomics: from protein identification to virtual cells.

Artificial intelligence (AI) is transforming scientific research, including proteomics. In this Perspective, we highlight key mass spectrometry (MS)-based proteomics areas where AI is driving innovation, ranging from protein identification to building AI virtual cells. These include improving peptide and protein identification and quantification; characterizing protein-protein interactions and protein complexes; advancing spatial and perturbation proteomics; integrating multi-omics data; and, ultimately, enabling AI virtual cells. Finally, we call for global collaboration among data producers, data consumers and other stakeholders to establish an AI-friendly ecosystem for MS-based proteomics, laying the foundation for transformative advancements in proteomics driven by AI.

Proteomics↗
PubMed2025

Enhanced fracture detection on radiographs with AI assistance for clinicians: a systematic review and meta-analysis.

BACKGROUND: Emergency radiographic interpretation for fractures is prone to missed or misdiagnoses. Artificial intelligence (AI) is expected to become a powerful tool to assist clinicians in fracture detection. PURPOSE: A systematic review and meta-analysis was performed to assess whether AI improves clinicians' ability to detect fractures on radiographs. MATERIALS AND METHODS: A literature search was conducted in PubMed, Web of Science, and Cochrane Library for studies published between January 1, 2010, and October 10, 2025. A meta-analysis of diagnostic accuracy studies was performed using a Summary Receiver Operating Characteristic (SROC) curve. The quality of included studies was assessed using the Quality Assessment of Diagnostic Accuracy Studies 2 (QUADAS-2) tool. Subgroup analysis and meta-regression were conducted to explore potential sources of heterogeneity. RESULTS: A total of 26 studies were included . The pooled sensitivity of clinicians increased from 77% (95% CI: 72-81) to 87% (95% CI: 83-90) with AI assistance, while the pooled specificity improved from 88% (95% CI: 85-90) to 92% (95% CI: 89-94). The corresponding AUC values were 0.90 (95% CI: 0.87-0.92) before and 0.95 (95% CI: 0.93-0.97) after AI assistance. Eight studies were rated as high risk of bias. Subgroup analysis and meta-regression identified potential sources of heterogeneity, including fracture location, AI model type, high risk of bias, and reference standards. CONCLUSION: AI assistance significantly improves clinicians' diagnostic performance in detecting fractures on radiographs for extremity and trunk fractures.

Humans↗
PubMed2026

Diagnostic Performance of Machine Learning for Systemic Lupus Erythematosus: Systematic Review and Meta-Analysis.

BACKGROUND: Early and accurate diagnosis of systemic lupus erythematosus (SLE) and its organ involvement is essential. Previous reviews of machine learning (ML) in SLE combined heterogeneous tasks and validation strategies and may have overinterpreted model performance. OBJECTIVE: This study evaluated the diagnostic performance of ML and deep learning (DL) models for 3 clinically distinct SLE-related tasks: SLE classification or diagnosis, lupus nephritis (LN) diagnosis, and neuropsychiatric systemic lupus erythematosus (NPSLE) discrimination. We also assessed methodological quality and certainty of evidence. METHODS: PubMed, Embase, Cochrane Library, Web of Science, and IEEE Xplore were searched from January 2014 to April 2026. Eligible peer-reviewed diagnostic accuracy studies developed or validated ML or DL models for 1 of the 3 prespecified tasks, used an accepted reference standard, and provided data for a 2×2 contingency table. Bivariate random-effects meta-analyses with the Hartung-Knapp-Sidik-Jonkman adjustment were used to pool sensitivity and specificity. We reported 95% prediction intervals (PIs), assessed risk of bias using the Quality Assessment of Diagnostic Accuracy Studies for Artificial Intelligence tool (QUADAS-AI; Viknesh Sounderajah [Imperial College London]), and evaluated certainty of evidence using the Grading of Recommendations Assessment, Development, and Evaluation framework for diagnostic test accuracy. RESULTS: Twenty-nine studies were included: 17 for SLE classification, 5 for LN diagnosis, and 7 for NPSLE discrimination. In the primary task-stratified analysis, pooled sensitivity was 0.91 (95% CI 0.86-0.94; 95% PI 0.56-0.99), and pooled specificity was 0.94 (95% CI 0.91-0.96; 95% PI 0.69-0.99), with low heterogeneity (I²=23.9% and 22.9%, respectively). DL models showed a sensitivity of 0.93 and specificity of 0.95, compared with 0.88 and 0.94 for traditional ML models. Certainty of evidence was high for most analyses but low for LN diagnosis because of inconsistency and imprecision. All studies were retrospective, and only 9 of 29 (31%) performed independent external validation. Overall risk of bias was high or unclear in 22 of 29 (75.9%) studies. No study reported model calibration, decision-curve analysis, or net clinical benefit. CONCLUSIONS: ML models showed promising diagnostic accuracy across 3 distinct SLE-related tasks, but wide PIs, limited external validation, and pervasive risk of bias restrict conclusions about real-world generalizability. Prospective multicenter studies with standardized tasks and reference standards, independent external validation, and formal assessment of calibration and clinical utility are required before clinical implementation.

Humans↗
PubMed1998

Towards the unification of inference structures in medical diagnostic tasks.

The central purpose of artificial intelligence applied to medicine is to develop models for diagnosis and therapy planning at the knowledge level, in the Newell sense, and software environments to facilitate the reduction of these models to the symbol level. The usual methodology (KADS, Common-KADS, GAMES, HELIOS, Protégé, etc) has been to develop libraries of generic tasks and reusable problem-solving methods with explicit ontologies. The principal problem which clinicians have with these methodological developments concerns the diversity and complexity of new terms whose meaning is not sufficiently clear, precise, unambiguous and consensual for them to be accessible in the daily clinical environment. As a contribution to the solution of this problem, we develop in this article the conjecture that one inference structure is enough to describe the set of analysis tasks associated with medical diagnoses. To this end, we first propose a modification of the systematic diagnostic inference scheme to obtain an analysis generic task and then compare it with the monitoring and the heuristic classification task inference schemes using as comparison criteria the compatibility of domain roles (data structures), the similarity in the inferences, and the commonality in the set of assumptions which underlie the functionally equivalent models. The equivalences proposed are illustrated with several examples. Note that though our ongoing work aims to simplify the methodology and to increase the precision of the terms used, the proposal presented here should be viewed more in the nature of a conjecture.

Algorithms↗
PubMed2026

The AI Revolution: Shaping the Present and Future of Pharmaceutical Research and Development.

The transformative role of artificial intelligence (AI) in the pharmaceutical industry is examined, with a focus on its significant contributions to drug discovery, development, and clinical trial processes. It highlights the inefficiencies and high costs associated with traditional drug development and explores how AI and machine learning (ML) can enhance these processes by analyzing extensive biological datasets. The historical context of AI in pharmaceutical development is examined, noting how advances in computational power and data accessibility have facilitated innovative methodologies, such as predictive analytics and natural language processing. Contemporary trends reveal the integration of AI technologies in drug design, repurposing, and patient response forecasting. This study also addresses the challenges of participant recruitment for clinical trials and proposes AI-driven solutions to optimize patient selection and data management. Furthermore, it discusses AI's role in tailored medicine, emphasizing its potential for advancing precision therapy through targeted drug development and personalized treatment strategies. The importance of digital tools, genomic data analysis, and AI-driven imaging technologies for customizing therapeutic approaches is underscored, along with the regulatory and ethical challenges posed by AI deployment in healthcare. This study illustrates the complexities of AI applications in the pharmaceutical sector, offering insights into both successful and unsuccessful initiatives. The findings suggest that the digitalization of the pharmaceutical industry and enhanced AI integration hold promise for developing safer and more effective therapeutic strategies, while also identifying obstacles to their widespread adoption and optimal functionality.

Artificial intelligence↗
PubMed1993

A new approach to probability of survival scoring for trauma quality assurance.

This study examined the application of an artificial intelligence technique, the neural network (NET), in predicting probability of survival (Ps) for patients with penetrating trauma. A NET is a computer construct that can detect complex patterns within a data set. A NET must be "trained" by supplying a series of input patterns and the corresponding expected output (e.g., survival). Once trained, the NET can recall the proper outputs for a specific set of inputs. It can also extrapolate correct outputs for patterns never before encountered. A neural network was trained on Revised Trauma Score, Injury Severity Score, age, and survival data contained in 3500 of 8300 state registry records of all patients with penetrating trauma reported in Pennsylvania from 1987 through 1990. The remaining 4800 records were analyzed by TRISS, ASCOT, and the trained NET. Sensitivity (accuracy of predicting death) and specificity (accuracy of predicting survival) were 0.840 and 0.985 for TRISS, 0.842 and 0.985 for ASCOT, and 0.904 and 0.972 for the neural network. This represents a decrease in the number of improperly classified ("unexpected") deaths, from 73 for TRISS and 72 for ASCOT, to 44 for the neural network. The increased sensitivity was statistically significant by Chi-square analysis. The NET for penetrating trauma provided a more sensitive but less specific technique for calculating Ps than did either TRISS or ASCOT. This translated into a 40% reduction in the number of deaths requiring review, and the potential for more efficient use of quality assurance resources.

Artificial Intelligence↗
PubMed2003

Building a case-based diet recommendation system without a knowledge engineer.

We present a new approach to the effective development of menu construction systems that allow to automatically construct a menu that is strongly tailored to the individual requirements and food preferences of a client. In hospitals and other health care institutions dietitians develop diets for clients which need to change their eating habits. Many clients have special needs in regards to their medical conditions, cultural backgrounds, or special levels of nutrient requirements for better recovery from diseases or surgery, etc. Existing computer support for this task is insufficient-many diets are not specifically tailored for the client's needs or require substantial time of a dietitian to be manually developed. Our approach is based on case-based reasoning, an artificial intelligence technique that finds increasing entry into industrial practice. Our approach goes beyond the traditional case-based reasoning (CBR) approach by allowing an incremental improvement of the system's competency during routine use of the system. The improvement of the system takes place through a direct expert user-system interaction while the expert is accomplishing their tasks of constructing a diet for a given client. Whenever the system performs unsatisfactorily, the expert will need to modify the system-produced diet 'manually', i.e. by entering the desired modifications into the system. Our implemented system, menu construction using an incremental knowledge acquisition system (MIKAS), asks the expert for simple explanations for each of the manual actions he/she takes and incorporates the explanations automatically into its knowledge base (KB) so that the system will perform these manually conducted actions automatically at the next occasion. We present MIKAS and discuss the results of our case study. While still being a prototype, the senior clinical dietitian involved in our evaluation studies judges the approach to have considerable potential to improve the daily routine of hospital dietitians as well as to improve the average quality of the dietary advice given to patients within the limited available time for dietary consultations. Our approach opens up a new avenue towards building highly specialised CBR systems in a more cost-effective way. Hence, our approach promises to allow a significantly more widespread development and practical deployment of CBR systems in a large variety of application domains including many medical applications.

Artificial Intelligence↗
PubMed2006

Nearest neighbors by neighborhood counting.

Finding nearest neighbors is a general idea that underlies many artificial intelligence tasks, including machine learning, data mining, natural language understanding, and information retrieval. This idea is explicitly used in the k-nearest neighbors algorithm (kNN), a popular classification method. In this paper, this idea is adopted in the development of a general methodology, neighborhood counting, for devising similarity functions. We turn our focus from neighbors to neighborhoods, a region in the data space covering the data point in question. To measure the similarity between two data points, we consider all neighborhoods that cover both data points. We propose to use the number of such neighborhoods as a measure of similarity. Neighborhood can be defined for different types of data in different ways. Here, we consider one definition of neighborhood for multivariate data and derive a formula for such similarity, called neighborhood counting measure or NCM. NCM was tested experimentally in the framework of kNN. Experiments show that NCM is generally comparable to VDM and its variants, the state-of-the-art distance functions for multivariate data, and, at the same time, is consistently better for relatively large k values. Additionally, NCM consistently outperforms HEOM (a mixture of Euclidean and Hamming distances), the "standard" and most widely used distance function for multivariate data. NCM has a computational complexity in the same order as the standard Euclidean distance function and NCM is task independent and works for numerical and categorical data in a conceptually uniform way. The neighborhood counting methodology is proven sound for multivariate data experimentally. We hope it will work for other types of data.

Algorithms↗
PubMed1998

TACHY: an expert system for the management of supraventricular tachycardia in the elderly.

PURPOSE: Many physicians find the management of supraventricular tachyarrhythmia (SVT) in the elderly complex and challenging. With the use of artificial intelligence theory, we developed an interactive computer expert system, TACHY, to recommend therapies and warn physicians of potential therapeutic side effects. METHODS: We developed a knowledge base that stores guidelines for the management of SVT in the elderly. After the diagnosis of current SVT was input into the computer, TACHY generated a list of therapeutic options as hypotheses. TACHY then prompted the user to provide current patient-specific clinical information, and the optimal therapeutic option was then selected. Potential therapeutic side effects were also displayed. TACHY was tested in a retrospective and a prospective study. The retrospective study, comprising 96 patients with 126 episodes of SVT, was performed to determine the concordance of therapy between TACHY and cardiologists. A prospective study in 18 patients with 26 episodes of SVT was also performed to validate TACHY's recommendations in restoring sinus rhythm. RESULTS: In the retrospective study the concordance between TACHY and the cardiologist's first therapeutic option was 95.9% (121 of 126 episodes). In the prospective study sinus rhythm was restored in 18 (69%) of 26 episodes of SVT by the first therapeutic option recommended by TACHY. In the remaining eight episodes use of the second or third suggestion of TACHY was successful in controlling the ventricular response to SVT. No adverse reaction to the therapeutic options suggested by TACHY occurred. CONCLUSION: TACHY, a knowledge-based computer expert system that simulates human decision making, produced promising results in the management of SVT in the elderly.

Aged↗
PubMed2025

AI-HOPE: an AI-driven conversational agent for enhanced clinical and genomic data integration in precision medicine research.

MOTIVATION: The growing complexity of clinical cancer research has fueled a surge in demand for automated bioinformatics tools capable of integrating clinical and genomic data to accelerate discovery efforts. RESULTS: We present the Artificial Intelligence Agent for High-Optimization and Precision Medicine (AI-HOPE), an AI-driven system that enables domain experts to conduct integrative data analyses through natural language interactions. Powered by Large Language Models, AI-HOPE interprets user instructions, converts them into executable code, and autonomously analyzes locally stored data. It supports flexible association studies, subset comparisons, clinical prevalence assessments and survival analyses. In addition, AI-HOPE enables global variable scans to identify features significantly associated with a user-defined outcome, making a powerful and intuitive tool for advancing precision medicine research. Importantly, its closed-system design prevents clinical data leakage. To demonstrate its utility, AI-HOPE was applied to The Cancer Genome Atlas data to address two clinical questions. First, it identified significant enrichment of TP53 mutations in late-stage colorectal cancer compared to early-stage cases. Second, it uncovered a strong association between KRAS mutations and poorer progression-free survival in FOLFOX-treated patients. These findings align with established literature and demonstrate AI-HOPE's ability to generate meaningful insights independently, without prior assumptions. By removing programming barriers and simplifying complex analyses, AI-HOPE bridges the gap between data complexity and research needs. With its scalable and adaptable framework, AI-HOPE has the potential to support diverse biomedical research fields, driving innovation and efficiency in translational studies. AVAILABILITY AND IMPLEMENTATION: The AI-HOPE software and demonstration data is available at https://github.com/Velazquez-Villarreal-Lab/AI-HOPE.

Precision Medicine↗
PubMed2006

On optimizing syntactic pattern recognition using tries and AI-based heuristic-search strategies.

This paper deals with the problem of estimating, using enhanced artificial-intelligence (AI) techniques, a transmitted string X* by processing the corresponding string Y, which is a noisy version of X*. It is assumed that Y contains substitution, insertion, and deletion (SID) errors. The best estimate X+ of X* is defined as that element of a dictionary H that minimizes the generalized Levenshtein distance (GLD) D (X, Y) between X and Y, for all X epsilon H. In this paper, it is shown how to evaluate D (X, Y) for every X epsilon H simultaneously, when the edit distances are general and the maximum number of errors is not given a priori, and when H is stored as a trie. A new scheme called clustered beam search (CBS) is first introduced, which is a heuristic-based search approach that enhances the well-known beam-search (BS) techniques used in AI. The new scheme is then applied to the approximate string-matching problem when the dictionary is stored as a trie. The new technique is compared with the benchmark depth-first search (DFS) trie-based technique (with respect to time and accuracy) using large and small dictionaries. The results demonstrate a marked improvement of up to 75% with respect to the total number of operations needed on three benchmark dictionaries, while yielding an accuracy comparable to the optimal. Experiments are also done to show the benefits of the CBS over the BS when the search is done on the trie. The results also demonstrate a marked improvement (more than 91%) for large dictionaries.

Algorithms↗
PubMed2005

[Self-organizing neural networks for automatic detection and classification of contrast (media) enhancement of lesions in dynamic MR-mammography].

PURPOSE: Investigation and statistical evaluation of "Self-Organizing Maps," a special type of neural networks in the field of artificial intelligence, classifying contrast enhancing lesions in dynamic MR-mammography. MATERIAL AND METHODS: 176 investigations with proven histology after core biopsy or operation were randomly divided into two groups. Several Self-Organizing Maps were trained by investigations of the first group to detect and classify contrast enhancing lesions in dynamic MR-mammography. Each single pixel's signal/time curve of all patients within the second group was analyzed by the Self-Organizing Maps. The likelihood of malignancy was visualized by color overlays on the MR-images. At last assessment of contrast-enhancing lesions by each different network was rated visually and evaluated statistically. RESULTS: A well balanced neural network achieved a sensitivity of 90.5 % and a specificity of 72.2 % in predicting malignancy of 88 enhancing lesions. Detailed analysis of false-positive results revealed that every second fibroadenoma showed a "typical malignant" signal/time curve without any chance to differentiate between fibroadenomas and malignant tissue regarding contrast enhancement alone; but this special group of lesions was represented by a well-defined area of the Self-Organizing Map. DISCUSSION: Self-Organizing Maps are capable of classifying a dynamic signal/time curve as "typical benign" or "typical malignant." Therefore, they can be used as second opinion. In view of the now known localization of fibroadenomas enhancing like malignant tumors at the Self-Organizing Map, these lesions could be passed to further analysis by additional post-processing elements (e.g., based on T2-weighted series or morphology analysis) in the future.

Algorithms↗