Search PubMed⌕ Search

SEARCH · Search PubMed

Results for “CLASSIFICATION”

Search indexed PubMed citations on genomics, clinical trials, systematic reviews and public health. Explore titles, authors and supplied subject terms, then open the PubMed record.

Quote a phrase for an exact phrase match. Source license links do not imply unrestricted reuse.

At least 1,153 records · Page 64Linked to original sources

Growing of a Fuzzy Recurrent Artificial Neural Network (FRANN) for pattern classification.

This paper describes a method for growing a recurrent neural network of fuzzy threshold units for the classification of feature vectors. Fuzzy networks seem natural for performing classification, since classification is concerned with set membership and objects generally belonging to sets of various degrees. A fuzzy unit in the architecture proposed here determines the degree to which the input vector lies in the fuzzy set associated with the fuzzy unit. This is in contrast to perceptrons that determine the correlation between input vector and a weighting vector. The resulting membership value, in the case of the fuzzy unit, is compared with a threshold, which is interpreted as a membership value. Training of a fuzzy unit is based on an algorithm for linear inequalities similar to Ho-Kashyap recording. These fuzzy threshold units are fully connected in a recurrent network. The network grows as it is trained. The advantages of the network and its training method are: (1) Allowing the network to grow to the required size which is generally much smaller than the size of the network which would be obtained otherwise, implying better generalization, smaller storage requirements and fewer calculations during classification; (2) The training time is extremely short; (3) Recurrent networks such as this one are generally readily implemented in hardware; (4) Classification accuracy obtained on several standard data sets is better than that obtained by the majority of other standard methods; and (5) The use of fuzzy logic is very intuitive since class membership is generally fuzzy.

Algorithms↗

WHO perspectives on international classification.

The classification of mental disorders improved greatly in the last decade of the 20th century and now provides a reliable operational tool. Both the ICD and DSM classifications have greatly facilitated practice, teaching and research by providing better delineation of 'syndromes' (i.e. clustering commonly seen symptoms together). The absence of aetiological information linked to brain physiology that could serve as the basis of independent definitional variables has limited understanding of mental illness and has been a stumbling block to the development of better classifications. The use of a universal classification for differing cultures has also raised concerns about a lack of sensitivity to local diversity, especially as human behaviour is not always context free. Given these limitations and the expectations of scientific advances in the field of genetics, neurobiology and cultural studies, we should be able to build better classifications based on an international consensus informed by evidence-based research.

Evidence-Based Medicine↗

Multiple classification and receiver operating characteristic (ROC) analysis.

The receiver operating characteristic (ROC) curve was applied to observer performances in a multiple-alternative decision task. It was shown that the probability of correct classification, a performance criterion often maximized in multiple-classification procedures, corresponds to the area under an appropriately constructed ROC curve. Degrees of confidence in the observer's judgment of 0, 1, ..., 10 were used for both classification and ROC rating. To demonstrate the validity of the method, 1,190 photofluorograms were examined by experienced staff radiologists to identify four cardiovascular conditions distinguishable on the basis of images of structural elements of the contours of the heart and great vessels. The classification matrices for three radiologists who achieved high, medium, and low performance ratings in this experiment are reported. The ROC curves are symmetric, with their points located around the off-diagonal. Differences between the overall probability of correct classification and the ROC curve index calculated from the same evaluator's data were very small, 0.004 to 0.011.

Cardiovascular Diseases↗

The Surgical Nosology In Primary-care Settings (SNIPS): a simple bridging classification for the interface between primary and specialist care.

BACKGROUND: The interface between primary care and specialist medical services is an important domain for health services research and policy. Of particular concern is optimising specialist services and the organisation of the specialist workforce to meet the needs and demands for specialist care, particularly those generated by referral from primary care. However, differences in the disease classification and reporting of the work of primary and specialist surgical sectors hamper such research. This paper describes the development of a bridging classification for use in the study of potential surgical problems in primary care settings, and for classifying referrals to surgical specialties. METHODS: A three stage process was undertaken, which involved: (1) defining the categories of surgical disorders from a specialist perspective that were relevant to the specialist-primary care interface; (2) classifying the 'terms' in the International Classification of Primary Care Version 2-Plus (ICPC-2 Plus) to the surgical categories; and (3) using referral data from 303,000 patient encounters in the BEACH study of general practice activity in Australia to define a core set of surgical conditions. Inclusion of terms was based on the probability of specialist referral of patients with such problems, and specialists' perception that they constitute part of normal surgical practice. RESULTS: A four-level hierarchy was developed, containing 8, 27 and 79 categories in the first, second and third levels, respectively. These categories classified 2050 ICPC-2 Plus terms that constituted the fourth level, and which covered the spectrum of problems that were managed in primary care and referred to surgical specialists. CONCLUSION: Our method of classifying terms from a primary care classification system to categories delineated by specialists should be applicable to research addressing the interface between primary and specialist care. By describing the process and putting the bridging classification system in the public domain, we invite comment and application in other settings where similar problems might be faced.

Australia↗

A nonlinear multi-omics data integration and classification model based on pathway self-attention and graph convolutional networks.

The abundance of omics data has significantly advanced the development of multi-omics data integration techniques. Non-linear embedding approaches for data integration have gradually become the mainstream in multi-omics research, as these approaches can substantially improve cancer analysis by enhancing the quality of the embeddings. However, current multi-omics data integration methods are typically confined to omics measurements, neglecting domain-specific prior knowledge encompassing biological pathways. In this study, we proposed a multi-omics integrated classification model, PathTransGCN, based on pathway self-attention and graph convolutional networks (GCN). The model integrated biological pathway information into multi-omics data analysis with the aim of enhancing the accuracy of cancer classification. Multi-omics data for breast cancer (BRCA), non-small cell lung cancer (NSCLC), and low-grade glioma (LGG) were obtained from The Cancer Genome Atlas (TCGA) and UCSC Xena databases. These data included gene mutations, DNA methylation, copy number variations, and gene expression, and were used to assess the model's generalizability across different cancers. First, PathTransGCN employed a pathway self-attention module to learn latent representations of samples across different pathways, thereby obtaining multi-omics integration vectors. Concurrently, a patient similarity network (PSN) was constructed using the similarity network fusion (SNF) approach. Second, the integrated vectors and the PSN were jointly fed into a GCN for end-to-end training, enabling precise classification of cancer subtypes. Through multi-omics data analysis of the BRCA dataset, PathTransGCN outperformed several popular algorithms (such as MoGCN and DeePathNet) in the five-class classification of cancer subtypes, achieving an accuracy rate of 87.6% and an F1 score of 86.4%. Moreover, the model demonstrated robust generalization capabilities across both NSCLC and LGG datasets, while effectively identifying key disease-associated biomarkers at the pathway level. Experimental results demonstrate that PathTransGCN exhibits outstanding performance in integrating omics data and delivering interpretable classification outcomes, presenting significant potential for clinical applications.

Humans↗

The International Classification for Nursing Practice: a progress report.

This paper will review and report progress on the development of the International Classification for Nursing Practice. This project, begun in 1990 by the International Council of Nurses, aims to develop a standardised vocabulary and classification of nursing phenomena (nursing diagnoses), nursing interventions, and nursing outcomes which can be used in both electronic and paper records to describe and compare nursing practice across clinical settings. An Alpha Version of the Classification of Nursing Phenomena and Nursing Interventions was released for further development and field testing in 1996 and an outline for a Classification of Nursing Outcomes in 1997. Nurses around the world, and other classification experts, have been invited to participate in the development of the Beta Version which it is hoped will be ready for release in 1999.

Classification↗

Using the GRAIL language for classification management.

This paper describes a novel approach in classification management where a formal model of medical semantics is being used for manipulations on existing classification systems. The paper addresses the issue of semi-automatically making specialist classifications that are compatible with the source classification. The examples in this paper are from a limited domain. At the time of the presentation results will be shown of the present modelling work within the GALEN-In-Use project. The model will then contain several thousands of medical procedures from four different classification centres.

Classification↗

[VCT classification (valve, cusp, tributary) and venous endoscopy].

The V.C.T. classification (valve, cusp, tributary) results from a visual interpretation of endoscopic images of acquired valvular lesions in the deep and superficial veins. In 1991, we published a classification of saphenous back flow based in endoscopic views, but the rich French language used is difficult for our foreign colleagues to use. In 1992, S. Hoshino published highly simplified endoscopic results which only distinguish three types of valves, but which have the advantage of allowing quite useful illustrations. We thus propose in 1997 an illustrated and schematic classification. This V.C.T. classification in English is based on our results in 1990, the three types proposed in 1992 by Hoshino, and new images obtained since our former publication. We distinguished five types of valves scored 0 to 4 (type 0 being a normal valve) and four types of cusp scored 0 to 3. In addition, we found it was quite useful to note the number and position of border or wallside supravascular tributary veins. This classification is indispensable for standardized assessment of valve damage and to compare results after valve repair or transposition.

Angioscopy↗

Inter- and intra-observer variability of the Los Angeles classification: a reassessment.

BACKGROUND: Los Angeles classification is widely adopted for reporting endoscopic gastroesophageal reflux disease. We assessed the inter- and intra-observer variability of the Los Angeles classification. METHODS: Still images (n = 254) of the lower esophagus were presented to 9 gastroenterologists (6 experts and 3 trainees) and they were asked to report the images according to the Los Angeles classification. After 2 weeks the images were reordered and they were asked to report them again. Kappa statistic was calculated for intra- and inter-observer variability. RESULTS: The kappa for intra-observer agreement was 0.54 (attendings: 0.54; trainees; 0.55; P = not significant) and the inter-observer agreement was 0.22 (attendings: 0.20; trainees: 0.31; P = 0.027). The inter- and intra-observer kappa values in differentiating nonerosive from erosive cases were 0.22 (attendings: 0.21; trainees: 0.31, P = not significant) and 0.57 (attendings: 0.58; trainees: 0.55, P = not significant), respectively. CONCLUSION: According to our data, the Los Angeles classification has acceptable intra-observer variability, both for detecting presence or absence of erosions and for differentiating between different degrees of esophagitis, while its inter-observer performance seems to be less acceptable. It may be reasonable and timely to have another look at the Los Angeles classification to see whether its performance can be improved even further.

Diagnosis, Differential↗

Dermoscopic classification of atypical melanocytic nevi (Clark nevi).

OBJECTIVES: To create a dermoscopic classification of atypical melanocytic nevi (Clark nevi) and to investigate whether individuals bear a predominant type. DESIGN: Digital dermoscopic images of Clark nevi were classified according to structural features, ie, reticular, globular, or homogeneous patterns or combinations of these types. The nevi were also characterized as central hypopigmented or hyperpigmented, eccentric peripheral hypopigmented or hyperpigmented, or multifocal hypopigmented or hyperpigmented. SETTING: Two pigmented skin lesion clinics. PATIENTS: We examined 829 Clark nevi on 23 individuals. MAIN OUTCOME MEASURE: A reliable dermoscopic classification of Clark nevi and frequency of different dermoscopic types. RESULTS: Using the dermoscopic classification, the 829 Clark nevi were classified as follows: 221 (26.7%) as reticular, 167 (20.1%) as reticular-homogeneous, 148 (17.9%) as globular-homogeneous, 112 (13.5%) as reticular-globular, 89 (10.7%) as homogeneous, 84 (10.1%) as globular, and 8 (1.0%) as unclassified. Most individuals were prone to a predominant type of Clark nevus. Seven individuals (30%) showed a single type of Clark nevus in more than 50% of their nevi and 5 (22%) in more than 40% of their nevi. CONCLUSIONS: The proposed dermoscopic classification of Clark nevi is easily applicable and allows a detailed characterization of the different dermoscopic types of Clark nevi. Knowledge of these dermoscopic types should reduce unnecessary surgery for benign melanocytic lesions. Exact classification of the different types of Clark nevi is a necessary prerequisite for further clinical, dermoscopic, and histopathologic studies, which will give new insights in the biology of acquired melanocytic nevi.

Adolescent↗

Classification and staging of dementia of the Alzheimer type: a comparison between neural networks and linear discriminant analysis.

OBJECTIVE: To examine the utility of artificial neural networks (ANNs) for differentiating patients with Alzheimer disease from healthy control subjects and for staging the degree of dementia. DESIGN: Comparison of the classification abilities of ANNs with the statistical technique of linear discriminant analysis (LDA) using the results of 11 neuropsychological tests as predictors. PARTICIPANTS: Ninety-two patients with a diagnosis of probable Alzheimer disease (referred from a geriatric clinic) and 43 elderly control subjects (independently solicited). The patients met National Institute of Neurological and Communicative Disorders and Stroke-Alzheimer's Disease and Related Disorders Association criteria for probable dementia, with clinical ratings of dementia severity derived from the Cambridge Examination for Mental Disorders of the Elderly (CAMDEX). MAIN OUTCOME MEASURES: Classifications between and within groups were determined by using LDA and ANNs, and more detailed comparisons of the 2 methods were performed by using chi2 analyses and unweighted and weighted kappa statistics. RESULTS: Linear discriminant analysis correctly identified 71.9% of cases. Artificial neural networks, trained to classify the subjects using the same data, correctly classified 91.1% of the cases. Subsidiary analyses showed that although both techniques effectively discriminated between the control subjects and patients with dementia, the ANNs were more powerful in discriminating severity levels within the dementia population. The analyses for goodness of fit revealed that the ANN classification produced a better fit to the actual data. A comparison of the weighted proportion of agreement between the criterion and predictor variables also showed that the ANNs clearly outperformed LDA in classification accuracy for the full data set and patients-only data set. CONCLUSION: The results demonstrate the utility of ANNs for group classification of patients with Alzheimer disease and elderly controls and for staging dementia severity using neuropsychological data.

Aged↗

Classification of visual field abnormalities in the ocular hypertension treatment study.

OBJECTIVES: (1) To develop a classification system for visual field (VF) abnormalities, (2) to determine interreader and test-retest agreement, and (3) to determine the frequency of various VF defects in the Ocular Hypertension Treatment Study. METHODS: Follow-up VFs are performed every 6 months and are monitored for abnormality, indicated by a glaucoma hemifield test result or a corrected pattern SD outside the normal limits. As of January 1, 2002, 1636 patients had 2509 abnormal VFs. Three readers independently classified each hemifield using a classification system developed at the VF reading center. A subset (50%) of the abnormal VFs was reread to evaluate test-retest reader agreement. A mean deviation was calculated separately for the hemifields as an index to the severity of VF loss. MAIN OUTCOME MEASURES: A 97% interreader hemifield agreement. RESULTS: The average hemifield classification agreement (between any 2 of 3 readers) for 5018 hemifields was 97% and 88% for the 1266 abnormal VFs that were reread (agreement between the first and second classifications). Glaucomatous patterns of loss (partial arcuate, paracentral, and nasal step defects) composed the majority of VF defects. CONCLUSION: The Ocular Hypertension Treatment Study classification system has high reproducibility and provides a possible nomenclature for characterizing VF defects.

Antihypertensive Agents↗

Radiographic classification of temporal bone fractures: clinical predictability using a new system.

OBJECTIVE: To compare the traditional system of radiographic classification of temporal bone fractures (transverse vs longitudinal vs oblique) with a newer system (otic capsule violating vs otic capsule sparing) with respect to their ability to predict sequelae of temporal bone trauma. DESIGN: Retrospective chart and radiology review. SETTING: University trauma center and Department of Otolaryngology-Head and Neck Surgery. PATIENTS: Patients with temporal bone fractures. INTERVENTIONS: Clinic records and computed tomographic scans were reviewed to evaluate the clinical predictability of complications of temporal bone fractures. MAIN OUTCOME MEASURES: Complications of temporal bone fractures (ie, sensorineural hearing loss, conductive hearing loss, cerebrospinal fluid leakage, and facial nerve weakness) were recorded. Two classification schemes for temporal bone fractures were statistically analyzed and compared as to their ability to predict each complication. RESULTS: A total of 234 temporal bone fractures were identified; 30 cases met our strict criteria for inclusion. The traditional classification system of temporal bone fractures did not significantly predict temporal bone complications (P = .71). On the other hand, the otic capsule-based system did demonstrate statistically significant predictive ability (P < .001). Patients with otic capsule-violating fractures were 5 times more likely to have facial nerve injury, 25 times more likely to have sensorineural hearing loss, and 8 times more likely to have cerebrospinal fluid otorrhea than those with otic capsule-sparing fractures. CONCLUSIONS: The traditional radiographic classification system failed to demonstrate clinical predictability in our series. Furthermore, the newer system of classification (otic capsule sparing vs otic capsule violating) demonstrated statistically significant predictive ability for serious clinical outcomes associated with temporal bone fractures.

Accidental Falls↗

Anatomic classification system for surgical management of paraspinal tumors.

HYPOTHESIS: An anatomic classification system for paraspinal tumors that identifies complexity of regional anatomy, morbidity in complete or partial resection of anatomic structures, and potential complications may assist surgeons in preoperative planning. DESIGN: Application of a 6-level anatomic classification system for paraspinal tumors by retrospective medical record analysis. The classification system is defined by the following divisions of the vertebral column: I (C3-T3), II (T3-T10), III (T10-L2), IV (L1-L5, anterior to spine), V (L2-L5, lateral to spine), and VI (S1-S5). PATIENTS: All patients seen by us who underwent paraspinal tumor resection between 1997 and 2002. SETTING: Tertiary referral facility. MAIN OUTCOME MEASURES: Level-specific preoperative and surgical procedures and expected and unexpected vascular and neurologic morbidity caused by surgical intervention. RESULTS: Twenty-six patients met the inclusion criteria, and each of the levels (I through VI) of the classification system was represented by at least 2 patients. Expected morbidity that occurred because of surgical intervention included laryngeal paralysis in 1 patient with a level I tumor, femoral nerve palsy in 1 patient with a level V tumor, and neurogenic bladder and rectal dysfunction in 2 patients with level VI tumors. No unexpected neurologic deficit developed in any patient. Unanticipated intestinal ischemia and infarction occurred in 1 patient, who died after undergoing level IV surgery. Follow-up period ranged from 3 months to more than 5 years. CONCLUSION: Application of this 6-level anatomic classification system based on paraspinal tumor location may allow surgeons to anticipate specific surgical problems and to evaluate risks of resection and potential complications on the basis of regional anatomy.

Adult↗

Validation of clinical classification schemes for predicting stroke: results from the National Registry of Atrial Fibrillation.

CONTEXT: Patients who have atrial fibrillation (AF) have an increased risk of stroke, but their absolute rate of stroke depends on age and comorbid conditions. OBJECTIVE: To assess the predictive value of classification schemes that estimate stroke risk in patients with AF. DESIGN, SETTING, AND PATIENTS: Two existing classification schemes were combined into a new stroke-risk scheme, the CHADS( 2) index, and all 3 classification schemes were validated. The CHADS( 2) was formed by assigning 1 point each for the presence of congestive heart failure, hypertension, age 75 years or older, and diabetes mellitus and by assigning 2 points for history of stroke or transient ischemic attack. Data from peer review organizations representing 7 states were used to assemble a National Registry of AF (NRAF) consisting of 1733 Medicare beneficiaries aged 65 to 95 years who had nonrheumatic AF and were not prescribed warfarin at hospital discharge. MAIN OUTCOME MEASURE: Hospitalization for ischemic stroke, determined by Medicare claims data. RESULTS: During 2121 patient-years of follow-up, 94 patients were readmitted to the hospital for ischemic stroke (stroke rate, 4.4 per 100 patient-years). As indicated by a c statistic greater than 0.5, the 2 existing classification schemes predicted stroke better than chance: c of 0.68 (95% confidence interval [CI], 0.65-0.71) for the scheme developed by the Atrial Fibrillation Investigators (AFI) and c of 0.74 (95% CI, 0.71-0.76) for the Stroke Prevention in Atrial Fibrillation (SPAF) III scheme. However, with a c statistic of 0.82 (95% CI, 0.80-0.84), the CHADS( 2) index was the most accurate predictor of stroke. The stroke rate per 100 patient-years without antithrombotic therapy increased by a factor of 1.5 (95% CI, 1.3-1.7) for each 1-point increase in the CHADS( 2) score: 1.9 (95% CI, 1.2-3.0) for a score of 0; 2.8 (95% CI, 2.0-3.8) for 1; 4.0 (95% CI, 3.1-5.1) for 2; 5.9 (95% CI, 4.6-7.3) for 3; 8.5 (95% CI, 6.3-11.1) for 4; 12.5 (95% CI, 8.2-17.5) for 5; and 18.2 (95% CI, 10.5-27.4) for 6. CONCLUSION: The 2 existing classification schemes and especially a new stroke risk index, CHADS( 2), can quantify risk of stroke for patients who have AF and may aid in selection of antithrombotic therapy.

Aged↗

Pathologic classification of prostate carcinoma: the impact of margin status.

BACKGROUND: A proposed pathologic (pTNM) classification system for prostate carcinoma was analyzed for its impact on survival outcome in the prostate specific antigen (PSA) era. The impact of margin status on the survival outcome of patients with otherwise organ-confined disease (i.e., without extraprostatic extension or seminal vesicle involvement) was assessed. METHODS: Among 5467 patients, the original pathologic classification was T2 in 2094 patients; those with evidence of positive margins, extraprostatic extension, or seminal vesicle involvement were initially classified as having pT3 disease (2920 patients) or pT4 residual disease (211 patients). According to the proposed pTNM system, 1512 patients for whom margin status was considered independent of T classification were reclassified. RESULTS: After reclassification, 803 specimens had been down-classified to pT2, resulting in 2932 (54%) with pT2N0 organ-confined disease and a margin positivity rate of 27%; originally, only 38% of patients had been classified as pT2N0. When the old and new classifications were compared, 5-year progression free survival to the combined endpoint of clinical and/or PSA progression (< or = 0.2 ng/mL) was 86% versus 84% and 70% versus 67% for disease classified as pT2N0 and pT3N0, respectively. Multivariate analysis assessed the effect of margin status on 2334 pT2N0 patients (classified according to the proposed pTNM system) who did not receive adjuvant therapy; adjustments were made for Gleason grade, preoperative PSA, and DNA ploidy. In this analysis, the relative risk (with 95% confidence interval) associated with positive margins was 1.65 (1.24-2.18); this was significant for the combined endpoint of clinical/PSA progression. The 5-year survival, free of clinical/PSA progression, was 86% for those without versus 75% for those with positive margins. CONCLUSIONS: This analysis supports the adoption of the proposed pTNM system, which will allow for uniform reporting of pathologic data on prostate carcinoma. For patients with organ-confined disease, positive margins are associated with higher rates of PSA progression. Accordingly, patients should be stratified based on margin positivity in addition to pT classification.

Humans↗

Particle classification from light scattering with the scanning flow cytometer.

BACKGROUND: The differential light-scattering pattern, an indicatrix, provides the most complete characterization of the optical properties of a particle. Particle classification can be performed on the basis of particle parameters retrieved from the indicatrices. This classification extends the ability of flow cytometry in particle recognition. METHODS: The scanning flow cytometer (SFC) permits an acquisition of traces of light scattering signals, i.e., native SFC traces, from single particles. The acquired native SFC traces are transformed into indicatrices. The performance of the SFC in measurements of indicatrices has been demonstrated for the following particles: lymphocytes, erythrocytes, polystyrene particles, and milk-fat particles. RESULTS: The structure and profile of the indicatrix for each particle type have been found to be unique. Classification of polystyrene particles has been performed on the basis of the map formed by particle refractive index and size. The polystyrene particles were classified using this map into different size categories ranging from 1.4-7 microm, with a size deviation of 0.07 microm. CONCLUSIONS: The method based on analysis of native SFC traces shows better performance in particle classification than the method based on the particle refractive index and size map. The classification performance of the SFC will be useful, for example, for particle sorting and particle identification, and with additional fluorescent measurements may have applications in multiparameter particle-based immunoassay.

Animals↗

A modified classification for the maxillectomy defect.

BACKGROUND: At present no widely accepted classification exists for the maxillectomy defect suitable for surgeons and prosthodontists. An acceptable classification that describes the defect and indicates the likely functional and aesthetic outcome is needed. METHODS: The classification is made on the basis of the assessment of 45 consecutive maxillectomy patients derived prospectively from the database (September 1992) and retrospectively from 1989. RESULTS: The classification of the vertical component is as follows: Class 1, maxillectomy without an oro-antral fistula; Class 2, low maxillectomy (not including orbital floor or contents); Class 3, high maxillectomy (involving orbital contents); and Class 4, radical maxillectomy (includes orbital exenteration); Classes 2 to 4 are qualified by adding the letter a, b, or c. The horizontal or palatal component is classified as follows: a, unilateral alveolar maxillectomy; b, bilateral alveolar maxillectomy; and c, total alveolar maxillary resection. CONCLUSION: This practical classification attempts to relate the likely aesthetic and functional outcomes of a maxillectomy to the method of rehabilitation.

Adult↗