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 1,765 records · Page 98Linked to original sources
PubMed2003

A genetic algorithm based nearest neighbor classification to breast cancer diagnosis.

This paper presents an application of a hybrid approach (the genetic algorithms and the k-nearest neighbour) proposed by Ishbuchi to Wisconsin breast cancer data. For the diagnosis of breast cancer, the determination of the presence of benign/malignant breast tumors represents a very complex problem (even for an experienced cytologist). Therefore the automatic classification of benign and malignant symptoms is highly desirable as a valuable aid to assist oncologists in the decision making of the diagnosis of breast cancer. In this paper, the genetic algorithm based k-nearest neighbour method for classification of benign and malignant breast tumors is presented. The genetic-algorithm (GA) is used for finding a compact reference set by selecting a small number of reference patterns from a large number of training patterns in nearest neighbor classification. The GA simultaneously performs feature selection and pattern selection and prunes unnecessary features. The goal is to maximize the classification performance of the reference set and minimize the number of selected patterns and features. Results are also compared with a fuzzy-genetic approach where each reference patten represents a fuzzy if-then rule with a circular-cone-type membership function.

Algorithms↗
PubMed1999

Comparison of prognostic significance of nodal staging between old (4th edition) and new (5th edition) UICC TNM classification for gastric carcinoma. International Union Against Cancer.

The description of nodal staging for gastric cancer was changed in the new fifth edition of the International Union Against Cancer (UICC) TNM classification from the anatomic sites of metastatic lymph nodes to the number of metastatic lymph nodes, as pN1 is metastasis in 1 to 6 lymph nodes, pN2 is in 7 to 15 lymph nodes, and pN3 is in 16 or more lymph nodes. The purpose of this study was to investigate the prognostic significance of the new staging system based on the number of metastatic lymph nodes compared to the old staging system by anatomic site. From 1987 to 1994 a total of 2108 patients who underwent potentially curative resections with D2 or D3 lymph node dissection and with 15 or more lymph nodes retrieved were studied retrospectively. Lymph node metastases were found in 1018 patients (48.3%). A mean of 37.9 lymph nodes were retrieved per patient, and a mean of 7.2 lymph nodes were invaded by tumor cells. We found that the new nodal staging based on the number of metastatic lymph nodes closely correlated with the depth of cancer invasion and with the old nodal staging based on the anatomic site of the metastatic nodes, with statistical significance. The 5-year survival rates after gastrectomy decreased significantly by increasing the extent of the pN classification in both nodal staging methods. In a subgroup analysis of survivals between the old and new nodal staging, the new classification showed more homogeneous survival at the same stage than the old one. With a multivariate analysis of prognostic factors, including the old and new nodal staging, the depth of invasion and the new nodal stage were the most significant prognostic factors, followed by the old nodal stage. Our data suggested that the new nodal staging based on the number of metastatic lymph nodes is not only a reliable and objective method for nodal classification, but it is also a significant prognostic determinant for gastric cancer that can be used in practice.

Female↗
PubMed1999

[Evaluation of the "new" TNM classification of head and neck tumors in 3247 patients].

UNLABELLED: The 5th edition of the TNM classification entails a number of changes concerning head and neck tumors. The division of stage IV tumors into three subcategories marks a significant expansion of the stage grouping procedure. METHODS: In a retrospective study the clinical course of 3247 patients with head and neck carcinomas were comparatively evaluated according to the 4th and 5th editions of the new TNM classification. In particular it was the aim of the study to test the prognostic relevance of the subdivision of stage IV especially in mucosal cancer. RESULTS: In classifying the primary tumor the most extensive changes were noted for supraglottic and salivary gland tumors. On the basis of the 4th edition of the TNM classification the following recurrence-free 5-year survival rates for 3033 cases of mucosal cancer were calculated: stage I 91,0%, stage II 78.6%, stage III 61.4%, stage IV 31.0%. The calculations based on the 5th edition yielded: stage I 91.0%, stage II 77.2%, stage III 61.2%, stage IVA 32.4%, stage IVB 25.3%, stage IVC 3.6%. CONCLUSIONS: The adequacy of the revised stage classification in establishing a prognostic hierarchy was confirmed. However, a significant prognostic distinction between N2- (stage IVA) and N3-metastasis (stage IVB) could not be found.

Adult↗
PubMed2003

[The roentgenmorphologic aspects of symptomatic calcifications in patients with calcifying tendinitis of the shoulder: determination of intra- and interobserver variabilities of Gärtner's classification].

AIM OF THE STUDY: The roentgenologic morphology of symptomatic calcified deposits of the rotator cuff can be classified according Gärtner. This classification influences therapeutic procedures and prognosis of clinical outcome in these patients. In the present study intraoberserver-reproducibility and interobserver-reliability of Gärtner's classification were tested. METHODS: Plane radiographs of 100 patients with calcifications of the supraspinatus tendon were classified according the criteria of Gärtner by 6 independent observers twice within 4 months. Intraoberserver-reproducibility and interobserver-reliability were calculated by means of Cohen's kappa-index. RESULTS: kappa-values of intraoberserver-reproducibility had a mean of 0.4208 (SD 0.1299), kappa-values of interobserver-reliability were 0.490 for the first and 0.474 for the second classification. CONCLUSIONS: Determination of intraoberserver-reproducibility gave insufficient to satisfactory results, interobserver-reliability was sufficient. The clinical use of Gärtner's classification to plan therapeutic procedures or to determine clinical prognosis in patients with calcifying tendinitis can be recommended only with limitations.

Adult↗
PubMed2002

[Supracondylar humerus fracture in childhood--an efficacy study. Results of a multicenter study by the Pediatric Traumatology Section of the German Society of Trauma Surgery--I: Epidemiology, effectiveness evaluation and classification].

In this retrospective study of the pediatric trauma group of German trauma society, issued to investigate the state of the art treatment of the supracondylar fracture of the humerus, 13 clinics took part. In this first part of our study we tested the epidemiology and effectivity of therapeutic interventions based on the classification of v. Laer. 886 fractures were included with an average patients age of 5.8 years (+/- 2.9). Causes of trauma was in 45% playing, followed by school/kindergarden and sports injuries. Fractures were initially classified according to v. Laer and showed following displacement: 35.4% Type I, 21.9% Type II, 18.1% Type III and 24.6% Type IV. 10 of the 886 cases (1.1%) were open fractures. Damages to nerves were described in 45 patients (5.1%) and only 7 (0.7%) had primary vessel lesions. 476 patients were treated by reduction of fragments, 72% using a closed technical approach and 28% using an open approach. 6% underwent a second resposition-maneuver, which was mainly observed after crossed Kirschner-wire in type-III-and-IV-fractures. Therapy was changed in 5.1% mostly of the cases were initially closed reduced and then fixed with a collar and cuff sling. 540 patients were seen at follow-up (61%). 81.1% of these patients showed symmetrical axis compared to the uninjured arm. A varus-deformity was noted in 11.7%, a valgus-deformity in 7.2%. Analysis of effectivity showed that the primarily used classification was not sufficient for prediction of the outcome after reposition and retention. Therefore the classification was modified based on 4 groups: Type I undisplaced, Type II displacement in one plane, Type III displacement in two planes and Type IV displacement in three spatial planes. Using this classification we could found that in group II 25% of reduction an 7% of retentions were ineffective. For group III and IV we found that > 20% of the retention proofed to be ineffective.

Adolescent↗
PubMed2004

[Renal cell carcinoma. Comparative analysis of the prognostic significance of the WHO-classification and the Störkel's prognostic score].

Due to the increasing epidemiological importance of renal cell carcinoma (RCC) in the past, several studies have been undertaken to evaluate a variety of parameters in view of their aptitude for reliably predicting individual prognosis. Currently, staging according to the TNM classification and pathohistological nuclear grading of the tumor is most widely used for determining prognosis. In the latest edition of the TNM system, a subdivision of the stage pT1 into the stages pT1a and pT1b has been established. Analyzing a total of 129 patients with a postoperative follow-up period of 60 months after radical nephrectomy, we investigated the TNM classification in regard to its prognostic potential with emphasis on the new subdivision of the stage pT1. Furthermore, the results were compared to Störkel's prognostic score, which was first described in 1990 as a useful tool for predicting individual prognosis in patients with RCC. In conclusion, our study demonstrates that subdivision of the stage pT1 into the stages pT1a and pT1b did not result in any improvement concerning the aptitude of the TNM classification to predict individual prognosis. In comparison, Störkel's prognostic score has statistically proven to be superior to the TNM classification in regard to its prognostic potential. According to our experience, determination of Störkel's prognostic score can be easily performed by the pathologist without much expense in the course of daily routine diagnostic procedures. Therefore, we strongly recommend Störkel's prognostic score as the parameter of choice to reliably predict individual prognosis of patients suffering from RCC.

Adult↗
PubMed1999

[Classification of vesico-urethral dysfunction].

Classification systems of bladder dysfunction are mainly based on functional and urodynamic characteristics. Under functional aspects classification relates to disturbances of storage and emptying function and the behaviour of its components, the bladder and the bladder outlet. The International Continence Society established a committee for the standardisation of terminology of lower urinary tract function and recommended worldwide accepted standards of terminology. These standards are the basis for any classification system and should be used to facilitate comparison of results. In addition, classification of bladder dysfunction should be completed by a clinical investigation to define the risks of underlying disorder.

Diagnosis, Differential↗
PubMed2005

Clinical classification of patellofemoral pain syndrome: guidelines for non-operative treatment.

The patellofemoral pain syndrome (PFPS) remains a challenging musculoskeletal entity encountered by clinicians. Reviewing the literature, conflicting data seem to exist regarding the effect of non-operative treatment in PFPS patients. A possible explanation may be lack of a clear classification system of patients with PFPS. It is our opinion that the term PFPS still is a 'wastebasket', which probably comprises several different entities. Therefore, it seems important to subdivide this broad group of patients into different categories with a specific rehabilitation approach. In this study, we introduce a classification system, which reflects a consensus reached by the European Rehabilitation Panel. This classification system should help the clinicians to identify the cause(s) of patellofemoral pain, and consequently help to select the most appropriate non-operative treatment. The authors are aware that no rehabilitation protocol will work for all PFPS patients, since the underlying mosaic of pathophysiology and tissue-healing responses are unique. Therefore, the aim of this study with a classification system was to guide the clinician through clinical examination in order to develop a non-operative treatment protocol, specific for each individual with PFPS.

Bone Malalignment↗
PubMed2003

Dermal and inhalation acute toxic class methods: test procedures and biometric evaluations for the Globally Harmonized Classification System.

The acute toxic class (ATC) methods were developed for determining LD(50)/LC(50) estimates of chemical substances with significantly fewer animals than needed when applying conventional LD(50)/LC(50) tests. The ATC methods are sequential stepwise procedures with fixed starting doses/concentrations and a maximum of six animals used per dose/concentration. The numbers of dead/moribund animals determine whether further testing is necessary or whether the test is terminated. In recent years we have developed classification procedures for the oral, dermal and inhalation routes of administration by using biometric methods. The biometric approach assumes a probit model for the mortality probability of a single animal and assigns the chemical to that toxicity class for which the best concordance is achieved between the statistically expected and the observed numbers of dead/moribund animals at the various steps of the test procedure. In previous publications we have demonstrated the validity of the biometric ATC methods on the basis of data obtained for the oral ATC method in two-animal ring studies with 15 participants from six countries. Although the test procedures and biometric evaluations for the dermal and inhalation ATC methods have already been published, there was a need for an adaptation of the classification schemes to the starting doses/concentrations of the Globally Harmonized Classification System (GHS) recently adopted by the Organization for Economic Co-operation and Development (OECD). Here we present the biometric evaluation of the dermal and inhalation ATC methods for the starting doses/concentrations of the GHS and of some other international classification systems still in use. We have developed new test procedures and decision rules for the dermal and inhalation ATC methods, which require significantly fewer animals to provide predictions of toxicity classes, that are equally good or even better than those achieved by using the conventional LD(50)/LC(50) methods. In order to cope with rather narrow dose/concentration classes of the GHS we have, as in our previous publications, combined the outcome of all results that can be obtained during testing for the allocation to one of the defined toxicity classes of the GHS. Our results strongly recommend the deletion of the dermal LD(50) and the inhalation LC(50) test as regulatory tests and the adoption of the dermal and inhalation ATC methods as internationally accepted alternatives.

Administration, Cutaneous↗
PubMed1998

Heterogeneity in Klippel-Feil syndrome: a new classification.

BACKGROUND: Klippel-Feil syndrome (KFS) is characterised by congenital vertebral fusion of the cervical spine and a wide spectrum of associated anomalies. KFS has often been considered a sporadic syndrome. However, since the publication of the original KFS classification early this century, a number of KFS families have indicated heterogeneity complicated by a broad range of variable expression. OBJECTIVE: The two major objectives of this study were (1) to identify differences and similarities in the postnatal appearance, morphology, position and inheritance of vertebral fusions within and between KFS families and (2) to establish a new KFS classification focussed on KFS aetiology. MATERIALS AND METHODS: Vertebral fusions were assessed via spinal radiography. Chromosomal karyotypes were performed using routine cytogenetics. RESULTS: The medical histories of three KFS families are presented. The postnatal time, position and appearance of vertebral fusions, associated anomalies and mode of inheritance were different for the three KFS families. Four classes of KFS are described in a comprehensive classification table that allays much of the uncertainty arising from KFS heterogeneity and variable expression. CONCLUSION: We have described four different KFS classes (KF1-4) within a comprehensive classification that addresses KFS genetic heterogeneity. The position of vertebral fusions in the cervical spine and their incidence within affected families are delineating features of KFS.

Adult↗
PubMed2003

The classification of lymphomas: a new beginning or the end of an era?

The World Health Organisation Classification of Tumours of the Haematopoietic and Lymphoid Tissues has recently been published. This is the latest in a long line of classifications of haematological malignancies and will be the international standard. It is now possible to achieve high levels of diagnostic accuracy for the main types of lymphoma. However, many of the entities encompass a wide spectrum of clinical outcomes and this approach to classification may be insufficiently precise for the future needs of haematological oncology. Rapid progress in targeted therapies may require further developments in tumour classification based on pathogenic features rather than arbitrary morphological criteria.

Humans↗
PubMedDate not supplied

Staging of pelvic endometriosis based on MRI findings versus laparoscopic classification according to the American Fertility Society.

BACKGROUND: Preoperative staging of pelvic endometriosis helps the gynecologist plan therapy and offers a prognosis to patients. We compared a staging system of pelvic endometriosis based on magnetic resonance imaging (MRI) findings with the American Fertility Society (AFS) laparoscopic classification. METHODS: Forty-four consecutive females with clinically suspected endometriosis underwent MRI examination to demonstrate the presence of endometriomas and pelvic implants. Laparoscopy was performed within 2 weeks. An MRI score was developed to classify endometriosis into four classes comparable to those of AFS laparoscopic staging. Concordance between MRI and laparoscopic classification was evaluated with kappa statistics. RESULTS: Laparoscopy confirmed 60 of 61 endometriomas detected by MRI. Implants were discovered in 20 of 44 patients with MRI and in 23 of 44 with laparoscopy. MRI detected 50 endometrial implants of 65 detected by laparoscopy (76.9%). With regard to endometriosis staging, we obtained a concordance between MRI and AFS classification in 42 of 44 patients (kappa = 0.913). CONCLUSION: Although MRI has limitations such as suboptimal depiction of small implants and adhesions, this technique is very useful to guide laparoscopy. Moreover, the optimal concordance (95%) between our proposed MRI staging and the AFS laparoscopic classification demonstrated a new advantage of MRI in preoperative staging of endometriosis.

Adult↗
PubMed1996

Observer variation in the radiographic classification of fractures of the neck of the femur using Garden's system.

By means of Kappa statistics, we calculated the inter- and intra-observer variation in the classification of fractures of the neck of the femur according to Garden's system. Radiographs of 96 consecutive patients were assessed independently by six observers who agreed on classification for only 14 fractures (15%). The level of agreement was poor for the overall classification (Kappa = 0.39). When reducing Garden's system into non-displaced (Stage I and II) and displaced fractures (Stage III and IV) the level of agreement became acceptable (Kappa = 0.68). However, problems remain in distinguishing Stage II and Stage III fractures, and further improvements in the classification system are necessary.

Femoral Neck Fractures↗
PubMed1998

Evaluation of simplified Frykman and AO classifications of fractures of the distal radius. Assessment of interobserver and intraobserver agreement.

In order to evaluate interobserver and intraobserver agreement of the Frykman and AO classifications and their variations between assessors with different levels of experience, three hand specialists, a fellow and two senior residents classified radiographs of 200 fractures of the distal radius in anteroposterior and lateral views. Reproducibility was assessed by the use of the proportion of agreement and kappa coefficient between pairs of observers. The Frykman classification showed moderate interobserver reproducibility (kappa = 0.43) and good intraobserver reproducibility (kappa = 0.61). The experience of the reviewers did not significantly affect either of these. The AO system showed regular interobserver reproducibility (kappa = 0.37) and moderate intraobserver reproducibility (kappa = 0.57). The younger group obtained higher intraobserver agreement than the senior. Possible causes for the low reproducibility of both classifications are discussed together with a review of the literature. We do not recommend the Frykman or AO classifications for clinical application because of their questionable reproducibility.

Adult↗
PubMedDate not supplied

Classification and treatment of prominent mandibular angle.

In Oriental culture, the contour of the mandibular angle is important for feminine facial shape because a woman who has a wide and square face is thought to have had an unhappy life. A prominent mandibular angle, which does not coincide with the natural look, produces a characteristic quadrangle, coarse, and muscular appearance. So Oriental women who have a prominent mandibular angle want to have an ovoid, reduced, and slender face by aesthetic mandibular angle resection. Many satisfactory corrections of a prominent mandibular angle by various operative techniques have been reported. But reasonable morphologic classification and treatment were not reported. So we classified prominent mandibular angles into four groups by morphology and operated on the patients according to their classification with different modalities: no square shape but only a reduced gonial angle in the profile view-class I, mild form; severe mandibular angle protrusion with lateral protrusion-class II, moderate form; a definite square-shaped angle (class II) with masseteric hypertrophy-class III, severe form; and combined prominent mandibular angle and chin deformity-class IV, complex form. We use angle ostectomy through the intraoral route alone or with an additional external stab incision for class I. An external stab incision to set up the reciprocating saw is sometimes helpful in class I cases because there is no lateral protrusion of the angle. For class II cases, we use conventional intraoral angle ostectomy only or angle splitting ostectomy with contouring. For class III cases, we use angle splitting ostectomy and contouring with partial masseteric myectomy. In class IV, we use angle ostectomy and additional genioplasty. During 7 years, we have performed 46 cases of mandibular angle resection. Of the mandibular angle resection cases, 19 were class I, 15 were class II, 9 were class III, and 3 were class IV. A total of 42 patients were satisfied with the postoperative results. For reasonable and satisfactory final results, classification according to the mandibular angle shape and suitable treatment according to the classification are essential.

Adolescent↗
PubMed2004

Hydrology or floristics? Mapping and classification of wetlands in Victoria, Australia, and implications for conservation planning.

A national approach to the conservation of biodiversity in Australia's freshwater ecosystems is a high priority. This requires a consistent and comprehensive system for the classification, inventory, and assessment of wetland ecosystems. This paper, using the State of Victoria as a case study, compares two classification systems that are commonly utilized to delineate and map wetlands--one based on hydrology (Victorian Wetland Database [VWD]) and one based on indigenous vegetation types and other natural features (Ecological Vegetation Classes [EVC]). We evaluated the extent of EVC mapping of wetlands relative to the VWD classification system using a number of datasets within a geographical information system. There were significant differences in the coverage of extant EVCs across bioregions, different-sized wetlands, and VWD wetland types. Resultant depletion levels were markedly different when examined using the two systems, with depletion levels, and therefore perceived conservation status, of EVCs being significantly higher. Although there is little doubt that many wetland ecosystems in Victoria are in fact threatened, the extent of this threat cannot accurately be determined by relying on the EVC mapping as it currently stands. The study highlighted the significant impact wetland classification methods have in determining the conservation status of freshwater ecosystems.

Biodiversity↗
PubMed2006

Emergence of indigenous vegetation classifications through integration of traditional ecological knowledge and remote sensing analyses.

Traditional ecological knowledge (TEK) can play an important role in the understanding of ecological systems. Although TEK has complemented scientific and managerial programs in a variety of contexts, its formal incorporation into remote sensing exercises has to date been limited. Here, we show that the vegetation classifications of the Ache, an indigenous hunter-gatherer tribe of the Mbaracayu Forest Reserve in Paraguay, are reflected in a supervised classification of satellite imagery of the reserve. Accuracy of classification was toward the low end of the range of published values, but was reasonable given the difficult nature of separating forest classes from satellite images. Comparison of the resultant map with a more traditionally elaborated vegetation map highlights differences between the two approaches and the gain in information obtained by considering TEK classifications. We suggest that integration of TEK and remote sensing may provide alternative insights into the ecology of vegetation communities and land cover, particularly in remote and densely forested areas where ecological field research is often limited by roads and/or trail systems.

Conservation of Natural Resources↗
PubMed2006

Comparing the use of indigenous knowledge with classification and ordination techniques for assessing the species composition and structure of vegetation in a tropical forest.

Identification of groups that are similar in their floristic composition and structure (habitat types) is essential for conservation and forest managers to allocate high priority areas and to designate areas for reserves, refuges, and other protected areas. In this study, the use of indigenous knowledge for the identification of habitat types in the field was compared against an ecological characterization of habitat types, including their species composition obtained by using classification and ordination techniques for a tropical landscape mosaic in a rural Mayan area of Quintana Roo, Mexico. Plant diversity data calculated from 141 sampled sites chosen randomly on a vegetation class's thematic map obtained by multispectral satellite image classification were used for this propose. Results indicated high similarity in the categorization of vegetation types between the Mayan classification and those obtained by cluster and detrended correspondence analysis. This suggests that indigenous knowledge has a practical use and can be comparable to that obtained by using science-based methods. Finally, identification and mapping of vegetation classes (habitat types) using satellite image classification allowed us to discriminate significantly different species compositions, in such a way that they can provide a useful mechanism for interpolating diversity values over the entire landscape.

Biodiversity↗