Classification of factor deficiencies from coagulation assays using neural networks

Givens, Thomas B; Braun, Paul

doi:10.1016/s1386-5056(97)00065-8

Cited by 7 publications

(5 citation statements)

References 15 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In the present study, we used a digital dermoscopy analyzer and a suitable ANN to achieve high diagnostic accuracy (94%). In particular, neural networks have found many successful applications in medicine 20, 21, 22, 23, 24, 25. The flexibility of ANN models, which like humans learn from example, combined with the reliability of automatic digital image processing of the DBDermo‐Mips system makes the classification method adaptable to any other environmental/clinical conditions so that a given center/department can use and tune the ANN classifier most suitable not only for the type of lesion to be observed/diagnosed but also for its histopathologic standard.…”

Section: Discussionmentioning

confidence: 99%

“…ANNs are a large class of models developed in the cognitive sciences, the structure of which was inspired by that of the nervous system of living beings 20. Certain applications of ANNs in medicine have led to significant improvements in medical decision making 21, 22, 23, 24. In a preliminary study, we used a digital dermoscopy analyzer together with a neural network on 147 clinically atypical PSLs (90 nevi and 57 melanomas), to determine its discriminating power with respect to histologic diagnosis.…”

mentioning

confidence: 99%

See 1 more Smart Citation

Automated diagnosis of pigmented skin lesions

Rubegni

Cevenini

Burroni

et al. 2002

Intl Journal of Cancer

165

View full text Add to dashboard Cite

Since advanced melanoma remains practically incurable, early detection is an important step toward a reduction in mortality. High expectations are entertained for a technique known as dermoscopy or epiluminescence light microscopy; however, evaluation of pigmented skin lesions by this method is often extremely complex and subjective. To obviate the problem of qualitative interpretation, methods based on mathematical analysis of pigmented skin lesions, such as digital dermoscopy analysis, have been developed. In the present study, we used a digital dermoscopy analyzer (DBDermo-Mips system) to evaluate a series of 588 excised, clinically atypical, flat pigmented skin lesions (371 benign, 217 malignant). The analyzer evaluated 48 parameters grouped into 4 categories (geometries, colors, textures and islands of color), which were used to train an artificial neural network. To evaluate the diagnostic performance of the neural network and to check it during the training process, we used the error area over the receiver operating characteristic curve. The discriminating power of the digital dermoscopy analyzer plus artificial neural network was compared with histologic diagnosis. A feature selection procedure indicated that as few as 13 of the variables were sufficient to discriminate the 2 groups of lesions, and this also ensured high generalization power. The artificial neural network designed with these variables enabled a diagnostic accuracy of about 94%. In conclusion, the good diagnostic performance and high speed in reading and analyzing lesions (real time) of our method constitute an important step in the direction of automated diagnosis of pigmented skin lesions.

show abstract

Section: Discussionmentioning

confidence: 99%

mentioning

confidence: 99%

Automated diagnosis of pigmented skin lesions

Rubegni

Cevenini

Burroni

et al. 2002

Intl Journal of Cancer

165

View full text Add to dashboard Cite

show abstract

“…Preliminary studies performed in house by the manufacturer of the MDA ® demonstrated that it was possible to predict the presence of heparin or factor deficiencies and provide an estimate of fibrinogen concentration from both PT and APTT assays (Givens et al ., 1996; Givens & Braun , 1997). Subsequently, independent investigators have confirmed the utility of waveform analysis in a number of different clinical settings.…”

Section: The Clinical Utility Of Clot Waveform Analysismentioning

confidence: 99%

Waveform analysis of clotting test optical profiles in the diagnosis and management of disseminated intravascular coagulation (DIC)

Toh

Giles

2002

Clinical &Amp; Laboratory Haematology

View full text Add to dashboard Cite

Transmittance waveform charts the changes in light transmittance on standard coagulation assays, such as the prothrombin time (PT) and activated partial thromboplastin time (APTT). Analysis and characterization of these data on photo-optical coagulation analysers provides additional qualitative and quantitative information to that obtained using the clotting time alone. The most thoroughly evaluated clinical application is that of the biphasic APTT waveform with disseminated intravascular coagulation (DIC). The degree of waveform abnormality correlates directly with the severity of haemostatic dysfunction and allows for both the prediction and monitoring from non-overt to overt DIC. As its performance is simple and rapid, this provides the means for targeting therapeutic intervention to an earlier stage of DIC. The recent identification that the mechanism underlying the biphasic waveform is a complex that exists in vivo between C reactive protein with very low density lipoprotein, provides potentially important insights into the molecular pathogenesis of DIC. Thus, in addition to the immediate clinical utility in diagnostic practice, it has important applications as a research tool. Preliminary experience in the application of this technology to the diagnosis and management of the haemophilias and the lupus anticoagulant syndrome has also provided evidence of the power and utility of waveform analysis in essentially simple clotting assays.

show abstract

“…Neural networks (NN) are a large class of models developed in the cognitive sciences, the structure of which was inspired by that of the nervous system of living beings. Certain applications of NN in medicine have led to significant improvement in medical decision making, [7][8][9][10] including pigmented skin lesions and skin cancer, [11][12][13][14][15][16] however, the fuzzy system was not addressed previously. Fuzzy logic is a form of multi-valued logic that deals with reasoning that is approximate rather than precise.…”

Section: Introductionmentioning

confidence: 99%

Skin Cancer Recognition by Using a Neuro-Fuzzy System

et al. 2011

View full text Add to dashboard Cite

Skin cancer is the most prevalent cancer in the light-skinned population and it is generally caused by exposure to ultraviolet light. Early detection of skin cancer has the potential to reduce mortality and morbidity. There are many diagnostic technologies and tests to diagnose skin cancer. However many of these tests are extremely complex and subjective and depend heavily on the experience of the clinician. To obviate these problems, image processing techniques, a neural network system (NN) and a fuzzy inference system were used in this study as promising modalities for detection of different types of skin cancer. The accuracy rate of the diagnosis of skin cancer by using the hierarchal neural network was 90.67% while using neuro-fuzzy system yielded a slightly higher rate of accuracy of 91.26% in diagnosis skin cancer type. The sensitivity of NN in diagnosing skin cancer was 95%, while the specificity was 88%. Skin cancer diagnosis by neuro-fuzzy system achieved sensitivity of 98% and a specificity of 89%.

show abstract

Classification of factor deficiencies from coagulation assays using neural networks

Cited by 7 publications

References 15 publications

Automated diagnosis of pigmented skin lesions

Automated diagnosis of pigmented skin lesions

Waveform analysis of clotting test optical profiles in the diagnosis and management of disseminated intravascular coagulation (DIC)

Skin Cancer Recognition by Using a Neuro-Fuzzy System

Contact Info

Product

Resources

About