Blood hyperviscosity identification with reflective spectroscopy of tongue tip based on principal component analysis combining artificial neural network
Abstract Background With spectral methods, noninvasive determination of blood hyperviscosity in vivo is very potential and meaningful in clinical diagnosis. In this study, 67 male subjects (41 health, and 26 hyperviscosity according to blood sample analysis results) participate. Methods Reflectance...
Main Authors: | , , , , , |
---|---|
Format: | Article |
Language: | English |
Published: |
BMC
2018-05-01
|
Series: | BioMedical Engineering OnLine |
Subjects: | |
Online Access: | http://link.springer.com/article/10.1186/s12938-018-0495-3 |
id |
doaj-518f0b7e9f1e46b6a8031a69af512d70 |
---|---|
record_format |
Article |
spelling |
doaj-518f0b7e9f1e46b6a8031a69af512d702020-11-24T20:58:33ZengBMCBioMedical Engineering OnLine1475-925X2018-05-0117111210.1186/s12938-018-0495-3Blood hyperviscosity identification with reflective spectroscopy of tongue tip based on principal component analysis combining artificial neural networkMing Liu0Jing Zhao1XiaoZuo Lu2Gang Li3Taixia Wu4LiFu Zhang5Institute of Biomedical Engineering, Chinese Academy of Medical Sciences and Peking Union Medical CollegeInstitute of Chinese Medicine, Tianjin University of Traditional Chinese MedicineInstitute of Chinese Medicine, Tianjin University of Traditional Chinese MedicineState Key Laboratory of Precision Measurement Technology and Instruments, Tianjin UniversityInstitute of Remote Sensing and Digital Earth, Chinese Academy of SciencesInstitute of Remote Sensing and Digital Earth, Chinese Academy of SciencesAbstract Background With spectral methods, noninvasive determination of blood hyperviscosity in vivo is very potential and meaningful in clinical diagnosis. In this study, 67 male subjects (41 health, and 26 hyperviscosity according to blood sample analysis results) participate. Methods Reflectance spectra of subjects’ tongue tips is measured, and a classification method bases on principal component analysis combined with artificial neural network model is built to identify hyperviscosity. Hold-out and Leave-one-out methods are used to avoid significant bias and lessen overfitting problem, which are widely accepted in the model validation. Results To measure the performance of the classification, sensitivity, specificity, accuracy and F-measure are calculated, respectively. The accuracies with 100 times Hold-out method and 67 times Leave-one-out method are 88.05% and 97.01%, respectively. Conclusions Experimental results indicate that the built classification model has certain practical value and proves the feasibility of using spectroscopy to identify hyperviscosity by noninvasive determination.http://link.springer.com/article/10.1186/s12938-018-0495-3Reflective spectroscopyNoninvasiveBlood hyperviscosity diagnosisPrincipal component analysisArtificial neural network |
collection |
DOAJ |
language |
English |
format |
Article |
sources |
DOAJ |
author |
Ming Liu Jing Zhao XiaoZuo Lu Gang Li Taixia Wu LiFu Zhang |
spellingShingle |
Ming Liu Jing Zhao XiaoZuo Lu Gang Li Taixia Wu LiFu Zhang Blood hyperviscosity identification with reflective spectroscopy of tongue tip based on principal component analysis combining artificial neural network BioMedical Engineering OnLine Reflective spectroscopy Noninvasive Blood hyperviscosity diagnosis Principal component analysis Artificial neural network |
author_facet |
Ming Liu Jing Zhao XiaoZuo Lu Gang Li Taixia Wu LiFu Zhang |
author_sort |
Ming Liu |
title |
Blood hyperviscosity identification with reflective spectroscopy of tongue tip based on principal component analysis combining artificial neural network |
title_short |
Blood hyperviscosity identification with reflective spectroscopy of tongue tip based on principal component analysis combining artificial neural network |
title_full |
Blood hyperviscosity identification with reflective spectroscopy of tongue tip based on principal component analysis combining artificial neural network |
title_fullStr |
Blood hyperviscosity identification with reflective spectroscopy of tongue tip based on principal component analysis combining artificial neural network |
title_full_unstemmed |
Blood hyperviscosity identification with reflective spectroscopy of tongue tip based on principal component analysis combining artificial neural network |
title_sort |
blood hyperviscosity identification with reflective spectroscopy of tongue tip based on principal component analysis combining artificial neural network |
publisher |
BMC |
series |
BioMedical Engineering OnLine |
issn |
1475-925X |
publishDate |
2018-05-01 |
description |
Abstract Background With spectral methods, noninvasive determination of blood hyperviscosity in vivo is very potential and meaningful in clinical diagnosis. In this study, 67 male subjects (41 health, and 26 hyperviscosity according to blood sample analysis results) participate. Methods Reflectance spectra of subjects’ tongue tips is measured, and a classification method bases on principal component analysis combined with artificial neural network model is built to identify hyperviscosity. Hold-out and Leave-one-out methods are used to avoid significant bias and lessen overfitting problem, which are widely accepted in the model validation. Results To measure the performance of the classification, sensitivity, specificity, accuracy and F-measure are calculated, respectively. The accuracies with 100 times Hold-out method and 67 times Leave-one-out method are 88.05% and 97.01%, respectively. Conclusions Experimental results indicate that the built classification model has certain practical value and proves the feasibility of using spectroscopy to identify hyperviscosity by noninvasive determination. |
topic |
Reflective spectroscopy Noninvasive Blood hyperviscosity diagnosis Principal component analysis Artificial neural network |
url |
http://link.springer.com/article/10.1186/s12938-018-0495-3 |
work_keys_str_mv |
AT mingliu bloodhyperviscosityidentificationwithreflectivespectroscopyoftonguetipbasedonprincipalcomponentanalysiscombiningartificialneuralnetwork AT jingzhao bloodhyperviscosityidentificationwithreflectivespectroscopyoftonguetipbasedonprincipalcomponentanalysiscombiningartificialneuralnetwork AT xiaozuolu bloodhyperviscosityidentificationwithreflectivespectroscopyoftonguetipbasedonprincipalcomponentanalysiscombiningartificialneuralnetwork AT gangli bloodhyperviscosityidentificationwithreflectivespectroscopyoftonguetipbasedonprincipalcomponentanalysiscombiningartificialneuralnetwork AT taixiawu bloodhyperviscosityidentificationwithreflectivespectroscopyoftonguetipbasedonprincipalcomponentanalysiscombiningartificialneuralnetwork AT lifuzhang bloodhyperviscosityidentificationwithreflectivespectroscopyoftonguetipbasedonprincipalcomponentanalysiscombiningartificialneuralnetwork |
_version_ |
1716785569055375360 |