Investigation on prediction formulae for calculating erythrocyte sedimentation rate

Nishisako, Hisashi; Kunishima, Hiroyuki; Shimizu, Gohji; Teruya, Yoko; Yokokawa, Masatoshi; Hirose, Masahiro; Sakai, Tsubasa; Yamasaki, Yukitaka; Tsuchida, Tomoya; Naitou, Yoshiyuki; Ogihara, Takashi; Torikai, Keito; Nakagawa, T.; Matsuda, Takahide

doi:10.1002/jgf2.1

Cited by 3 publications

(2 citation statements)

References 4 publications

(9 reference statements)

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…Shteinshnaider et al demonstrated that ESR values at 60 min can be predicted by ESR values at 30 min by using simple linear regression 9 . Nishisako et al applied a formula for calculating a normal maximum range of ESR with only age information of patients 10 . However, this formula was only applicable to Asian patients aged more than 65 years.…”

Section: Introductionmentioning

confidence: 99%

Neural network ensemble model for prediction of erythrocyte sedimentation rate (ESR) using partial least squares regression

Lee

Hong

Song

et al. 2022

Sci Rep

View full text Add to dashboard Cite

The erythrocyte sedimentation rate (ESR) is a non-specific blood test for determining inflammatory conditions. However, the long measurement time (60 min) to obtain ESR is an obstacle for a prompt evaluation. In this study, to reduce the measurement time of ESR, deep neural networks (DNNs) were applied to the sedimentation tendency of blood samples. DNNs using multilayer perceptron (MLP), long short-term memory (LSTM), and gated recurrent unit (GRU) were assessed and compared to determine a suitable length of time for the input sequence. To avoid overfitting, a stacking ensemble learning was adopted, which combines multiple models by using a meta model. Four meta models were compared: mean, median, least absolute shrinkage and selection operator, and partial least squares regression (PLSR) schemes. From the empirical results, LSTM and GRU models have better prediction than MLP over sequence lengths of 5 to 20 min. The decrease in $$\overline{\mathrm{MAPE} }$$ MAPE ¯ and $$\overline{\mathrm{RMSE} }$$ RMSE ¯ of GRU and LSTM was attenuated after a sequence length of 15 min, so the input sequence length is determined as 15 min. In terms of the meta model, the statistical comparison suggests that GRU combined with PLSR (GRU–PLSR) is the best case. Then, the GRU–PLSR was tested for prediction of ESR data obtained from periodontitis patients to check its applicability to a specific disease. The Bland–Altman plot shows acceptable agreement between measured and predicted ESR values. Based on the results, the GRU–PLSR can predict ESR with improved performance within 15 min and has potential applicability to ESR data with inflammatory and non-inflammatory conditions.

show abstract

Section: Introductionmentioning

confidence: 99%

Neural network ensemble model for prediction of erythrocyte sedimentation rate (ESR) using partial least squares regression

Lee

Hong

Song

et al. 2022

Sci Rep

View full text Add to dashboard Cite

show abstract

“…Однако такие методы, как ультрацентрифугирование и ряд известных весовых методов определения скорости седиментационных процессов, направлены на исследование грубодисперсных систем, не обладающих большим разнообразием фракций [9]. Используемые на данный момент в медицине методы изначально рассматривают поведение отдельной фракции частиц в биологических жидкостях и не позволяют оценить поведение всей системы [10]. Изучение процесса фракционирования систем такого сложного состава и интерпретация полученных результатов пред-ставляют значительный интерес для биомедицинских исследований.…”

Section: Introductionunclassified

Исследование Фракционирования Молока Как Типичной Биологической Жидкости Методом Цифровой Голографической Интерферометрии

Кузьмина¹,

Андреева²,

Исмагилов³

et al. 2019

Журнал Технической Физики

View full text Add to dashboard Cite

We present the results of a study of milk as a complex biological fluid. The simultaneous occurrence of both direct and reverse sedimentation associated, respectively, with the protein and fat components of milk is demonstrated. Digital holographic interferometry enables the determination of the spatial and temporal changes in the refractive index of the suspension under study caused by fractionation processes with an accuracy of 10^–6, which exceeds the capabilities of other research methods. The results can be used to create a mathematical model of biological fluid fractionation processes and to develop physical models (phantoms) of such systems.

show abstract

A Study of Fractionation of Milk As a Typical Biological Fluid by Digital Holographic Interferometry

et al. 2018

View full text Add to dashboard Cite

Investigation on prediction formulae for calculating erythrocyte sedimentation rate

Cited by 3 publications

References 4 publications

Neural network ensemble model for prediction of erythrocyte sedimentation rate (ESR) using partial least squares regression

Neural network ensemble model for prediction of erythrocyte sedimentation rate (ESR) using partial least squares regression

Исследование Фракционирования Молока Как Типичной Биологической Жидкости Методом Цифровой Голографической Интерферометрии

A Study of Fractionation of Milk As a Typical Biological Fluid by Digital Holographic Interferometry

Contact Info

Product

Resources

About