Simultaneous determination of captopril and hydrochlorothiazide by time-resolved chemiluminescence with artificial neural network calibration

Yao, Hanchun; Sun, Min; Yang, Xiao-Feng; Zhang, Zhenzhong; Li, Hua

doi:10.1016/s2095-1779(11)70006-5

Cited by 12 publications

(6 citation statements)

References 29 publications

(41 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Many applications of ANN to analytical systems have been published, − including calibration-related problems in areas as diverse as fuels, , foodstuff, − pharmaceuticals, , and industrial products. , In the specific case of NIR applications, spectrometer manufacturers currently advertise ANN calibrations as simple, robust, and accurate . However, usually the average prediction error or the ratio of performance to deviation (RPD) − for a test set of samples have been used to assess the accuracy in the case of nonlinear calibrations.…”

mentioning

confidence: 99%

Sensitivity, Prediction Uncertainty, and Detection Limit for Artificial Neural Network Calibrations

Allegrini

Olivieri

2016

Anal. Chem.

View full text Add to dashboard Cite

With the proliferation of multivariate calibration methods based on artificial neural networks, expressions for the estimation of figures of merit such as sensitivity, prediction uncertainty, and detection limit are urgently needed. This would bring nonlinear multivariate calibration methodologies to the same status as the linear counterparts in terms of comparability. Currently only the average prediction error or the ratio of performance to deviation for a test sample set is employed to characterize and promote neural network calibrations. It is clear that additional information is required. We report for the first time expressions that easily allow one to compute three relevant figures: (1) the sensitivity, which turns out to be sample-dependent, as expected, (2) the prediction uncertainty, and (3) the detection limit. The approach resembles that employed for linear multivariate calibration, i.e., partial least-squares regression, specifically adapted to neural network calibration scenarios. As usual, both simulated and real (near-infrared) spectral data sets serve to illustrate the proposal.

show abstract

mentioning

confidence: 99%

Sensitivity, Prediction Uncertainty, and Detection Limit for Artificial Neural Network Calibrations

Allegrini

Olivieri

2016

Anal. Chem.

View full text Add to dashboard Cite

show abstract

“…An attractive alternative to cope with non-linearity in multivariate calibration has been the use of artificial neural networks (ANN), which are nowadays frequently reported in the literature. − One of the most popular type of ANN for multivariate calibration is the so-called multilayer perceptron (MLP) . In particular, recent applications of MLP calibration to near infrared (NIR) and fluorescence data sets can be mentioned in areas as diverse as industrial products, pharmaceuticals, , foodstuff, , fuels, , etc. However, when calibrating with an MLP, usually, only the average root-mean-square error for a set of test samples is reported, with no insight into the usual analytical figures of merit (AFOMs).…”

Section: Introductionmentioning

confidence: 99%

Sensitivity for Multivariate Calibration Based on Multilayer Perceptron Artificial Neural Networks

Chiappini

Allegrini²,

Goicoechea

et al. 2020

Anal. Chem.

View full text Add to dashboard Cite

The use of machine learning for multivariate spectroscopic data analysis in applications related to process monitoring has become very popular since non-linearities in the relationship between signal and predicted variables are commonly observed. In this regard, the use of artificial neural networks (ANN) to develop calibration models has demonstrated to be more appropriate and flexible than classical multivariate linear methods. The most frequently reported type of ANN is the so-called multilayer perceptron (MLP). Nevertheless, the latter models still lack a complete statistical characterization in terms of prediction uncertainty, which is an advantage of the parametric counterparts. In the field of analytical calibration, developments regarding the estimation of prediction errors would derive in the calculation of other analytical figures of merit (AFOMs), such as sensitivity, analytical sensitivity, and limits of detection and quantitation. In this work, equations to estimate the sensitivity in MLP-based calibrations were deduced and are here reported for the first time. The reliability of the derived sensitivity parameter was assessed through a set of simulated and experimental data. The results were also applied to a previously reported MLP fluorescence calibration methodology for the biopharmaceutical industry, yielding a value of sensitivity ca. 30 times larger than for the univariate reference method.

show abstract

“…Captopril, 1-(2S)-3-mercapto-2-methyl propionyl- l -proline ( Fig. 1 ), is an angiotensin converting enzyme (ACE) inhibitor, which reduces peripheral resistance and lowers blood pressure [1] , [2] . It is widely utilized in the treatment of hypertension and some types of congestive heart failure [3] , [4] .…”

Section: Introductionmentioning

confidence: 99%

A chemiluminescence reagent free method for the determination of captopril in medicine and urine samples by using trivalent silver

Huang

et al. 2017

Journal of Pharmaceutical Analysis

View full text Add to dashboard Cite

A novel flow-injection chemiluminescence (FI-CL) method free of CL reagent was developed for the determination of captopril based on its enhancing effect on the CL derived from diperiodatoargentate(III)-sulfuric acid system. Compared with the conventional CL system, the CL system based on trivalent silver was characterized of good selectivity for the absence of CL reagent. The CL mechanism was discussed through CL spectra and UV–vis absorption spectra. The conditions of the FI-CL system were investigated and optimized. Under the optimal conditions, the relative CL intensity was linear with the captopril concentration in the range of 0.3–15.0 μg/mL. The detection limit for captopril was 0.05 μg/mL, and the relative standard deviation (n=11) was 2.0% for 5.0 μg/mL captopril. The proposed method was applied to the analysis of captopril in tablet and human urine with the recoveries of 83.1%–112.5%, and the relative standard deviations of 0.5%–4.4%. The results obtained by the proposed method agreed well with those obtained from HPLC method. The proposed method is fast, convenient, and cost-effective for the determination of captopril in medicine and biological samples.

show abstract

Simultaneous determination of captopril and hydrochlorothiazide by time-resolved chemiluminescence with artificial neural network calibration

Cited by 12 publications

References 29 publications

Sensitivity, Prediction Uncertainty, and Detection Limit for Artificial Neural Network Calibrations

Sensitivity, Prediction Uncertainty, and Detection Limit for Artificial Neural Network Calibrations

Sensitivity for Multivariate Calibration Based on Multilayer Perceptron Artificial Neural Networks

A chemiluminescence reagent free method for the determination of captopril in medicine and urine samples by using trivalent silver

Contact Info

Product

Resources

About