Assessment of Robustness for a Near-Infrared Concentration Model for Real-Time Release Testing in a Continuous Manufacturing Process

Colon, Yleana Marie; Vargas, Jenny M.; Sánchez, Eric; Navarro, Gilfredo; Romañach, Rodolfo J.

doi:10.1007/s12247-016-9265-6

Cited by 13 publications

(6 citation statements)

References 51 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Moreover, within the broader context of the increasing efforts toward continuous manufacturing, robustness of a model can be also associated with obtaining good predictions for a prolonged period of time, i.e., increasing up-time of a model. 37 Although this idea of prolonging model applicability extends the concept of robustness to include the time dimension, it does not touch upon the definition of robustness at the time of model creation, and thus, it is not further discussed here. The remainder of this discussion focuses on exploring the trade-offs between accuracy and robustness and quantifying the robustness metric.…”

Section: Validation Metricsmentioning

confidence: 99%

“…Model accuracy is typically put forward in terms of goodness of fit of the prediction. As previously mentioned, the use of RMSEP is commonly utilized in this regard. , Alternative/complementary metrics for accuracy, such as root-mean-square error of calibration, or cross validation and/or bias are conceivable. These measures are sufficient for understanding the average errors in a data set; however they should not be interpreted as an estimate for the uncertainty of a specific prediction at a new input .…”

Section: Latent Variable Regressionmentioning

confidence: 99%

“…Note that in both the EMA and the FDA guidelines rejecting outliers is addressed in the context of another metric, specificity, and is not further discussed here. Moreover, within the broader context of the increasing efforts toward continuous manufacturing, robustness of a model can be also associated with obtaining good predictions for a prolonged period of time, i.e., increasing up-time of a model . Although this idea of prolonging model applicability extends the concept of robustness to include the time dimension, it does not touch upon the definition of robustness at the time of model creation, and thus, it is not further discussed here.…”

Section: Latent Variable Regressionmentioning

confidence: 99%

See 2 more Smart Citations

An Optimization Approach Coupling Preprocessing with Model Regression for Enhanced Chemometrics

Kappatou

Odgers

García‐Muñoz

et al. 2023

Ind. Eng. Chem. Res.

View full text Add to dashboard Cite

Chemometric methods are broadly used in the chemical and biochemical sectors. Typically, derivation of a regression model follows data preprocessing in a sequential manner. Yet, preprocessing can significantly influence the regression model and eventually its predictive ability. In this work, we investigate the coupling of preprocessing and model parameter estimation by incorporating them simultaneously in an optimization step. Common model selection techniques rely almost exclusively on the performance of some accuracy metric, yet having a quantitative metric for model robustness can prolong model up-time. Our approach is applied to optimize for model accuracy and robustness. This requires the introduction of a novel mathematical definition for robustness. We test our method in a simulated set up and with industrial case studies from multivariate calibration. The results highlight the importance of both accuracy and robustness properties and illustrate the potential of the proposed optimization approach toward automating the generation of efficient chemometric models.

show abstract

Section: Validation Metricsmentioning

confidence: 99%

Section: Latent Variable Regressionmentioning

confidence: 99%

Section: Latent Variable Regressionmentioning

confidence: 99%

See 1 more Smart Citation

An Optimization Approach Coupling Preprocessing with Model Regression for Enhanced Chemometrics

Kappatou

Odgers

García‐Muñoz

et al. 2023

Ind. Eng. Chem. Res.

View full text Add to dashboard Cite

show abstract

“…4 The spectra vary correspondingly to the change of the drug concentration in the tablets. 5 However, the NIR spectra are affected by both, the chemical composition and physical properties of pharmaceutical materials which alter the light scattering. 6–9 The common physical properties of pharmaceutical materials include particle size and bulk density of API and excipients, the hardness and thickness of the final tablets, etc.…”

Section: Introductionmentioning

confidence: 99%

Fractal and Polarization Properties of Light Scattering Using Microcrystalline Pharmaceutical Aggregates

et al. 2020

Self Cite

View full text Add to dashboard Cite

Fractal and polarization analysis of diffusively scattered light is applied to determine the complex relationship between fractal dimension of structural morphology and concentration of chemically active ingredients in two pharmaceutical mixture systems including a series of binary mixtures of acetaminophen in lactose and three multicomponent blends with a proprietary active ingredient. A robust approach is proposed to identify and filter out multiple- and single-scattering components of scattering indicatrix. The fractal dimension extracted from scattering field reveals complex structural details of the sample, showing strong dependence on low-dose drug concentration in the blend. Low-angle diffraction shows optical “halo” patterns near the angle of specular reflection caused by light refraction in microcrystalline aggregates. Angular measurements of diffuse reflection demonstrate noticeable dependence of Brewster's angle on drug concentration. It is shown that the acetaminophen microcrystals produce scattered light depolarization due to their optical birefringence. The light scattering measurement protocol developed for diffusively scattered light by microcrystalline pharmaceutical compositions provides a novel approach for the pattern recognition, analysis and classification of materials with a low concentration of active chemical ingredients.

show abstract

“…While the regulators have moved to accept PAT, to overcome the industry inertia to rapid on-line process analysis, PAT process monitoring techniques must demonstrate a suitable measurement accuracy and reliability that can produce quality assurance concomitant with industry requirements. A prime industrial driver is to demonstrate the capability and effectiveness of on-line techniques for assuring quality, with real time release (RTR) of the product being the sought after operating policy [1]. A balance arises between the introduction of novel and powerful measurement methods and the requirement to ensure consistent, repeatable with a (statistical) confidence in process outputs that are comparable to more traditional validated procedures.…”

Section: Introductionmentioning

confidence: 99%

Opportunities for Process Control and Quality Assurance Using Online NIR Analysis to a Continuous Wet Granulation Tableting Line

et al. 2018

View full text Add to dashboard Cite

This paper investigates the application of on-line near infra-red measurements as a means to measure blend uniformity in a continuous tableting line. Underlying all the monitoring and control methods is the ability to measure key tablet properties on-line at a rate suitable for control purposes. The use of NIR to determine any deviations in blend uniformity is demonstrated by interpreting the relevant spectral signature allowing quantitative information to be acquired for process monitoring and quality assurance. In addition to demonstrating the functionality of the NIR probe, the practical issues arising in the application are discussed. The composition of the blend was measured using an NIR probe over a range of concentrations and the results were calculated comparing sub unit dose scale of scrutiny of small populations. This was compared with predicted product quality for whole tablets over the whole production period. This technique has demonstrated how data collected online can be used to successfully predict the quality of the whole production run for the purposes of real time product quality assurance.

show abstract

Assessment of Robustness for a Near-Infrared Concentration Model for Real-Time Release Testing in a Continuous Manufacturing Process

Cited by 13 publications

References 51 publications

An Optimization Approach Coupling Preprocessing with Model Regression for Enhanced Chemometrics

An Optimization Approach Coupling Preprocessing with Model Regression for Enhanced Chemometrics

Fractal and Polarization Properties of Light Scattering Using Microcrystalline Pharmaceutical Aggregates

Opportunities for Process Control and Quality Assurance Using Online NIR Analysis to a Continuous Wet Granulation Tableting Line

Contact Info

Product

Resources

About