Development and comparison of machine learning models for in-vitro drug permeation prediction from microneedle patch.

The field of machine learning (ML) is advancing to a larger extent and finding its applications across numerous fields. ML has the potential to optimize the development process of microneedle patch by predicting the drug release pattern prior to its fabrication and production. The early predictions could not only assist the in-vitro and in-vivo experimentation of drug release but also conserve materials, reduce cost, and save time. In this work, we have used a dataset gleaned from the literature to train and evaluate different ML models, such as stacking regressor, artificial neural network (ANN) model, and voting regressor model. In this study, models were developed to improve prediction accuracy of the in-vitro drug release amount from the hydrogel-type microneedle patch and the in-vitro drug permeation amount through the micropores created by solid microneedles on the skin. We compared the performance of these models using various metrics, including R-squared score (R2 score), root mean squared error (RMSE), and mean absolute error (MAE). Voting regressor model performed better with drug permeation percentage as an outcome feature having RMSE value of 3.24. In comparison, stacking regressor have a RMSE value of 16.54, and ANN model has shown a RMSE value of 14. The value of permeation amount calculated from the predicted percentage is found to be more accurate with RMSE of 654.94 than direct amount prediction, having a RMSE of 669.69. All our models have performed far better than the previously developed model before this research, which had a RMSE of 4447.23. We then optimized voting regressor model's hyperparameter and cross validated its performance. Furthermore, it was deployed in a webapp using Flask framework, showing a way to develop an application to allow other users to easily predict drug permeation amount from the microneedle patch at a particular time period. This project demonstrates the potential of ML to facilitate the development of microneedle patch and other drug delivery systems.

Machine Learning-Enabled NIR Spectroscopy. Part 3: Hyperparameter by Design (HyD) Based ANN-MLP Optimization, Model Generalizability, and Model Transferability.

Data variations, library changes, and poorly tuned hyperparameters can cause failures in data-driven modelling. In such scenarios, model drift, a gradual shift in model performance, can lead to inaccurate predictions. Monitoring and mitigating drift are vital to maintain model effectiveness. USFDA and ICH regulate pharmaceutical variation with scientific risk-based approaches. In this study, the hyperparameter optimization for the Artificial Neural Network Multilayer Perceptron (ANN-MLP) was investigated using open-source data. The design of experiments (DoE) approach in combination with target drift prediction and statistical process control (SPC) was employed to achieve this objective. First, pre-screening and optimization DoEs were conducted on lab-scale data, serving as internal validation data, to identify the design space and control space. The regression performance metrics were carefully monitored to ensure the right set of hyperparameters was selected, optimizing the modelling time and storage requirements. Before extending the analysis to external validation data, a drift analysis on the target variable was performed. This aimed to determine if the external data fell within the studied range or required retraining of the model. Although a drift was observed, the external data remained well within the range of the internal validation data. Subsequently, trend analysis and process monitoring for the mean absolute error of the active content were conducted. The combined use of DoE, drift analysis, and SPC enabled trend analysis, ensuring that both current and external validation data met acceptance criteria. Out-of-specification and process control limits were determined, providing valuable insights into the model's performance and overall reliability. This comprehensive approach allowed for robust hyperparameter optimization and effective management of model lifecycle, crucial in achieving accurate and dependable predictions in various real-world applications.

Machine Learning-Enabled NIR Spectroscopy. Part 2: Workflow for Selecting a Subset of Samples from Publicly Accessible Data.

An increasingly large dataset of pharmaceutics disciplines is frequently challenging to comprehend. Since machine learning needs high-quality data sets, the open-source dataset can be a place to start. This work presents a systematic method to choose representative subsamples from the existing research, along with an extensive set of quality measures and a visualization strategy. The preceding article (Muthudoss et al.. in AAPS PharmSciTech 23, 2022) describes a workflow for leveraging near infrared (NIR) spectroscopy to obtain reliable and robust data on pharmaceutical samples. This study describes the systematic and structured procedure for selecting subsamples from the historical data. We offer a wide range of in-depth quality measures, diagnostic tools, and visualization techniques. A real-world, well-researched NIR dataset was employed to demonstrate this approach. This open-source tablet dataset ( http://www.models.life.ku.dk/Tablets ) consists of different doses in milligrams, different shapes, and sizes of dosage forms, slots in tablets, three different manufacturing scales (lab, pilot, production), coating differences (coated vs uncoated), etc. This sample is appropriate; that is, the model was developed on one scale (in this research, the lab scale), and it can be great to investigate how well the top models are transferable when tested on new data like pilot-scale or production (full) scale. A literature review indicated that the PLS regression models outperform artificial neural network-multilayer perceptron (ANN-MLP). This work demonstrates the selection of appropriate hyperparameters and their impact on ANN-MLP model performance. The hyperparameter tuning approaches and performance with available references are discussed for the data under investigation. Model extension from lab-scale to pilot-scale/production scale is demonstrated. HIGHLIGHTS: • We present a comprehensive quality metrics and visualization strategy in selecting subsamples from the existing studies • A comprehensive assessment and workflow are demonstrated using historical real-world near-infrared (NIR) data sets • Selection of appropriate hyperparameters and their impact on artificial neural network-multilayer perceptron (ANN-MLP) model performance • The choice of hyperparameter tuning approaches and performance with available references are discussed for the data under investigation • Model extension from lab-scale to pilot-scale successfully demonstrated.

Machine Learning-Enabled NIR Spectroscopy in Assessing Powder Blend Uniformity: Clear-Up Disparities and Biases Induced by Physical Artefacts.

NIR spectroscopy is a non-destructive characterization tool for the blend uniformity (BU) assessment. However, NIR spectra of powder blends often contain overlapping physical and chemical information of the samples. Deconvoluting the information related to chemical properties from that associated with the physical effects is one of the major objectives of this work. We achieve this aim in two ways. Firstly, we identified various sources of variability that might affect the BU results. Secondly, we leverage the machine learning-based sophisticated data analytics processes. To accomplish the aforementioned objectives, calibration samples of amlodipine as an active pharmaceutical ingredient (API) with the concentrations ranging between 67 and 133% w/w (dose ~ 3.6% w/w), in powder blends containing excipients, were prepared using a gravimetric approach and assessed using NIR spectroscopic analysis, followed by HPLC measurements. The bias in NIR results was investigated by employing data quality metrics (DQM) and bias-variance decomposition (BVD). To overcome the bias, the clustered regression (non-parametric and linear) was applied. We assessed the model's performance by employing the hold-out and k-fold internal cross-validation (CV). NIR-based blend homogeneity with low mean absolute error and an interval estimates of 0.674 (mean) ± 0.218 (standard deviation) w/w was established. Additionally, bootstrapping-based CV was leveraged as part of the NIR method lifecycle management that demonstrated the mean absolute error (MAE) of BU ± 3.5% w/w and BU ± 1.5% w/w for model generalizability and model transferability, respectively. A workflow integrating machine learning to NIR spectral analysis was established and implemented. Impact of various data learning approaches on NIR spectral data.

A new Febuxostat-Telmisartan Drug-Drug Cocrystal for Gout-Hypertension Combination Therapy.

Drug-drug cocrystalllization is a novel mechanism for effective pharmacological combination therapy. In this work, we have demonstrated the preparation of a drug-drug cocrystal of a hypertension drug (Telmisartan; TEL) with a hyperuricemia drug (Febuxostat; FEB) in 1:1 molar ratio using a solvent evaporation method for the first time. Generally, a multi-component system may yield either a eutectic, salt, and/or a cocrystal. This study adopted a methodical orthogonal framework to analyze the final solid form. A single crystal X-ray structural investigation revealed the formation of a heterosynthon with carboxylic and benzimidazole groups of FEB and TEL, respectively, in the triclinic P-1 space group. ΔpKa of the heterosynthon is ∼1.5, hence, based on the empirical rules, a salt-cocrystal continuum is hypothesized. Further, attenuated total reflectance Fourier transform infrared (ATR-FTIR), and Raman spectroscopy were employed to corroborate the hydrogen bond formation in the heterosynthon (-N---H-O-), which confirmed the propensity for cocrystal formation. An accelerated stability study and an in vitro biorelevant dissolution study of the cocrystal were performed, which demonstrated that it is physiochemically stable, but it resulted in a slower dissolution rate when compared with plain drugs.

Topologically directed confocal Raman imaging (TD-CRI): Advanced Raman imaging towards compositional and micromeritic profiling of a commercial tablet components.

Particle size distribution (PSD), spatial location and particle cluster size of ingredients, polymorphism, compositional distribution of a pharmaceutical product are few of the most important attributes in establishing the drug release-controlling microstructural and solid state properties that would be used to (re)design or reproduce similar products. There are numerous solid-state techniques available for PSD analysis. Laser diffraction (LD) is mostly used to study PSD of raw materials. However, a constraint of LD is the interference between the active pharmaceutical ingredients (API) and excipients, where it is very challenging to measure API size in a tablet. X-ray powder diffraction (XRPD) is widely employed in establishing the polymorphism of API and excipients. This research examined a commercial osmotic tablet in terms of extracting solid state properties of API and functional excipient by Raman Imaging. Establishing repeatability, reproducibility, and sample representativeness when the samples are non-uniform and inhomogeneous necessitates multiple measurements. In such scenarios, when employing imaging-based techniques, it can be time-consuming and tedious. Advanced statistical methodologies are used to overcome these disadvantages and expedite the characterization process. Overall, this study demonstrates that Raman imaging can be employed as a non-invasive and effective offline method for assessing the solid-state characteristics of API and functional excipients in complex dosage forms like osmotic tablets.

Quantitative Microscopy: Particle Size/Shape Characterization, Addressing Common Errors Using 'Analytics Continuum' Approach.

Particle size/shape characterization of active pharmaceutical ingredient (API) is integral to successful product development. It is more of a correlative property than a decision-making measure. Though microscopy is the only technique that provides a direct measure of particle properties, it is neglected for reasons like non-repeatability and non-reproducibility which is often attributed to a) fundamental error, b) segregation error, c) human error, d) sample randomness, e) sample representativeness etc. Using the "Sucrose" as model sample, we propose "analytics continuum" approach that integrates optical microscope PSD measurements complimented by NIR spectroscopy-based trending analysis as a prescreening tool to demonstrate sample randomness and representativeness. Furthermore, plethora of statistical tests are utilized to infer population statistics. Subsequently, an attribute-based control chart and bootstrap-based confidence interval was developed to monitor product performance. A flowchart to serve as an elementary guideline is developed, which is then extended to handle more complex situations involving API crystallized from two different solvent systems. The results show that the developed methodology can be utilized as a quantitative procedure to assess the suitability of API/excipients from different batches or from alternate vendors and can significantly help in understanding the differences between material even on a minor scale.