Work

Rapid detection and quantification of falsified Viagra using cloud-based portable NIR technology and machine learning

Year: 2025

Type: article

Abstract: The prevalence of falsified medications remains a global health challenge, intensified by globalization, internet accessibility, and the high profitability associated with low risks for this type of trafficking. This study explores the innovative integration of portable Near-Infrared (NIR) spectroscopy, with a cloud-based advanced data processing and management architecture, to not only rapidly detect falsified Viagra tablets but also to obtain their absolute sildenafil content. Utilizing data from both authentic and seized falsified samples, Principal Component Analysis (PCA) and Euclidean distance measurements demonstrate the ability of portable NIR devices to differentiate between authentic and falsified tablets. This type of model can be integrated into an online system and combined with a mobile application, thereby allowing for intelligible and nearly instantaneous results. Further, machine learning models were developed to calculate the sildenafil content in falsified tablets, showing excellent accuracy in comparison to a reference chromatographic based method. The results highlight the potential of portable NIR measurements streamlined with machine learning data treatment for field deployment, offering a rapid, non-destructive and reliable method to enhance the detection and analysis of falsified medications. This approach represents a significant advancement in ensuring medication quality and safety, providing a robust tool for regulatory bodies and healthcare providers.

Source: Journal of Pharmaceutical and Biomedical Analysis

DOI: 10.1016/j.jpba.2025.116940