arXiv subjects

Eugene Wickett

Publications and source records attributed to Eugene Wickett.

2 recordsLinked to original sources

arXiv2025

Measuring sampling plan utility in post-marketing surveillance of medical products

Ensuring product quality is critical to combating the global challenge of substandard and falsified medical products. Post-marketing surveillance is a central quality-assurance activity in which products from consumer-facing locations are collected and tested. Regulators in low-resource settings use post-marketing surveillance to evaluate product quality across locations and determine corrective actions. Part of post-marketing surveillance is developing a sampling plan, which specifies where to test and the number of tests to conduct at a location. With limited resources, it is important to base decisions on the utility of the samples tested. We propose a Bayesian approach to generate a comprehensive utility metric for sampling plans. This sampling plan utility integrates regulatory risk assessments with prior testing data, available supply-chain information, and valuations of regulatory objectives. We develop an efficient method for calculating sampling plan utility. We illustrate the value of the utility metric with a case study based on de-identified post-marketing surveillance data from a low-resource setting.

stat.AP↗

arXiv2023

Inferring sources of substandard and falsified products in pharmaceutical supply chains

Substandard and falsified pharmaceuticals, prevalent in low- and middle-income countries, substantially increase levels of morbidity, mortality and drug resistance. Regulatory agencies combat this problem using post-market surveillance by collecting and testing samples where consumers purchase products. Existing analysis tools for post-market surveillance data focus attention on the locations of positive samples. This paper looks to expand such analysis through underutilized supply-chain information to provide inference on sources of substandard and falsified products. We first establish the presence of unidentifiability issues when integrating this supply-chain information with surveillance data. We then develop a Bayesian methodology for evaluating substandard and falsified sources that extracts utility from supply-chain information and mitigates unidentifiability while accounting for multiple sources of uncertainty. Using de-identified surveillance data, we show the proposed methodology to be effective in providing valuable inference.

stat.AP↗