An Application of Machine Learning in Pharmacovigilance: Estimating Likely Patient Genotype From Phenotypical Manifestations of Fluoropyrimidine Toxicity

Abstract

Dihydropyrimidine dehydrogenase (DPD)‐deficient patients might only become aware of their genotype after exposure to dihydropyrimidines, if testing is performed. Case reports to pharmacovigilance databases might only contain phenotypical manifestations of DPD, without information on the genotype. This poses a difficulty in estimating the cases due to DPD. Auto machine learning models were developed to train patterns of phenotypical manifestations of toxicity, which were then used as a surrogate to estimate the number of cases of DPD‐related toxicity. Results indicate that between 8,878 (7.0%) and 16,549 (13.1%) patients have a profile similar to DPD deficient status. Results of the analysis of variable importance match the known end‐organ damage of DPD‐related toxicity, however, accuracies in the range of 90% suggest presence of overfitting, thus, results need to be interpreted carefully. This study shows the potential for use of machine learning in the regulatory context but additional studies are required to better understand regulatory applicability.

Artificial intelligence for optimizing benefits and minimizing risks of pharmacological therapies: challenges and opportunities

“…Therefore, ML can be used to identify populations at high risk of developing ADRs, determine the severity of ADRs (Routray et al, 2020), as well as accurately identify patients most susceptible to the toxic effects of specific medicines (Correia Pinheiro L et al, 2020). A clear application of ML to achieve these objectives is AwareDX, a pharmacovigilance algorithm using pharmacogenomic data to predict the sex-specific risk of experiencing ADRs (Chandak and Tatonetti, 2020).…”

Artificial intelligence in pharmacovigilance: A regulatory perspective on explainability

“…Artificial intelligence (AI) holds the promise of boosting efficiency of processes and increasing insights into data across all aspects of life, including healthcare, such as for cardiac function assessment or lung cancer screening 1 . In medicines regulation, the use of AI in pharmacovigilance has become a topic of interest, with multiple papers being published in the past few years on potential applications of AI 2–7 …”

“…1 In medicines regulation, the use of AI in pharmacovigilance has become a topic of interest, with multiple papers being published in the past few years on potential applications of AI. [2][3][4][5][6][7] A recent industry survey on the use of AI and machine learning in pharmacovigilance indicated that pharmacovigilance organizations intend to move rapidly with the planning, piloting, and production implementation of intelligent automation, while also pointing out that regulatory guidance is a potential challenge. 8 Medicines Regulators also need innovation that can deliver for public health.…”