Pharmacovigilance is essential for protecting public health as it identifies and evaluates adverse events (AEs) associated with the use of pharmaceuticals and vaccines. This study explores a novel approach for detecting adverse drug reactions which integrates AE ontology into a zero-inflated negative binomial model. Correlated AEs are more effectively disentangled by taking account of their similarities while accounting for excess of zero counts. The aim of this contribution is to numerically assess the model on Italian pharmacovigilance data.
Exploring Ontology-Based Mining of ADRs
Dame, Kenenisa Tadesse
;Belloni, Pietro;Brazzale, Alessandra R.
2025
Abstract
Pharmacovigilance is essential for protecting public health as it identifies and evaluates adverse events (AEs) associated with the use of pharmaceuticals and vaccines. This study explores a novel approach for detecting adverse drug reactions which integrates AE ontology into a zero-inflated negative binomial model. Correlated AEs are more effectively disentangled by taking account of their similarities while accounting for excess of zero counts. The aim of this contribution is to numerically assess the model on Italian pharmacovigilance data.
File in questo prodotto:
Non ci sono file associati a questo prodotto.
Pubblicazioni consigliate
I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.
