Innovation in Pharmacovigilance: Use of Artificial Intelligence in Adverse Event Case Processing.

Automation of pharmaceutical safety case processing represents a significant opportunity to affect the strongest cost driver for a company's overall pharmacovigilance budget. A pilot was undertaken to test the feasibility of using artificial intelligence and robotic process automation to automate processing of adverse event reports. The pilot paradigm was used to simultaneously test proposed solutions of three commercial vendors. The result confirmed the feasibility of using artificial intelligence-based technology to support extraction from adverse event source documents and evaluation of case validity. In addition, the pilot demonstrated viability of the use of safety database data fields as a surrogate for otherwise time-consuming and costly direct annotation of source documents. Finally, the evaluation and scoring method used in the pilot was able to differentiate vendor capabilities and identify the best candidate to move into the discovery phase.

Evaluating the postmarketing experience of risperidone use during pregnancy: pregnancy and neonatal outcomes.

BACKGROUND: A significant number of women of childbearing age have schizophrenia or other psychoses. This means that there is a considerable risk of in utero exposure to risperidone due to maternal use. OBJECTIVE: To determine whether in utero exposure to the atypical antipsychotic risperidone is associated with poor pregnancy and fetal/neonatal outcomes. METHODS: A search of the Benefit Risk Management Worldwide Safety database, using a selection of preferred terms from the Medical Dictionary of Regulatory Activities, was performed to identify all cases of pregnancy or fetal/neonatal outcomes reported in association with risperidone treatment from its first market launch (international birth date, 1 June 1993) to 31 December 2004. The main measures were the patterns and reporting rates of pregnancy (stillbirth and spontaneous and induced abortion) and fetal/neonatal outcomes (congenital abnormalities, perinatal syndromes and withdrawal symptoms) for women administered risperidone during pregnancy. RESULTS: Overall, 713 pregnancies were identified in women who were receiving risperidone. Data were considered prospective in 516 of these, and retrospective in the remaining 197 cases. The majority of the known adverse pregnancy and fetal/neonatal outcomes were retrospectively reported. Of the 68 prospectively reported pregnancies with a known outcome, organ malformations and spontaneous abortions occurred 3.8% and 16.9% (when the 15 induced abortions were excluded from the denominator, as they were predominantly undertaken for nonmedical reasons), respectively, a finding consistent with background rates of the general population. There were 12 retrospectively reported pregnancies involving major organ malformations, the most frequently reported of which affected the heart, brain, lip and/or palate. There were 37 retrospectively reported pregnancies involving perinatal syndromes, of which 21 cases involved behavioural or motor disorders. In particular, there was a cluster of cases reporting tremor, jitteriness, irritability, feeding problems and somnolence, which may represent a withdrawal-emergent syndrome. CONCLUSION: This comprehensive review of the Benefit Risk Management Worldwide Safety database for case reports of risperidone exposure during pregnancy represents the largest ever published dataset documenting pregnancy outcomes for women taking the atypical antipsychotic risperidone. It indicates that in utero exposure to risperidone does not appear to increase the risk of spontaneous abortions, structural malformations and fetal teratogenic risk above that of the general population. Self-limited extrapyramidal effects in neonates were observed after maternal exposure to risperidone during the third trimester of pregnancy. Risperidone should only be used during pregnancy if the benefits outweigh the potential risks.