Don Roosan1, Anandi V Law2, Moom R Roosan3, Yan Li4. 1. Department of Pharmacy Practice and Administration, Western University of Health Sciences, 309 E 2nd St, Pomona, CA, 91766, USA. droosan@westernu.edu. 2. Department of Pharmacy Practice and Administration, Western University of Health Sciences, 309 E 2nd St, Pomona, CA, 91766, USA. 3. Department of Pharmacy Practice, Chapman University, 9401 Geronimo Rd, Irvine, CA, 92618, USA. 4. Center for Information Systems and Technology, Claremont Graduate University, 150 E 19th St, Claremont, CA, 91711, USA.
Abstract
INTRODUCTION: Pharmacovigilance (PV) has proven to detect post-marketing adverse drug events (ADE). Previous research used the natural language processing (NLP) tool to extract unstructured texts relevant to ADEs. However, texts without context reduce the efficiency of such algorithms. Our objective was to develop and validate an innovative NLP tool, aTarantula, using a context-aware machine-learning algorithm to detect existing ADEs from social media using an aggregated lexicon. METHOD: aTarantula utilized FastText embeddings and an aggregated lexicon to extract contextual data from three patient forums (i.e., MedHelp, MedsChat, and PatientInfo) taking warfarin. The lexicon used warfarin package inserts and synonyms of warfarin ADEs from UMLS and FAERS databases. Data was stored on SQLite and then refined and manually checked by three clinical pharmacists for validation. RESULTS: Multiple organ systems where the most frequent ADE were reported at 1.50%, followed by CNS side effects at 1.19%. Lymphatic system ADEs were the least common side effect reported at 0.09%. The overall Spearman rank correlation coefficient between patient-reported data from the forums and FAERS was 0.19. As determined by pharmacist validation, aTarantula had a sensitivity of 84.2% and a specificity of 98%. Three clinical pharmacists manually validated our results. Finally, we created an aggregated lexicon for mining ADEs from social media. CONCLUSION: We successfully developed aTarantula, a machine-learning algorithmn based on artificial intelligence to extract warfarin-related ADEs from online social discussion forums automatically. Our study shows that it is feasible to use aTarantula to detect ADEs. Future researchers can validate aTarantula on the diverse dataset.
INTRODUCTION: Pharmacovigilance (PV) has proven to detect post-marketing adverse drug events (ADE). Previous research used the natural language processing (NLP) tool to extract unstructured texts relevant to ADEs. However, texts without context reduce the efficiency of such algorithms. Our objective was to develop and validate an innovative NLP tool, aTarantula, using a context-aware machine-learning algorithm to detect existing ADEs from social media using an aggregated lexicon. METHOD: aTarantula utilized FastText embeddings and an aggregated lexicon to extract contextual data from three patient forums (i.e., MedHelp, MedsChat, and PatientInfo) taking warfarin. The lexicon used warfarin package inserts and synonyms of warfarin ADEs from UMLS and FAERS databases. Data was stored on SQLite and then refined and manually checked by three clinical pharmacists for validation. RESULTS: Multiple organ systems where the most frequent ADE were reported at 1.50%, followed by CNS side effects at 1.19%. Lymphatic system ADEs were the least common side effect reported at 0.09%. The overall Spearman rank correlation coefficient between patient-reported data from the forums and FAERS was 0.19. As determined by pharmacist validation, aTarantula had a sensitivity of 84.2% and a specificity of 98%. Three clinical pharmacists manually validated our results. Finally, we created an aggregated lexicon for mining ADEs from social media. CONCLUSION: We successfully developed aTarantula, a machine-learning algorithmn based on artificial intelligence to extract warfarin-related ADEs from online social discussion forums automatically. Our study shows that it is feasible to use aTarantula to detect ADEs. Future researchers can validate aTarantula on the diverse dataset.
Authors: Florence T Bourgeois; Michael W Shannon; Clarissa Valim; Kenneth D Mandl Journal: Pharmacoepidemiol Drug Saf Date: 2010-09 Impact factor: 2.890
Authors: Nadine Shehab; Maribeth C Lovegrove; Andrew I Geller; Kathleen O Rose; Nina J Weidle; Daniel S Budnitz Journal: JAMA Date: 2016-11-22 Impact factor: 56.272
Authors: Clark C Freifeld; John S Brownstein; Christopher M Menone; Wenjie Bao; Ross Filice; Taha Kass-Hout; Nabarun Dasgupta Journal: Drug Saf Date: 2014-05 Impact factor: 5.606