Search

Introduction: Adverse drug reaction reports are usually manually assessed by pharmacovigilance experts to detect safety signals associated with drugs. With the recent extension of reporting to patients and the emergence of mass media-related sanitary crises, adverse drug reaction reports currently frequently overwhelm pharmacovigilance networks. Artificial intelligence could help support the work of pharmacovigilance experts during such crises, by automatically coding reports, allowing them to prioritise or accelerate their manual assessment. After a previous study showing first results, we developed and compared state-of-the-art machine learning models using a larger nationwide dataset, aiming to automatically pre-code patients' adverse drug reaction reports., Objectives: We aimed to determine the best artificial intelligence model identifying adverse drug reactions and assessing seriousness in patients reports from the French national pharmacovigilance web portal., Methods: Reports coded by 27 Pharmacovigilance Centres between March 2017 and December 2020 were selected (n = 11,633). For each report, the Portable Document Format form containing free-text information filled by the patient, and the corresponding encodings of adverse event symptoms (in Medical Dictionary for Regulatory Activities Preferred Terms) and seriousness were obtained. This encoding by experts was used as the reference to train and evaluate models, which contained input data processing and machine-learning natural language processing to learn and predict encodings. We developed and compared different approaches for data processing and classifiers. Performance was evaluated using receiver operating characteristic area under the curve (AUC), F-measure, sensitivity, specificity and positive predictive value. We used data from 26 Pharmacovigilance Centres for training and internal validation. External validation was performed using data from the remaining Pharmacovigilance Centres during the same period., Results: Internal validation: for adverse drug reaction identification, Term Frequency-Inverse Document Frequency (TF-IDF) + Light Gradient Boosted Machine (LGBM) achieved an AUC of 0.97 and an F-measure of 0.80. The Cross-lingual Language Model (XLM) [transformer] obtained an AUC of 0.97 and an F-measure of 0.78. For seriousness assessment, FastText + LGBM achieved an AUC of 0.85 and an F-measure of 0.63. CamemBERT (transformer) + Light Gradient Boosted Machine obtained an AUC of 0.84 and an F-measure of 0.63. External validation for both adverse drug reaction identification and seriousness assessment tasks yielded consistent and robust results., Conclusions: Our artificial intelligence models showed promising performance to automatically code patient adverse drug reaction reports, with very similar results across approaches. Our system has been deployed by national health authorities in France since January 2021 to facilitate pharmacovigilance of COVID-19 vaccines. Further studies will be needed to validate the performance of the tool in real-life settings., (© 2022. The Author(s).)

Adverse drug reaction (ADR) reporting is a major component of drug safety monitoring; its input will, however, only be optimized if systems can manage to deal with its tremendous flow of information, based primarily on unstructured text fields. The aim of this study was to develop an automated system allowing to code ADRs from patient reports. Our system was based on a knowledge base about drugs, enriched by supervised machine learning (ML) models trained on patients reporting data. To train our models, we selected all cases of ADRs reported by patients to a French Pharmacovigilance Centre through a national web-portal between March 2017 and March 2019 (n = 2,058 reports). We tested both conventional ML models and deep-learning models. We performed an external validation using a dataset constituted of a random sample of ADRs reported to the Marseille Pharmacovigilance Centre over the same period (n = 187). Here, we show that regarding area under the curve (AUC) and F-measure, the best model to identify ADRs was gradient boosting trees (LGBM), with an AUC of 0.93 (0.92-0.94) and F-measure of 0.72 (0.68-0.75). This model was run for external validation showing an AUC of 0.91 and a F-measure of 0.58. We evaluated an artificial intelligence pipeline that was found able to learn how to identify correctly ADRs from unstructured data. This result allowed us to start a new study using more data to further improve our performance and offer a tool that is useful in practice to efficiently manage drug safety information., (© 2021 The Authors. Clinical Pharmacology & Therapeutics published by Wiley Periodicals LLC on behalf of American Society for Clinical Pharmacology and Therapeutics.)

Objective: To compare the risk of all-cause death, hospitalizations (any cause), ectopic pregnancy, pelvic inflammatory disease or infection, uterine perforation, device removal, neuro-psychiatric drugs initiation, or new psychiatric visit(s) between levonorgestrel (LNG) 52 mg intrauterine system (IUS) and copper intrauterine device (IUD) users in France., Study Design: We identified a historical cohort of women aged 20-55 years with a first dispensing of either LNG 52 mg IUS or copper-IUD between January 1, 2010, and December 31, 2014, in the French National Claims database, SNDS. We used propensity score matching to balance the two groups on baseline sociodemographic and clinical characteristics to minimize confounding. We estimated Cox proportional hazards models to compare health outcomes between LNG 52 mg IUS and copper-IUDs users., Results: We matched 9318 LNG 52 mg IUS users (mean age 36.2±6.8 years) to 10,185 copper-IUD users (mean age 35.4±7.1 years). After matching and age-adjustment, LNG 52 mg IUS users had a slightly higher risk of anxiolytic drugs initiation (HR 1.08, 95%CI 1.01-1.15) and device removal (HR 1.05, 95%CI 1.01-1.10) compared to copper-IUD users, with no differences for other studied outcomes., Conclusion: French IUS users report slightly more anxiolytic treatment initiation and IUD removal compared to copper-IUD users. These results are consistent with a potential pharmacovigilance signal of anxiety-related disorders in LNG 52 mg IUS users., Implications Statement: In French LNG 52 mg IUS users, there was slightly more anxiolytic treatment initiation and IUD removal compared to copper-IUD users. No risk difference was found for all-cause death, hospitalizations, ectopic pregnancy, pelvic disorders, and uterine perforation. We cannot exclude that the associations are related to differences in characteristics of women who chose each type of type of IUD., (Copyright © 2019 Elsevier Inc. All rights reserved.)

Background: Many studies have been conducted to estimate the incidence and economic impact of adverse drug reactions. Most of these studies used historical data or were based on single hospital units. Little is known, however, about the frequency of serious adverse drug reactions in general practice., Objective: To estimate the incidence of serious adverse drug reactions in the community., Methods: A prospective study during 5 consecutive working days between March 1 and April 30, 1998, was conducted among a random representative sample of 254 general practitioners in Aquitaine, France. The main outcome measure was the number of serious adverse drug reactions (ie, resulting in death, life-threatening condition, hospitalization, incapacity, or sequel) observed by each general practitioner during the study period and validated by an expert panel., Results: Thirteen validated serious adverse drug reactions, 2 of which were fatal (1 subarachnoidal hemorrhage with oral anticoagulant and 1 aplastic anemia with antineoplastics), were observed, resulting in an incidence density of 10.2 (95% confidence interval [CI], 5.4 to 17.5) per 1000 days of practice. Eleven case subjects (84.6%) were hospitalized. This represents an average of 2.6 cases per general practitioner per year, and 123,000 adverse drug reaction cases (95% CI, 65,400 to 210,000) for the 60,000 general practitioners in France. Antineoplastics and anticoagulants were the drugs most frequently involved, and blood dyscrasia and bleeding were the most frequent adverse drug reactions., Conclusion: This study, which is one of the few available that has prospectively measured the incidence of serious adverse drug reactions in general practice settings, confirms that serious adverse drug reactions are a major public health concern.

The French system of evaluation of dependence has been defined in the French Public Health Code by decree 99-249 of 31 March 1999. It was created by health authorities 10 years earlier and concerns dependence and abuse, which were previously just submitted to control under the designation of non-conforming use and misuse. The consultative function of the narcotics and psychotropics commission has been reinforced and its mission extended to include evaluation. Cooperation with different actors has been organized. This is based on the complexity of the methods of evaluation and the impact of decisions concerning control and/or information. The same principles organize the cooperation of this system at the European and international levels.