RESUMO
Background: The use of patient health and treatment information captured in structured and unstructured formats in computerized electronic health record (EHR) repositories could potentially augment the detection of safety signals for drug products regulated by the US Food and Drug Administration (FDA). Natural language processing and other artificial intelligence (AI) techniques provide novel methodologies that could be leveraged to extract clinically useful information from EHR resources. Objective: Our aim is to develop a novel AI-enabled software prototype to identify adverse drug event (ADE) safety signals from free-text discharge summaries in EHRs to enhance opioid drug safety and research activities at the FDA. Methods: We developed a prototype for web-based software that leverages keyword and trigger-phrase searching with rule-based algorithms and deep learning to extract candidate ADEs for specific opioid drugs from discharge summaries in the Medical Information Mart for Intensive Care III (MIMIC III) database. The prototype uses MedSpacy components to identify relevant sections of discharge summaries and a pretrained natural language processing (NLP) model, Spark NLP for Healthcare, for named entity recognition. Fifteen FDA staff members provided feedback on the prototype's features and functionalities. Results: Using the prototype, we were able to identify known, labeled, opioid-related adverse drug reactions from text in EHRs. The AI-enabled model achieved accuracy, recall, precision, and F1-scores of 0.66, 0.69, 0.64, and 0.67, respectively. FDA participants assessed the prototype as highly desirable in user satisfaction, visualizations, and in the potential to support drug safety signal detection for opioid drugs from EHR data while saving time and manual effort. Actionable design recommendations included (1) enlarging the tabs and visualizations; (2) enabling more flexibility and customizations to fit end users' individual needs; (3) providing additional instructional resources; (4) adding multiple graph export functionality; and (5) adding project summaries. Conclusions: The novel prototype uses innovative AI-based techniques to automate searching for, extracting, and analyzing clinically useful information captured in unstructured text in EHRs. It increases efficiency in harnessing real-world data for opioid drug safety and increases the usability of the data to support regulatory review while decreasing the manual research burden.
RESUMO
OBJECTIVES: To compare the gender distribution of clinical trial leadership in coronavirus disease 2019 (COVID-19) clinical trials. METHODS: We searched https://clinicaltrials.gov/ and retrieved all clinical trials on COVID-19 from 1 January 2020 to 26 June 2020. As a comparator group, we have chosen two fields that are not related to emerging infections and infectious diseases: and considered not directly affected by the pandemic: breast cancer and type 2 diabetes mellitus (T2DM) and included studies within the aforementioned study period as well as those registered in the preceding year (pre-study period: 1 January 2019 to 31 December 2019). Gender of the investigator was predicted using the genderize.io application programming interface. The repository of the data sets used to collect and analyse the data are available at https://osf.io/k2r57/. RESULTS: Only 27.8% (430/1548) of principal investigators among COVID-19-related studies were women, which is significantly different compared with 54.9% (156/284) and 42.1% (56/133) for breast cancer (p < 0.005) and T2DM (p < 0.005) trials over the same period, respectively. During the pre-study period, the proportion of principal investigators who were predicted to be women were 49.7% (245/493) and 44.4% (148/333) for breast cancer and T2DM trials, respectively, and the difference was not statistically significant when compared with results from the study period (p > 0.05). CONCLUSION: We demonstrate that less than one-third of COVID-19-related clinical trials are led by women, half the proportion observed in non-COVID-19 trials over the same period, which remained similar to the pre-study period. These gender disparities during the pandemic may not only indicate a lack of female leadership in international clinical trials and involvement in new projects but also reveal imbalances in women's access to research activities and funding during health emergencies.