Artificial Intelligence-Based Pharmacovigilance in the Setting of Limited Resources.

With the rapid development of artificial intelligence (AI) technologies, and the large amount of pharmacovigilance-related data stored in an electronic manner, data-driven automatic methods need to be urgently applied to all aspects of pharmacovigilance to assist healthcare professionals. However, the quantity and quality of data directly affect the performance of AI, and there are particular challenges to implementing AI in limited-resource settings. Analyzing challenges and solutions for AI-based pharmacovigilance in resource-limited settings can improve pharmacovigilance frameworks and capabilities in these settings. In this review, we summarize the challenges into four categories: establishing a database for an AI-based pharmacovigilance system, lack of human resources, weak AI technology and insufficient government support. This study also discusses possible solutions and future perspectives on AI-based pharmacovigilance in resource-limited settings.

Comparative evaluation of four hydrogen peroxide-based systems to decontaminate N95 respirators.

Objective: Protocols designed to facilitate N95 filtering facepiece respirator (FFR) decontamination by commercial sterilization devices do not recommend that operators verify the device's performance against pathogens deposited on FFRs. Here, we compared the treatment efficacy of 4 hydrogen peroxide-based systems that were authorized for N95 decontamination during the COVID-19 pandemic. Methods: Suspensions prepared from S. aureus ATCC 29213 and 44300, B. subtilis ATCC 6633, a vancomycin-resistant E. faecium isolate (VRE), E. coli ATCC 25922, and P. aeruginosa ATCC 27853 colonies were inoculated onto nine 1-cm2 areas on a 3M 1805, 1860, 1860S, 1870+, 8210, 8110S, or 9105S FFR. Contaminated respirators were treated according to protocols recommended by the STERRAD 100NX, Bioquell Z-2, Sterizone VP4, or Clean Works Mini systems. Decontamination efficacy was determined by comparing colony counts cultured from excised segments of treated and untreated FFR. Results: All devices achieved a 6-log reduction in bacterial burden and met FDA sterilization criteria. The Bioquell Z-2 device demonstrated 100% efficacy against both gram-positive and gram-negative organisms with all FFRs tested. Colonies of S. aureus ATCC 29213 and 44300 and VRE were cultivable from up to 9 (100%) of 9 STERRAD 100NX- and Sterizone VP4-treated segments. Viable B. subtilis ATCC 6633 organisms were recovered from 76.0% of STERRAD 100NX-treated FFR segments. Conclusions: Variability in decontamination efficacy was noted across devices and FFR types. gram-positive organisms were more difficult to completely eliminate than were gram-negative organisms. Prior to initiating FFR decontamination practices, institutions should verify the effectiveness of their devices and the safety of treated FFR.