Reaching high-hanging fruit in antimicrobial stewardship: a hospital-based intervention to withdraw inappropriately prescribed antimicrobials.

Background: Antimicrobial stewardship programs (ASPs) are responsible for addressing unnecessary antimicrobial use. We describe our experience with a unique intervention to withdraw unnecessary antimicrobials. Methods: Design, Setting, Participants: descriptive case series of adult inpatients at a single academic medical center, December 2021 to December 2022; Intervention: hospital-wide policy allowing ASP to discontinue inappropriate antimicrobials in select cases not resolved by prospective audit and feedback; Measures: count, date, and generic names of antimicrobials prescribed; reason for antimicrobial withdrawal (prolonged duration, no evidence of infection, or other); withdrawals by inpatient service (surgical or medical); time from antimicrobial start date to withdrawal intervention; days of therapy (DOT) saved; "nudge effect" defined as the prescribing team self-discontinuing withdrawn antimicrobial within 24 hours of withdrawal notice; appeals to withdrawals; ordering of alternative antimicrobials following withdrawal; incident infections, readmission, in-hospital mortality within 30 days of withdrawal intervention. Results: There were 54 antimicrobials withdrawn among 36 unique patients during the study period; piperacillin-tazobactam followed by vancomycin were the most frequently withdrawn agents; prolonged duration of therapy or prophylaxis followed by no evidence of infection were the most common reasons for withdrawal; withdrawals occurred most often on surgical services; an estimated 236 DOT (27.2 DOT per 100 patient-days) were saved; 32% of withdrawals were appealed; alternative antimicrobials were ordered following 20% of withdrawals; no incident infections, readmissions or in-hospital deaths were definitively attributed to withdrawal intervention. Conclusions: Our antimicrobial withdrawal intervention was a safe and effective addition to ASP activities to reduce inappropriate antimicrobial use and improve prescriber accountability.

FlatNet3D: intensity and absolute depth from single-shot lensless capture.

Lensless cameras are ultra-thin imaging systems that replace the lens with a thin passive optical mask and computation. Passive mask-based lensless cameras encode depth information in their measurements for a certain depth range. Early works have shown that this encoded depth can be used to perform 3D reconstruction of close-range scenes. However, these approaches for 3D reconstructions are typically optimization based and require strong hand-crafted priors and hundreds of iterations to reconstruct. Moreover, the reconstructions suffer from low resolution, noise, and artifacts. In this work, we propose FlatNet3D-a feed-forward deep network that can estimate both depth and intensity from a single lensless capture. FlatNet3D is an end-to-end trainable deep network that directly reconstructs depth and intensity from a lensless measurement using an efficient physics-based 3D mapping stage and a fully convolutional network. Our algorithm is fast and produces high-quality results, which we validate using both simulated and real scenes captured using PhlatCam.