ABSTRACT
INTRODUCTION: For treatment of Esophagectomy Complications Consensus Group (ECCG) type II leak, self-expanding metal stents (SEMS) can be placed, or endoscopic vacuum therapy (EVT) can be applied;however, there are no prospective data concerning the optimal endoscopic treatment strategy. The aim of the study was to report outcomes of treatment strategies for patients with an ECCG type II anastomotic leak after robotic-assisted minimally invasive esophagectomy (RAMIE). METHOD(S): All patients who developed an ECCG type II anastomotic leak since the introduction of RAMIE at our high-volume center (>200 cases/y) were included in the analysis. Time to EVT, duration of EVT, and follow-up treatment were analyzed for all patients. RESULT(S): Since 2017, a total of 157 patients have undergone a RAMIE at our clinic. Twenty-three patients developed an ECCG type II anastomotic leak (14.6% leak rate). Successful completion was achieved in 21 of 23 of patients (91%). Two patients were deceased before the completion of endoscopic therapy: 1 of unrelated COVID-19 pneumonia and 1 of sepsis with unknown focus. Mean duration of EVT was12 days (range 4 to 28 days), mean of 2 endoscopic sponge changes (range 0 to 5). Anastomotic leak was diagnosed at a mean of 9 days postoperative (range 2 to 19 days). Placement of a SEMS was performed in 5 patients (24%) after completion of EVT. No patient needed conversion to operative therapy;however, pre-emptive EVT was performed after surgical revision in 3 patients (37.5%) with an ECCG type III leak. CONCLUSION(S): EVT has been shown to be a safe and successful treatment option for anastomotic leak after robotic-assisted esophagectomy with success rate of 91% in our cohort. No additional surgical revision was performed in any patient.
ABSTRACT
Direct-to-consumer medical artificial intelligence/machine learning applications are increasingly used for a variety of diagnostic assessments, and the emphasis on telemedicine and home healthcare during the COVID-19 pandemic may further stimulate their adoption. In this Perspective, we argue that the artificial intelligence/machine learning regulatory landscape should operate differently when a system is designed for clinicians/doctors as opposed to when it is designed for personal use. Direct-to-consumer applications raise unique concerns due to the nature of consumer users, who tend to be limited in their statistical and medical literacy and risk averse about their health outcomes. This creates an environment where false alarms can proliferate and burden public healthcare systems and medical insurers. While similar situations exist elsewhere in medicine, the ease and frequency with which artificial intelligence/machine learning apps can be used, and their increasing prevalence in the consumer market, calls for careful reflection on how to effectively regulate them. We suggest regulators should strive to better understand how consumers interact with direct-to-consumer medical artificial intelligence/machine learning apps, particularly diagnostic ones, and this requires more than a focus on the system’s technical specifications. We further argue that the best regulatory review would also consider such technologies’ social costs under widespread use. © 2021, Springer Nature Limited.