Privacy-proof Live Surgery Streaming: Development and Validation of a Low-cost, Real-time Robotic Surgery Anonymization Algorithm.

OBJECTIVE: Develop a pioneer surgical anonymization algorithm for reliable and accurate real-time removal of out-of-body images validated across various robotic platforms. BACKGROUND: The use of surgical video data has become a common practice in enhancing research and training. Video sharing requires complete anonymization, which, in the case of endoscopic surgery, entails the removal of all nonsurgical video frames where the endoscope can record the patient or operating room staff. To date, no openly available algorithmic solution for surgical anonymization offers reliable real-time anonymization for video streaming, which is also robotic-platform and procedure-independent. METHODS: A data set of 63 surgical videos of 6 procedures performed on four robotic systems was annotated for out-of-body sequences. The resulting 496.828 images were used to develop a deep learning algorithm that automatically detected out-of-body frames. Our solution was subsequently benchmarked against existing anonymization methods. In addition, we offer a postprocessing step to enhance the performance and test a low-cost setup for real-time anonymization during live surgery streaming. RESULTS: Framewise anonymization yielded a receiver operating characteristic area under the curve score of 99.46% on unseen procedures, increasing to 99.89% after postprocessing. Our Robotic Anonymization Network outperforms previous state-of-the-art algorithms, even on unseen procedural types, despite the fact that alternative solutions are explicitly trained using these procedures. CONCLUSIONS: Our deep learning model, Robotic Anonymization Network, offers reliable, accurate, and safe real-time anonymization during complex and lengthy surgical procedures regardless of the robotic platform. The model can be used in real time for surgical live streaming and is openly available.

Acute gastric dilatation causing acute limb ischemia in an anorexia nervosa patient.

BACKGROUND: Acute gastric dilatation is a rare but severe complication of anorexia nervosa. Gastric dilatation causing abdominal compartment syndrome with lower-limb ischemia is even less common. This case report illustrates the importance of a holistic clinical approach of every patient presenting to the emergency department (ED), even when the reason for admittance is organ specific. CASE REPORT: We report the case of a young female patient presenting to the ED with a painful white left leg. Clinical examination revealed acute lower-limb ischemia, abdominal distention, and shock. Diagnostic work-up, including an abdominal computed tomography scan, showed compression of the aorta, inferior vena cava, and both iliac arteries, as well as hypoperfusion of the right kidney and left liver lobe, all due to compression by a massive gastric dilatation. Gastroscopy revealed a massively dilated stomach containing > 6 L of fluid and gastric wall ischemia. After decompression, the circulation to the lower limbs recovered immediately. The day after admission the patient developed an acute abdomen leading to a semi-urgent laparoscopy during which a sleeve gastrectomy was performed for the treatment of partial gastric necrosis. Clinical evolution afterward was favorable and the patient recovered completely. CONCLUSIONS: This case report underscores the importance of a thorough clinical examination in every patient admitted to the ED. Early diagnosis and treatment are mandatory in preventing fatal complications.

Percutaneous tracheostomy for long-term ventilated COVID-19-patients: rationale and first clinical-safe for all-experience.

INTRODUCTION: COVID-19 infection has resulted in thousands of critically ill patients admitted to ICUs and treated with mechanical ventilation. Percutaneous tracheostomy is a well-known technique utilised as a strategy to wean critically ill patients from mechanical ventilation. Worldwide differences exist in terms of methods, operators, and settings, and questions remain regarding timing and indications. If tracheostomy is to be performed in COVID-19 patients, a safe environment is needed for optimal care. MATERIAL AND METHODS: We present a guidewire dilating forceps tracheostomy procedure in COVID-19 patients that was optimised including apnoea-moments, protective clothing, checklists, and clear protocols. We performed a retrospective analysis of the outcome after tracheostomy in COVID-19 patients between March 2020 and May 2020. RESULTS: The follow-up of the first 16 patients, median age 62 years, revealed a median intubation time until tracheostomy of 18 days and median cannulation time of 20 days. The overall perioperative complication rate and complication rate while cannulated was 19%, mainly superficial bleeding. None of the healthcare providers involved in performing the procedure developed any symptoms of the disease. CONCLUSIONS: This COVID-19-centred strategy based on flexibility, preparation, and cooperation between healthcare providers with different backgrounds facilitated percutaneous tracheostomy in COVID-19 patients without an increase in the overall complication rate or evidence of risk to healthcare providers. Our findings provide initial evidence that tracheostomy can be performed safely as a standard of care for COVID-19 patients requiring prolonged mechanical ventilation as was standard practice in ICU patients prior to the COVID-19 pandemic to promote ventilator weaning and patient recovery.

Relevance of Geriatric Assessment in Older Patients With Colorectal Cancer.

INTRODUCTION: This study aims to evaluate the relevance of geriatric assessment (GA) in older patients with colorectal cancer (CRC) and to study functional status (FS) and chemotherapy-related toxicity during treatment. METHODS: Patients with CRC aged ≥ 70 years were evaluated at baseline using a GA. Results were communicated to the treating physician. At 2 to 3 months follow-up, FS was reassessed, and chemotherapy-related toxicity was recorded. RESULTS: A total of 193 patients, with a median age of 77 years, were included. GA was abnormal in 75% and revealed unknown problems in 40%. Treatment was altered in 37% based on clinical assessment. GA led to geriatric interventions in 9 patients (5%) and additionally influenced treatment in 1 patient. At follow-up (n = 164), functional decline was observed in 29 patients (18%) for activities of daily living (ADL) and in 60 patients (37%) for instrumental activities of daily living (IADL). Baseline IADL, depression, fatigue, and cognition were predictors for ADL decline, whereas no predictors for IADL decline could be identified. In the 109 patients receiving chemotherapy, stage and baseline fatigue were predictive for grade 3/4 hematologic toxicity, and baseline ADL, fatigue, and nutrition were predictive for grade 3/4 nonhematologic toxicity. CONCLUSION: Although GA identified previously unknown problems in more than one-third of older CRC patients, the impact on interventions or treatment decisions was limited. Baseline GA parameters may predict functional decline and chemotherapy-related toxicity. Education of physicians treating older patients with CRC is an essential step in the implementation of GA and subsequent interventions.