Machine learning risk prediction of mortality for patients undergoing surgery with perioperative SARS-CoV-2: the COVIDSurg mortality score

Abstract

To support the global restart of elective surgery, data from an international prospective cohort study of 8492 patients (69 countries) was analysed using artificial intelligence (machine learning techniques) to develop a predictive score for mortality in surgical patients with SARS-CoV-2. We found that patient rather than operation factors were the best predictors and used these to create the COVIDsurg Mortality Score (https://covidsurgrisk.app). Our data demonstrates that it is safe to restart a wide range of surgical services for selected patients.

Unequal Impact of COVID-19 on Private and Academic Neurosurgical Workforce: Results of an International Survey

“…One of the most relevant points is that the early termination of any elective neurosurgical service by about 70% was very diffused regardless of the nationality and type of hospital practice of the responders. Not surprisingly, the concerns raised by a large proportion of responders regarding the risks of triaging patients and rationing the neurosurgical offer are in keeping with those recently reported by others (2,9,12,18,(24)(25)(26)(27)(28). Furthermore, it should be noted that the extended lockdown period, and the justified patients' anxiety of getting infected with SARS-CoV-2 when attending hospitals, might have delayed access to care for most pathological conditions.…”

Mortality and pulmonary complications in emergency general surgery patients with COVID-19: A large international multicenter study

“…In addition, the recently developed COVIDSurg mortality score can serve as a practical and reliable adjuvant to estimate personalized mortality risk for patients with perioperative SARS-CoV-2 infection. 19 …”

Feasibility and usability of a regional hub model for colorectal cancer services during the COVID-19 pandemic

“…[2,19,20] Evidence supports the feasibility and safety of surgery for common colorectal conditions that, even if non-emergent, might impair patient's quality of life and long-term survival if treatment is delayed [21][22][23]. However, it is important that strategies are developed to mitigate the risk of complications related to perioperative SARS-CoV-2 infection [11,15,[20][21][22][24][25][26][27][28][29]-which is reported to have a detrimental effect on short-term outcomes of surgery [30].…”