Interpretation and Use of Applied/Operational Machine Learning and Artificial Intelligence in Surgery.

Applications for artificial intelligence (AI) and machine learning in surgery include image interpretation, data summarization, automated narrative construction, trajectory and risk prediction, and operative navigation and robotics. The pace of development has been exponential, and some AI applications are working well. However, demonstrations of clinical utility, validity, and equity have lagged algorithm development and limited widespread adoption of AI into clinical practice. Outdated computing infrastructure and regulatory challenges which promote data silos are key barriers. Multidisciplinary teams will be needed to address these challenges and to build AI systems that are relevant, equitable, and dynamic.

Sudden-Onset Disaster Mass-Casualty Incident Response: A Modified Delphi Study on Triage, Prehospital Life Support, and Processes.

The application and provision of prehospital care in disasters and mass-casualty incident response in Europe is currently being explored for opportunities to improve practice. The objective of this translational science study was to align common principles of approach and action and to identify how technology can assist and enhance response. To achieve this objective, the application of a modified Delphi methodology study based on statements derived from key findings of a scoping review was undertaken. This resulted in 18 triage, eight life support and damage control interventions, and 23 process consensus statements. These findings will be utilized in the development of evidence-based prehospital mass-casualty incident response tools and guidelines.

Outcomes after concomitant traumatic brain injury and hemorrhagic shock: A secondary analysis from the Pragmatic, Randomized Optimal Platelets and Plasma Ratios trial.

BACKGROUND: Often the clinician is faced with a diagnostic and therapeutic dilemma in patients with concomitant traumatic brain injury (TBI) and hemorrhagic shock (HS), as rapid deterioration from either can be fatal. Knowledge about outcomes after concomitant TBI and HS may help prioritize the emergent management of these patients. We hypothesized that patients with concomitant TBI and HS (TBI + HS) had worse outcomes and required more intensive care compared with patients with only one of these injuries. METHODS: This is a post hoc analysis of the Pragmatic, Randomized Optimal Platelets and Plasma Ratios (PROPPR) trial. TBI was defined by a head Abbreviated Injury Scale score greater than 2. HS was defined as a base excess of -4 or less and/or shock index of 0.9 or greater. The primary outcome for this analysis was mortality at 30 days. Logistic regression, using generalized estimating equations, was used to model categorical outcomes. RESULTS: Six hundred seventy patients were included. Patients with TBI + HS had significantly higher lactate (median, 6.3; interquartile range, 4.7-9.2) compared with the TBI group (median, 3.3; interquartile range, 2.3-4). TBI + HS patients had higher activated prothrombin times and lower platelet counts. Unadjusted mortality was higher in the TBI + HS (51.6%) and TBI (50%) groups compared with the HS (17.5%) and neither group (7.7%). Adjusted odds of death in the TBI and TBI + HS groups were 8.2 (95% confidence interval, 3.4-19.5) and 10.6 (95% confidence interval, 4.8-23.2) times higher, respectively. Ventilator, intensive care unit-free and hospital-free days were lower in the TBI and TBI + HS groups compared with the other groups. Patients with TBI + HS or TBI had significantly greater odds of developing a respiratory complication compared with the neither group. CONCLUSION: The addition of TBI to HS is associated with worse coagulopathy before resuscitation and increased mortality. When controlling for multiple known confounders, the diagnosis of TBI alone or TBI+HS was associated with significantly greater odds of developing respiratory complications. LEVEL OF EVIDENCE: Prognostic study, level II.

Gender disparities in colorectal cancer screening: true or false?

To date, nearly all studies examining gender disparities in colorectal cancer screening report a lower endoscopic screening rate in women. Using a statewide claims database, gender differences in screening rates were analyzed in an attempt to validate gender disparities reported in prior survey-based studies. Procedural-level dataset containing all patient encounters for 2003 in which a colonoscopy or flexible sigmoidoscopy were performed was created. Procedures were selected using CPT codes and univariate analysis was performed using SAS v 8.0. Statewide for average-risk individuals 50 years or older, 65,232 endoscopic procedures were performed in 2003. The majority (83%) of endoscopic screening procedures were colonoscopies. Overall, the rate of screening in average-risk women 50 years or older (38 procedures/1000 people) was slightly lower than in men (42/1000) but not statistically significant. The rates of screening were higher in women before the age of 60 years and lower after the age of 60 years. No clinically significant difference was found in the type of screening procedure performed. Gender disparities in rates and types of colorectal cancer screening reported in prior survey studies are not validated in this patient encounter data study.