Liu Nan

Risk prediction in emergency medicine (EM) holds unique challenges due to issues surrounding urgency, blurry research-practise distinctions, and the high-pressure environment in emergency departments (ED). Artificial intelligence (AI) risk prediction tools have been developed with the aim of streamlining triaging processes and mitigating perennial issues affecting EDs globally, such as overcrowding and delays. The implementation of these tools is complicated by the potential risks associated with over-triage and under-triage, untraceable false positives, as well as the potential for the biases of healthcare professionals toward technology leading to the incorrect usage of such tools. This paper explores risk surrounding these issues in an analysis of a case study involving a machine learning triage tool called the Score for Emergency Risk Prediction (SERP) in Singapore. This tool is used for estimating mortality risk in presentation at the ED. After two successful retrospective studies demonstrating SERP’s strong predictive accuracy, researchers decided that the pre-implementation randomised controlled trial (RCT) would not be feasible due to how the tool interacts with clinical judgement, complicating the blinded arm of the trial. This led them to consider other methods of testing SERP’s real-world capabilities, such as ongoing-evaluation type studies. We discuss the outcomes of a risk–benefit analysis to argue that the proposed implementation strategy is ethically appropriate and aligns with improvement-focused and systemic approaches to implementation, especially the learning health systems framework (LHS) to ensure safety, efficacy, and ongoing learning.

ObjectiveTo investigate the characteristics of response inhibition of overweight/obese people, using behavior experiments combine with neural electrophysiological technology and discussing the difference in impulse level between obesity/overweight and normal-weight people through EEG data, questionnaire, and behavior experiment.Method All participants completed the Go/Nogo task; meanwhile, behavior data and 64 channel EEG data were recorded. Participants completed the Stop-Signal task and behavior date was recorded.Results During Go/Nogo task, no significant differences were found in reaction time, omission errors of the Go task between the two groups, while commission errors of the Nogo task of the control group were significantly greater than the overweight/obesity group. About SSRT during the Stop-Signal Task, the interaction of stimulus type and group was significant. No significant differences were found between the two groups in amplitude and latency of N2. About the amplitude of P3, the interaction of task type, electrode point, and groups were significant, the control group P3 amplitude was significantly greater than overweight/obesity group during the Nogo task. Regarding about latency of P3, the interaction of group and electrode point were not significant, but the main effect of task type was significant.Conclusion In terms of behavioral outcomes, overweight–obese subjects had lower dominant response inhibition and response cessation compared to normal-weight subjects. In terms of EEG results, overweight–obese subjects showed no difference in processing speed and level of conflict monitoring for early inhibitory processing compared to normal-weight subjects, but there was a deficit in behavioral control for late inhibitory processing.