Use of surgical video–based automated performance metrics to predict blood loss and success of simulated vascular injury control in neurosurgery: a pilot study

OBJECTIVE Experts can assess surgeon skill using surgical video, but a limited number of expert surgeons are available. Automated performance metrics (APMs) are a promising alternative but have not been created from operative videos in neurosurgery to date. The authors aimed to evaluate whether video-based APMs can predict task success and blood loss during endonasal endoscopic surgery in a validated cadaveric simulator of vascular injury of the internal carotid artery. METHODS Videos of cadaveric simulation trials by 73 neurosurgeons and otorhinolaryngologists were analyzed and manually annotated with bounding boxes to identify the surgical instruments in the frame. APMs in five domains were defined—instrument usage, time-to-phase, instrument disappearance, instrument movement, and instrument interactions—on the basis of expert analysis and task-specific surgical progressions. Bounding-box data of instrument position were then used to generate APMs for each trial. Multivariate linear regression was used to test for the associations between APMs and blood loss and task success (hemorrhage control in less than 5 minutes). The APMs of 93 successful trials were compared with the APMs of 49 unsuccessful trials. RESULTS In total, 29,151 frames of surgical video were annotated. Successful simulation trials had superior APMs in each domain, including proportionately more time spent with the key instruments in view (p < 0.001) and less time without hemorrhage control (p = 0.002). APMs in all domains improved in subsequent trials after the participants received personalized expert instruction. Attending surgeons had superior instrument usage, time-to-phase, and instrument disappearance metrics compared with resident surgeons (p < 0.01). APMs predicted surgeon performance better than surgeon training level or prior experience. A regression model that included APMs predicted blood loss with an R2 value of 0.87 (p < 0.001). CONCLUSIONS Video-based APMs were superior predictors of simulation trial success and blood loss than surgeon characteristics such as case volume and attending status. Surgeon educators can use APMs to assess competency, quantify performance, and provide actionable, structured feedback in order to improve patient outcomes. Validation of APMs provides a benchmark for further development of fully automated video assessment pipelines that utilize machine learning and computer vision.

Use of a disposable vascular pressure device to guide balloon inflation of resuscitative endovascular balloon occlusion of the aorta: a bench study

Resuscitative endovascular balloon occlusion of the aorta (REBOA) for rapid hemorrhage control is increasingly being used in trauma management. Its beneficial hemodynamic effects on unstable patients beyond temporal hemostasis has led to growing interest in its use in other patient populations, such as during cardiac arrest from nontraumatic causes. The ability to insert the catheters without fluoroscopic guidance makes the technique available in the prehospital setting. However, in addition to correct positioning, challenges include reliably achieving aortic occlusion while minimizing the risk of balloon rupture. Without fluoroscopic control, inflation of the balloon relies on estimated aortic diameters and on the disappearing pulse in the contralateral femoral artery. In the case of cardiac arrest or absent palpable pulses, balloon inflation is associated with excess risk of overinflation and adverse events (vessel damage, balloon rupture). In this bench study, we examined how the pressure in the balloon is related to the surrounding blood pressure and the balloon's contact with the vessel wall in two sets of experiments, including a pulsatile circulation model. With this data, we developed a rule of thumb to guide balloon inflation of the ER-REBOA catheter with a simple disposable pressure-reading device (COMPASS). We recommend slowly filling the balloon with saline until the measured balloon pressure is 160 mmHg, or 16 mL of saline have been used. If after 16 mL the balloon pressure is still below 160 mmHg, saline should be added in 1-mL increments, which increases the pressure target about 10 mmHg at each step, until the maximum balloon pressure is reached at 240 mmHg (= 24 mL inflation volume). A balloon pressure greater than 250 mmHg indicates overinflation. With this rule and a disposable pressure-reading device (COMPASS), ER-REBOA balloons can be safely filled in austere environments where fluoroscopy is unavailable. Pressure monitoring of the balloon allows for recognition of unintended deflation or rupture of the balloon.

Have Students Used Techniques to Stop the Bleed?

Introduction The Stop the Bleed course was initiated in response to the Hartford Consensus and over 1 million people have been taught basic bleeding control techniques. Our study sought to determine the extent to which this training has been utilized. Methods Surveys were sent by email to students that had taken the Stop the Bleed course through our institution in 2017 or 2018. Data were collected utilizing the REDCap system and statistical calculations were performed. Results 2505 surveys were sent with 445 (18%) responses. The mean age of respondents was 48 years of age, 343 (77%) were female, and 230 (52%) were in the medical field. There were 17 respondents (3.8%) that stated they had utilized the techniques taught in the course; 16 out of 17 put pressure on a wound, 7 packed a wound, and 6 used a tourniquet. Patients had been injured by a variety of mechanisms including gunshot wound, stabbing, accidental laceration, and motor vehicle collision. Patients had good outcomes with 3 out of 17 surviving to emergency medical services arrival without known final outcome and the remaining 14 were known to do well. Conclusion The Stop the Bleed course is important to enable bystanders to provide hemorrhage control. Our study shows that the techniques have been utilized with 17 treated patients having a good outcome and while a utilization rate of 3.8% may appear low, it is similar to the utilization rate of cardiopulmonary resuscitation instruction of 2%.