Simulated outcomes for durotomy repair in minimally invasive spine surgery.

Minimally invasive spine surgery (MISS) is increasingly performed using endoscopic and microscopic visualization, and the captured video can be used for surgical education and development of predictive artificial intelligence (AI) models. Video datasets depicting adverse event management are also valuable, as predictive models not exposed to adverse events may exhibit poor performance when these occur. Given that no dedicated spine surgery video datasets for AI model development are publicly available, we introduce Simulated Outcomes for Durotomy Repair in Minimally Invasive Spine Surgery (SOSpine). A validated MISS cadaveric dural repair simulator was used to educate neurosurgery residents, and surgical microscope video recordings were paired with outcome data. Objects including durotomy, needle, grasper, needle driver, and nerve hook were then annotated. Altogether, SOSpine contains 15,698 frames with 53,238 annotations and associated durotomy repair outcomes. For validation, an AI model was fine-tuned on SOSpine video and detected surgical instruments with a mean average precision of 0.77. In summary, SOSpine depicts spine surgeons managing a common complication, providing opportunities to develop surgical AI models.

Lessons Learned from a Single Institution's Eight Years of Experience with Early Cleft Lip Repair.

Background and Objectives: The traditional approach in managing wide cleft lip deformities involves presurgical nasoalveolar molding (NAM) therapy followed by surgical cleft lip repair between three and six months of age. This institution has implemented an early cleft lip repair (ECLR) protocol where infants undergo primary cleft lip repair between two and five weeks of age without NAM. This study aims to present this institution's ECLR repair protocol over the past eight years from 188 consecutive patients with unilateral or bilateral CL/P deformity. Materials and Methods: Retrospective review was conducted at Children's Hospital Los Angeles evaluating patients who underwent ECLR before three months of age and were classified as American Society of Anesthesiologists (ASA) class I or II from 2015-2022. Anthropometric analysis was performed, and pre- and postoperative photographs were evaluated to assess nasal and lip symmetry. Results: The average age at cleft lip repair after correcting for gestational age was 1.0 ± 0.5 months. Mean operative and anesthetic times were 120.3 ± 33.0 min and 189.4 ± 35.4, respectively. Only 2.1% (4/188) of patients had postoperative complications. Lip revision rates were 11.4% (20/175) and 15.4% (2/13) for unilateral and bilateral repairs, respectively, most of which were minor in severity (16/22, 72.7%). Postoperative anthropometric measurements demonstrated significant improvements in nasal and lip symmetry (p < 0.001). Conclusions: This analysis demonstrates the safety and efficacy of ECLR in correcting all unilateral cleft lip and nasal deformities of patients who were ASA classes I or II. At this institution, ECLR has minimized the need for NAM, which is now reserved for patients with bilateral cleft lip, late presentation, or comorbidities that preclude them from early repair. ECLR serves as a valuable option for patients with a wide range of cleft severity while reducing the burden of care.

Assessment of Cranial Sexual Dimorphism Using 3D Reconstruction: Implications for Gender-Affirming Surgery.

BACKGROUND: As more centers offer gender-affirming procedures, dissemination of best practices is critical to ensuring quality care. This study is the first to use advanced 3-dimensional visualization software to characterize cranial differences between natal males and females, as they relate to planning for facial gender-affirming operations. MATERIALS AND METHODS: A retrospective analysis was conducted on randomly selected patients with facial computed tomography imaging performed at a single institution between February 2020 and July 2021. Patients with acquired bony deformity on computed tomography or documented history of hormone replacement therapy were excluded. The images were retrieved and analyzed using advanced 3-dimensional visualization software (Vitrea). Independent sample t tests were performed to analyze variation in typically sexually dimorphic facial features between natal males and females. RESULTS: We identified 50 patients (25 natal males and 25 natal females) who met the inclusion criteria. Ages ranged from 19 to 91. Natal males were found to have significantly greater frontosellar distances (difference between means, SEM: 2.7±1.2; P =0.03) and mandible volumes (difference between means, SEM: 14.0±4.2; P =0.002) than natal females. Statistical analysis revealed no significant differences in gonial angle, chin width, nasofrontal angle, or nasolabial angle between natal males and females. CONCLUSION: In this diverse sample of natal males and females, statistical analysis revealed that the sexually dimorphic facial characteristics most relevant to the planning of facial gender-affirming surgery are frontosellar distance and mandible volume. When planning facial gender-affirming surgery, we recommend that these characteristics be considered to achieve optimum results.

Tympanostomy Tubes: Are They Necessary? A Systematic Review on Implementation in Cleft Care.

OBJECTIVE: To understand the indication for and the effects of early ventilation tube insertion (VTI) on hearing and speech for patients with cleft lip and/or palate (CLP). DESIGN: We conducted a Preferred Reporting Items for Systematic Reviews and Meta-Analysis (PRISMA)-guided systematic review of relevant literature. SETTING: Setting varied by geographical location and level of clinical care across studies. PATIENTS, PARTICIPANTS: Patients with CLP who underwent VTI were included. INTERVENTIONS: No interventions were performed. MAIN OUTCOME MEASURE(S): Primary outcome measures were hearing and speech following VTI. Secondary outcome measures were tube-related and middle ear complications. Early VTI occurred before or at time of palatoplasty while late VTI occurred after palatoplasty. RESULTS: Twenty-three articles met inclusion criteria. Articles varied among study design, outcome measures, sample size, follow-up, and quality. Few studies demonstrated support for early VTI. Many studies reported no difference in hearing or speech between early and late VTI. Others reported worse outcomes, greater likelihood of complications, or needing repeat VTI following early tympanostomy placement. Several studies had significant limitations, including confounding variables, small sample size, or not reporting on our primary outcome. CONCLUSIONS: No consistency was found regarding which patients would benefit most from early VTI. Given the aforementioned variability and sub-optimal methodologies, additional studies are warranted to provide stronger evidence regarding VTI timing in cleft care.

Utility of the Simulated Outcomes Following Carotid Artery Laceration Video Data Set for Machine Learning Applications.

Importance: Surgical data scientists lack video data sets that depict adverse events, which may affect model generalizability and introduce bias. Hemorrhage may be particularly challenging for computer vision-based models because blood obscures the scene. Objective: To assess the utility of the Simulated Outcomes Following Carotid Artery Laceration (SOCAL)-a publicly available surgical video data set of hemorrhage complication management with instrument annotations and task outcomes-to provide benchmarks for surgical data science techniques, including computer vision instrument detection, instrument use metrics and outcome associations, and validation of a SOCAL-trained neural network using real operative video. Design, Setting, and Participants: For this quailty improvement study, a total of 75 surgeons with 1 to 30 years' experience (mean, 7 years) were filmed from January 1, 2017, to December 31, 2020, managing catastrophic surgical hemorrhage in a high-fidelity cadaveric training exercise at nationwide training courses. Videos were annotated from January 1 to June 30, 2021. Interventions: Surgeons received expert coaching between 2 trials. Main Outcomes and Measures: Hemostasis within 5 minutes (task success, dichotomous), time to hemostasis (in seconds), and blood loss (in milliliters) were recorded. Deep neural networks (DNNs) were trained to detect surgical instruments in view. Model performance was measured using mean average precision (mAP), sensitivity, and positive predictive value. Results: SOCAL contains 31 443 frames with 65 071 surgical instrument annotations from 147 trials with associated surgeon demographic characteristics, time to hemostasis, and recorded blood loss for each trial. Computer vision-based instrument detection methods using DNNs trained on SOCAL achieved a mAP of 0.67 overall and 0.91 for the most common surgical instrument (suction). Hemorrhage control challenges standard object detectors: detection of some surgical instruments remained poor (mAP, 0.25). On real intraoperative video, the model achieved a sensitivity of 0.77 and a positive predictive value of 0.96. Instrument use metrics derived from the SOCAL video were significantly associated with performance (blood loss). Conclusions and Relevance: Hemorrhage control is a high-stakes adverse event that poses unique challenges for video analysis, but no data sets of hemorrhage control exist. The use of SOCAL, the first data set to depict hemorrhage control, allows the benchmarking of data science applications, including object detection, performance metric development, and identification of metrics associated with outcomes. In the future, SOCAL may be used to build and validate surgical data science models.

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.

Death Cafés for prevention of burnout in intensive care unit employees: study protocol for a randomized controlled trial (STOPTHEBURN).

BACKGROUND: Burnout is an occupational syndrome that leads to mental health problems, job turnover, and patient safety events. Those caring for critically ill patients are especially susceptible due to high patient mortality, long hours, and regular encounters with trauma and ethical issues. Interventions to prevent burnout in this population are needed. Preliminary studies suggest debriefing sessions may reduce burnout. This study aims to assess whether participation in regular debriefing can prevent burnout in intensive care unit (ICU) clinicians. METHODS: A randomized controlled trial will be conducted in two large academic medical centers. Two hundred ICU clinicians will be recruited with target enrollment of 100 physicians and 100 non-physicians (nurses, pharmacists, therapists). Participants must have worked in the ICU for the equivalent of at least 1 full time work week in the preceding 4 weeks. Enrolled subjects will be randomized to virtually attend biweekly debriefing sessions facilitated by a psychotherapist for 3 months or to a control arm without sessions. Our debriefs are modeled after Death Cafés, which are informal discussions focusing on death, dying, loss, grief, and illness. These sessions allow for reflection on distressing events and offer community and collaboration among hospital employees outside of work. The primary outcome is clinician burnout as measured by the Maslach Burnout Inventory (MBI) Score. Secondary outcomes include depression and anxiety, as measured by the Patient Health Questionnaire 8 (PHQ-8) and Generalized Anxiety Disorder 7-item scale (GAD-7), respectively. Questionnaires will be administered prior to the intervention, at 1 month, at 3 months, and at 6 months after enrollment. These values will be compared between groups temporally. Qualitative feedback will also be collected and analyzed. DISCUSSION: With ICU clinician burnout rates exceeding 50%, Death Café debriefing sessions may prove to be an effective tool to avert this debilitating syndrome. With COVID-19 limiting social interactions and overloading ICUs worldwide, the virtual administration of the Death Café for ICU clinicians provides an innovative strategy to potentially mitigate burnout in this vulnerable population. TRIAL REGISTRATION: ClinicalTrials.gov NCT04347811 . Registered on 15 April 2020.