Usability, Acceptability, and Implementation of Artificial Intelligence (AI) and Machine Learning (ML) Techniques in Surgical Coaching and Training: A Scoping Review.

OBJECTIVE: To define the current state of peer-reviewed literature demonstrating the usability, acceptability, and implementation of artificial intelligence (AI) and machine learning (ML) techniques in surgical coaching and training. DESIGN: We conducted a literature search with defined inclusion and exclusion criteria. We searched five scholarly databases: MEDLINE via PubMed, Embase via Elsevier, Scopus via Elsevier, Cochrane Central Register of Controlled Trials, and the Healthcare Administration Database via ProQuest. We followed the Preferred Reporting Items for Systematic Reviews and Meta-Analyses Extension for Scoping Reviews (PRISMA-ScR) guidelines. RESULTS: Only 4 articles met the inclusion criteria and used standardized methods for performance evaluation with expert observation. We found no literature examining the impact on performance, user acceptance, or implementation of AI/ML techniques used for surgical coaching and training. We highlight the need for qualitative and quantitative research demonstrating these techniques' effectiveness before broad implementation. CONCLUSION AND RELEVANCE: We emphasize the need for research to specifically evaluate performance, impact, user acceptance, and implementation of AI/ML techniques. Incorporating these facets of research when developing AI/ML techniques for surgical training is crucial to ensure emerging technology meets user needs without increasing cognitive burden or frustrating users.

Coaching your faculty and yourself.

Surgical skills vary drastically among practicing surgeons. This variation in skill has been demonstrated to translate directly into patient outcomes, highlighting the importance of skill development. Despite this, directed efforts to improve surgical skills and performance among practicing surgeons remain limited. The development of surgical coaching programs offers an exciting opportunity for surgeon performance improvement and lifelong development. In this article, we will discuss the promise of surgical coaching programs, some of the challenges met when developing a program, and future avenues and opportunities for growth within the field.

Surgical Education.

This paper summarizes the proceedings of the joint European Surgical Association ESA/American Surgical Association symposium on Surgical Education that took place in Bordeaux, France, as part of the celebrations for 30 years of ESA scientific meetings. Three presentations on the use of quantitative metrics to understand technical decisions, coaching during training and beyond, and entrustable professional activities were presented by American Surgical Association members and discussed by ESA members in a symposium attended by members of both associations.

Disposal of Unused Postoperative Opioids: A Real-World Demonstration of Surgeon-initiated Strategies Using an Activated Charcoal Bag System.

Excessive opioid prescribing following surgery creates a reservoir of unused medications available for diversion and abuse. We conducted a cohort study examining the impact of clinic-based, surgeon-initiated strategies using an activated charcoal bag (ACB) system on disposal of unused opioids. Among patients undergoing a variety of general surgery procedures, 67% of those with unused opioids disposed of them using the ACB. Our findings demonstrate practical ways to incorporate opioid disposal into surgical practice as a complement to judicious opioid prescribing.

Discussion-based interprofessional education: A positive step toward promoting shared understanding between surgical residents and nurses.

Interprofessional education during medical training may improve communication by promoting collaboration and the development of shared mental models between professions. We implemented a novel discussion-based intervention for surgical residents and nurses to promote mutual understanding of workflows and communication practices. General surgery residents and inpatient nurses from our institution were recruited to participate. Surveys and paging data were collected prior to and following the intervention. Surveys contained original questions and validated subscales. Interventions involved facilitated discussions about workflows, perceptions of urgency, and technology preferences. Discussions were recorded and transcribed for qualitative content analysis. Pre and post-intervention survey responses were compared with descriptive sample statistics. Group characteristics were compared using Fisher's exact tests. Eleven intervention groups were conducted (2-6 participants per group) (n = 38). Discussions achieved three aims: Information-Sharing (learning about each other's workflows and preferences), 2) Interpersonal Relationship-Building (establishing rapport and fostering empathy) and 3) Interventional Brainstorming (discussing strategies to mitigate communication challenges). Post-intervention surveys revealed improved nurse-reported grasp of resident schedules and tailoring of communication methods based on workflow understanding; however, communication best practices remain limited by organizational and technological constraints. Systems-level changes must be prioritized to allow intentions toward collegial communication to thrive.

The influence of anatomic stage and receptor status on first recurrence for breast cancer within 5 years (AFT-01).

BACKGROUND: Risk-stratified follow-up guidelines that account for the absolute risk and timing of recurrence may improve the quality and efficiency of breast cancer follow-up. The objective of this study was to assess the relationship of anatomic stage and receptor status with timing of the first recurrence for patients with local-regional breast cancer and generate risk-stratified follow-up recommendations. METHODS: The authors conducted a secondary analysis of 8007 patients with stage I-III breast cancer who enrolled in nine Alliance legacy clinical trials from 1997 to 2013 (ClinicalTrials.gov identifier NCT02171078). Patients who received standard-of-care therapy were included. Patients who were missing stage or receptor status were excluded. The primary outcome was days from the earliest treatment start date to the date of first recurrence. The primary explanatory variable was anatomic stage. The analysis was stratified by receptor type. Cox proportional-hazards regression models produced cumulative probabilities of recurrence. A dynamic programming algorithm approach was used to optimize the timing of follow-up intervals based on the timing of recurrence events. RESULTS: The time to first recurrence varied significantly between receptor types (p < .0001). Within each receptor type, stage influenced the time to recurrence (p < .0001). The risk of recurrence was highest and occurred earliest for estrogen receptor (ER)-negative/progesterone receptor (PR)-negative/Her2neu-negative tumors (stage III; 5-year probability of recurrence, 45.5%). The risk of recurrence was lower for ER-positive/PR-positive/Her2neu-positive tumors (stage III; 5-year probability of recurrence, 15.3%), with recurrences distributed over time. Model-generated follow-up recommendations by stage and receptor type were created. CONCLUSIONS: This study supports considering both anatomic stage and receptor status in follow-up recommendations. The implementation of risk-stratified guidelines based on these data has the potential to improve the quality and efficiency of follow-up.

Local/Regional Recurrence Rates After Breast-Conserving Therapy in Patients Enrolled in Legacy Trials of the Alliance for Clinical Trials in Oncology (AFT-01).

OBJECTIVE: We sought to evaluate local/regional recurrence rates after breast-conserving surgery in a cohort of patients enrolled in legacy trials of the Alliance for Clinical Trials in Oncology and to evaluate variation in recurrence rates by receptor subtype. BACKGROUND: Multiple randomized controlled trials have demonstrated equivalent survival between breast conservation and mastectomy, albeit with higher local/regional recurrence rates after breast conservation. However, absolute rates of local/regional recurrence have been declining with multi-modality treatment. METHODS: Data from 5 Alliance for Clinical Trials in Oncology legacy trials that enrolled women diagnosed with breast cancer between 1997 and 2010 were included. Women who underwent breast-conserving surgery and standard systemic therapies (n=4,404) were included. Five-year rates of local/regional recurrence were estimated from Kaplan-Meier curves. Patients were censored at the time of distant recurrence (if recorded as the first recurrence), death, or last follow-up. Multivariable Cox proportional hazards models were used to identify factors associated with time to local/regional recurrence, including patient age, tumor size, lymph node status, and receptor subtype. RESULTS: Overall 5-year recurrence was 4.6% (95% CI=4.0-5.4%). Five-year recurrence rates were lowest in those with ER+ or PR+ tumors (Her2+ 3.4% [95% CI 2.0-5.7%], Her2- 4.0% [95% CI 3.2-4.9%]) and highest in the triple-negative subtype (7.1% [95% CI 5.4-9.3%]). On multivariable analysis, increasing nodal involvement and triple-negative subtype were positively associated with recurrence ( P <0.0001). CONCLUSIONS: Rates of local/regional recurrence after breast conservation in women with breast cancer enrolled in legacy trials of the Alliance for Clinical Trials in Oncology are significantly lower than historic estimates. This data can better inform patient discussions and surgical decision-making.

Surveillance Imaging vs Symptomatic Recurrence Detection and Survival in Stage II-III Breast Cancer (AFT-01).

BACKGROUND: Guidelines for follow-up after locoregional breast cancer treatment recommend imaging for distant metastases only in the presence of patient signs and/or symptoms. However, guidelines have not been updated to reflect advances in imaging, systemic therapy, or the understanding of biological subtype. We assessed the association between mode of distant recurrence detection and survival. METHODS: In this observational study, a stage-stratified random sample of women with stage II-III breast cancer in 2006-2007 and followed through 2016 was selected, including up to 10 women from each of 1217 Commission on Cancer facilities (n = 10 076). The explanatory variable was mode of recurrence detection (asymptomatic imaging vs signs and/or symptoms). The outcome was time from initial cancer diagnosis to death. Registrars abstracted scan type, intent (cancer-related vs not, asymptomatic surveillance vs not), and recurrence. Data were merged with each patient's National Cancer Database record. RESULTS: Surveillance imaging detected 23.3% (284 of 1220) of distant recurrences (76.7%, 936 of 1220 by signs and/or symptoms). Based on propensity-weighted multivariable Cox proportional hazards models, patients with asymptomatic imaging compared with sign and/or symptom detected recurrences had a lower risk of death if estrogen receptor (ER) and progesterone receptor (PR) negative, HER2 negative (triple negative; hazard ratio [HR] = 0.73, 95% confidence interval [CI] = 0.54 to 0.99), or HER2 positive (HR = 0.51, 95% CI = 0.33 to 0.80). No association was observed for ER- or PR-positive, HER2-negative (HR = 1.14, 95% CI = 0.91 to 1.44) cancers. CONCLUSIONS: Recurrence detection by asymptomatic imaging compared with signs and/or symptoms was associated with lower risk of death for triple-negative and HER2-positive, but not ER- or PR-positive, HER2-negative cancers. A randomized trial is warranted to evaluate imaging surveillance for metastases results in these subgroups.

A Statewide Approach to Reducing Re-excision Rates for Women With Breast-conserving Surgery.

OBJECTIVE: Test the effectiveness of benchmarked performance reports based on existing discharge data paired with a statewide intervention to implement evidence-based strategies on breast re-excision rates. BACKGROUND: Breast-conserving surgery (BCS) is a common breast cancer surgery performed in a range of hospital settings. Studies have demonstrated variations in post-BCS re-excision rates, identifying it as a high-value improvement target. METHODS: Wisconsin Hospital Association discharge data (2017-2019) were used to compare 60-day re-excision rates following BCS for breast cancer. The analysis estimated the difference in the average change preintervention to postintervention between Surgical Collaborative of Wisconsin (SCW) and nonparticipating hospitals using a logistic mixed-effects model with repeated measures, adjusting for age, payer, and hospital volume, including hospitals as random effects. The intervention included 5 collaborative meetings in 2018 to 2019 where surgeon champions shared guideline updates, best practices/challenges, and facilitated action planning. Confidential benchmarked performance reports were provided. RESULTS: In 2017, there were 3692 breast procedures in SCW and 1279 in nonparticipating hospitals; hospital-level re-excision rates ranged from 5% to >50%. There was no statistically significant baseline difference in re-excision rates between SCW and nonparticipating hospitals (16.1% vs. 17.1%, P =0.47). Re-excision significantly decreased for SCW but not for nonparticipating hospitals (odds ratio=0.69, 95% confidence interval=0.52-0.91). CONCLUSIONS: Benchmarked performance reports and collaborative quality improvement can decrease post-BCS re-excisions, increase quality, and decrease costs. Our study demonstrates the effective use of administrative data as a platform for statewide quality collaboratives. Using existing data requires fewer resources and offers a new paradigm that promotes participation across practice settings.

To page or not to page? A qualitative study of communication practices of general surgery residents and nurses.

BACKGROUND: Communication errors contribute to preventable adverse hospital events; however, communication between general surgery residents and nurses remains insufficiently studied. The purpose of our study was to use qualitative methods to characterize communication practices of surgical residents and nurses on inpatient general and intermediate care units to inform best practices and future interprofessional interventions. METHODS: Our study cohort consisted of 14 general surgery residents and 13 inpatient nurses from a tertiary academic medical center. Focus groups were conducted via a secure video platform, recorded, and transcribed. Two authors performed open coding of transcripts for qualitative analysis. Codes were reviewed iteratively with themes generated via abductive analysis, contextualizing results within 3 domains of an established communication space framework: organizational, cognitive, and social complexity. RESULTS: Communication practices of general surgery residents and inpatient nurses are affected by workflow differences, disruptive communication patterns, and communication technology. Barriers to effective communication, as well as strategies used to mitigate challenges, were characterized, with select communication practices found to negatively affect the well-being of patients, nurses, and residents. CONCLUSION: Communication practices of general surgery residents and inpatient nurses are influenced by entrenched and interrelated organizational, technological, and interpersonal factors. Given that current communication practices negatively affect patient and provider well-being, collaboration between surgeons, nurses, systems engineers, health information technology experts, and other stakeholders is critical to (1) establish communication best practices, and (2) design interventions to assess and improve multiple areas (rather than isolated domains) of surgical interprofessional communication.

Surgical coaching in obstetrics and gynecology: an evidence-based strategy to elevate surgical education and promote lifelong learning.

The American Board of Medical Specialties, of which the American Board of Obstetrics and Gynecology is a member, released recommendations in 2019 reimagining specialty certification and highlighting the importance of individualized feedback and data-driven advances in clinical practice throughout the physicians' careers. In this article, we presented surgical coaching as an evidence-based strategy for achieving lifelong learning and practice improvement that can help to fulfill the vision of the American Board of Medical Specialties. Surgical coaching involves the development of a partnership between 2 surgeons in which 1 surgeon (the coach) guides the other (the participant) in identifying goals, providing feedback, and facilitating action planning. Previous literature has demonstrated that surgical coaching is viewed as valuable by both coaches and participants. In particular, video-based coaching involves reviewing recorded surgical cases and can be integrated into the physicians' busy schedules as a means of acquiring and advancing both technical and nontechnical skills. Establishing surgical coaching as an option for continuous learning and improvement in practice has the potential to elevate surgical performance and patient care.

Modeling Performance of Open Surgical Cases.

INTRODUCTION: Previous efforts used digital video to develop computer-generated assessments of surgical hand motion economy and fluidity of motion. This study tests how well previously trained assessment models match expert ratings of suturing and tying video clips recorded in a new operating room (OR) setting. METHODS: Enabled through computer vision of the hands, this study tests the applicability of assessments born out of benchtop simulations to in vivo suturing and tying tasks recorded in the OR. RESULTS: Compared with expert ratings, computer-generated assessments for fluidity of motion (slope = 0.83, intercept = 1.77, R2 = 0.55) performed better than motion economy (slope = 0.73, intercept = 2.04, R2 = 0.49), although 85% of ratings for both models were within ±2 of the expert response. Neither assessment performed as well in the OR as they did on the training data. Assessments were sensitive to changing hand postures, dropped ligatures, and poor tissue contact-features typically missing from training data. Computer-generated assessment of OR tasks was contingent on a clear, consistent view of both surgeon's hands. CONCLUSIONS: Computer-generated assessment may help provide formative feedback during deliberate practice, albeit with greater variability in the OR compared with benchtop simulations. Future work will benefit from expanded available bimanual video records.

Experiences of Gender Discrimination and Sexual Harassment Among Residents in General Surgery Programs Across the US.

Importance: Mistreatment is a common experience among surgical residents and is associated with burnout. Women have been found to experience mistreatment at higher rates than men. Further characterization of surgical residents' experiences with gender discrimination and sexual harassment may inform solutions. Objective: To describe the types, sources, and factors associated with (1) discrimination based on gender, gender identity, or sexual orientation and (2) sexual harassment experienced by residents in general surgery programs across the US. Design, Setting, and Participants: This cross-sectional national survey study was conducted after the 2019 American Board of Surgery In-Training Examination (ABSITE). The survey asked respondents about their experiences with gender discrimination and sexual harassment during the academic year starting July 1, 2018, through the testing date in January 2019. All clinical residents enrolled in general surgery programs accredited by the Accreditation Council for Graduate Medical Education were eligible. Exposures: Specific types, sources, and factors associated with gender-based discrimination and sexual harassment. Main Outcomes and Measures: Primary outcome was the prevalence of gender discrimination and sexual harassment. Secondary outcomes included sources of discrimination and harassment and associated individual- and program-level factors using gender-stratified multivariable logistic regression models. Results: The survey was administered to 8129 eligible residents; 6956 responded (85.6% response rate)from 301 general surgery programs. Of those, 6764 residents had gender data available (3968 [58.7%] were male and 2796 [41.3%] were female individuals). In total, 1878 of 2352 female residents (79.8%) vs 562 of 3288 male residents (17.1%) reported experiencing gender discrimination (P < .001), and 1026 of 2415 female residents (42.5%) vs 721 of 3360 male residents (21.5%) reported experiencing sexual harassment (P < .001). The most common type of gender discrimination was being mistaken for a nonphysician (1943 of 5640 residents [34.5%] overall; 1813 of 2352 female residents [77.1%]; 130 of 3288 male residents [4.0%]), with patients and/or families as the most frequent source. The most common form of sexual harassment was crude, demeaning, or explicit comments (1557 of 5775 residents [27.0%] overall; 901 of 2415 female residents [37.3%]; 656 of 3360 male residents [19.5%]); among female residents, the most common source of this harassment was patients and/or families, and among male residents, the most common source was coresidents and/or fellows. Among female residents, gender discrimination was associated with pregnancy (odds ratio [OR], 1.93; 95% CI, 1.03-3.62) and higher ABSITE scores (highest vs lowest quartile: OR, 1.67; 95% CI, 1.14-2.43); among male residents, gender discrimination was associated with parenthood (OR, 1.72; 95% CI, 1.31-2.27) and lower ABSITE scores (highest vs lowest quartile: OR, 0.57; 95% CI, 0.43-0.76). Senior residents were more likely to report experiencing sexual harassment than interns (postgraduate years 4 and 5 vs postgraduate year 1: OR, 1.77 [95% CI, 1.40-2.24] among female residents; 1.31 [95% CI, 1.01-1.70] among male residents). Conclusions and Relevance: In this study, gender discrimination and sexual harassment were common experiences among surgical residents and were frequently reported by women. These phenomena warrant multifaceted context-specific strategies for improvement.

National Evaluation of Surgical Resident Grit and the Association With Wellness Outcomes.

Importance: Grit, defined as perseverance and passion for long-term goals, is predictive of success and performance even among high-achieving individuals. Previous studies examining the effect of grit on attrition and wellness during surgical residency are limited by low response rates or single-institution analyses. Objectives: To characterize grit among US general surgery residents and examine the association between resident grit and wellness outcomes. Design, Setting, and Participants: A cross-sectional national survey study of 7464 clinically active general surgery residents in the US was administered in conjunction with the 2018 American Board of Surgery In-Training Examination and assessed grit, burnout, thoughts of attrition, and suicidal thoughts during the previous year. Multivariable logistic regression models were constructed to assess the association of grit with resident burnout, thoughts of attrition, and suicidal thoughts. Statistical analyses were performed from June 1 to August 15, 2019. Exposures: Grit was measured using the 8-item Short Grit Scale (scores range from 1 [not at all gritty] to 5 [extremely gritty]). Main Outcomes and Measures: The primary outcome was burnout. Secondary outcomes were thoughts of attrition and suicidal thoughts within the past year. Results: Among 7464 residents (7413 [99.3%] responded; 4469 men [60.2%]) from 262 general surgery residency programs, individual grit scores ranged from 1.13 to 5.00 points (mean [SD], 3.69 [0.58] points). Mean (SD) grit scores were significantly higher in women (3.72 [0.56] points), in residents in postgraduate training year 4 or 5 (3.72 [0.58] points), and in residents who were married (3.72 [0.57] points; all P ≤ .001), although the absolute magnitude of the differences was small. In adjusted analyses, residents with higher grit scores were significantly less likely to report duty hour violations (odds ratio [OR], 0.85; 95% CI, 0.77-0.93), dissatisfaction with becoming a surgeon (OR, 0.53; 95% CI, 0.48-0.59), burnout (OR, 0.53; 95% CI, 0.49-0.58), thoughts of attrition (OR, 0.61; 95% CI, 0.55-0.67), and suicidal thoughts (OR, 0.58; 95% CI, 0.47-0.71). Grit scores were not associated with American Board of Surgery In-Training Examination performance. For individual residency programs, mean program-level grit scores ranged from 3.18 to 4.09 points (mean [SD], 3.69 [0.13] points). Conclusions and Relevance: In this national survey evaluation, higher grit scores were associated with a lower likelihood of burnout, thoughts of attrition, and suicidal thoughts among general surgery residents. Given that surgical resident grit scores are generally high and much remains unknown about how to employ grit measurement, grit is likely not an effective screening instrument to select residents; instead, institutions should ensure an organizational culture that promotes and supports trainees across this elevated range of grit scores.

Rates of Ipsilateral Local-regional Recurrence in High-risk Patients Undergoing Immediate Post-mastectomy Reconstruction (AFT-01).

BACKGROUND: Some surgeons remain hesitant to perform immediate breast reconstruction (IBR) in patients with higher risk cancers owing to concerns about cancer recurrence and/or detection. Our objective was to determine the rate of ipsilateral local-regional recurrence for stage II/III patients who underwent IBR. METHODS: The National Cancer Database special study mechanism was used to create a stratified sample of women diagnosed with stage II/III breast cancer from 1217 facilities. Demographic, tumor, and recurrence data for women who underwent mastectomy with or without IBR were abstracted, including location of recurrence and method of detection. Estimates of 5-year local-regional recurrence rates were calculated and factors associated with recurrence were identified with multivariable Cox regression. RESULTS: Some 13% (692/5318) of stage II/III patients underwent IBR after mastectomy. Patients undergoing IBR were younger (P < .001), with fewer comorbid conditions (P < .001), and with lower tumor burden in the breast (P = .001) and the lymph nodes (P = 0.01). The 5-year rate of ipsilateral local-regional recurrence was 3.6% with no significant difference between patients with or without IBR (3.0% vs. 3.7%, P = .4). Most recurrences were detected by the patient (45%) or on physician examination (24%). Reconstruction was not associated with recurrence on multivariable analysis (hazard ratio = 0.83, P = .52). CONCLUSION: Women with stage II/III breast cancer selected for IBR had similar rates of ipsilateral local-regional recurrence compared with those undergoing mastectomy alone. Offering IBR after mastectomy in a patient-centered manner to select patients with stage II/III breast cancer is an acceptable consideration.