How to Establish Benchmarks for Surgical Outcomes?: A Checklist Based on an International Expert Delphi Consensus

Recommendations on Robotic Hepato-Pancreato-Biliary Surgery. The Paris Jury-Based Consensus Conference

OBJECTIVE

To establish the first consensus guidelines on the safety and indications of robotics in Hepato-Pancreatic-Biliary (HPB) surgery. The secondary aim was to identify priorities for future research.

BACKGROUND

HPB robotic surgery is reaching the IDEAL 2b exploration phase for innovative technology. An objective assessment endorsed by the HPB community is timely and needed.

METHODS

The ROBOT4HPB conference developed consensus guidelines using the Zurich-Danish model. An impartial and multidisciplinary jury produced unbiased guidelines based on the work of 10 expert panels answering predefined key questions and considering the best-quality evidence retrieved after a systematic review. The recommendations conformed with the GRADE and SIGN50 methodologies.

RESULTS

Sixty-four experts from 20 countries considered 285 studies, and the conference included an audience of 220 attendees. The jury (n=10) produced recommendations or statements covering 5 sections of robotic HPB surgery: technology, training and expertise, outcome assessment, and liver and pancreatic procedures. The recommendations supported the feasibility of robotics for most HPB procedures and its potential value in extending minimally invasive indications, emphasizing, however, the importance of expertise to ensure safety. The concept of expertise was defined broadly, encompassing requirements for credentialing HPB robotics at a given center. The jury prioritized relevant questions for future trials and emphasized the need for prospective registries, including validated outcome metrics for the forthcoming assessment of HPB robotics.

CONCLUSIONS

The ROBOT4HPB consensus represents a collaborative and multidisciplinary initiative, defining state-of-the-art expertise in HPB robotics procedures. It produced the first guidelines to encourage their safe use and promotion.

From Data Integration to Precision Medicine: A Value-Based Healthcare Approach for Sarcoma Care

The transformation of healthcare from a fee-for-service model to value-based care is particularly crucial in managing complex and rare diseases like sarcoma, where data fragmentation and variability present significant challenges. This manuscript reviews strategies for structured and harmonized data integration-a critical precursor to precision medicine in sarcoma care. We demonstrate how standardizing data formats, ontologies, and coding systems enable seamless integration of clinical, economic, and patient-reported outcomes across institutions, paving the way for comprehensive predictive analytics. By establishing robust value-based healthcare (VBHC) frameworks through digital transformation and predictive models, including digital twins, we create the foundation for personalized sarcoma treatment and real-world-time clinical decision-making. The manuscript also addresses practical challenges, including the need for system standardization, overcoming regulatory and privacy concerns, and managing high costs. We propose actionable strategies to overcome these barriers and discuss the role of advanced analytics and future research directions that further enhance VBHC and precision medicine. This work outlines the necessary steps to build a cohesive, data-driven approach that supports the transition to precision medicine, fundamentally improving outcomes for sarcoma patients.

Benchmark Outcomes for Distal Pancreatectomy: A Multicenter Prospective Snapshot Study from the Spanish Distal Pancreatectomy Project (SPANDISPAN)

BACKGROUND

Improving the quality of care is a priority for health systems to obtain better care and reduce costs. One of the tools for measuring quality is benchmarking (BM). We presented a 1-country prospective study of distal pancreatectomies (DPs) and determined BM.

STUDY DESIGN

Prospective, multicenter, observational snapshot study of DP carried out at Spanish hepatopancreatobiliary centers for a year (February 1, 2022, to January 31, 2023). Hepatopancreatobiliary centers were defined as high volume if they performed more than 10 DPs per year. Inclusion criteria include any scheduled DP for any diagnosis and age older than 18 years. The low-risk group was defined following the criteria given by Durin and colleagues and major complications as Clavien-Dindo ≥III.

RESULTS

A total of 313 patients from 42 centers and 46.6% from high-volume centers were included. Median DP by center was 7 (interquartile range 5 to 10), median age was 65 years (interquartile range 55 to 74), and 53.4% were female. The surgical approach was minimally invasive in 69.3%. Major complications were 21.1%. Postoperative pancreatic fistula grade B/C rate was 20.1%, and 90-day mortality was 1.6%. One hundred forty-three patients were in low-risk group (43.8%). Compared with previous BM data, an increasing MIS rate and fewer hospital stay were obtained.

CONCLUSIONS

We present the first determination of DP-BM in a prospective series, obtaining similar results to the previous ones, but our BM values include a shorter hospital stay and a higher percentage of minimally invasive surgery probably related to Enhanced Recovery after Surgery protocols and prospective data collection. BM is a multiparameter valuable tool for reporting outcomes, comparing centers, and identifying the points to improve surgical care.

Impact of Back-to-Base Normothermic Machine Perfusion on Complications and Costs: A Multicenter, Real-World Risk-Matched Analysis

OBJECTIVE

Assess cost and complication outcomes after liver transplantation (LT) using normothermic machine perfusion (NMP).

BACKGROUND

End-ischemic NMP is often used to aid logistics, yet its impact on outcomes after LT remains unclear, as does its true impact on costs associated with transplantation.

METHODS

Deceased donor liver recipients at 2 centers (January 1, 2019, to June 30, 2023) were included. Retransplants, splits, and combined grafts were excluded. End-ischemic NMP (OrganOx-Metra) was implemented in October 2022 for extended-criteria donation after brain death (DBDs), all donations after circulatory deaths (DCDs), and logistics. NMP cases were matched 1:2 with static cold storage controls (SCS) using the Balance-of-Risk [donation after brain death (DBD)-grafts] and UK-DCD Score (DCD-grafts).

RESULTS

Overall, 803 transplantations were included, 174 (21.7%) receiving NMP. Matching was achieved between 118 NMP-DBDs with 236 SCS; and 37 NMP-DCD with 74 corresponding SCS. For both graft types, median inpatient comprehensive complications index values were comparable between groups. DCD-NMP grafts experienced reduced cumulative 90-day comprehensive complications index (27.6 vs 41.9, P =0.028). NMP also reduced the need for early relaparotomy and renal replacement therapy, with subsequently less frequent major complications (Clavien-Dindo ≥IVa). This effect was more pronounced in DCD transplants. NMP had no protective effect on early biliary complications. Organ acquisition/preservation costs were higher with NMP, yet NMP-treated grafts had lower 90-day pretransplant costs in the context of shorter waiting list times. Overall costs were comparable for both cohorts.

CONCLUSIONS

This is the first risk-adjusted outcome and cost analysis comparing NMP and SCS. In addition to logistical benefits, NMP was associated with a reduction in relaparotomy and bleeding in DBD grafts, and overall complications and post-LT renal replacement for DCDs. While organ acquisition/preservation was more costly with NMP, overall 90-day health care costs-per-transplantation were comparable.

REDISCOVER International Guidelines on the Perioperative Care of Surgical Patients With Borderline-resectable and Locally Advanced Pancreatic Cancer

OBJECTIVE

The REDISCOVER consensus conference aimed at developing and validating guidelines on the perioperative care of patients with borderline-resectable (BR-) and locally advanced (LA) pancreatic ductal adenocarcinoma (PDAC).

BACKGROUND

Coupled with improvements in chemotherapy and radiation, the contemporary approach to pancreatic surgery supports the resection of BR-PDAC and, to a lesser extent, LA-PDAC. Guidelines outlining the selection and perioperative care for these patients are lacking.

METHODS

The Scottish Intercollegiate Guidelines Network (SIGN) methodology was used to develop the REDISCOVER guidelines and create recommendations. The Delphi approach was used to reach a consensus (agreement ≥80%) among experts. Recommendations were approved after a debate and vote among international experts in pancreatic surgery and pancreatic cancer management. A Validation Committee used the AGREE II-GRS tool to assess the methodological quality of the guidelines. Moreover, an independent multidisciplinary advisory group revised the statements to ensure adherence to nonsurgical guidelines.

RESULTS

Overall, 34 recommendations were created targeting centralization, training, staging, patient selection for surgery, possibility of surgery in uncommon scenarios, timing of surgery, avoidance of vascular reconstruction, details of vascular resection/reconstruction, arterial divestment, frozen section histology of perivascular tissue, extent of lymphadenectomy, anticoagulation prophylaxis, and role of minimally invasive surgery. The level of evidence was however low for 29 of 34 clinical questions. Participants agreed that the most conducive means to promptly advance our understanding in this field is to establish an international registry addressing this patient population ( https://rediscover.unipi.it/ ).

CONCLUSIONS

The REDISCOVER guidelines provide clinical recommendations pertaining to pancreatectomy with vascular resection for patients with BR-PDAC and LA-PDAC, and serve as the basis of a new international registry for this patient population.

A Multi-institutional Analysis of a Textbook Outcome Among Patients Undergoing Microvascular Breast Reconstruction

BACKGROUND

Individual outcomes may not accurately reflect the quality of perioperative care. Textbook outcomes (TOs) are composite metrics that provide a comprehensive evaluation of hospital performance and surgical quality. This study aimed to investigate the prevalence and predictors of TOs in a multi-institutional cohort of patients who underwent breast reconstruction with deep inferior epigastric artery perforator flaps.

METHODS

For autologous reconstruction, a TO was previously defined as a procedure without intraoperative complications, reoperation, infection requiring intravenous antibiotics, readmission, mortality, systemic complications, operative duration ≤12 hours for bilateral and ≤10 hours for unilateral/stacked reconstruction, and length of stay (LOS) ≤5 days. We investigated associations between patient-level factors and achieving a TO using multivariable regression analysis.

RESULTS

Of 1000 patients, most (73.2%) met a TO. The most common reasons for deviation from a TO were reoperation (9.6%), prolonged operative time (9.5%), and prolonged LOS (9.2%). On univariate analysis, tobacco use, obesity, widowed/divorced marital status, and contralateral prophylactic mastectomy or bilateral reconstruction were associated with a lower likelihood of TOs (P < 0.05). After adjustment, bilateral prophylactic mastectomy (odds ratio [OR], 5.71; P = 0.029) and hormonal therapy (OR, 1.53; P = 0.050) were associated with a higher likelihood of TOs; higher body mass index (OR, 0.91; P = <0.001) was associated with a lower likelihood.

CONCLUSION

Approximately 30% of patients did not achieve a TO, and the likelihood of achieving a TO was influenced by patient and procedural factors. Future studies should investigate how this metric may be used to evaluate patient and hospital-level performance to improve the quality of care in reconstructive surgery.

Current and future applications of artificial intelligence in surgery: implications for clinical practice and research

Surgeons are skilled at making complex decisions over invasive procedures that can save lives and alleviate pain and avoid complications in patients. The knowledge to make these decisions is accumulated over years of schooling and practice. Their experience is in turn shared with others, also via peer-reviewed articles, which get published in larger and larger amounts every year. In this work, we review the literature related to the use of Artificial Intelligence (AI) in surgery. We focus on what is currently available and what is likely to come in the near future in both clinical care and research. We show that AI has the potential to be a key tool to elevate the effectiveness of training and decision-making in surgery and the discovery of relevant and valid scientific knowledge in the surgical domain. We also address concerns about AI technology, including the inability for users to interpret algorithms as well as incorrect predictions. A better understanding of AI will allow surgeons to use new tools wisely for the benefit of their patients.

Benchmarks in Liver Resection for Intrahepatic Cholangiocarcinoma

INTRODUCTION

Benchmarking in surgery has been proposed as a means to compare results across institutions to establish best practices. We sought to define benchmark values for hepatectomy for intrahepatic cholangiocarcinoma (ICC) across an international population.

METHODS

Patients who underwent liver resection for ICC between 1990 and 2020 were identified from an international database, including 14 Eastern and Western institutions. Patients operated on at high-volume centers who had no preoperative jaundice, ASA class <3, body mass index <35 km/m2, without need for bile duct or vascular resection were chosen as the benchmark group.

RESULTS

Among 1193 patients who underwent curative-intent hepatectomy for ICC, 600 (50.3%) were included in the benchmark group. Among benchmark patients, median age was 58.0 years (interquartile range [IQR] 49.0-67.0), only 28 (4.7%) patients received neoadjuvant therapy, and most patients had a minor resection (n = 499, 83.2%). Benchmark values included ≥3 lymph nodes retrieved when lymphadenectomy was performed, blood loss ≤600 mL, perioperative blood transfusion rate ≤42.9%, and operative time ≤339 min. The postoperative benchmark values included TOO achievement ≥59.3%, positive resection margin ≤27.5%, 30-day readmission ≤3.6%, Clavien-Dindo III or more complications ≤14.3%, and 90-day mortality ≤4.8%, as well as hospital stay ≤14 days.

CONCLUSIONS

Benchmark cutoffs targeting short-term perioperative outcomes can help to facilitate comparisons across hospitals performing liver resection for ICC, assess inter-institutional variation, and identify the highest-performing centers to improve surgical and oncologic outcomes.

Defining benchmark outcomes for mesial temporal lobe epilepsy surgery: A global multicenter analysis of 1119 cases

OBJECTIVE

Benchmarking has been proposed to reflect surgical quality and represents the highest standard reference values for desirable results. We sought to determine benchmark outcomes in patients after surgery for drug-resistant mesial temporal lobe epilepsy (MTLE).

METHODS

This retrospective multicenter study included patients who underwent MTLE surgery at 19 expert centers on five continents. Benchmarks were defined for 15 endpoints covering surgery and epilepsy outcome at discharge, 1 year after surgery, and the last available follow-up. Patients were risk-stratified by applying outcome-relevant comorbidities, and benchmarks were calculated for low-risk ("benchmark") cases. Respective measures were derived from the median value at each center, and the 75th percentile was considered the benchmark cutoff.

RESULTS

A total of 1119 patients with a mean age (range) of 36.7 (1-74) years and a male-to-female ratio of 1:1.1 were included. Most patients (59.2%) underwent anterior temporal lobe resection with amygdalohippocampectomy. The overall rate of complications or neurological deficits was 14.4%, with no in-hospital death. After risk stratification, 377 (33.7%) benchmark cases of 1119 patients were identified, representing 13.6%-72.9% of cases per center and leaving 742 patients in the high-risk cohort. Benchmark cutoffs for any complication, clinically apparent stroke, and reoperation rate at discharge were ≤24.6%, ≤.5%, and ≤3.9%, respectively. A favorable seizure outcome (defined as International League Against Epilepsy class I and II) was reached in 83.6% at 1 year and 79.0% at the last follow-up in benchmark cases, leading to benchmark cutoffs of ≥75.2% (1-year follow-up) and ≥69.5% (mean follow-up of 39.0 months).

SIGNIFICANCE

This study presents internationally applicable benchmark outcomes for the efficacy and safety of MTLE surgery. It may allow for comparison between centers, patient registries, and novel surgical and interventional techniques.

Design and validation of a decision support checklist for efficient resource allocation in research projects during proposal preparation

PURPOSE

This article presents the design and validation of evaluation criteria checklist aimed at facilitating decision-making processes regarding participation in research projects and allocation of resources before the preparation of research proposals.

MATERIALS AND METHODS

A multidisciplinary team developed a comprehensive evaluation focusing on the proposal preparation phase of research projects. A Delphi survey method was used to establish a connection between the relevance of the project and the possible success of research proposals. Assessment criteria were agreed upon, each assigned specific weights. The results of the survey were applied to a database of 62 proposals for which our research group sought funding during 2020-2021. The method was validated using the funding body's outcomes (approval or rejection) of the submitted proposals as the ground truth per project type (national, European and regional).

RESULTS

The results of the survey generated a checklist of 8 criteria (excellence, impact, and efficiency aspects) that effectively assess the possibility of success of research proposals during the preparatory phase. For national projects, the tool validation demonstrated a sensitivity of 100% and a specificity of 76.19%; European projects exhibited a sensitivity of 100% and a specificity of 53.84%; and regional projects showed a sensitivity of 80% and a specificity of 30%.

CONCLUSIONS

By establishing an agreed set of evaluation criteria, the developed comprehensive index enables a more precise decision support tool for the participation in research proposals and the allocation of necessary resources. This control system saves valuable time and effort for research groups while enhancing the overall efficiency of available resources.

Global Outcomes for Microsurgical Clipping of Unruptured Intracranial Aneurysms: A Benchmark Analysis of 2245 Cases

BACKGROUND AND OBJECTIVES

Benchmarks represent the best possible outcome and help to improve outcomes for surgical procedures. However, global thresholds mirroring an optimal and reachable outcome for microsurgical clipping of unruptured intracranial aneurysms (UIA) are not available. This study aimed to define standardized outcome benchmarks in patients who underwent clipping of UIA.

METHODS

A total of 2245 microsurgically treated UIA from 15 centers were analyzed. Patients were categorized into low- ("benchmark") and high-risk ("nonbenchmark") patients based on known factors affecting outcome. The benchmark was defined as the 75th percentile of all centers' median scores for a given outcome. Benchmark outcomes included intraoperative (eg, duration of surgery, blood transfusion), postoperative (eg, reoperation, neurological status), and aneurysm-related factors (eg, aneurysm occlusion). Benchmark cutoffs for aneurysms of the anterior communicating/anterior cerebral artery, middle cerebral artery, and posterior communicating artery were determined separately.

RESULTS

Of the 2245 cases, 852 (37.9%) patients formed the benchmark cohort. Most operations were performed for middle cerebral artery aneurysms (53.6%), followed by anterior communicating and anterior cerebral artery aneurysms (25.2%). Based on the results of the benchmark cohort, the following benchmark cutoffs were established: favorable neurological outcome (modified Rankin scale ≤2) ≥95.9%, postoperative complication rate ≤20.7%, length of postoperative stay ≤7.7 days, asymptomatic stroke ≤3.6%, surgical site infection ≤2.7%, cerebral vasospasm ≤2.5%, new motor deficit ≤5.9%, aneurysm closure rate ≥97.1%, and at 1-year follow-up: aneurysm closure rate ≥98.0%. At 24 months, benchmark patients had a better score on the modified Rankin scale than nonbenchmark patients.

CONCLUSION

This study presents internationally applicable benchmarks for clinically relevant outcomes after microsurgical clipping of UIA. These benchmark cutoffs can serve as reference values for other centers, patient registries, and for comparing the benefit of other interventions or novel surgical techniques.

An attempt to establish and apply global benchmarks for liver resection of malignant hepatic tumors

BACKGROUND

Benchmarking is a process of continuous self-evaluation and comparison with best-in-class hospitals to guide quality improvement initiatives. We sought to define global benchmarks relative to liver resection for malignancy and to assess their achievement in hospitals in the United States.

METHODS

Patients who underwent curative-intent liver resection for hepatocellular carcinoma, intrahepatic cholangiocarcinoma, or colorectal or neuroendocrine liver metastases between 2000 and 2019 were identified from an international multi-institutional database. Propensity score matching was conducted to balance baseline characteristics between open and minimally invasive approaches. Best-in-class hospitals were defined relative to the achievement rate of textbook oncologic outcomes and case volume. Benchmark values were established relative to best-in-class institutions. The achievement of benchmark values among hospitals in the National Cancer Database was then assessed.

RESULTS

Among 2,624 patients treated at 20 centers, a majority underwent liver resection for hepatocellular carcinoma (n = 1,609, 61.3%), followed by colorectal liver metastases (n = 650, 24.8%), intrahepatic cholangiocarcinoma (n = 299, 11.4%), and neuroendocrine liver metastases (n = 66, 2.5%). Notably, 1,947 (74.2%) patients achieved a textbook oncologic outcome. After propensity score matching, 6 best-in-class hospitals with the highest textbook oncologic outcome rates (≥75.0%) were identified. Benchmark values were calculated for margin positivity (≤11.7%), 30-day readmission (≤4.1%), 30-day mortality (≤1.6%), minor postoperative complications (≤24.7%), severe complications (≤12.4%), and failure to achieve the textbook oncologic outcome (≤22.8%). Among the National Cancer Database hospitals, global benchmarks for margin positivity, 30-day readmission, 30-day mortality, severe complications, and textbook oncologic outcome failure were achieved in 62.9%, 27.1%, 12.1%, 7.1%, and 29.3% of centers, respectively.

CONCLUSION

These global benchmarks may help identify hospitals that may benefit from quality improvement initiatives, aiming to improve patient safety and surgical oncologic outcomes.

Novel Benchmark Values for Open Major Anatomic Liver Resection in Non-cirrhotic Patients: A Multicentric Study of 44 International Expert Centers

OBJECTIVE

This study aims at establishing benchmark values for best achievable outcomes following open major anatomic hepatectomy for liver tumors of all dignities.

BACKGROUND

Outcomes after open major hepatectomies vary widely lacking reference values for comparisons among centers, indications, types of resections, and minimally invasive procedures.

METHODS

A standard benchmark methodology was used covering consecutive patients, who underwent open major anatomic hepatectomy from 44 high-volume liver centers from 5 continents over a 5-year period (2016-2020). Benchmark cases were low-risk non-cirrhotic patients without significant comorbidities treated in high-volume centers (≥30 major liver resections/year). Benchmark values were set at the 75th percentile of median values of all centers. Minimum follow-up period was 1 year in each patient.

RESULTS

Of 8044 patients, 2908 (36%) qualified as benchmark (low-risk) cases. Benchmark cutoffs for all indications include R0 resection ≥78%; liver failure (grade B/C) ≤10%; bile leak (grade B/C) ≤18%; complications ≥grade 3 and CCI ® ≤46% and ≤9 at 3 months, respectively. Benchmark values differed significantly between malignant and benign conditions so that reference values must be adjusted accordingly. Extended right hepatectomy (H1, 4-8 or H4-8) disclosed a higher cutoff for liver failure, while extended left (H1-5,8 or H2-5,8) were associated with higher cutoffs for bile leaks, but had superior oncologic outcomes, when compared to formal left hepatectomy (H1-4 or H2-4). The minimal follow-up for a conclusive outcome evaluation following open anatomic major resection must be 3 months.

CONCLUSION

These new benchmark cutoffs for open major hepatectomy provide a powerful tool to convincingly evaluate other approaches including parenchymal-sparing procedures, laparoscopic/robotic approaches, and alternative treatments, such as ablation therapy, irradiation, or novel chemotherapy regimens.

Novel Benchmark for Adult-to-Adult Living-donor Liver Transplantation: Integrating Eastern and Western Experiences

OBJECTIVE

To define benchmark values for adult-to-adult living-donor liver transplantation (LDLT).

BACKGROUND

LDLT utilizes living-donor hemiliver grafts to expand the donor pool and reduce waitlist mortality. Although references have been established for donor hepatectomy, no such information exists for recipients to enable conclusive quality and comparative assessments.

METHODS

Patients undergoing LDLT were analyzed in 15 high-volume centers (≥10 cases/year) from 3 continents over 5 years (2016-2020), with a minimum follow-up of 1 year. Benchmark criteria included a Model for End-stage Liver Disease ≤20, no portal vein thrombosis, no previous major abdominal surgery, no renal replacement therapy, no acute liver failure, and no intensive care unit admission. Benchmark cutoffs were derived from the 75th percentile of all centers' medians.

RESULTS

Of 3636 patients, 1864 (51%) qualified as benchmark cases. Benchmark cutoffs, including posttransplant dialysis (≤4%), primary nonfunction (≤0.9%), nonanastomotic strictures (≤0.2%), graft loss (≤7.7%), and redo-liver transplantation (LT) (≤3.6%), at 1-year were below the deceased donor LT benchmarks. Bile leak (≤12.4%), hepatic artery thrombosis (≤5.1%), and Comprehensive Complication Index (CCI ® ) (≤56) were above the deceased donor LT benchmarks, whereas mortality (≤9.1%) was comparable. The right hemiliver graft, compared with the left, was associated with a lower CCI ® score (34 vs 21, P < 0.001). Preservation of the middle hepatic vein with the right hemiliver graft had no impact neither on the recipient nor on the donor outcome. Asian centers outperformed other centers with CCI ® score (21 vs 47, P < 0.001), graft loss (3.0% vs 6.5%, P = 0.002), and redo-LT rates (1.0% vs 2.5%, P = 0.029). In contrast, non-benchmark low-volume centers displayed inferior outcomes, such as bile leak (15.2%), hepatic artery thrombosis (15.2%), or redo-LT (6.5%).

CONCLUSIONS

Benchmark LDLT offers a valuable alternative to reduce waitlist mortality. Exchange of expertise, public awareness, and centralization policy are, however, mandatory to achieve benchmark outcomes worldwide.

Quality and Outcome Assessment for Surgery

ABSTRACT

This forum summarizes the proceedings of the joint European Surgical Association (ESA)/American Surgical Association (ASA) symposium on Quality and Outcome Assessment for Surgery that took place in Bordeaux, France, as part of the celebrations of the 30th anniversary of the ESA. Three presentations focused on a) the main messages from the Outcome4Medicine Consensus Conference, which took place in Zurich, Switzerland, in June 2022, b) the patient perspective, and c) benchmarking were hold by ESA members and discussed by ASA members in a symposium attended by members of both associations.

Unlocking the Power of Benchmarking: Real-World-Time Data Analysis for Enhanced Sarcoma Patient Outcomes

Benchmarking is crucial for healthcare providers to enhance quality and efficiency, notably for complex conditions like sarcomas. Multidisciplinary teams/sarcoma boards (MDT/SBs) are vital in sarcoma management, but differences in their processes can affect patient outcomes and treatment costs, despite adherence to international guidelines. To address this issue, this study aimed to compare two MDT/SBs and establish an interoperable digital platform, Sarconnector®, for real-time-world data assessment and automated analysis. The study included 983 patients, 46.0% of whom female, with a median age of 58 years, and 4.5% of patients presented with metastasis at diagnosis. Differences were observed in the number of first-time presentations, follow-up presentations, primary sarcomas, biopsies and chemotherapy indications between the two MDT/SB. The results highlight the importance of benchmarking and utilizing a harmonized data approach, such as the RWT approach provided by the Sarconnector®, to standardize and evaluate quality and cost metrics. By identifying areas of improvement and making data-driven decisions on the meta-level, healthcare providers can optimize resources and improve patient outcomes. In conclusion, benchmarking with the RWT harmonized data approach provided by the Sarconnector® can help healthcare providers improve the overall effectiveness of the healthcare system and achieve better outcomes for their patients in terms of both outcomes and costs.

Defining benchmark outcomes for transsphenoidal surgery of pituitary adenomas: a multicenter analysis

IMPORTANCE

Benchmarks aid in improve outcomes for surgical procedures. However, best achievable results that have been validated internationally for transsphenoidal surgery (TS) are not available.

OBJECTIVE

We aimed to establish standardized outcome benchmarks for TS of pituitary adenomas.

DESIGN

A total of 2685 transsphenoidal tumor resections from 9 expert centers in 3 continents were analyzed.

SETTING

Patients were risk stratified, and the median values of each center's outcomes were established. The benchmark was defined as the 75th percentile of all median values for a particular outcome. The postoperative benchmark outcomes included surgical factors, endocrinology-specific values, and neurology-specific values.

RESULTS

Of 2685 patients, 1149 (42.8%) defined the low-risk benchmark cohort. Within these benchmark cases, 831 (72.3%) patients underwent microscopic TS, and 308 (26.8%) patients underwent endoscopic endonasal resection. Of all tumors, 799 (29.8%) cases invaded the cavernous sinus. The postoperative complication rate was 19.6% with mortality between 0.0% and 0.8%. Benchmark cutoffs were ≤2.9% for reoperation rate, ≤1.9% for cerebrospinal fluid leak requiring intervention, and ≤15.5% for transient diabetes insipidus. At 6 months, benchmark cutoffs were calculated as follows: readmission rate: ≤6.9%, new hypopituitarism ≤6.0%, and tumor remnant ≤19.2%.

CONCLUSIONS

This analysis defines benchmark values for TS targeting morbidity and mortality and represents the best outcomes in the best patients in expert centers. These cutoffs can be used to assess different centers, patient populations, and novel surgical techniques. It should be noted that the benchmark values may influence each other and must be evaluated in their own context.

Defining Benchmark Outcomes for Distal Pancreatectomy: Results of a French Multicentric Study

OBJECTIVE

Defining robust and standardized outcome references for distal pancreatectomy (DP) by using Benchmark analysis.

BACKGROUND

Outcomes after DP are recorded in medium or small-sized studies without standardized analysis. Therefore, the best results remain uncertain.

METHODS

This multicenter study included all patients undergoing DP for resectable benign or malignant tumors in 21 French expert centers in pancreas surgery from 2014 to 2018. A low-risk cohort defined by no significant comorbidities was analyzed to establish 18 outcome benchmarks for DP. These values were tested in high risk, minimally invasive and benign tumor cohorts.

RESULTS

A total of 1188 patients were identified and 749 low-risk patients were screened to establish Benchmark cut-offs. Therefore, Benchmark rate for mini-invasive approach was ≥36.8%. Benchmark cut-offs for postoperative mortality, major morbidity grade ≥3a and clinically significant pancreatic fistula rates were 0%, ≤27%, and ≤28%, respectively. The benchmark rate for readmission was ≤16%. For patients with pancreatic adenocarcinoma, cut-offs were ≥75%, ≥69.5%, and ≥66% for free resection margins (R0), 1-year disease-free survival and 3-year overall survival, respectively. The rate of mini-invasive approach in high-risk cohort was lower than the Benchmark cut-off (34.1% vs ≥36.8%). All Benchmark cut-offs were respected for benign tumor group. The proportion of benchmark cases was correlated to outcomes of DP. Centers with a majority of low-risk patients had worse results than those operating complex cases.

CONCLUSION

This large-scale study is the first benchmark analysis of DP outcomes and provides robust and standardized data. This may allow for comparisons between surgeons, centers, studies, and surgical techniques.

Benchmarking outcomes for distal pancreatectomy: critical evaluation of four multicenter studies

BACKGROUND

Benchmarking is a validated tool for outcome assessment and international comparison of best achievable surgical outcomes. The methodology is increasingly applied in pancreatic surgery and the aim of the review was to critically compare available benchmark studies evaluating distal pancreatectomy (DP).

METHODS

A literature search of English articles reporting on benchmarking DP was conducted of the electronic databases MEDLINE and Web of Science (until April 2023). Studies on open (ODP), laparoscopic (LDP), and robotic DP (RDP) were included.

RESULTS

Four retrospective multicenter studies were included. Studies reported on outcomes of minimally invasive DP only (n = 2), ODP and LDP (n = 1), and RDP only (n = 1). Either the Achievable Benchmark of Care™ method or the 75th percentile from the median was selected to define benchmark cutoffs. Robust and reproducible benchmark values were provided by the four studies for intra- and postoperative short-term outcomes.

CONCLUSION

Benchmarking DP is a valuable tool for obtaining internationally accepted reference outcomes for open and minimally invasive DP approaches with only minor variances in four international cohorts. Benchmark cutoffs allow for outcome comparisons between institutions, surgeons, and to monitor the introduction of novel minimally invasive DP techniques.

Classification of Adverse Events in Adult Surgery

Successful surgery combines quality (achievement of a positive outcome) with safety (avoidance of a negative outcome). Outcome assessment serves the purpose of quality improvement in health care by establishing performance indicators and allowing the identification of performance gaps. Novel surgical quality metric tools (benchmark cutoffs and textbook outcomes) provide procedure-specific ideal surgical outcomes in a subgroup of well-defined low-risk patients, with the aim of setting realistic and best achievable goals for surgeons and centers, as well as supporting unbiased comparison of surgical quality between centers and periods of time. Validated classification systems have been deployed to grade adverse events during the surgical journey: (1) the ClassIntra classification for the intraoperative period; (2) the Clavien-Dindo classification for the gravity of single adverse events; and the (3) Comprehensive Complication Index (CCI) for the sum of adverse events over a defined postoperative period. The failure to rescue rate refers to the death of a patient following one or more potentially treatable postoperative adverse event(s) and is a reliable proxy of the institutional safety culture and infrastructure. Complication assessment is undergoing digital transformation to decrease resource-intensity and provide surgeons with real-time pre- or intraoperative decision support. Standardized reporting of complications informs patients on their chances to realize favorable postoperative outcomes and assists surgical centers in the prioritization of quality improvement initiatives, multidisciplinary teamwork, surgical education, and ultimately, in the enhancement of clinical standards.

Consensus recommendations on how to assess the quality of surgical interventions

Postoperative complications represent a major public health burden worldwide. Without standardized, clinically relevant and universally applied endpoints, the evaluation of surgical interventions remains ill-defined and inconsistent, opening the door for biased interpretations and hampering patient-centered health care delivery. We conducted a Jury-based consensus conference incorporating the perspectives of different stakeholders, who based their recommendations on the work of nine panels of experts. The recommendations cover the selection of postoperative outcomes from the perspective of patients and other stakeholders, comparison and interpretation of outcomes, consideration of cultural and demographic factors, and strategies to deal with unwarranted outcomes. With the recommendations developed exclusively by the Jury, we provide a framework for surgical outcome assessment and quality improvement after medical interventions, that integrates the main stakeholders' perspectives.

Benchmarking: a novel measuring tool for outcome comparisons in surgery

INTRODUCTION

Benchmarking, a novel measuring tool for outcome comparisons, is a recent concept in surgery. The objectives of this review are to examine the concept, definition, and evolution of benchmarking and its application in surgery.

METHODS

The literature about benchmarking was reviewed through an ever-narrowing search strategy, commencing from the concept, definition, and evolution of benchmarking to the application of benchmarking and experiences of benchmarking in surgery. PubMed, Web of Science, Embase, and Science Direct databases were searched until 20 September 2022, in the English language according to the PRISMA (Preferred Reporting Items for Systematic reviews and Meta-Analyses) guidelines.

RESULTS

In the first phase of the literature search, the development of benchmarking was identified. The definitions of benchmarking evolved from a surveying term to a novel quality-improvement tool to assess the best achievable results in surgery. In the second phase, a total of 23 studies were identified about benchmarking in surgery, including esophagectomy, hepatic surgery, pancreatic surgery, rectum resection, and bariatric surgery. All studies were multicenter analyses from national, international, or global expert centers. Most studies (87.0%) adopted the definition that benchmark was the 75th percentile of the median values of centers. Performance metrics to define benchmarks were clinically relevant intraoperative and postoperative outcome indicators.

CONCLUSION

Benchmarking in surgery is a novel quality-improvement tool to define and measure the best achievable results, establishing a meaningful reference to evaluate surgical performance.

Textbook outcomes in DIEP flap breast reconstruction: a Delphi study to establish consensus

PURPOSE

Composite measures, like textbook outcomes, may be superior to individual metrics when assessing hospital performance and quality of care. This study utilized a Delphi process to define a textbook outcome in DIEP flap breast reconstruction.

METHODS

A two-round Delphi survey defined: (1) A textbook outcome, (2) Exclusion criteria for a study population, and (3) Respondent opinion regarding textbook outcomes. An a priori threshold of ≥ 70% agreement among respondents established consensus among the tested statements.

RESULTS

Out of 85 invitees, 48 responded in the first round and 41 in the second. A textbook outcome was defined as one that meets the following within 90 days: (1) No intraoperative complications, (2) Operative duration ≤ 12 h for bilateral and ≤ 10 h for unilateral/stacked reconstruction, (3) No post-surgical complications requiring re-operation, (4) No surgical site infection requiring IV antibiotics, (5) No readmission, (6) No mortality, (7) No systemic complications, and (8) Length of stay < 5 days. Exclusion criteria for medical and surgical characteristics (e.g., BMI > 40, HgbA1c > 7) and case-volume cut-offs for providers (≥ 21) and institutions (≥ 44) were defined. Most agreed that textbook outcomes should be defined for complex plastic surgery procedures (75%) and utilized to gauge hospital performance for microsurgical breast reconstruction (77%).

CONCLUSION

This Delphi study identified (1) Key elements of a textbook outcome for DIEP flap breast reconstruction, (2) Exclusion criteria for future studies, and (3) Characterized surgeon opinions regarding the utility of textbook outcomes in serving as quality metric for breast reconstruction care.

The Benefits of Benchmarking-A New Perspective on Measuring Quality in Surgery

This Viewpoint discusses benchmarking as a new means to assess surgical quality.

[Robots in visceral and thoracic surgery-Quo vadis?]

Robotic surgical systems are now an inherent part of the German hospital landscape. In recent years, there has been an enormous increase in installed systems and operations performed, especially in abdominal surgery. Even though there is a lack of studies with the highest grade of evidence, the advantages of the technique are obvious-particularly technically demanding operations can now be performed safely and less invasively for patients. Robotics are now being implemented in many non-university institutions. At the Israelite Hospital (Israelitisches Krankenhaus) Hamburg it could be demonstrated that with systematic and modular training, i.e. execution of certain surgical steps, it is possible to significantly flatten the learning curve while maintaining excellent oncological quality, postoperative morbidity and mortality. The costs to have a system up and running are the main limitations for the implementation of robotic surgery. The acquisition, material and maintenance costs are substantial so that the type of intervention and the training of prospective surgeons are limited by the costs. The robotic approach will fully unroll its disruptive character compared to laparoscopy once it is competitive not only qualitatively in the field of medical contents but also economically. In the future the ROBIN working group of the German Society for General and Visceral Surgery (DGAV) wants to create the basic prerequisites for valid studies by working with registers and could act as an independent central intermediary between hospitals and the industry to promote practical innovations and systematic training for surgeons.

Benchmarks in colorectal surgery: multinational study to define quality thresholds in high and low anterior resection

BACKGROUND

Benchmark comparisons in surgery allow identification of gaps in the quality of care provided. The aim of this study was to determine quality thresholds for high (HAR) and low (LAR) anterior resections in colorectal cancer surgery by applying the concept of benchmarking.

METHODS

This 5-year multinational retrospective study included patients who underwent anterior resection for cancer in 19 high-volume centres on five continents. Benchmarks were defined for 11 relevant postoperative variables at discharge, 3 months, and 6 months (for LAR). Benchmarks were calculated for two separate cohorts: patients without (ideal) and those with (non-ideal) outcome-relevant co-morbidities. Benchmark cut-offs were defined as the 75th percentile of each centre's median value.

RESULTS

A total of 3903 patients who underwent HAR and 3726 who had LAR for cancer were analysed. After 3 months' follow-up, the mortality benchmark in HAR for ideal and non-ideal patients was 0.0 versus 3.0 per cent, and in LAR it was 0.0 versus 2.2 per cent. Benchmark results for anastomotic leakage were 5.0 versus 6.9 per cent for HAR, and 13.6 versus 11.8 per cent for LAR. The overall morbidity benchmark in HAR was a Comprehensive Complication Index (CCI®) score of 8.6 versus 14.7, and that for LAR was CCI® score 11.9 versus 18.3.

CONCLUSION

Regular comparison of individual-surgeon or -unit outcome data against benchmark thresholds may identify gaps in care quality that can improve patient outcome.

Novel Benchmark Values for Redo Liver Transplantation: Does the Outcome Justify the Effort?

OBJECTIVE

To define benchmark cutoffs for redo liver transplantation (redo-LT).

BACKGROUND

In the era of organ shortage, redo-LT is frequently discussed in terms of expected poor outcome and wasteful resources. However, there is a lack of benchmark data to reliably evaluate outcomes after redo-LT.

METHODS

We collected data on redo-LT between January 2010 and December 2018 from 22 high-volume transplant centers. Benchmark cases were defined as recipients with model of end stage liver disease (MELD) score ≤25, absence of portal vein thrombosis, no mechanical ventilation at the time of surgery, receiving a graft from a donor after brain death. Also, high-urgent priority and early redo-LT including those for primary nonfunction (PNF) or hepatic artery thrombosis were excluded. Benchmark cutoffs were derived from the 75th percentile of the medians of all benchmark centers.

RESULTS

Of 1110 redo-LT, 373 (34%) cases qualified as benchmark cases. Among these cases, the rate of postoperative complications until discharge was 76%, and increased up to 87% at 1-year, respectively. One-year overall survival rate was excellent with 90%. Benchmark cutoffs included Comprehensive Complication Index CCI ® at 1-year of ≤72, and in-hospital and 1-year mortality rates of ≤13% and ≤15%, respectively. In contrast, patients who received a redo-LT for PNF showed worse outcomes with some values dramatically outside the redo-LT benchmarks.

CONCLUSION

This study shows that redo-LT achieves good outcome when looking at benchmark scenarios. However, this figure changes in high-risk redo-LT, as for example in PNF. This analysis objectifies for the first-time results and efforts for redo-LT and can serve as a basis for discussion about the use of scarce resources.

Liver Transplantation as a New Standard of Care in Patients With Perihilar Cholangiocarcinoma? Results From an International Benchmark Study

OBJECTIVE

To define benchmark values for liver transplantation (LT) in patients with perihilar cholangiocarcinoma (PHC) enabling unbiased comparisons.

BACKGROUND

Transplantation for PHC is used with reluctance in many centers and even contraindicated in several countries. Although benchmark values for LT are available, there is a lack of specific data on LT performed for PHC.

METHODS

PHC patients considered for LT after Mayo-like protocol were analyzed in 17 reference centers in 2 continents over the recent 5-year period (2014-2018). The minimum follow-up was 1 year. Benchmark patients were defined as operated at high-volume centers (≥50 overall LT/year) after neoadjuvant chemoradiotherapy, with a tumor diameter <3 cm, negative lymph nodes, and with the absence of relevant comorbidities. Benchmark cutoff values were derived from the 75th to 25th percentiles of the median values of all benchmark centers.

RESULTS

One hundred thirty-four consecutive patients underwent LT after completion of the neoadjuvant treatment. Of those, 89.6% qualified as benchmark cases. Benchmark cutoffs were 90-day mortality ≤5.2%; comprehensive complication index at 1 year of ≤33.7; grade ≥3 complication rates ≤66.7%. These values were better than benchmark values for other indications of LT. Five-year disease-free survival was largely superior compared with a matched group of nodal negative patients undergoing curative liver resection (n=106) (62% vs 32%, P <0.001).

CONCLUSION

This multicenter benchmark study demonstrates that LT offers excellent outcomes with superior oncological results in early stage PHC patients, even in candidates for surgery. This provocative observation should lead to a change in available therapeutic algorithms for PHC.

Can Early Postoperative Complications Predict High Morbidity and Decrease Failure to Rescue Following Major Abdominal Surgery?

OBJECTIVE

To assess whether specific patterns of early postoperative complications may predict overall severe morbidity after major surgery, warranting early escalation of care and prevention of failure to rescue.

SUMMARY OF BACKGROUND DATA

It is unclear whether early postoperative complications predict a poor outcome. Detailed knowledge of the chronology and type of early complications after major surgery may alert clinicians when to expect higher risk for subsequent major negative events.

METHODS

All 90-day postoperative events following complex pancreas, liver, and rectal surgeries, and liver transplantation were analyzed over a 3-year period in a single tertiary center. Each complication was recorded regarding severity, type (cardiac, infectious, etc), etiology (surgical/medical), and timing of occurrence. The Comprehensive Complication Index (CCI), covering the first 7 postoperative days, was calculated as a measure for early cumulative postoperative morbidity. The statistical analysis (descriptive, sequence pattern analyses, and logistic regression analyses) aimed to detect any combinations of events predicting poor outcome as defined by a cumulative CCI ≥37.1 at 90-days.

RESULTS

The occurrence of ≥2 complications, irrespective of severity, type or etiology, was strongly associated with a severe postoperative course (P < 0.001). Even 2 mild complications (≤ grade II) greatly increased the chance for high morbidity compared to patients with 0 or 1 complication within the first postoperative week (odds ratio 10.2, 95% confidence interval 5.82-17.98). The CCI at postoperative day 7 strongly predicted high 90-day morbidity (odds ratio 3.96 per 10 CCI points, P < 0.001).

CONCLUSION

Multiple complications of any cause or severity within the first postoperative days represents a "warning-signal" for overall high morbidity by 90 days, which should be used to trigger an escalation of care to prevent failure to rescue and eventually poor outcome.

Missing something? A scoping review of venous thromboembolic events and their associations with bariatric surgery. Refining the evidence base

BACKGROUND

Venous thromboembolic events (VTE) post-bariatric surgery (BS) lead to morbidity and mortality.

METHODS

This scoping review assessed whether reported VTE post-BS could be under/over-estimated; suggested a possible number of VTE post-BS; appraised whether VTE are likely to decrease/increase; examined BS as risk/protective factor for VTE; and mapped the gaps, proposing potential solutions.

RESULTS

VTE appears under-estimated due to: identification/coding of BS and VTE; reporting of exposure (BS); and reporting of outcomes (VTE). The review proposes a hypothetical calculation of VTE post-BS. VTE are unlikely to decrease soon. BS represents risk and protection for VTE. Better appreciation of VTE-BS relationships requires longer-term strategies.

CONCLUSION

VTE are underestimated. Actions are required for understanding the VTE-BS relationships to in order to crease VTE by better-informed prevention strategy/ies.

Sleeve gastrectomy or gastric bypass: a "post-code" lottery? A comprehensive national analysis of the utilization of bariatric surgery in Switzerland between 2011-2017

BACKGROUND

Sleeve gastrectomy (SG) recently became the most frequently performed bariatric surgery (BS) worldwide, overtaking the long-time standard Roux-en-Y gastric bypass (RYGB). Main indications for one or the other procedure show large inter-center variations and warrant further investigations.

OBJECTIVES

The aim of this study was to identify the influencers of primary BS selection in Switzerland.

SETTING

Switzerland.

METHODS

Retrospective analysis of all hospitalizations in Switzerland January 1, 2011 through December 31, 2017 with anonymized data provided by the Swiss Federal Statistical Office. BS procedures were identified based on ICD-10 and national surgical codes. Statistical analyses were performed with R.

RESULTS

During the study period 27,375 BS were performed. The annual BS caseload doubled over time, whereas inpatient complications decreased (∼-33%). RYGB was the prevailing procedure, although its annual proportion decreased from 80% to 70% over 7 years. Meanwhile, use of SG increased from 14% to 23%. Primary RYGB and SG had similar rates of inpatient mortality (∼.05%) and morbidity (8.0 versus 7.4%, P =.148), with the exception of higher ileus rates following RYGB (.7 versus .1%, P < .001). Patient-related factors favoring the indication of SG were male sex, extremes of age, and metabolic co-morbidities , while gastroesophageal reflux disease and private insurance-favored RYGB. Strikingly, differences between geographic regions outweighed patient-related factors in procedure selection: inhabitants of German- and Italian-speaking areas had higher likelihood (OR 4.6; 3.9, P < .001) to receive SG than those in French-speaking areas.

CONCLUSION

Geographic differences in primary BS procedure selection indicate a lack of objective rationales. Long-term risk-benefit and cost-effectiveness analyses are needed to assist evidence-based decision making.

Global Benchmark Values for Laparoscopic Roux-en-Y-Gastric Bypass: a Potential New Indicator of the Surgical Learning Curve

Background

Laparoscopic Roux-en-Y gastric bypass (LRYGB) is a technically demanding procedure. The learning curve of LRYGB is challenging and potentially associated with increased morbidity. This study evaluates whether a general laparoscopic surgeon can be safely trained in performing LRYGB in a peripheral setting, by comparing perioperative outcomes to global benchmarks and to those of a senior surgeon.

Methods

All consecutive patients undergoing primary LRYGB between January 2014 and December 2017 were operated on by a senior (A) or a trainee (B) bariatric surgeon and were prospectively included. The main outcome of interest was all-cause morbidity at 90 days. Perioperative outcomes were compared with global benchmarks pooled from 19 international high-volume centers and between surgeons A and B for their first and last 30 procedures.

Results

The 213 included patients had a mean all-cause morbidity rate at 90 days of 8% (17/213). 95.3% (203/213) of the patients were uneventfully discharged after surgery. Perioperative outcomes of surgeon B were all within the global benchmark cutoffs. Mean operative time for the first 30 procedures was significantly shorter for surgeon A compared with surgeon B, with 108.6 min (± 21.7) and 135.1 min (± 28.1) respectively and decreased significantly for the last 30 procedures to 95 min (± 33.7) and 88.8 min (± 26.9) for surgeons A and B respectively.

Conclusion

Training of a new bariatric surgeon did not increase morbidity and operative time improved for both surgeons. Perioperative outcomes within global benchmarks suggest that it may be safe to teach bariatric surgery in peripheral setting.

Taking Morbidity and Mortality Conferences to a Next Level: The Resilience Engineering Concept

OBJECTIVE

To explore possibilities to improve morbidity and mortality conferences using advancing insights in safety science.

SUMMARY BACKGROUND DATA

Mortality and Morbidity conferences (M&M) are the golden practice for case-based learning. While learning from complications is useful, M&M does not meet expectations for system-wide improvement. Resilience engineering principles may be used to improve M&M.

METHODS

After a review of the shortcomings of traditional M&M, resilience engineering principles are explored as a new way to evaluate performance. This led to the development of a new M&M format that also reviews successful outcomes, rather than only complications. This "quality assessment meeting" (QAM) is presented and the first experiences are evaluated using local observations and a survey.

RESULTS

During the QAM teams evaluate all discharged patients, addressing team resilience in terms of surgeons' ability to respond to irregularities and to monitor and learn from experiences. The meeting was feasible to implement and well received by the surgical team. Observations reveal that reflection on both complicated and uncomplicated cases strengthened team morale but also triggered reflection on the entire clinical course. The QAM serves as a tool to identify how adapting behavior led to success despite challenging conditions, so that this resilient performance can be supported.

CONCLUSIONS

The resilience engineering concept can be used to adjust M&M, in which learning is focused not only on complications but also on how successful outcomes were achieved despite ever-present challenges. This reveals the actual ratio between successful and unsuccessful outcomes, allowing to learn from both to reinforce safety-enhancing behavior.