Preperitoneal Pelvic Packing is Associated With Increased Risk of Venous Thromboembolism.

INTRODUCTION: Preperitoneal pelvic packing (PPP) is an important intervention for control of severe pelvic hemorrhage in blunt trauma patients. We hypothesized that PPP is associated with an increased incidence of deep vein thrombosis (DVT) and pulmonary embolism (PE). METHODS: A retrospective cohort analysis of blunt trauma patients with severe pelvic fractures (AIS ≥4) using the 2015-2017 American College of Surgeons-Trauma Quality Improvement Program database was performed. Patients who underwent PPP within four hours of admission were matched to patients who did not using propensity score matching. Matching was performed based on demographics, comorbidities, injury- and resuscitation-related parameters, vital signs at presentation, and initiation and type of prophylactic anticoagulation. The rates of DVT and PE were compared between the matched groups. RESULTS: Out of 5129 patients with severe pelvic fractures, 157 (3.1%) underwent PPP within four h of presentation and were matched with 157 who did not. No significant differences were detected between the two matched groups in any of the examined baseline variables. Similarly, mortality and end-organ failure rates were not different. However, PPP patients were significantly more likely to develop DVT (12.7% versus 5.1%, P = 0.028) and PE (5.7% versus 0.0%, P = 0.003). CONCLUSIONS: PPP in severe pelvic fractures secondary to blunt trauma is associated with an increased risk of DVT and PE. A high index of suspicion and a low threshold for screening for these conditions should be maintained in patients who undergo PPP.

Intraoperative Deaths: Who, Why, and Can We Prevent Them?

INTRODUCTION: Intraoperative deaths (IODs) are rare but catastrophic. We systematically analyzed IODs to identify clinical and patient safety patterns. METHODS: IODs in a large academic center between 2015 and 2019 were included. Perioperative details were systematically reviewed, focusing on (1) identifying phenotypes of IOD, (2) describing emerging themes immediately preceding cardiac arrest, and (3) suggesting interventions to mitigate IOD in each phenotype. RESULTS: Forty-one patients were included. Three IOD phenotypes were identified: trauma (T), nontrauma emergency (NT), and elective (EL) surgery patients, each with 2 sub-phenotypes (e.g., ELm and ELv for elective surgery with medical arrests or vascular injury and bleeding, respectively). In phenotype T, cardiopulmonary resuscitation was initiated before incision in 42%, resuscitative thoracotomy was performed in 33%, and transient return of spontaneous circulation was achieved in 30% of patients. In phenotype NT, ruptured aortic aneurysms accounted for half the cases, and median blood product utilization was 2,694 mL. In phenotype ELm, preoperative evaluation did not include electrocardiogram in 12%, cardiac consultation in 62%, stress test in 87%, and chest x-ray in 37% of patients. In phenotype ELv, 83% had a single peripheral intravenous line, and vascular injury was almost always followed by escalation in monitoring (e.g., central/arterial line), alert to the blood bank, and call for surgical backup. CONCLUSIONS: We have created a framework for IOD that can help with intraoperative safety and quality analysis. Focusing on interventions that address appropriateness versus futility in care in phenotypes T and NT, and on prevention and mitigation of intraoperative vessel injury (e.g., intraoperative rescue team) or preoperative optimization in phenotype EL may help prevent IODs.

Intensive Care Unit Volume of Sepsis Patients Does Not Affect Mortality: Results of a Nationwide Retrospective Analysis.

BACKGROUND: There is little research evaluating outcomes from sepsis in intensive care units (ICUs) with lower sepsis patient volumes as compared to ICUs with higher sepsis patient volumes. Our objective was to compare the outcomes of septic patients admitted to ICUs with different sepsis patient volumes. MATERIALS AND METHODS: We included all patients from the eICU-CRD database admitted for the management of sepsis with blood lactate ≥ 2mmol/L within 24 hours of admission. Our primary outcome was ICU mortality. Secondary outcomes included hospital mortality, 30-day ventilator free days, and initiation of renal replacement therapy (RRT). ICUs were grouped in quartiles based on the number of septic patients treated at each unit. RESULTS: 10,716 patients were included in our analysis; 272 (2.5%) in low sepsis volume ICUs, 1,078 (10.1%) in medium-low sepsis volume ICUs, 2,608 (24.3%) in medium-high sepsis volume ICUs, and 6,758 (63.1%) in high sepsis volume ICUs. On multivariable analyses, no significant differences were documented regarding ICU and hospital mortality, and ventilator days in patients treated in lower versus higher sepsis volume ICUs. Patients treated at lower sepsis volume ICUs had lower rates of RRT initiation as compared to high volume units (medium-high vs. high: OR = 0.78, 95%CI = 0.66-0.91, P-value = 0.002 and medium-low vs. high: OR = 0.57, 95%CI = 0.44-0.73, P-value < 0.001). CONCLUSION: The previously described volume-outcome association in septic patients was not identified in an intensive care setting.

Hospital Academic Status and the Volume-Outcome Association in Postoperative Patients Requiring Intensive Care: Results of a Nationwide Analysis of Intensive Care Units in the United States.

Objective: To determine whether the outcomes of postoperative patients admitted directly to an intensive care unit (ICU) differ based on the academic status of the institution and the total operative volume of the unit. Methods: This was a retrospective analysis using the eICU Collaborative Research Database v2.0, a national database from participating ICUs in the United States. All patients admitted directly to the ICU from the operating room were included. Transfer patients and patients readmitted to the ICU were excluded. Patients were stratified based on admission to an ICU in an academic medical center (AMC) versus non-AMC, and to ICUs with different operative volume experience, after stratification in quartiles (high, medium-high, medium-low, and low volume). Primary outcomes were ICU and hospital mortality. Secondary outcomes included the need for continuous renal replacement therapy (CRRT) during ICU stay, ICU length of stay (LOS), and 30-day ventilator free days. Results: Our analysis included 22,180 unique patients; the majority of which (15,085[68%]) were admitted to ICUs in non-AMCs. Cardiac and vascular procedures were the most common types of procedures performed. Patients admitted to AMCs were more likely to be younger and less likely to be Hispanic or Asian. Multivariable logistic regression indicated no meaningful association between academic status and ICU mortality, hospital mortality, initiation of CRRT, duration of ICU LOS, or 30-day ventilator-free-days. Contrarily, medium-high operative volume units had higher ICU mortality (OR = 1.45, 95%CI = 1.10-1.91, p-value = 0.040), higher hospital mortality (OR = 1.33, 95%CI = 1.07-1.66, p-value = 0.033), longer ICU LOS (Coefficient = 0.23, 95%CI = 0.07-0.39, p-value = 0.038), and fewer 30-day ventilator-free-days (Coefficient = -0.30, 95%CI = -0.48 - -0.13, p-value = 0.015) compared to their high operative volume counterparts. Conclusions: This study found that a volume-outcome association in the management of postoperative patients requiring ICU level of care immediately after a surgical procedure may exist. The academic status of the institution did not affect the outcomes of these patients.

Risk factors for ischemic gastrointestinal complications in patients undergoing open cardiac surgical procedures: A single-center retrospective experience.

BACKGROUND: Ischemic gastrointestinal complications (IGIC) following cardiac surgery are associated with high morbidity and mortality and remain difficult to predict. We evaluated perioperative risk factors for IGIC in patients undergoing open cardiac surgery. METHODS: All patients that underwent an open cardiac surgical procedure at a tertiary academic center between 2011 and 2017 were included. The primary outcome was IGIC, defined as acute mesenteric ischemia necessitating a surgical intervention or postoperative gastrointestinal bleeding that was proven to be of ischemic etiology and necessitated blood product transfusion. A backward stepwise regression model was constructed to identify perioperative predictors of IGIC. RESULTS: Of 6862 patients who underwent cardiac surgery during the study period, 52(0.8%) developed IGIC. The highest incidence of IGIC (1.9%) was noted in patients undergoing concomitant coronary artery, valvular, and aortic procedures. The multivariable regression identified hypertension (odds ratio [OR] = 5.74), preoperative renal failure requiring dialysis (OR = 3.62), immunocompromised status (OR = 2.64), chronic lung disease (OR = 2.61), and history of heart failure (OR = 2.03) as independent predictors for postoperative IGIC. Pre- or intraoperative utilization of intra-aortic balloon pump or catheter-based assist devices (OR = 4.54), intraoperative transfusion requirement of >4 RBC units(OR = 2.47), and cardiopulmonary bypass > 180 min (OR = 2.28) were also identified as independent predictors for the development of IGIC. CONCLUSIONS: We identified preoperative and intraoperative risk factors that independently increase the risk of developing postoperative IGIC after cardiac surgery. A high index of suspicion must be maintained and any deviation from the expected recovery course in patients with the above-identified risk factors should trigger an immediate evaluation with the involvement of the acute care surgical team.

Andexanet Alfa or Prothrombin Complex Concentrate for Factor Xa Inhibitor Reversal in Acute Major Bleeding: A Systematic Review and Meta-Analysis.

OBJECTIVES: To combine evidence on andexanet alfa and prothrombin complex concentrates for factor Xa inhibitor-associated bleeding to guide clinicians on reversal strategies. DATA SOURCES: Embase, Pubmed, Web of Science, and the Cochrane Library. STUDY SELECTION: Observational studies and randomized clinical trials studying hemostatic effectiveness of andexanet alfa or prothrombin complex concentrate for acute reversal of factor Xa inhibitor-associated hemorrhage. DATA EXTRACTION: Two independent reviewers extracted the data from the studies. Visualization and comparison of hemostatic effectiveness using Sarode et al or International Society of Thrombosis and Hemostasis Scientific and Standardization Committee criteria at 12 and 24 hours, (venous) thrombotic event rates, and inhospital mortality were performed by constructing Forest plots. Exploratory analysis using a logistic mixed model analysis was performed to identify factors associated with effectiveness and venous thromboembolic event. DATA SYNTHESIS: A total of 21 studies were included (andexanet: 438 patients; prothrombin complex concentrate: 1,278 patients). The (weighted) mean effectiveness for andexanet alfa was 82% at 12 hours and 71% at 24 hours. The (weighted) mean effectiveness for prothrombin complex concentrate was 88% at 12 hours and 76% at 24 hours. The mean 30-day symptomatic venous thromboembolic event rates were 5.0% for andexanet alfa and 1.9% for prothrombin complex concentrate. The mean 30-day total thrombotic event rates for andexanet alfa and prothrombin complex concentrate were 10.7% and 3.1%, respectively. Mean inhospital mortality was 23.3% for andexanet versus 15.8% for prothrombin complex concentrate. Exploratory analysis controlling for potential confounders did not demonstrate significant differences between both reversal agents. CONCLUSIONS: Currently, available evidence does not unequivocally support the clinical effectiveness of andexanet alfa or prothrombin complex concentrate to reverse factor Xa inhibitor-associated acute major bleeding, nor does it permit conventional meta-analysis of potential superiority. Neither reversal agent was significantly associated with increased effectiveness or a higher rate of venous thromboembolic event. These results underscore the importance of randomized controlled trials comparing the two reversal agents and may provide guidance in designing institutional guidelines.

Performance of the Emergency Surgery Score (ESS) Across Different Emergency General Surgery Procedures.

BACKGROUND: The Emergency Surgery Score (ESS) has been previously validated as a reliable tool to predict postoperative outcomes in emergency general surgery (EGS). The purpose of this study is to assess the differential performance of the ESS in specific EGS procedures. METHODS: The American College of Surgeons' National Surgical Quality Improvement Program database was retrospectively analyzed for patients undergoing EGS between 2007 and 2017. Patients who underwent the following EGS procedures were identified: laparoscopic appendectomy, laparoscopic cholecystectomy, surgery for small bowel obstruction (SBO), colectomy, and incarcerated ventral or inguinal hernia repair. The performance of the ESS in predicting mortality in each procedure was assessed using receiver operating characteristic analyses. RESULTS: A total of 467,803 patients underwent EGS (mean age 50 ± 19.9 y, females 241,330 [51.6%]), of which 191,930 (41%) underwent laparoscopic appendectomy, 40,353 (8.6%) underwent laparoscopic cholecystectomy, and 35,152 (7.5%) patients underwent surgery for SBO. The ESS correlated extremely well with mortality for patients who underwent laparoscopic appendectomy (area under the curve (AUC) 0.91), laparoscopic cholecystectomy (AUC 0.91), lysis of adhesions for SBO (AUC 0.83), colectomy (AUC 0.83), and incarcerated hernia repair (AUC 0.85). CONCLUSIONS: ESS performance accurately predicts mortality across a wide range of EGS procedures, and its use should be encouraged for preoperative patient counseling and for nationally benchmarking the quality of care of EGS.

Rhabdomyolysis in Severe COVID-19: Male Sex, High Body Mass Index, and Prone Positioning Confer High Risk.

BACKGROUND: Bedside experience and studies of critically ill patients with coronavirus disease 2019 (COVID-19) indicate COVID-19 to be a devastating multisystem disease. We aim to describe the incidence, associated variables, and outcomes of rhabdomyolysis in critically ill COVID-19 patients. MATERIALS AND METHODS: Data for all critically ill adult patients (≥18 years old) admitted to the ICU at a large academic medical center with confirmed COVID-19 between March 13, 2020 and April 18, 2020 were prospectively collected. Patients with serum creatine kinase (CK) concentrations greater than 1000 U/L were diagnosed with rhabdomyolysis. Patients were further stratified as having moderate (serum CK concentration 1000-4999 U/L) or severe (serum CK concentration ≥5000 U/L) rhabdomyolysis. Univariate and multivariate analyses were performed to identify outcomes and variables associated with the development of rhabdomyolysis. RESULTS: Of 235 critically ill COVID-19 patients, 114 (48.5%) met diagnostic criteria for rhabdomyolysis. Patients with rhabdomyolysis more often required mechanical ventilation (P < 0.001), prone positioning (P < 0.001), pharmacological paralysis (P < 0.001), renal replacement therapy (P = 0.010), and extracorporeal membrane oxygenation (ECMO) (P = 0.025). They also had longer median ICU length of stay (LOS) (P < 0.001) and hospital LOS (P < 0.001). No difference in mortality was observed. Male sex, patients with morbid obesity, SOFA score, and prone positioning were independently associated with rhabdomyolysis. CONCLUSIONS: Nearly half of critically ill COVID-19 patients in our cohort met diagnostic criteria for rhabdomyolysis. Male sex, morbid obesity, SOFA score, and prone position were independently associated with rhabdomyolysis.

Provocative Angiography, Followed by Therapeutic Interventions, in the Management of Hard-To-Diagnose Gastrointestinal Bleeding.

BACKGROUND: Despite significant advances in imaging and endoscopic diagnostic techniques, adequate localization of gastrointestinal bleeding (GIB) can be challenging. Provocative angiography (PROVANGIO) has not been part of the standard diagnostic algorithms yet. We sought to examine the ability of PROVANGIO to identify the bleeding source when conventional radiography fails. METHODS: Patients undergoing PROVANGIO for GIB during 2008-2014 were retrospectively included. Demographics and periprocedural patient characteristics were recorded. PROVANGIO was performed in a multidisciplinary setting, involving interventional radiology, surgery and anesthesiology teams, ready to intervene in case of uncontrolled bleeding. The procedure included conventional angiography of the celiac, superior and inferior mesenteric arteries (SMA, IMA) followed by a stepwise bleeding provocation with anticoagulating, vasodilating and/or thrombolytic agent administration, combined with angiography. RESULTS: Twenty-three PROVANGIO were performed. Patients were predominantly male (15, 65.2%), and hematochezia was the most common presenting symptom (12, 52.2%). Patients with a positive PROVANGIO had lower Charlson comorbidity index (1 vs. 7, p = 0.009) and were less likely to have a prior history of GIB (14.3% vs. 87.5%, p = 0.001). PROVANGIO localized bleeding in 7 (30%) patients. In 6 out of 7 patients, the bleeding source was identified in the SMA and, in one case, in the IMA distribution. The bleeding was controlled angiographically in four cases, endoscopically in one case and surgically in the remaining two. No complications related to PROVANGIO were detected. CONCLUSIONS: In our series, PROVANGIO safely identified the bleeding source, and provided that necessary safeguards are put into place, we recommend incorporating it in the diagnostic algorithms for GIB management.

The Effect of Immunosuppression on Emergency Colectomy Outcomes: A Nationwide Retrospective Analysis.

BACKGROUND: The impact of immunosuppression on the outcomes of emergent surgery remains poorly described. We aimed to quantify the impact of chronic immunosuppression on outcomes of patients undergoing emergent colectomy (EC). METHODS: The Colectomy-Targeted ACS-NSQIP database 2012-2016 was queried for patients who underwent colectomy for an emergent indication. As per NSQIP, chronic immunosuppression was defined as the use of corticosteroid or immunosuppressant medication within the prior 30 days. Patients undergoing EC for any indication were divided into two groups: immunosuppressant use (IMS) and no immunosuppressant use (NIS). Patients were propensity-score-matched on demographics, comorbidities, preoperative laboratory values, and operative variables in a 1:1 ratio to control for confounding factors. The primary outcome was 30-day mortality. Secondary outcomes included overall 30-day morbidity, individual postoperative complications (e.g., wound dehiscence, anastomotic leak, and sepsis), and hospital length of stay. RESULTS: Out of a total of 130,963 patients, 17,707 patients underwent an EC, of which 15,422 were NIS and 2285 were IMS. Totally, 2882 patients were matched (1441 NIS; 1441 IMS). The median age was 66 [IQR 56-76]; 56.8% were female; patients more frequently underwent a diversion procedure rather than primary anastomosis (68.4% vs 31.6%). Overall, as compared to NIS, IMS patients had higher 30-day mortality (21.4% vs 18.5%, p = 0.045) and overall morbidity (79.7% vs 75.7%, p = 0.011). Particularly, IMS patients had increased rates of unplanned intubations (11.5% vs 7.9%, p = 0.001), wound dehiscence (5.7% vs 3.5%, p = 0.006), progressive renal insufficiency 2.2% vs 1.2%, p = 0.042), pneumonia (12.6% vs 10.0%, p = 0.029), and longer median hospital length of stay [12.0 (8.0-21.0) vs 11.0 (7.0-19.0), p < 0.001] as compared to NIS patients. CONCLUSIONS: Chronic immunosuppression is independently associated with a significant and quantifiable increase in 30-day mortality and complications for patients undergoing EC. Our results provide the emergency surgeon with quantifiable risk estimates that can help guide better patient counseling while setting reasonable expectations.

Solid Pseudopapillary Neoplasms of the Pancreas: A Surgical and Genetic Enigma.

Solid pseudopapillary neoplasms of the pancreas are rare tumors accounting for 1-2% of pancreatic exocrine neoplasms. This entity was first described by Dr. Frantz in 1959 and was defined by the World Health Organization in 1996 as "solid pseudopapillary tumor." It is most often a benign neoplasm, but 10-15% of the cases are malignant. Over the past decades, the incidence of this tumor is increasing. However, many surgeons are still unfamiliar with this neoplasm and its unique characteristics, which can lead to pitfalls in the diagnosis and treatment. The correct diagnosis of SPNP is of utmost importance since it has a low malignant potential and with the appropriate treatment, patients have a long life expectancy. There are many genetic alterations, involving various signaling pathways that have been associated with SPNP and are very important in diagnosing the tumor. The cornerstone of SPNP treatment includes surgical excision of the tumor, preserving as much pancreatic tissue as possible. We review the information in the literature regarding more organ-preserving techniques and possible clinical features that might indicate a malignant potential, thus demanding a more radical intraoperative excision.

Safety of the injectable expanding biopolymer foam for non-compressible truncal bleeding in swine.

BACKGROUND: A novel hydrophobically modified chitosan (hm-chitosan) polymer has been previously shown to improve survival in a non-compressible intra-abdominal bleeding model in swine. We performed a 28-day survival study to evaluate the safety of the hm-chitosan polymer in swine. METHODS: Female Yorkshire swine (40-50 kg) were used. A mild, non-compressible, closed-cavity bleeding model was created with splenic transection. The hm-chitosan polymer was applied intra-abdominally through an umbilical nozzle in the same composition and dose previously shown to improve survival. Animals were monitored intraoperatively and followed 28 days postoperatively for survival, signs of pain, and end-organ function. Gross pathological and microscopic evaluations were performed at the conclusion of the experiment. RESULTS: A total of 10 animals were included (hm-chitosan = 8; control = 2). The 2 control animals survived through 28 days, and 7 of the 8 animals from the hm-chitosan group survived without any adverse events. One animal from the hm-chitosan group required early termination of the study for signs of pain, and superficial colonic ulcers were found on autopsy. Laboratory tests showed no signs of end-organ dysfunction after exposure to hm-chitosan after 28 days. On gross pathological examination, small (<0.5 cm) peritoneal nodules were noticed in the hm-chitosan group, which were consistent with giant-cell foreign body reaction in microscopy, presumably related to polymer remnants. Microscopically, no signs of systemic polymer embolization or thrombosis were noticed. CONCLUSION: Prolonged intraperitoneal exposure to the hm-chitosan polymer was tolerated without any adverse event in the majority of animals. In the single animal that required early termination, the material did not appear to be associated with end-organ dysfunction in swine. Superficial colonic ulcers that would require surgical repair were identified in 1 out of 8 animals exposed to hm-chitosan.

Use of artificial intelligence for nonlinear benchmarking of surgical care.

BACKGROUND: Existent methodologies for benchmarking the quality of surgical care are linear and fail to capture the complex interactions of preoperative variables. We sought to leverage novel nonlinear artificial intelligence methodologies to benchmark emergency surgical care. METHODS: Using a nonlinear but interpretable artificial intelligence methodology called optimal classification trees, first, the overall observed mortality rate at the index hospital's emergency surgery population (index cohort) was compared to the risk-adjusted expected mortality rate calculated by the optimal classification trees from the American College of Surgeons National Surgical Quality Improvement Program database (benchmark cohort). Second, the artificial intelligence optimal classification trees created different "nodes" of care representing specific patient phenotypes defined by the artificial intelligence optimal classification trees without human interference to optimize prediction. These nodes capture multiple iterative risk-adjusted comparisons, permitting the identification of specific areas of excellence and areas for improvement. RESULTS: The index and benchmark cohorts included 1,600 and 637,086 patients, respectively. The observed and risk-adjusted expected mortality rates of the index cohort calculated by optimal classification trees were similar (8.06% [95% confidence interval: 6.8-9.5] vs 7.53%, respectively, P = .42). Two areas of excellence and 4 for improvement were identified. For example, the index cohort had lower-than-expected mortality when patients were older than 75 and in respiratory failure and septic shock preoperatively but higher-than-expected mortality when patients had respiratory failure preoperatively and were thrombocytopenic, with an international normalized ratio ≤1.7. CONCLUSION: We used artificial intelligence methodology to benchmark the quality of emergency surgical care. Such nonlinear and interpretable methods promise a more comprehensive evaluation and a deeper dive into areas of excellence versus suboptimal care.

Circulating cellular clusters are associated with thrombotic complications and clinical outcomes in COVID-19.

We sought to study the role of circulating cellular clusters (CCC) -such as circulating leukocyte clusters (CLCs), platelet-leukocyte aggregates (PLA), and platelet-erythrocyte aggregates (PEA)- in the immunothrombotic state induced by COVID-19. Forty-six blood samples from 37 COVID-19 patients and 12 samples from healthy controls were analyzed with imaging flow cytometry. Patients with COVID-19 had significantly higher levels of PEAs (p value<0.001) and PLAs (p value = 0.015) compared to healthy controls. Among COVID-19 patients, CLCs were correlated with thrombotic complications (p value = 0.016), vasopressor need (p value = 0.033), acute kidney injury (p value = 0.027), and pneumonia (p value = 0.036), whereas PEAs were associated with positive bacterial cultures (p value = 0.033). In predictive in silico simulations, CLCs were more likely to result in microcirculatory obstruction at low flow velocities (≤1 mm/s) and at higher branching angles. Further studies on the cellular component of hyperinflammatory prothrombotic states may lead to the identification of novel biomarkers and drug targets for inflammation-related thrombosis.

Development of a Machine Learning-Based Prescriptive Tool to Address Racial Disparities in Access to Care After Penetrating Trauma.

Importance: The use of artificial intelligence (AI) in clinical medicine risks perpetuating existing bias in care, such as disparities in access to postinjury rehabilitation services. Objective: To leverage a novel, interpretable AI-based technology to uncover racial disparities in access to postinjury rehabilitation care and create an AI-based prescriptive tool to address these disparities. Design, Setting, and Participants: This cohort study used data from the 2010-2016 American College of Surgeons Trauma Quality Improvement Program database for Black and White patients with a penetrating mechanism of injury. An interpretable AI methodology called optimal classification trees (OCTs) was applied in an 80:20 derivation/validation split to predict discharge disposition (home vs postacute care [PAC]). The interpretable nature of OCTs allowed for examination of the AI logic to identify racial disparities. A prescriptive mixed-integer optimization model using age, injury, and gender data was allowed to "fairness-flip" the recommended discharge destination for a subset of patients while minimizing the ratio of imbalance between Black and White patients. Three OCTs were developed to predict discharge disposition: the first 2 trees used unadjusted data (one without and one with the race variable), and the third tree used fairness-adjusted data. Main Outcomes and Measures: Disparities and the discriminative performance (C statistic) were compared among fairness-adjusted and unadjusted OCTs. Results: A total of 52 468 patients were included; the median (IQR) age was 29 (22-40) years, 46 189 patients (88.0%) were male, 31 470 (60.0%) were Black, and 20 998 (40.0%) were White. A total of 3800 Black patients (12.1%) were discharged to PAC, compared with 4504 White patients (21.5%; P < .001). Examining the AI logic uncovered significant disparities in PAC discharge destination access, with race playing the second most important role. The prescriptive fairness adjustment recommended flipping the discharge destination of 4.5% of the patients, with the performance of the adjusted model increasing from a C statistic of 0.79 to 0.87. After fairness adjustment, disparities disappeared, and a similar percentage of Black and White patients (15.8% vs 15.8%; P = .87) had a recommended discharge to PAC. Conclusions and Relevance: In this study, we developed an accurate, machine learning-based, fairness-adjusted model that can identify barriers to discharge to postacute care. Instead of accidentally encoding bias, interpretable AI methodologies are powerful tools to diagnose and remedy system-related bias in care, such as disparities in access to postinjury rehabilitation care.