Stephen H. Gray

Background: The use of large-scale data and artificial intelligence (AI) to support complex transplantation decisions is in its infancy. Transplant candidate decision-making, which relies heavily on subjective assessment (ie, high variability), provides a ripe opportunity for AI-based clinical decision support (CDS). However, AI-CDS for transplant applications must consider important concerns regarding fairness (ie, health equity). The objective of this study was to use human-centered design methods to elicit providers’ perceptions of AI-CDS for liver transplant listing decisions. Methods: In this multicenter qualitative study conducted from December 2020 to July 2021, we performed semistructured interviews with 53 multidisciplinary liver transplant providers from 2 transplant centers. We used inductive coding and constant comparison analysis of interview data. Results: Analysis yielded 6 themes important for the design of fair AI-CDS for liver transplant listing decisions: (1) transparency in the creators behind the AI-CDS and their motivations; (2) understanding how the AI-CDS uses data to support recommendations (ie, interpretability); (3) acknowledgment that AI-CDS could mitigate emotions and biases; (4) AI-CDS as a member of the transplant team, not a replacement; (5) identifying patient resource needs; and (6) including the patient’s role in the AI-CDS. Conclusions: Overall, providers interviewed were cautiously optimistic about the potential for AI-CDS to improve clinical and equitable outcomes for patients. These findings can guide multidisciplinary developers in the design and implementation of AI-CDS that deliberately considers health equity. Export

Racial and ethnic disparities persist in access to the liver transplantation (LT) waiting list; however, there is limited knowledge about underlying system‐level factors that may be responsible for these disparities. Given the complex nature of LT candidate evaluation, a human factors and systems engineering approach may provide insights. We recruited participants from the LT teams (coordinators, advanced practice providers, physicians, social workers, dieticians, pharmacists, leadership) at two major LT centers. From December 2020 to July 2021, we performed ethnographic observations (participant–patient appointments, committee meetings) and semistructured interviews (N = 54 interviews, 49 observation hours). Based on findings from this multicenter, multimethod qualitative study combined with the Systems Engineering Initiative for Patient Safety 2.0 (a human factors and systems engineering model for health care), we created a conceptual framework describing how transplant work system characteristics and other external factors may improve equity in the LT evaluation process. Participant perceptions about listing disparities described external factors (e.g., structural racism, ambiguous national guidelines, national quality metrics) that permeate the LT evaluation process. Mechanisms identified included minimal transplant team diversity, implicit bias, and interpersonal racism. A lack of resources was a common theme, such as social workers, transportation assistance, non–English‐language materials, and time (e.g., more time for education for patients with health literacy concerns). Because of the minimal data collection or center feedback about disparities, participants felt uncomfortable with and unadaptable to unwanted outcomes, which perpetuate disparities. We proposed transplant center–level solutions (i.e., including but not limited to training of staff on health equity) to modifiable barriers in the clinical work system that could help patient navigation, reduce disparities, and improve access to care. Our findings call for an urgent need for transplant centers, national societies, and policy makers to focus efforts on improving equity (tailored, patient‐centered resources) using the science of human factors and systems engineering.

We reviewed the role of transesophageal echocardiography (TEE) in the management of renal cell carcinoma (RCC) with associated tumor thrombus. Many consider intraoperative TEE as imperative in cases of Level 4 thrombi with atrial involvement, as well as in cases that require the use of cardiopulmonary bypass (CPB). However, the role of TEE in the surgical management of RCC with associated inferior vena cava (IVC) thrombus may expand beyond this subset. When performed after induction, TEE provides updated information regarding tumor thrombus staging, which is essential for optimal surgical planning. Furthermore, TEE provides feedback regarding properties of the thrombus, such as fragility and adherence, which may alter surgical technique. TEE can also be used intraoperatively for central venous line placement, to monitor cardiovascular and fluid status, to guide vascular clamp placement, and to ensure complete removal of the tumor thrombus. In some cases, the use of TEE allows for less morbid procedures and safe avoidance of CPB. We therefore recommend the use of preoperative TEE in all cases with a known tumor thrombus with discretion as to what extent TEE is used throughout the remainder of the case. Further investigation is necessary to elucidate the effect of TEE on patient outcomes, including surgical complication rates, morbidity and mortality of procedures, and cancer control.

Transarterial chemoembolization (TACE) is the most common oncologic therapy used according to the American Association for the Study of Liver Diseases (AASLD) guidelines established in 2005, revised in 2011. The purpose of this study was to determine how AASLD criteria for the management of hepatocellular carcinoma (HCC) have impacted TACE practice in the community. Clinical, demographic, and cause of death information were collected for patients diagnosed with HCC in the 2012 linkage of the Surveillance, Epidemiology, and End Results Medicare database. Propensity score survival analysis was used to compare survival outcomes in patients whose HCC tumor characteristics were less than, met, or were beyond AASLD criteria. The proportion of patients with HCC receiving TACE who met the AASLD‐recommended criteria increased after the 2005 guidelines were published. Up to 17% of patients treated with TACE had tumor characteristics less than the AASLD criteria and were not offered potentially curative therapies. Propensity score matching demonstrated the largest survival advantage in patients with HCC whose tumor characteristics met the AASLD criteria (hazard ratio, 0.42; 95% confidence interval, 0.38‐0.47). A significant survival advantage was also observed in patients with HCC whose tumor characteristics exceeded the AASLD criteria. Conclusion: The AASLD criteria successfully identify a population of patients with HCC that maximally benefit from TACE therapy. However, patients with HCC with tumor characteristics beyond the AASLD criteria also appear to receive a significant survival advantage with TACE. Further studies are necessary to improve referral patterns and appropriate use of chemoembolization in the management of unresectable HCC. (Hepatology Communications 2017;1:338–346)

Background Studies have demonstrated that African American race is a strong predictor of nondonation. However, it is often and correctly argued that African American race is a crude explanatory variable that is a surrogate marker of socioeconomic status, education, and access to health care. We hypothesized that, when controlling for these factors, African American race would cease to be a predictor of organ donation. Methods A retrospective review of 1292 Alabama decedents who were approached for organ donation between 2006 and 2009 was performed. Multivariable logistic regression models were constructed to identify the most parsimonious model that could explain the variation in the log odds of obtaining consent. Results Consent for donation was obtained from 49% of the decedents’ families. Household income was a predictor of organ donor consent only in whites. Surprisingly, household income was not statistically different between consented and nonconsented African American decedents (U.S. $25,147 vs. U.S. $26,137, P=0.90). On multivariable analysis, education, urban residence, and shorter distance between the decedent’s residence and donor hospital were significantly associated with obtaining consent for organ donation. On univariate analysis, the odds ratio of donor consent in whites compared with African Americans was 2.76 (95% confidence interval, 2.17–3.57). When controlling for socioeconomic status and access to health care variables, the odds ratio of donor consent increased to 4.36 (95% confidence interval, 2.88–6.61). Conclusions We interpret this result to indicate that there remains unknown but important factor(s) associated with both race and obtaining organ donor consent. Further studies are required to isolate and determine whether this factor(s) is modifiable.