Bankes, Audrey

ABSTRACT Background Evaluating fairness in artificial intelligence (AI) is essential before clinical implementation to prevent unintended harm across diverse patient populations. This study assesses performance differences of an image-based surgical site infection (SSI) detection model across age, gender, geography, race, and skin color. Methods Model development/validation study using retrospective, multicenter data across surgical subspecialties from adults who submitted an image of their incision via the electronic health record within 30 days of their procedure between 2019-2024. Area under receiver operating curve (AUROC) was compared by age (<55 vs. ≥55 years old), gender (male vs. female), geography (Rochester, Minnesota vs. Jacksonville, Florida vs. Scottsdale, Arizona vs. regional Minnesota/Wisconsin areas), race (White/Caucasian vs. non-White/Caucasian), and skin color (Fitpatrick I-III vs. IV-VI and Monk A-E vs. F-J). Results Training data contained 13,702 images from 4,274 patients between 2019-2022 (50.1% ≥55 years old; 63.2% female; 91.6% White/Caucasian; 58.5% Rochester, 17.3% Florida, 10.5% Arizona; 96.3% light skin tone), of which 1,348 images (9.8%) had an SSI. No differences in SSI detection existed for age, gender, race, or skin color (AUROC 0.83-0.87, p>0.09), however geographical differences were significant: lowest AUROC 0.83 (95% CI 0.77-0.88) vs. highest AUROC 0.87 (95% CI 0.84-0.89, p=0.01). Temporal validation using 4,242 images from 1,353 patients between 2022-2023 showed intact fairness across subgroups (ΔAUROC ≤0.06) except geography (ΔAUROC ≤0.16). Conclusions The model behaved fairly across age, gender, race, and skin color, however geographical differences persisted. These findings have practical implications underscoring the importance of evaluating bias in clinical AI before deployment.

Multi-listing (ML) increases the odds of transplantation compared with single-center listing. However, not all patients have equivalent access to ML. The recent allocation policy change prioritized distance from the donor hospital in an attempt to decrease geographic disparities. This study assessed access to liver transplant (LT) given ML practices before and after the acuity circles policy change. United Network for Organ Sharing data were queried for LTs between January 1, 2016, and November 1, 2024. Patients were grouped by listing at one versus multiple centers and by acuity circle era (ACE). Cohort characteristics and comparisons were described using chi-square and Wilcoxon rank tests. Multivariable logistic regressions and propensity score match (PSM) were performed to assess associations between ML and LT. The final cohort consisted of 105,030 patients; 4084 (3.9%) were multi-listed. Racial/ethnic minority groups, less educated, and publicly insured candidates were less often multi-listed. ML was positively associated with LT in all analyses (overall: OR=1.180, p <0.001; PSM: OR=1.164, p =0.001; pre-ACE: OR=1.127, p =0.015; post-ACE: OR=1.218, p <0.001). Education, race/ethnicity, and insurance type were also associated with LT across all analyses. ML patients were more often transplanted at their primary center with a significant increase in primary center LT post-ACE (53.4% vs. 63.4%, p <0.001). ML and LT had a positive correlation. There was a negative association between minority groups and ML as well as LT. Although acuity circles decreased geographic disparities, they did not change ML accessibility across candidates.

Background: Little is known about how silicone metacarpophalangeal (MCP) arthroplasty outcomes compare between rheumatoid arthritis (RA) and osteoarthritis (OA) patients. Methods: Using our single institutional data from 2000 to 2022, we propensity matched 46 primary silicone MCP arthroplasties in 33 OA patients 1:2 to 92 arthroplasties in 54 RA patients based on age, sex, body mass index, operative digit, and if the surgery was on the dominant hand. We used Kaplan-Meier estimates and cluster-robust Cox proportional hazard models to compare survival free from revision, all-cause reoperation, and development of coronal plane deviation >10°. Results: There was comparable 10-year survival free of revision (94% OA, 91% RA) and all-cause reoperation (91% OA, 87% RA), with no difference in risk for each outcome between groups. Revision in OA patients occurred early (mean 0.6 years) for recurrent deformity (n = 2) and periprosthetic joint infection (n = 1). Revision in the RA cohort occurred later (mean 6.3 years postoperatively) for recurrent deformity (n = 3) and dislocation (n = 1). Osteoarthritis patients had less coronal plane deviation at the final radiographic follow-up (6.5° vs 16.2°, P < .001), higher 10-year survival free from coronal deviation > 10° (79% vs 17%), and lower risk of progressive coronal deformity (hazard ratio 0.15, P < .001). Conclusions: Silicone MCP arthroplasty remains a durable option with low reoperation rates for RA and OA. Osteoarthritis patients experience less coronal deviation and late reoperation for deformity than RA patients, likely due to their more robust soft-tissue stabilizers and noninflammatory disease process.

Background: Anti-cyclic citrullinated peptide antibodies (ACPAs) are associated with more aggressive rheumatoid arthritis disease. We aimed to determine the effect of ACPA serostatus on survival free from revision, all-cause reoperation, and recurrence of coronal plane deformity in patients with rheumatoid arthritis (RA) undergoing silicone metacarpophalangeal (MCP) arthroplasty. Methods: We retrospectively identified silicone MCP arthroplasties performed in patients with RA with known ACPA serostatus from 2000 to 2022. Kaplan-Meier estimates were used to report survival free from revision, all-cause reoperation, and recurrence of coronal plane deviation >10° on postoperative radiographs. We analyzed ACPA serostatus as a risk factor for these endpoints using cluster-robust Cox proportional hazard models, adjusting for patient sex. Results: We included 133 joints in 39 ACPA seropositive patients (9.0 years mean follow-up) and 63 joints in 21 ACPA seronegative patients (5.7 years mean follow-up). Survival free from revision, all-cause reoperation, and recurrent coronal deformity was higher in seropositive patients than in seronegative patients. Anti-cyclic citrullinated peptide antibody seropositivity was significantly associated with lower risk for revision (hazard ratio [HR] = 0.16), all-cause reoperation (HR = 0.20), and recurrent coronal plane deviation >10° (HR = 0.28). Seropositive patients had longer average time to recurrent coronal deviation >10° (3.5 years vs 1.3 years) and less coronal deviation at final radiographic follow-up (15.9° vs 21.5°). Conclusions: Anti-cyclic citrullinated peptide antibody seropositivity is associated with improved silicone MCP implant survivorship and lower risk of recurrent coronal plane deformity in patients with rheumatoid arthritis. More work is needed to better understand the biologic basis of these findings.