Scott, C

Image-derived artificial intelligence (AI) risk models have shown promise in short-term risk assessment for improving breast cancer (BC) screening. No image-derived long-term AI risk model for primary prevention has been developed and externally validated. Individuals aged 31 to 94 years were recruited between 2010 and 2020 in two population-based case cohorts (Olmsted County, Minnesota, US, and KARMA, Sweden) and one hospital-based case-control study (EMBED, Atlanta, US). Median follow-up in the case cohorts was 10 years, with BCs diagnosed through June 2022. Additional validation was performed in EMBED with 3-year follow-up. An AI risk model was developed in Sweden, and we report independent validation in Olmsted/KARMA/EMBED. Absolute 10-year risks were estimated at study entry. Time-dependent discriminatory performance [AUC( t )] and expected-to-observed events (E/O) were estimated. Comparisons were performed with clinical risk tools and the image-based Mirai tool. Across Olmsted/KARMA, 8696 individuals (mean age, 54.4±10.6) and 1633 individuals with incident BC (mean age, 57.0±10.6) were included. Average 10-year risks were 3.83 and 3.14%, and E/O ratios were 0.99 and 0.99. Ten-year AUC( t ) for invasive BCs were 0.72 in Olmsted and 0.72 in KARMA. Similar discriminatory results were observed in EMBED. Our AI risk tool performed significantly better than Mirai in Olmsted/KARMA/EMBED. In KARMA, in the top 10% of high-risk individuals, the AI risk tool predicted 33% of BCs compared with 23%/20%/24% predicted by Tyrer-Cuzick-v8/BCSC-v3/Mirai (all P < 0.01). The 10-year image-derived AI risk model showed significantly higher performance than clinical risk models and Mirai in diverse populations, supporting its clinical potential for primary prevention.

Abstract Rationale Acute cellular rejection (ACR) within first-year post-lung transplantation has important implications for prognosis. Calcineurin inhibitors (CNI), including tacrolimus or cyclosporine, along with cell cycle inhibitors (CCI) and steroids, remain the standard immunosuppression regimen post-transplant. Although tacrolimus is used as the primary CNI, target therapeutic levels vary across recipients due to adverse effects and tolerability, sometimes requiring switching over to Cyclosporine. We hypothesized that ACR within the first year is associated with switching CNI from Tacrolimus to Cyclosporine. Methods We performed a cross-sectional study of 255 adult lung transplant recipients between June 2019 to November 2024 at Mayo Clinic, Florida. Demographics, induction regimens, CNI type and their levels (average low and high levels) were compared between the 2 groups. The institutional maintenance immunosuppression regimen is Tacrolimus, Mycophenolate Mofetil (MMF) and prednisone, but could be switched to Cyclosporine if the previous regimen is not tolerated. The primary outcome was ACR &lt;1 year diagnosed based on biopsy and/or clinical criteria. Comparisons between groups were performed using Chi-Square test for categorical variables and t-test or Wilcoxon Rank sum test for continuous variables. Multivariable regression analysis was performed with ACR &lt;1 year as the outcome to adjust for the confounders. Results Our cohort included 255 lung transplant recipients with median age of 63 years, 61% Male, 84% Caucasians, 88% bilateral lung transplant (Further details elucidated in Table 1). A total of 173 (67%) out of 255 patients had ACR &lt;1 year. The group with ACR &lt; 1 year had higher proportion of Interstitial Lung Disease (ILD) (81% vs 68%, p = 0.044), use of Basiliximab for induction (70% vs 55%, p = 0.018), and cyclosporine instead of tacrolimus (23% vs 11%, p = 0.027). Group with ACR &lt;1 year also had higher Antibody Mediated Rejection (AMR) &lt; 1year (15% vs 6.1%, p = 0.041) and higher CLAD (BOS 0p-3: 43% vs 25.6%, p = 0.033) compared to the group without ACR &lt; 1 year (Table 1.1). Multivariate regression analysis showed ILD (adjusted odds ratio, aOR 2.84, 95% CI 1.31 - 6.27, p = 0.008) and use of cyclosporine (aOR 2.55, 95% CI 1.07 - 6.78, p = 0.034) as independent predictors of ACR &lt; 1 year (Table 2). Conclusions The presence of ACR &lt; 1 year was associated with the use of Cyclosporine over Tacrolimus as a maintenance regimen. Also, ACR &lt; 1year was associated with higher AMR and CLAD. Further prospective studies are needed to study this long-term given its significant prognostic implications. This abstract is funded by: Not Applicable