Citations

Abstract Aims The diagnosis of heart failure with preserved ejection fraction (HFpEF) remains challenging based on resting assessments. Exercise echocardiography is often used to unmask abnormalities that develop during exercise, but the diagnostic criteria have not been standardized. This study aimed to elucidate how cardiologists utilize exercise echocardiography to diagnose HFpEF in real-world practice. Methods and results An international web-based survey involving 87 cardiologists was performed. We also performed a retrospective cross-sectional study to investigate the impact of different exercise echocardiographic diagnostic criteria in 652 dyspnoeic patients who underwent exercise echocardiography. The HFA-PEFF algorithm was the most commonly used exercise echocardiography criterion for HFpEF diagnoses (48%), followed by the ASE/EACVI criteria (24%) and other combinations of multiple parameters (22%). Among 652 patients, the proportion of HFpEF diagnosis varied substantially according to the criteria used ranging from 20.1% (ASE/EACVI criteria) to 44.3% (HFA-PEFF algorithm). Many cases (49.4–70.5%) remained indeterminate after exercise echocardiography, but only 41% of surveyed cardiologists would utilize exercise right heart catheterization to resolve an indeterminate result. Despite these diagnostic uncertainties, 54% of surveyed cardiologists would utilize exercise echocardiography results to initiate sodium–glucose co-transporter 2 inhibitors. Conclusion In real-world practice, exercise echocardiographic criteria utilized across cardiologists vary, which meaningfully impacts the frequency of HFpEF diagnoses, with indeterminate results being common. Despite these diagnostic uncertainties, many cardiologists initiate pharmacotherapy based on exercise echocardiography. The lack of consensus on universal diagnostic criteria for exercise echocardiography and approaches to indeterminate results may limit the delivery of evidence-based treatment for HFpEF.

LBA7005 Background: Despite recent advances, there remains a need for novel therapies for pts with R/R DLBCL. BV, an anti-CD30 antibody-drug conjugate, has shown efficacy and safety when combined with lenalidomide (len) and with rituximab (R) in heavily pretreated populations (Bartlett 2022; Ward 2022). The double-blind, global phase 3 ECHELON-3 study (NCT04404283) compared BV with R+len (R2) vs R2 in pts with R/R DLBCL who are ineligible for HSCT or CAR T-cell therapy. Here, we present results from the interim analysis (IA) for overall survival (OS). Methods: Pts with R/R DLBCL received BV+R2 or placebo+R2 (randomized 1:1). Pts received BV (1.2 mg/kg) or placebo q3w, R (375 mg/m2) q3w, and len (20 mg) qd. The primary endpoint was OS in the intent-to-treat population. Secondary endpoints were investigator-assessed progression-free survival (PFS), objective response rate (ORR), and complete response (CR) rate. The preplanned IA was performed at 134 OS events with a prespecified efficacy boundary of 2-sided P=0.0232. Results: 230 pts were randomized: 112 to BV+R2 and 118 to R2; all but 2 pts (both in R2 arm) received ≥1 dose of study drug. Median age was 71 yrs (range, 21-89), 56.5% were male, and 10.9% had an ECOG of 2. Median prior lines of therapy was 3 (range, 2-8); 29% had prior CAR T-cell therapy and 68% were CD30- (<1% CD30 tumor expression). At median follow-up of 16.4 months (mos) (range, 0.1-31.5) (cut-off: January 22, 2024), median OS was 13.8 mos (95% CI: 10.3-18.8) with BV+R2 vs 8.5 mos (95% CI: 5.4-11.7) with R2 (HR 0.629; 95% CI: 0.445-0.891; P=0.0085); OS benefit was consistent across key subgroups. Median PFS was 4.2 mos (95% CI: 2.9-7.1) with BV+R2 vs 2.6 mos (95% CI: 1.4-3.1) with R2 (HR 0.527; 95% CI: 0.380-0.729; P<0.0001). ORR was 64.3% (95% CI: 54.7-73.1) with BV+R2 vs 41.5% with R2 (95% CI: 32.5-51.0; P=0.0006); CR rate was 40.2% vs 18.6%, respectively. In CD30+ vs CD30- subgroups, ORR/CR was 72.2%/38.9% vs 60.5%/40.8% with BV+R2, respectively, and 50.0%/26.3% vs 37.5%/15.0% with R2, respectively. Efficacy analysis including cell of origin will be presented. The safety profile of BV+R2 was tolerable vs R2: Grade (Gr) ≥3 treatment-emergent adverse events (TEAEs) were 88% vs 77%, serious TEAEs were 60% vs 50%, and Gr 5 TEAEs were 12% vs 8%, respectively. Most common TEAEs were neutropenia (46% vs 32%), anemia (29% vs 27%), and diarrhea (31% vs 23%). Rates of peripheral neuropathy for BV+R2 vs R2 were 31% vs 24% (all Gr) and 6% vs 2% (Gr 3). Median treatment duration was 3.6 mos with BV+R2 vs 2.0 mos with R2. Conclusions: Treatment with BV+R2 triplet, compared to R2, demonstrated statistically significant and clinically meaningful improvements in all key efficacy outcomes including OS in high-risk subgroups, with manageable safety. This triplet regimen represents a novel treatment option for pts with heavily pretreated R/R DLBCL. Clinical trial information: NCT04404283 .

PURPOSE We investigated time to pregnancy, efficacy and safety of fertility preservation, and assisted reproductive technologies (ARTs) in women with early hormone receptor–positive breast cancer (BC) desiring future pregnancy. PATIENTS AND METHODS POSITIVE is an international, single-arm, prospective trial, in which 518 women temporarily interrupted adjuvant endocrine therapy to attempt pregnancy. We evaluated menstruation recovery and factors associated with time to pregnancy and investigated if ART use was associated with achieving pregnancy. The cumulative incidence of BC-free interval (BCFI) events was estimated according to the use of ovarian stimulation at diagnosis. The median follow-up was 41 months. RESULTS Two hundred seventy-three patients (53%) reported amenorrhea at enrollment, of whom 94% resumed menses within 12 months. Among 497 patients evaluable for pregnancy, 368 (74%) reported at least one pregnancy. Young age was the main factor associated with shorter time to pregnancy with cumulative incidences of pregnancy by 1 year of 63.5%, 54.3%, and 37.7% for patients age <35, 35-39, and 40-42 years, respectively. One hundred and seventy-nine patients (36%) had embryo/oocyte cryopreservation at diagnosis, of whom 68 reported embryo transfer after enrollment. Cryopreserved embryo transfer was the only ART associated with higher chance of pregnancy (odds ratio, 2.41 [95% CI, 1.75 to 4.95]). The cumulative incidence of BCFI events at 3 years was similar for women who underwent ovarian stimulation for cryopreservation at diagnosis, 9.7% (95% CI, 6.0 to 15.4), compared with those who did not, 8.7% (95% CI, 6.0 to 12.5). CONCLUSION In POSITIVE, fertility preservation using ovarian stimulation was not associated with short-term detrimental impact on cancer prognosis. Pregnancy rates were highest among those who underwent embryo/oocyte cryopreservation followed by embryo transfer.

Objective Previous studies indicate that eosinophils are recruited into the allograft following orthotopic liver transplantation and protect from ischaemia reperfusion (IR) injury. In the current studies, we aim to explore whether their protective function could outlast during liver repair. Design Eosinophil-deficient mice and adoptive transfer of bone marrow-derived eosinophils (bmEos) were employed to investigate the effects of eosinophils on tissue repair and regeneration after hepatic IR injury. Aside from exogenous cytokine or neutralising antibody treatments, mechanistic studies made use of a panel of mouse models of eosinophil-specific IL-4/IL-13-deletion, cell-specific IL-4rα-deletion in liver macrophages and hepatocytes and macrophage-specific deletion of heparin-binding epidermal growth factor-like growth factor (hb-egf). Result We observed that eosinophils persisted over a week following hepatic IR injury. Their peak accumulation coincided with that of hepatocyte proliferation. Functional studies showed that eosinophil deficiency was associated with a dramatic delay in liver repair, which was normalised by the adoptive transfer of bmEos. Mechanistic studies demonstrated that eosinophil-derived IL-4, but not IL-13, was critically involved in the reparative function of these cells. The data further revealed a selective role of macrophage-dependent IL-4 signalling in liver regeneration. Eosinophil-derived IL-4 stimulated macrophages to produce HB-EGF. Moreover, macrophage-specific hb-egf deletion impaired hepatocyte regeneration after IR injury. Conclusion Together, these studies uncovered an indispensable role of eosinophils in liver repair after acute injury and identified a novel crosstalk between eosinophils and macrophages through the IL-4/HB-EGF axis.

Abstract Background: Oncofertility counseling in BRCA carriers has unique challenges due to a possible negative impact of germline pathogenic/likely pathogenic variants (PVs) on reproductive potential and the indication to undergo risk-reducing bilateral salpingo-oophorectomy. While previous studies demonstrated the safety of pregnancy in women with prior breast cancer (BC) history, limited evidence exists in BRCA carriers specifically. We report the results of the largest study to date investigating likelihood of pregnancy after BC, reproductive and disease outcomes specifically in BRCA carriers. Methods: This was an international, multicenter, hospital-based, retrospective cohort study including young BRCA carriers with history of BC (NCT03673306). Eligible patients were women harboring germline PVs in BRCA1 and/or BRCA2 and diagnosed with stage I-III invasive BC at the age of ≤ 40 years between January 2000 and December 2020. BRCA healthy carriers or patients with BRCA variants of unknown significance, non-invasive BC, lack of follow-up, prior ovarian cancer or other malignancies without history of BC were excluded. Primary endpoints were pregnancy rate and disease-free survival (DFS). Overall survival (OS), BC specific survival (BCSS), pregnancy, fetal and obstetric outcomes were secondary endpoints. To mitigate the impact of guaranteed time bias, two survival analyses were performed: 1) Extended Cox model with occurrence of pregnancy as a time-varying covariate; 2) Case-control analysis by matching 1:3 patients with and without a pregnancy for type of BRCA PV, hormone receptor status, nodal status and year at diagnosis; moreover, each control had to have a disease-free interval longer than the time occurring between BC diagnosis and conception of the matched case. Results: From 78 centers worldwide, 4,732 patients were included, of whom 659 had at least one pregnancy after BC (pregnancy cohort) and 4,073 did not (non-pregnancy cohort). Patients in the pregnancy cohort were significantly more likely to carry BRCA1 PVs, to be younger at BC diagnosis, to have node-negative and hormone receptor-negative (HR-) BC (all p&lt; 0.01). Pregnancy rate at 10 years was 22% (95% CI 21%-24%) overall, 18% (95% CI 16%-21%) and 26% (95% CI 24%-26%) in patients with HR+ and HR- BC, respectively (p&lt; 0.01). Median time from BC diagnosis to conception was 3.5 years (IQR 2.2-5.3 years), significantly longer in patients with HR+ than HR- BC (4.3 vs 3.2 years, p&lt; 0.01). Among 659 patients with a pregnancy after BC, 45 (6.8%) and 63 (9.6%) experienced an induced abortion or a miscarriage, respectively. Of the 517 (78.5%) patients with completed pregnancy, 54 (10.4%) had twins and 406 (78.5%) delivered at term (delivery ≥37 weeks). Among the 571 babies born, 5 (0.9%) had congenital anomalies. Median follow-up was 7.8 years (IQR, 4.5-12.6 years). No significant difference in DFS was observed between the pregnancy and non-pregnancy cohorts (unadjusted HR 0.97, 95% CI 0.82-1.15, p=0.74; adjusted HR [aHR] 0.99, 95% CI 0.81-1.20, p=0.90). Patients in the pregnancy cohort showed significantly better BCSS (HR 0.53, 95% CI 0.38-0.74, p&lt; 0.01; aHR 0.59, 95% CI 0.41-0.86, p&lt; 0.01) and OS (HR 0.52, 95% CI 0.38-0.72, p&lt; 0.01; aHR 0.58, 95% CI 0.40-0.85, p&lt; 0.01). Similar results were obtained in the case-control analysis. Subgroup analyses of survival endpoints according to patient, tumor and treatment characteristics will be presented at the conference. Conclusions: In this global study, 1 out of 5 young BRCA carriers conceived within 10 years after a BC diagnosis, higher than rates previously reported in unselected young BC populations. Pregnancy following BC in BRCA carriers did not appear to adversely impact maternal prognosis or fetal outcomes. These findings should be incorporated into oncofertility counseling of young BRCA carriers with BC. Citation Format: Matteo Lambertini, Eva Blondeaux, Elisa Agostinetto, Anne-Sophie Hamy-Petit, Hee Jeong Kim, Camila Chiodi, Rinat Bernstein-Molho, Florentine Hilbers, Katarzyna Pogoda, Estela Carrasco Lopez, Kevin Punie, Jyoti Bajpai, Michail Ignatiadis, Halle Moore, Kelly-Anne Phillips, Angela Toss, Christine Rousset-Jablonski, Fedro Alessandro Peccatori, Tiphaine Renaud, Alberta Ferrari, Shani Paluch-Shimon, Robert Fruscio, Wanda Cui, Stephanie Wong, Claudio Vernieri, Kathryn Ruddy, Maria Vittoria Dieci, Alexios Matikas, Mariya Rozenblit, Cynthia Villareal Garza, Laura De Marchis, Lucia Del Mastro, Fabio Puglisi, Maria Del Pilar Estevez-Diz, Kenny A. Rodriguez-Wallberg, Bela Mrinakova, Sarah Meister, Luca Livraghi, Florian Clatot, Rinat Yerushalmi, Carmine De Angelis, Rodrigo Sánchez-Bayona, Icro Meattini, Natalia Cichowska-Cwalińska, Martine Berlière, Mahmoud Salama, Ugo De Giorgi, Amir Sonnenblick, Hatem Azim, Ann Partridge. Pregnancy after breast cancer in young women with germline BRCA pathogenic variants: results from an international cohort study [abstract]. In: Proceedings of the 2023 San Antonio Breast Cancer Symposium; 2023 Dec 5-9; San Antonio, TX. Philadelphia (PA): AACR; Cancer Res 2024;84(9 Suppl):Abstract nr GS02-13.

Abstract Background: The POSITIVE trial recently demonstrated that temporary interruption of ET to attempt pregnancy does not increase the short-term risk of recurrence in pts with hormone receptor-positive (HR+) BC. Yet, uncertainty exists regarding the safety of ovarian stimulation for embryo/oocyte cryopreservation to preserve fertility in these pts. In addition, very limited data exist regarding safety and efficiency of ART to achieve pregnancy after ET interruption. Methods: POSITIVE is an international, single-arm, prospective trial that enrolled pts ≤ 42 years with stage I-III HR+ BC who had already received 18-30 months of ET prior to enrollment. The use of ART was a predefined 2ry endpoint. We evaluated factors associated with time to pregnancy in a Fine and Gray competing risks model, which included chemotherapy (chemo) ± GnRH analogue (GnRHa), age, prior ET, prior birth, and menstrual status at enrollment. The cumulative incidence of pregnancy at 12 months from enrollment by age was estimated controlling for competing risks. We performed a logistic regression model to evaluate whether ART use was associated with achieving pregnancy, adjusting for age, receipt of chemo ± GnRHa. The cumulative incidence of BCFI events was estimated according to whether or not ovarian stimulation for cryopreservation was performed at diagnosis and prior to enrollment. BC-free interval (BCFI) was defined as the time from enrollment until the first BC event (invasive local, regional, or distant recurrence or contralateral disease). A 24-month landmark analysis was performed to investigate the safety of ART use after enrollment. Median follow-up was 41 months. Results: 497 out of 516 included pts (96%) were followed for at least 6 months and were evaluable for pregnancy status. 368 out of 497 evaluable pts (74%) reported at least one pregnancy. In a multivariable model, young age was the only factor associated with shorter time to pregnancy. The cumulative incidence of pregnancy at 12 months was 64%, 54% and 38% for pts aged &lt; 35, 35-39 and 40-42 years, respectively. 179 pts (36.0%) had undergone ovarian stimulation for embryo/oocyte cryopreservation at diagnosis and prior to enrollment, of whom 68 (37.9%) reported cryopreserved embryo transfer after enrollment. 215 pts (43.3%) reported using any ART after enrollment, of whom 80 (37.2%) underwent ovarian stimulation for in-vitro fertilization (FIVET) or intracytoplasmic sperm injection (ICSI). Other ART used included clomiphene (n=19), intrauterine insemination (n=37) and egg donation (n=17). Pregnancy rates were 82.4% and 67.5% for women who underwent cryopreserved embryo transfer and FIVET/ICSI, respectively. In a multivariate model, cryopreserved embryo transfer was the only ART independently associated with a higher chance of pregnancy (OR:2.41, 95% CI: 1.75-4.95). The cumulative incidence of BCFI events at 3 years was similar for women who underwent ovarian stimulation for cryopreservation at diagnosis and before enrollment, 9.7% (95% CI: 6.0-15.4%), and those who did not, 8.7% (95% CI: 6.0-12.5%). A 24-month landmark analysis showed no impact of ovarian stimulation for FIVET/ICSI after enrollment on BCFI. Conclusions: This is the largest prospective study to investigate fertility preservation and ART in pts with HR+ BC. Young age was the main factor associated with shorter time to pregnancy. Embryo/oocyte cryopreservation at BC diagnosis followed by embryo transfer after ET interruption was the only approach associated with an increased chance of pregnancy. Ovarian stimulation either at BC diagnosis for embryo/oocyte cryopreservation or after enrollment to POSITIVE for FIVET/ICSI did not appear to impact prognosis in the short term. These data are of paramount importance for oncofertility counselling of young BC pts. Citation Format: Hatem Azim, Samuel Niman, Ann Partridge, Isabelle Demeestere, Monica Ruggeri, Marco Colleoni, Cristina Saura, Chikako Shimizu, Anna Saetersdal, Judith Kroep, Audrey Mailliez, Ellen Warner, Virginia Borges, Frédéric Amant, Andrea Gombos, Akemi Kataoka, Christine Rousset-Jablonski, Simona Borstnar, Junko Takei, Jeong Eon Lee, Janice Walshe, Manuel Ruíz - Borrego, Halle Moore, Christobel Saunders, Vesna Bjelic-Radisic, Snezana Susnjar, Fatima Cardoso, Natalie Klar, Tanya Spanic, Kathryn Ruddy, Martine Piccart, Larissa Korde, Aron Goldhirsch, Richard Gelber, Olivia Pagani, Fedro Alessandro Peccatori. Fertility preservation and assisted reproductive technologies (ART) in breast cancer (BC) patients (pts) interrupting endocrine therapy (ET) to attempt pregnancy [abstract]. In: Proceedings of the 2023 San Antonio Breast Cancer Symposium; 2023 Dec 5-9; San Antonio, TX. Philadelphia (PA): AACR; Cancer Res 2024;84(9 Suppl):Abstract nr GS02-11.

Background: Differential kidney function assessment is an important part of preoperative evaluation of various urological interventions. It is obtained through dedicated nuclear medical imaging and is not yet implemented through conventional Imaging. Objective: We assess if differential kidney function can be obtained through evaluation of contrast-enhanced computed tomography(CT) using a combination of deep learning and (2D and 3D) radiomic features. Methods: All patients who underwent kidney nuclear scanning at Mayo Clinic sites between 2018–2022 were collected. CT scans of the kidneys were obtained within a 3-month interval before or after the nuclear scans were extracted. Patients who underwent a urological or radiological intervention within this time frame were excluded. A segmentation model was used to segment both kidneys. 2D and 3D radiomics features were extracted and compared between the two kidneys to compute delta radiomics and assess its ability to predict differential kidney function. Performance was reported using receiver operating characteristics, sensitivity, and specificity. Results: Studies from Arizona & Rochester formed our internal dataset ( n = 1,159). Studies from Florida were separately processed as an external test set to validate generalizability. We obtained 323 studies from our internal sites and 39 studies from external sites. The best results were obtained by a random forest model trained on 3D delta radiomics features. This model achieved an area under curve (AUC) of 0.85 and 0.81 on internal and external test sets, while specificity and sensitivity were 0.84,0.68 on the internal set, 0.70, and 0.65 on the external set. Conclusion: This proposed automated pipeline can derive important differential kidney function information from contrast-enhanced CT and reduce the need for dedicated nuclear scans for early-stage differential kidney functional assessment. Clinical Impact: We establish a machine learning methodology for assessing differential kidney function from routine CT without the need for expensive and radioactive nuclear medicine scans.

BACKGROUND: Associations of early changes in vasoactive support with cardiogenic shock (CS) mortality remain incompletely defined. METHODS: The Critical Care Cardiology Trials Network is a multicenter registry of cardiac intensive care units. Patients admitted with CS (2018–2023) had vasoactive dosing assessed at 4 and 24 hours from cardiac intensive care unit admission and quantified by the vasoactive-inotropic score (VIS). Prognostic associations of VIS at both time points, as well as change in VIS from 4 to 24 hours, were examined. Interaction testing was performed based on mechanical circulatory support status. RESULTS: Among 3665 patients, 82% had a change in VIS <10, with 7% and 11% having a ≥10-point increase and decrease from 4 to 24 hours, respectively. The 4 and 24-hour VIS were each associated with cardiac intensive care unit mortality (13%–45% and 11%–73% for VIS <10 to ≥40, respectively; P trend <0.0001 for each). Stratifying by the 4-hour VIS, changes in VIS from 4 to 24 hours had a graded association with mortality, ranging from a 2- to >4-fold difference in mortality comparing those with a ≥10-point increase to ≥10-point decrease in VIS ( P trend <0.0001). The change in VIS alone provided good discrimination of cardiac intensive care unit mortality (C-statistic, 0.72 [95% CI, 0.70–0.75]) and improved discrimination of the 24-hour Sequential Organ Failure Assessment score (0.72 [95% CI, 0.69–0.74] to 0.76 [95% CI, 0.74–0.78]) and the clinician-assessed Society for Cardiovascular Angiography and Interventions shock stage (0.72 [95% CI, 0.70–0.74] to 0.77 [95% CI, 0.75–0.79]). Although present in both groups, the mortality risk associated with VIS was attenuated in patients managed with versus without mechanical circulatory support (odds ratio per 10-point higher 24-hour VIS, 1.36 [95% CI, 1.23–1.49] versus 1.84 [95% CI, 1.69–2.01]; P interaction <0.0001). CONCLUSIONS: Early changes in the magnitude of vasoactive support in CS are associated with a gradient of risk for mortality. These data suggest that early VIS trajectory may improve CS prognostication, with the potential to be leveraged for clinical decision-making and research applications in CS.

AbstractThe APOE4 allele is recognized as a significant genetic risk factor to Alzheimer's disease (AD) and influences longevity. Nonetheless, some APOE4 carriers exhibit resistance to AD even in advanced age. Humanin, a mitochondrial‐derived peptide comprising 24 amino acids, has variants linked to cognitive resilience and longevity. Our research uncovered a unique humanin variant, P3S, specifically enriched in centenarians with the APOE4 allele. Through in silico analyses and subsequent experimental validation, we demonstrated a strong affinity between humanin P3S and APOE4. Utilizing an APOE4‐centric mouse model of amyloidosis (APP/PS1/APOE4), we observed that humanin P3S significantly attenuated brain amyloid‐beta accumulation compared to the wild‐type humanin. Transcriptomic assessments of mice treated with humanin P3S highlighted its potential mechanism involving the enhancement of amyloid beta phagocytosis. Additionally, in vitro studies corroborated humanin P3S's efficacy in promoting amyloid‐beta clearance. Notably, in the temporal cortex of APOE4 carriers, humanin expression is correlated with genes associated with phagocytosis. Our findings suggest a role of the rare humanin variant P3S, especially prevalent among individuals of Ashkenazi descent, in mitigating amyloid beta pathology and facilitating phagocytosis in APOE4‐linked amyloidosis, underscoring its significance in longevity and cognitive health among APOE4 carriers.

Abstract Background: Microsatellite instability-high (MSI-H) tumors respond well to immune checkpoint blockade and oftentimes not to chemotherapeutics. Despite value of determining MSI status to guide therapy, many patients’ samples are not untested. Deep learning models may be able to predict MSI status by analyzing hematoxylin and eosin (H&E) stained whole-slide images (WSIs). Validation of this tool will provide another tool to increase MSI testing. However, to be deployed into clinical routine care, prediction models need be externally validated in large and diverse patient cohorts. In addition, these models should provide uncertainty of prediction to help clinicians make informed decisions. Results: In this study, we introduce a novel Bayesian prediction model using whole-slide images (WSIs) and deep Gaussian processes (DGPs) in a weakly supervised learning context. Extensively tested on large datasets (n=3,146) from multiple centers, our model not only demonstrated superior performance but also showed that incorporating uncertainty into predictions significantly improves MSI prediction accuracy, achieving AUROC of &gt;0.91 in colon cancer and &gt;0.94 in gastric cancer. Additionally, an in-depth analysis within the gastric cancer cohort indicated a significant correlation between predicted MSI-H regions and immunotherapy response. Patients who responded to immune checkpoint inhibitors had a higher proportion of MSI-H regions (P-value &lt; 0.05). This correlation was also observed in patients categorized as MSS but responsive to ICIs, highlighting the potential of our model to identify MSI-H patterns not detected through standard laboratory tests. This advancement could lead to more precise patient selection for ICI therapy, enhancing personalized treatment strategies in gastrointestinal cancer. Citation Format: Sunho Park, Minj Kim, Ji-Youn Sung, Jeong Hwan Park, Sung Hak Lee, Sam C. Wang, Jaeho Cheong, Tae Hyun Hwang. Explainable AI model incorporating uncertainty estimation for enhanced MSI-H prediction and immunotherapy response in gastrointestinal cancer [abstract]. In: Proceedings of the American Association for Cancer Research Annual Meeting 2024; Part 1 (Regular Abstracts); 2024 Apr 5-10; San Diego, CA. Philadelphia (PA): AACR; Cancer Res 2024;84(6_Suppl):Abstract nr 7385.