Citations

Clear

6273 citation(s) found for "To, Andrew".

Finite Element Modeling of the Scaphoid Shift Maneuver: Implications for Scapholunate Ligament injuries
Andreassen, Thor E. , Thoreson, Andrew R. , Parunyu, Vilai, An, Kai-Nan, Kakar, Sanjeev , Zhao, Kristin D. , Trentadue, Taylor P , Thoreson, Andrew R , An, Kai-Nan , Kakar, Sanjeev , Trentadue, Taylor P , Andreassen, Thor E , Trentadue, Taylor P. , Vilai, Parunyu , An, Kai‐Nan

Mayo Clinic

No container title available | February 19, 2026 | Volume: No volume available | Issue: No issue available | Pages: No page available

10.64898/2026.02.17.705556 | PMID 41756899 Get It

Abstract Background Computational modeling is a tool being deployed for orthopaedic solutions but its use in the hand and wrist remains limited. This work used a model to simulate a clinically relevant provocative scaphoid shift maneuver (SSM) with different levels of scapholunate interosseous ligament (SLIL) injuries to observe the effect on different metrics. Methods A personalized model simulated the full SSM motion cycle from ulnar deviation with extension to radial deviation with flexion informed by the participant’s motion obtained from dynamic computed tomography. Models repeated the SSM under different levels of SLIL injury and reported changes in joint kinematics, contact mechanics, and ligament forces. Results The fully injured model increased scaphoid dorsal translation, flexion, and radial deviation compared to the intact condition and caused a subluxation of the scaphoid. Radioscaphoid contact areas were approximately 200% greater in the fully injured model compared with all others and the fully injured model was the only condition where contact force decreased across the motion cycle. Ligament forces in the intact condition were on average 33.0 N and 54.2 N for the volar and dorsal SLIL, respectively. Lastly, the long radiolunate, an extrinsic stabilizer, had forces that increased following SLIL injury. Conclusions Computational models can successfully recreate clinically observed behaviors of an SSM, including scaphoid subluxation, while providing new insights via quantification of contact mechanics and ligament forces. Contact mechanics metrics may be important for understanding the long-term progression of untreated SLIL injuries to osteoarthritis. Additionally, ligament force metrics may explain the progression of SLIL injuries from volar SLIL to dorsal SLIL and highlight the importance of repairing extrinsic stabilizers of the joint, due to increased force sharing following SLIL injury. This work provides a pathway to future studies investigating the effects of SLIL injury and repair, both acutely and chronically.
Patterns of care and clinical outcomes in systemic peripheral T-cell lymphoma: the LEO-MER prospective cohort study
Ruan, Jia , Chen, Zhengming , Larson, Melissa C, Bennani, N Nora, Allen, Pamela B. , Mou, Eric , Wallace, Danielle , Mehta-Shah, Neha, Lossos, Izidore S, Castillo, Luis E Malpica, Vega, Francisco, Inghirami, Giorgio GA, Pongas, Georgios , Akkad, Neha, Casulo, C., Martin, Peter, Cohen, Jonathon B. , Habermann, Thomas M, Maurer, Matthew J., Leonard, John P, Friedberg, Jonathan W. , Cerhan, James R, Flowers, Christopher R, Feldman, Andrew L, Bennani, N. Nora , Chen, Zhengming , Malpica, Luis , Bennani, N Nora , Allen, Pamela Blair , Mehta-Shah, Neha , Lossos, Izidore S , Malpica Castillo, Luis E , Vega, Francisco , Inghirami, Giorgio , Casulo, Carla , Cohen, Jonathon B , Maurer, Matthew , Kahl, Brad S , Cerhan, James R , Flowers, Christopher R , Feldman, Andrew L , Mou, Eric , Wallace, Danielle S , Larson, Melissa C. , Mehta–Shah, Neha , Lossos, Izidore S. , Castillo, Luis Enrique Malpica , Jaye, David L. , Inghirami, Giorgio , Akkad, Neha , Casulo, Carla , Habermann, Thomas M. , Leonard, John P. , Kahl, Brad S. , Cerhan, James R. , Flowers, Christopher R. , Feldman, Andrew L.

Mayo Clinic

Blood Advances | February 18, 2026 | Volume: 10 | Issue: 10 | Pages: 3480-3493

10.1182/bloodadvances.2025018455 | PMID 41707114 Get It

Abstract Few prospective benchmark studies exist to characterize the evolving contemporary real-world practice for peripheral T-cell lymphoma (PTCL). We report the patterns of first-line care and outcomes for 720 patients with systemic PTCL enrolled in 2 related prospective cohort studies, Lymphoma Epidemiology of Outcomes (LEO) from 2015 to 2020 and Molecular Epidemiology Resource (MER) from 2002 to 2015, both followed to 2024. The primary end points were event-free survival (EFS) and overall survival (OS) using Kaplan-Meier estimator and Cox regression model. Secondary end points included correlations of clinical and treatment factors with survival. The most common induction regimens were CHOP (cyclophosphamide, doxorubicin, vincristine, prednisone) based (70%), given as CHOP (36%), CHOP plus etoposide (23%), or CHOP-like plus novel agents (11.5%, including 5% BV-CHP [brentuximab plus cyclophosphamide, doxorubicin, and prednisone]). Consolidative autologous stem cell transplant was performed in 102 patients (14%). Within nodal PTCL, EFS and OS were adversely associated with International Prognostic Index 2 to 5, prognostic index for T-cell lymphoma score 1 to 4, and non–anaplastic large-cell lymphoma (ALCL) subtypes. Within LEO, which captured increasing first-line etoposide and brentuximab vedotin, adding etoposide to CHOP was associated with better OS in anaplastic lymphoma kinase-negative ALCL. BV-CHP showed a trend toward OS improvement in ALCL. Patients failing EFS6 and EFS24 had 5-year subsequent OS of 12% and 17%, respectively. The inferior outcomes in non-ALCL subtypes and patients failing EFS6 and EFS24 highlight unmet needs with CHOP-based induction, where clinical trials with targeted therapy should be prioritized. This trial was registered at www.clinicaltrials.gov as NCT02736357.
Collaborative large language models (LLMs) are all you need for screening in systematic reviews
Parmar, Mihir, Naqvi, Syed Arsalan Ahmed , Warraich, Kainat , Saeidi, Amir, Rawal, Samarth, Faisal, Kunwer Sufyan , Kazmi, Syeda Zainab , Fatima, Maurish , He, Huan, Safdar, Mohammad, Liu, Wei, Haddad, Tufia C., Wang, Zhen , Murad, Mohammad Hassan, Baral, Chitta, Haddad, Tufia, Riaz, Irbaz Bin , Saeidi, Amir, Haddad, Tufia C.

Mayo Clinic

No container title available | February 18, 2026 | Volume: No volume available | Issue: No issue available | Pages: No page available

10.64898/2026.02.07.26345640 | PMID 41757212 Get It

Abstract Background The ability of large language models (LLMs) to work collaboratively and screen studies in a systematic review (SR) is under-explored. Hence, we aimed to evaluate the effectiveness of LLMs in automating the process of screening in systematic reviews. Methods This is an observational study which included labeled data (title and abstracts) for five SRs. Originally, two reviewers screened the citations independently for eligibility. A third reviewer cross-checked each citation for quality assurance. GPT-4, Claude-3-Sonnet, and Gemini-Pro-1.0 were used using zero-shot chain-of-thought prompting. Collaborative approaches included (i): conflict resolution using benefit of the doubt, (ii) majority voting using an independent third LLM and (iii) conflict resolution using an informed third LLM. Performance was assessed using accuracy, precision for exclusion, and recall for inclusion. Work saved over samples (WSS) was computed to estimate the reduction in manual human effort. Results A total of 11300 articles were included in this study. The individual models, GPT-4, Claude-3-Sonnet, and Gemini-Pro-1.0 exhibited a high precision for exclusion, achieving 99.7%, 99.7%, and 99.2% and high recall for inclusion achieving 95.5%, 96.6% and 85.7%, respectively. However, the collaborative approach utilizing the two best-performing models (GPT-4 and Claude-3S) achieved an average precision of 99.9% and a recall of 98.5% (across all collaborative approaches). Furthermore, the proposed collaborative approach resulted in an average WSS of 63.5%, compared to the average WSS of 45.2% for individual models. Conversational LLM interactions showed a consistent pattern of results. Limitations This study was limited due to reliance on proprietary models, and evaluation on oncology datasets. Conclusion Evidence shows that collaborative LLMs enable efficient, high-performing screening in systematic reviews, supporting continuous evidence updates. Primary funding source NIH (U24CA265879-01-1) and Carolyn-Ann-Kennedy-Bacon Fund.
Spatial transcriptomics reveals mechanism of autoimmunity driven by internalized autoantibodies
Pinal-Fernandez, Iago , Pak, Katherine, Casal-Dominguez, Maria, Muñoz-Braceras, Sandra, Wigerblad, Gustaf , Naz, Faiza, Islam, Shamima, Gutierrez-Cruz, Gustavo, Kinder, Travis B. , Ogbonnaya-Whittlesey, S. Amara, Fernández-Codina, Andreu, Ellezam, Benjamin , Laverny, Gilles, Gilbart, Valentine , Landon-Cardinal, Océane, Hudson, Marie, Troyanov, Yves, Kenea, Aster, Matas-García, Ana, Garrabou, Gloria, Aldecoa, Iban, Ailen-Caballero, Gabriela, Gil-Vila, Albert, Trallero, E., Milone, Margherita , Naddaf, Elie, Espinosa, Gerard, Simeon-Aznar, Carmen Pilar, Guillen-Del-Castillo, Alfredo, Preusse, Corinna, Kleefeld, Felix, Bublitz, Nikolas, Meyer, Alain, Pope, Janet E., Selva-O’Callaghan, Albert, Milisenda, Jose C., Mammen, Andrew L., Pinal‐Fernandez, Iago , Preuße, Corinna , Giannini, Margherita , Ellezam, Benjamin , Milone, M , Liewluck, Teerin , Naddaf, Elie , Kleefeld, Felix , Casal-Domínguez, María , Dell’Orso, Stefania , Naz, Faiza , Islam, Shamima , Ogbonnaya, Sandra Amara, Fernández‐Codina, Andreu , LAVERNY, Gilles , Landon‐Cardinal, Océane , Randazzo, Davide , Matas-García, Ana , Garrabou, Glòria , Aldecoa, Ibán , Gil‐Vila, Albert , Naddaf, Elie , Espinosa, Gerard , Castillo, Alfredo Guillén del , Stenzel, Werner , Meyer, Alain , Pope, Janet , Selva-O’Callaghan, Albert , Milisenda, Jose César , Mammen, Andrew L.

Mayo Clinic

No container title available | February 17, 2026 | Volume: No volume available | Issue: No issue available | Pages: No page available

10.64898/2026.02.14.26346329 | PMID 41757163 Get It

ABSTRACT Autoantibody internalization has been implicated in autoimmune disease pathogenesis, yet its mechanisms, and generality across different diseases, cell types, and affected tissues remain poorly defined. Using bulk RNA sequencing, we identified reproducible, autoantibody-specific transcriptomic signatures consistent with autoantigen dysfunction in muscle biopsies from patients with anti-Mi2 dermatomyositis and anti-PM/Scl scleromyositis across independent cohorts. Electroporation of purified patient IgG into primary cultures of healthy cells was sufficient to induce the corresponding transcriptomic programs in vitro . Direct immunofluorescence demonstrated immunoglobulin internalization into subcellular compartments matching the localization of the autoantigen in different affected tissues. Spatial transcriptomic analyses revealed that antibody-secreting cells translocated cytoplasmic material (i.e., immunoglobulin RNA) into adjacent affected cells expressing autoantibody-specific transcripts. The disease-specific transcripts were present not only in muscle fibers, but also in other cells, including macrophages, endothelial cells, and fibroblasts. Autoantibody-induced transcriptomic programs were associated with cell damage and autoantibody-specific reactive inflammatory programs, including activation of type I interferon and TGF-ß1 signaling in anti-Mi2 dermatomyositis and activation of type II interferon in anti-PM/Scl scleromyositis. Antibody internalization was also observed in different tissues from patients with other autoimmune diseases, including anti-U1RNP mixed connective tissue disease, anti-Ku overlap syndrome, and anti-Scl70 systemic sclerosis. Together, these findings establish autoantibody internalization as a shared pathogenic mechanism across diverse autoimmune diseases, providing a unifying framework for conditions driven by autoantibodies against intracellular antigens.
Abstract PD4-11: Contralateral Breast Cancer Risk in Women with PALB2-Associated Breast Cancer
Metcalfe, Kelly , Stachowski, A , Couch, F. J., Marabelli, Monica , Wong, S. M., Domchek, S. M., Kim, R., Cajal, T. Ramon y, Fruscio, R, Yadav, S., Hoey, C., Karamali, S., Sun, P., Lubinski, J., Narod, S., Pal, T., Eisen, Andrea , Kim, Raymond H. , Metcalfe, Kelly A , Eisen, Andrea , Kim, Raymond H , Couch, F.J., Aeilts, Amber M. , Eisen, Andrew , Hoey, Christianne, Lubiński, Jan

Mayo Clinic

Clinical Cancer Research | February 17, 2026 | Volume: 32 | Issue: 4_Supplement | Pages: PD4-11-PD4-11

10.1158/1557-3265.sabcs25-pd4-11 Get It

Abstract Introduction: Women with a germline pathogenic variant (PV) in PALB2 face a lifetime risk of breast cancer, generally exceeding 40%. We have initiated an international clinical follow up study of women with stage 0 to stage 4 breast cancer and a PALB2 PV to evaluate clinical characteristics and to determine optimal treatments. The objective of the current study was to estimate and to identify factors predictive of contralateral breast cancer (CBC) risk. Methods: Clinical data, including diagnostic, treatment, and follow-up data, were collected by medical record review for eligible women with breast cancer and a germline PV in PALB2. PV carriers were followed every two years to collect information about recurrences, new cancers, and vital status. Data was summarized using descriptive statistics. The risk of CBC was estimated by following women from the date of breast cancer diagnosis until the date of: 1) contralateral breast cancer, 2) contralateral mastectomy, 3) death from any cause, or 4) last follow-up. The cumulative incidence of CBC was calculated with the Kaplan-Meier method. Cox proportional hazards regression was used to identify factors associated with contralateral breast cancer risk. Covariates included age at diagnosis, ER status, grade, nodal status, chemotherapy, radiation therapy, tamoxifen, and bilateral salpingo-oophorectomy (time-dependent). Results: Among 888 PALB2 carriers, the mean age at diagnosis of breast cancer was 49.3 years (range 22 to 83 years). Overall, 36 women (4.1%) were diagnosed with synchronous bilateral breast cancer. 73.6% of the breast cancers were ER-positive, and 29% were lymph node-positive. Patients were followed for a mean of 5.6 years (range 0.3 to 22 years) from date of diagnosis. During the follow-up period, 53 patients were diagnosed with a metachronous CBC. The 15-year risk of metachronous CBC was 26.4% overall; 19.5% for those diagnosed younger than 50 years, and 34.8% for those diagnosed at 50 years or older. In a multivariate analysis, ER status was not significantly associated with CBC risk (RR 1.15, 95%CI 0.45-2.93, p=0.77). Bilateral salpingo-oophorectomy (BSO) was associated with a significant reduction in the risk of CBC (RR 0.17, 95%CI 0.04-0.70, p=0.02). In the follow-up period, 47 women were diagnosed with another incident cancer, including seven with pancreatic cancer and three with ovarian cancer Conclusion: The high 15-year risk of contralateral breast cancer suggests that bilateral mastectomy should be considered for primary surgical intervention. Moreover, bilateral salpingo-oophorectomy (BSO) significantly reduces the risk of CBC and should be considered post-treatment. Citation Format: K. Metcalfe, A. Stachowski, F. Couch, M. Marabelli, S. Wong, S. Domchek, A. Aeilts, A. Eisen, R. Kim, T. Ramon y Cajal, R. Fruscio, S. Yadav, C. Hoey, S. Karamali, P. Sun, J. Lubinski, S. Narod, T. Pal. Contralateral Breast Cancer Risk in Women with PALB2-Associated Breast Cancer [abstract]. In: Proceedings of the San Antonio Breast Cancer Symposium 2025; 2025 Dec 9-12; San Antonio, TX. Philadelphia (PA): AACR; Clin Cancer Res 2026;32(4 Suppl):Abstract nr PD4-11.
Abstract GS3-01: Menopausal Hormone Therapy and the Risk of Breast Cancer in Women with a Pathogenic Variant in BRCA1 or BRCA2
Kotsopoulos, J., Seca, M., Jacek, G., Huzarski, T., Møller, P., Kim, R. H., Singer, C. F., Karlan, B., Cajal, T. Ramon y, Pal, Tuya, Bordeleau, Louise , Foulkes, W., Tung, N. M., Couch, F. J., Neuhausen, S., Zakalik, Dana , Cybulski, C., Olopade, O. I., Metcalfe, K., Fruscio, R, Sun, P., Lubinski, J., Narod, S., Eisen, Andrea , Metcalfe, Kelly , Kim, Raymond H. , Metcalfe, Kelly A , Eisen, Andrea , Bordeleau, Louise , Kim, Raymond H , Kotsopoulos, Joanne , Seca, Marta , Huzarski, T., Møller, Pål , Kim, R.H., Singer, Christian F. , Karlan, Beth Y. , Aeilts, Amber M. , Pal, Tuya , Eisen, Andrew , Foulkes, William D. , Couch, F.J., Neuhausen, Susan L. , Cybulski, Cezary , Lubiński, Jan

Mayo Clinic

Clinical Cancer Research | February 17, 2026 | Volume: 32 | Issue: 4_Supplement | Pages: GS3-01-GS3-01

10.1158/1557-3265.sabcs25-gs3-01 Get It

Abstract Background: Women with a pathogenic variant in the BRCA1 or BRCA2 gene (carriers) are at a high risk of developing ovarian cancer and recommended to undergo bilateral salpingo-oophorectomy at an early age resulting in surgical menopause. Menopausal hormone therapy (MHT) is the most effective way to mitigate the adverse outcomes of early menopause; however, the safety of MHT on breast cancer risk in this population has not been established. Methods: We conducted a prospective matched analysis of MHT use following menopause (predominantly surgical) and breast cancer risk in BRCA carriers using a matched prospective analysis to emulate a randomized clinical trial. Women without a history of any cancer or bilateral mastectomy and who were enrolled in a longitudinal study with detailed data collection were eligible for inclusion. Women who initiated MHT (exposed) after menopause were matched one-to-one to women who had not initiated MHT (unexposed) by gene, year of birth, and age at menopause, resulting in 676 matched pairs. Cox proportional hazards regression to estimate the hazard ratios (HR) and 95%CIs (CI) of incident breast cancer associated with MHT use. Results: After a mean follow-up of 5.6 years from the date of first MHT use in the exposed woman, there were 87 incident breast cancer cases in the exposed group (12·9%) and 128 cases in the unexposed group (18·9%) (P = 0·002). Compared to their unexposed match, women who used estrogen (E) experienced a significant decrease in the risk of breast cancer (HR = 0·37; 95%: CI 0·24-0·57). There was no protective (or adverse) effect associated with the use of E plus progestogen (E+P) (HR = 0·94; 95%CI 0·54-1·63), with progestogen alone (P) (HR = 1·14; 95%CI: 0·21-6·22) or with tibolone (HR = 0·57; 95%CI: 0·19-1·69). There were no diagnoses of breast cancer in the 43 women who used a CEE + bazedoxifene. Findings were similar for carriers of either gene mutation. Conclusion: To our knowledge, this represents the largest prospective report of MHT use and breast cancer risk in BRCA1 and BRCA2 carriers. Our findings showed no increase in the risk of breast cancer with the use of MHT, irrespective of gene mutation or formulation. These findings provide an evidence-based approach for the management of women at high-risk of breast cancer who are facing the acute and chronic effects of early surgical menopause. The safe use of MHT by BRCA carriers will continue to be an important research topic as formulations continue to evolve. Citation Format: J. Kotsopoulos, M. Seca, G. Jacek, T. Huzarski, P. Møller, R. H. Kim, C. Singer, B. Karlan, A. Aeilts, T. Ramon y Cajal, T. Pal, A. Eisen, L. Bordeleau, W. Foulkes, N. Tung, F. Couch, S. Neuhausen, D. Zakalik, C. Cybulski, O. Olopade, K. Metcalfe, R. Fruscio, P. Sun, J. Lubinski, S. Narod, Hereditary Breast Cancer Clinical Study Group. Menopausal Hormone Therapy and the Risk of Breast Cancer in Women with a Pathogenic Variant in BRCA1 or BRCA2 [abstract]. In: Proceedings of the San Antonio Breast Cancer Symposium 2025; 2025 Dec 9-12; San Antonio, TX. Philadelphia (PA): AACR; Clin Cancer Res 2026;32(4 Suppl):Abstract nr GS3-01.
Longitudinal Trends in Iron Deficiency Screening and Treatment Before Elective Surgery: A Retrospective Observational Study
Cho, David , Medina-Rincón, Germán José , Behaine, Juan Jose Morales , Robbins, Kellie A., Hanson, Andrew C. , Crispell, Ethan H., Cho, David J , Robbins, Kellie A , Crispell, Ethan H. , Warner, Matthew A.

Mayo Clinic

Anesthesia & Analgesia | February 16, 2026 | Volume: 143 | Issue: 2 | Pages: 434-437

10.1213/ane.0000000000007976 | PMID 41698238 Get It

A Pilot Validation Study of Plant‐Based and Allergy‐Friendly Alternative for Testing Gastric Emptying: A Randomized Trial in Healthy Participants
Abdelnaem, Nada, Carlson, Paula, Busciglio, Irene, Burton, Duane, Ryks, Michael, Johnson, Derek R., Navin, Patrick J. , Bach, Corrie R. , Paulsen, Andrew, Bartlett, David J. , Camilleri, M., Jencks, Kara J. , Bach, Corrie, Paulsen, Andrew M, Camilleri, M , Navin, Patrick , Ryks, Michael, Johnson, Derek R., Camilleri, Michael

Mayo Clinic

Neurogastroenterology & Motility | February 13, 2026 | Volume: 38 | Issue: 2 | Pages: No page available

10.1111/nmo.70268 | PMID 41681033 Get It

ABSTRACT Background Gastric emptying (GE) scintigraphy with 4‐h imaging and a radiolabeled chicken egg‐based meal (320 kcal, 30% fat) is the standard test for gastroparesis at Mayo Clinic, with an intraindividual coefficient of variation (COV intra ) of 23.8% for GE half emptying time (T 1/2 ). Alternative meals for patients with dietary restrictions, including egg allergies or vegan diets, are lacking, limiting test accessibility. The study aimed to establish a vegan, lactose‐, nut‐, and gluten‐free meal with similar caloric and fat content to the egg meal and to assess its performance in GE studies. Methods In Vitro: 99m Tc binding to egg meal over 4 h was compared to a calorically and nutritionally similar vegan alternative, JUST Egg, using a validated in vitro model simulating gastric conditions of pH, pepsin, and stirring. In Vivo: 10 healthy participants underwent randomized crossover GE scintigraphy with standard and vegan meals, spaced ≥ 3 days apart to measure GE% at 2 h, 4 h, and GE T 1/2 . Group comparisons and variance analysis included Rank Sum tests and Bland–Altman plots. Key Results In Vitro: A strong correlation ( R = 0.975, p ‐value < 0.01) between 99m Tc binding in the egg and vegan egg models was observed. Minimal variance (< 10%) was recorded at all time points. In Vivo: GE at 4 h and GE T 1/2 showed non‐statistically significant mean differences, < 2% and < 10 min respectively, between both meals. The intra‐individual variability was 18.8%. Conclusions and Inferences The vegan meal demonstrated in vitro stability, in vivo performance comparable to the egg meal, and a COV intra of 18.8%, which was lower than the 23.8% reported in repeat egg meal GE studies. Trial Registration ClinicalTrials.gov number NCT06991036 ( https://clinicaltrials.gov/study/NCT06991036?term=NCT06991036&rank=1 )
Fatal Cardiomyopathy Secondary to Seronegative Immune-Mediated Necrotizing Myopathy: A Case Report
Lueck, Benjamin D. , Layman, Andrew J. , Ernste, Floranne C. , Arment, Courtney A., Maclean, Alyssa K W, El Hasbani, Georges, Maclean, Alyssa K. W. , Hasbani, Georges El , Layman, Andrew J. , Arment, Courtney A.

Mayo Clinic

American Journal of Case Reports | February 12, 2026 | Volume: 27 | Issue: No issue available | Pages: No page available

10.12659/ajcr.951603 | PMID 41834235 Get It

Artificial Intelligence for Gastroenterology Practice: A Modified Delphi Consensus
Gross, Seth, Shaukat, Aasma, Afzali, A, Ahn, Joseph C., Bajaj, Jasmohan S. , Barkin, Jodie A. , Bilal, Mohammad, Chawla, Saurabh , Coelho-Prabhu, Nayantara, Enslin, Sarah , Feld, Andrew, Gagneja, Harish K., Hass, David J., Horst, Sara N., Jones, Patricia D. , Kushnir, Vladimir M., Leggett, Cadman L. , Leung, Galen G., Mascarenhas, M., Parasa, Sravanthi, Parsa, Nasim , Schairer, Jason N., Spiegel, Brennan, Suthrum, Praveen, Thomas, Sapna, Phillips, Meridith E., Coelho–Prabhu, Nayantara , Spiegel, Brennan , Afzali, Anita , Ahn, Joseph , Bilal, Mohammad , Afzali, Anita , Ahn, Joseph C , Coelho-Prabhu, Nayantara , Enslin, Sarah M , Hernandez-Barco, Yasmin G , Horst, Sara , Jacobson, Brian C , Jones, Patricia D , Kaul, Vivek , Leggett, Cadman L , Leung, Galen , Mascarenhas, Miguel , Parasa, Sravanthi , Shah, Eric D , Simonetto, Douglas A , Stidham, Ryan W , Suthrum, Praveen , Thomas, Sapna , Phillips, Meridith E , Bilal, Mohammad , Spiegel, Brennan , Shaukat, Aasma , Afzali, Arya , Feld, Andrew D., Hernandez‐Barco, Yasmin G. , Horst, Sara , Kushnir, Vladimir , Parasa, Sravanthi , Schairer, Jason, Shah, Eric D. , Simonetto, Douglas A.

Mayo Clinic

American Journal of Gastroenterology | February 10, 2026 | Volume: 121 | Issue: 4 | Pages: 1017-1024

10.14309/ajg.0000000000003944 | PMID 41665234 Get It

INTRODUCTION: The American College of Gastroenterology assembled a multidisciplinary task force to evaluate the current state and future direction of artificial intelligence (AI) in gastroenterology, hepatology, and endoscopy leading to the development of consensus-based recommendations for responsible AI integration in clinical practice. METHODS: A total of 32 subject-matter experts and 12 industry partners, representing diverse practice settings and expertise, conducted subgroup literature reviews across 5 key areas (endoscopy, practice management clinical applications, training and education, inflammatory bowel disease and liver disease, ethics and equity). Draft statements were developed and rated on a 5-point Likert scale using a modified Delphi process. A consensus was set at ≥70% combined agreement. Nonconsensus items were revised and revoted electronically. RESULTS: A total of 43 statements, 40 (93%) reached consensus in round 1 and the remaining 3 achieved consensus after round 2. Evidence supports computer-aided detection improving adenoma detection rate and miss rate in controlled studies, with mixed real-world impact and insufficient long-term outcomes (e.g., interval colon cancer rate). Recommendations emphasize thorough validation and reduction of bias by heterogeneous Data sets. Outside endoscopy, ambient AI scribes, natural language processing (NLP)-enabled coding, workflow optimization, and previous authorization support show potential. Training recommendations endorse a structured AI curriculum while preserving independent procedural competence to avoid deskilling. In inflammatory bowel disease and hepatology, AI could help improve diagnostic accuracy, help predict risk of disease progression, and help guide therapy. Equity, governance, and reimbursement statements call for chain-of-custody data protections, specialty-society oversight, and payment models that reward quality and cost reduction. DISCUSSION: This consensus outlines how AI can augment rather than replace clinical expertise while promoting safety, transparency, interoperability, and equity. Priorities include pragmatic and prospective trials, multi-institutional data-sharing consortia, bias mitigation, and workforce training to enable trustworthy and clinically impactful AI adoption in gastroenterology, liver, and endoscopy care.