Citations

Abstract Deep learning models enable the prediction of clinical endpoints from whole-slide images (WSIs), but many such models function as “black boxes”, lacking transparency about whether and which histomorphological patterns drive their predictions, hindering interpretability and clinical adoption. Here we propose a human-in-the-loop explanation framework, MorphoXAI, which provides both local and global interpretability for deep learning models by incorporating human-expert interpretations. At the global level, it reveals the histomorphological patterns on which the model consistently relies to distinguish between classes of WSIs, as well as the patterns associated with confusion between classes. At the local level, it indicates which of these patterns are used in the prediction of an individual WSI and which regions within the slide correspond to such patterns. We validated our method on a deep learning model trained for ovarian tumor histologic subtype prediction. The results show that our framework generates explanations that accurately reflect the histomorphology underlying the model’s predictions at both global and local levels. For interpretability and clinical utility in diagnostic contexts, human evaluation results showed that our explanations were easy to interpret, rich in diagnostic features, and directly helpful for diagnostic decision-making, thereby enhancing pathologist-AI collaboration. Our work highlights that unifying global and local explanations and grounding them in expert-interpreted morphology enhances the interpretability and verifiability of deep learning models, thereby facilitating the transparent deployment of such models in clinical practice.

Objective: This study aims to develop a contrast-free, high-sensitivity ultrasound method, denoted as Radon transform-based flow measurement (R-Flow), for in vivo mapping of microvascular flow vectors and for establishing R-Flow-derived vector-field metrics to noninvasively quantify microcirculatory patterns in liver cirrhosis. Impact Statement: R-Flow enables robust, contrast-free imaging of microvascular dynamics and demonstrates translational feasibility in the human liver. Its direction-aware indices offer pilot in vivo quantification of flow redistribution and remodeling, providing unique insights into hepatic flow dynamics. Introduction: Microvascular dysfunction is a hallmark of many diseases, yet noninvasive visualization and quantitative assessment of abnormal microcirculation remain limited. Methods: R-Flow leverages Radon transform to decode red blood cell dynamics from the spatiotemporal domain of ultrasound flow signals, reconstructing velocity vectors at microvascular scale. From these vector maps, unique direction-aware indices are further derived to characterize flow distribution and heterogeneity. Results: Validated across simulations, phantoms, and in vivo studies, R-Flow provides robust velocity estimation across a wide range (1 to 60 mm/s). Notably, it enables high-sensitivity microvascular flow vector mapping of human liver, showing strong agreement with references ( r > 0.9). In a rat model, these direction-aware indices revealed a shift from healthy multipath perfusion in control livers to directionally biased vascular pattern in cirrhotic livers, demonstrating significant correlation with pathological indicators. Conclusion: R-Flow enables noninvasive, contrast-free mapping of microvascular blood flow velocity and offers a promising approach for high-resolution assessment of microvascular flow characteristics.

ABSTRACT Background Cardiac amyloidosis (CA) is frequently complicated by atrial fibrillation (AF), yet outcomes after left atrial appendage occlusion (LAAO) in this population remain poorly defined. Methods We conducted a retrospective TriNetX study of adults with AF undergoing LAAO, comparing patients with and without CA after 1:1 propensity matching. Outcomes were assessed using Kaplan–Meier analyses and Cox regression. Results Among 532 matched pairs, mortality and major adverse cardiovascular events were similar between groups, whereas major bleeding was higher in CA (HR 1.90). Conclusions LAAO yields comparable ischemic outcomes in CA, though bleeding risk is increased.

Background: In patients with irritable bowel syndrome with constipation (IBS-C), rapid, sustained relief from constipation and abdominal symptoms, such as pain, discomfort, and bloating, can improve quality of life. Objective: This post hoc analysis evaluates the time to constipation and abdominal symptom relief achieved with tenapanor. Design: Post hoc analysis of data pooled from three randomized placebo-controlled studies (phase IIb, T3MPO-1, and T3MPO-2) of tenapanor 50 mg twice daily in patients with IBS-C. Methods: The time to first response for complete spontaneous bowel movement (CSBM) frequency, abdominal pain, discomfort, bloating, and 3-item abdominal score (AS3) were assessed. The AS3 was derived as the average of the weekly scores for abdominal pain, discomfort, and bloating. Cumulative incidences of response over time were estimated using the Kaplan–Meier method. A Cox proportional hazards model was used to assess the effect of baseline and demographic characteristics on the time to first response. Results: Among 1372 patients with IBS-C (684 tenapanor; 688 placebo), median time to first CSBM response was 2 weeks, and median time to abdominal pain, discomfort, bloating, or AS3 response was 4–5 weeks in those treated with tenapanor, with 67.8%–76.7% achieving first response in CSBM frequency and abdominal symptoms by week 12. These time frames were shorter than those observed with the placebo (4 weeks for CSBM and 6–8 weeks for pain, discomfort, bloating, and AS3), of whom 59.1%–69.4% achieved the first response in CSBM and abdominal symptoms by week 12. Higher weekly response rates were observed with tenapanor than with placebo for all endpoints in each week of the 12-week treatment period. Conclusion: This novel post hoc analysis demonstrates that, compared with placebo, tenapanor reduces the time to first response in CSBM frequency and abdominal symptoms and consistently increases the weekly response rate during 12 weeks of treatment. Trial registration: NCT01923428; NCT02621892; NCT02686138.

The iStent series constitutes a range of trabecular bypass minimally invasive glaucoma surgery (MIGS) devices, which offers intraocular pressure (IOP) reduction with favourable safety profiles, in patients with open-angle glaucoma (OAG). Having undergone significant evolution since its initial US FDA-approval in 2012, successive generations address previous limitations, while enhancing IOP-lowering efficacy through device and delivery system design iterations. Longer-term and real-world iStent data demonstrate the durability of IOP- and medication-lowering outcomes with minimal complications, while preliminary studies across a wider spectrum of glaucoma subtypes and severities provide limited evidence of successful outcomes beyond mild-to-moderate OAG, both with and without concomitant cataract surgery. Aqueous humour outflow assessment and novel intra-operative techniques may further facilitate more accurate and effective iStent positioning. Despite typically higher upfront costs, results from both cost-effectiveness and patient-reported outcome studies are encouraging. Combination MIGS with the iStent, leveraging on the multiple mechanisms of actions of various procedures, may provide greater IOP-lowering efficacy without compromising safety. With expanding clinical data and progressive enhancements, iStent technology is likely to remain a key component of the evolving MIGS landscape.

Abstract Objective This study aimed to evaluate how differences in case complexity affect information-processing burden, as measured by eye-tracking, as well as the efficiency of electronic health record (EHR) use among healthcare providers in the intensive care unit. Materials and Methods This cross-sectional study recruited providers from 4 U.S. medical centers that use 2 prominent EHR systems (Epic and Oracle). After reporting demographic information, participants reviewed 2 complex cases and 2 standard cases in their institution’s EHR system and then responded to 5 questions about each case, yielding a performance score. Information-processing burden was assessed by measuring the number of eye fixations via eye-tracking software. The efficiency of EHR use was assessed by measuring the task completion time, number of mouse clicks per minute, number of EHR screens viewed, and performance score. Results Eighty-one providers were included for analysis. Providers exhibited significantly more eye fixations (P < .001) and longer task completion times (P < .001) for complex cases than for standard cases. There were also significantly fewer mouse clicks per minute during complex cases (P < .001). Reviewing a complex case first led to significantly more eye fixations (P = .015) and longer task completion times (P < .01) than when a standard case was presented first. Case complexity did not significantly affect performance scores or the number of EHR screens viewed. Discussion Higher case complexity was shown to be associated with greater information-processing burden and less efficient EHR use. These findings have implications for enhancing the efficiency of EHR use, thereby leading to improved clinical decision-making and patient safety. Furthermore, reviewing complex cases first led to a greater information-processing burden, suggesting that providers could benefit from “warming up” with standard cases before reviewing complex cases.

Abstract Background Global data demonstrate an inverse relationship between hospital ileoanal pouch volume and adverse outcomes, highlighting the need for quality metrics for this technically demanding procedure.1-4 Currently, there are no standardised quality indicators to define high-quality pouch surgery. This study aimed to establish international consensus on key performance indicators (KPIs) in pouch surgery. Methods A modified Delphi process was conducted among an international, multidisciplinary panel of experts. Participants were identified through professional networks, literature review, and direct email invitation; additional participants recruited via a snowball sampling approach over one month. Candidate KPIs were generated from literature review and expert input across 5 domains. Each item was rated on a 9-point Likert scale (1 = not important, 9 = critically important); consensus was predefined as ≥ 80% of respondents rating an item 7–9. Items not reaching consensus were re-rated in a second round following anonymized group feedback. Results Round 1 included 312 participants from 37 countries. Demographics (Table 1): 53% were age 45 years, 35.2% were female, and included surgeons (68.6%) and gastroenterologists (31.1%). Most (76.6%) practice at academic or university hospitals, with a median of 11 (5–17) years in practise; 78.9% perform >1 pouchoscopy per month, and 39.5% of surgeons perform 5 pouches/year. Respondents’ regions included North America (51%), Europe (26%), Oceania (9%), Asia (6%), Latin America (4%), and the Middle East/Africa (4%). Seven (18%) countries (Denmark, Lithuania, Malaysia, Norway, United Arab Emirates, Sweden, and Switzerland) reported pouch surgery is already centralised, while 70.6% agreed pouch centralisation should be implemented. Cost/logistics and professional autonomy were the most important barriers to centralisation, whereas capacity and training exposure were least important. Overall, 37/59 (62.7%) candidate KPIs reached consensus after Round 1. The Round 2 response rate was 61%, and 2 additional KPIs reached consensus (preop ileitis and long-term risk of pouchitis). Additionally, 14 of 25 (56%) informed consent items reached consensus, and 64% of respondents felt informed consent for pouch surgery requires 2 or more office visits. Consensus items were used to populate a KPIPS Checklist (Figure 1). Conclusion Through an international Delphi process, the KPIPS study identified a consensus-derived set of key performance indicators to measure quality in pouch surgery. These quality metrics provide a foundation for benchmarking outcomes and represent a critical step towards centralization and the development of designated pouch centres of excellence to improve global standards of care for pouch patients. References: 1. Worley GHT, Fearnhead NS, Brown SR, et al. Review of current practice and outcomes following ileoanal pouch surgery: Lessons learned from the ileoanal pouch registry and the 2017 ileoanal pouch report. Colorectal Dis 2018;20:913–22. 2. Giddings HL, Yang PF, Steffens D, Solomon MJ, Ng KS. Influence of hospital-level and surgeon factors on the outcomes after ileo-anal pouch surgery for inflammatory bowel disease: Systematic review. Br J Surg 2024;111. 3. Hoang CM, Maykel JA, Davids JS, et al. Distribution of elective ileal pouch-anal anastomosis cases for ulcerative colitis: A study utilizing the university health system consortium database. J Gastrointest Surg 2020;24:2613–9. 4. Moojen TB, Visser E, Reijntjes MA, et al. One-year stoma-free survival of ileoanal pouches for uc in european centers: The miracle project. Ann Surg Open 2025;6:e596. Conflict of interest: Prof. Holubar, Stefan: No conflict of interest Soop, Mattias: No conflict of interest Poskus, Tomas: No conflict of interest Neary, Peter: No conflict of interest Uchino, Tairin: No conflict of interest Yang, Song-soo: No conflict of interest Adamina, Michel: No conflict of interest Avellaneda, Nicolas Luis: No conflict of interest Barnes, Edward: No conflict of interest Brouquet, Antoine: No conflict of interest Brown, Steven Ross: No conflict of interest De Buck Van Overstraeten, Anthony: No conflict of interest Buskens, Christianne J.: No conflict of interest Chiorean, Michael: No conflict of interest Clark, David: No conflict of interest Cohen, Benjamin: No conflict of interest El Ouali, Sara: No conflict of interest Faiz, Omar Darius: No conflict of interest Fichera, Alessandro: No conflict of interest Hahnloser, Dieter: No conflict of interest Hancock, Laura: No conflict of interest Herfarth, Hans: No conflict of interest Johnston, Michael: No conflict of interest Kayal, Maia: No conflict of interest Laharie, David: No conflict of interest Liberman, Sender: No conflict of interest Loftus, Jr, Edward: No conflict of interest Moeslein, Gabriela: No conflict of interest Myrelid, Pär: No conflict of interest Poylin, Vitaliy: No conflict of interest Qazi, Taha: No conflict of interest Raffals, Laura: No conflict of interest Rubin, David T.: No conflict of interest Spinelli, Antonino: No conflict of interest Steinhagen, Emily: No conflict of interest Tozer, Philip: No conflict of interest Verstockt, Bram: No conflict of interest Warusavitarne, Janindra: No conflict of interest Wexner, Steven: No conflict of interest Winter, Desmond: No conflict of interest

Abstract Background Measurement of cardiac troponin (cTn) using high-sensitivity assays is recommended for the diagnosis of myocardial infarction. We determined sex-specific and uniform 99th percentile upper reference limits (URLs) using the new Elecsys® Troponin T high-sensitivity Gen 6 assay in a global, healthy reference range cohort. Methods Lithium-heparin plasma and serum samples were prospectively collected from apparently healthy individuals aged ≥20 years across 34 global sites in the United States, Europe, China, and Japan. cTnT was measured using the Troponin T high-sensitivity Gen 6 assay on the Cobas® e 801 analyzer. Exclusion criteria were defined according to the 2022 IFCC guidance. Uniform and sex-specific 99th percentile URLs and nonparametric 95% CIs were determined in plasma and serum separately and combined. Results The final study population comprised 4147 participants (52.5% female) with a median (25th–75th percentiles) age of 48.0 (33.0–59.0) years; 45.8%, 47.9%, 5.2%, and 1.1% were White, Asian, Black, and other/unknown, respectively. For sample matrices combined (n = 8294), 81.0% and 99.2% of cTnT values were above the limit of detection in females and males, respectively. Sex-specific 99th percentile URLs (95% CI) were 18 (16–23) ng/L for females and 32 (28–35) ng/L for males; the uniform 99th percentile URL was 27 (24–31) ng/L. URLs were comparable in plasma and serum samples. Conclusions This study determined sex-specific and uniform 99th percentile URLs for the Troponin T high-sensitivity Gen 6 assay that were comparable irrespective of the matrix used in a large, global, healthy reference population.

Introduction Placental inflammation is a major contributor to preterm birth (PTB), and there are currently few targeted strategies to prevent PTB and its associated adverse neonatal outcomes. Serum amyloid A (SAA), particularly the isoforms SAA1 and SAA2, are well-recognized inflammatory markers, but their functional roles in placental inflammation remain poorly defined. Methods Using a translational mouse model of sub-chronic maternal inflammation, we investigated the immune mechanisms and therapeutic potential of siRNA-mediated targeting of Saa2 (siSaa2). Placental expression patterns of SAA2 were examined in vivo , and macrophage responses to extracellular SAA2 were modeled in vitro using RAW264.7 cells to assess downstream P2X7R-dependent signaling and functional outcomes. Results SAA2 is primarily induced in placental trophoblast and endothelial compartments during inflammation, where it acts as an extracellular inflammatory mediator. In vitro , we model macrophage responses to extracellular SAA2 using RAW264.7 cells to examine downstream P2X7R-dependent signaling and functional outcomes. Maternal administration of siSaa2 improved PTB rates, placental morphology and fetal brain development. Additionally, SAA1 and SAA2 exhibited distinct expression patterns in the mouse and human placenta. Discussion These findings identify placental SAA2 as a key inflammatory mediator in inflammation-associated PTB and demonstrate that targeted silencing of Saa2 represents a potential therapeutic strategy to mitigate placental injury and adverse fetal outcomes.