Citations

Aims: To synthesise and critically appraise evidence on artificial intelligence (AI) and multimodal data approaches for diagnosis, prognosis, and treatment decision support in diffuse large B-cell lymphoma (DLBCL) and acute myeloid leukaemia (AML), and to compare how disease biology shapes model design and clinical readiness. Study Design: Systematic review with narrative synthesis. Place and Duration of Study: PubMed/MEDLINE, Embase, Scopus, Web of Science Core Collection, IEEE Xplore, and the Cochrane Library were searched from database inception to 29 July 2026. Methodology: English-language original studies involving human participants, clinical images, human-derived samples, or patient-derived datasets were eligible. Two reviewers independently screened records, assessed full texts, and extracted study characteristics, data modalities, analytical methods, validation approaches, and performance measures. PROBAST+AI domains were used to guide appraisal of eligible patient-level prediction models; exploratory multi-omics, molecular-subtyping, biomarker-discovery, and segmentation studies underwent structured descriptive appraisal. TRIPOD+AI informed assessment of reporting completeness. Owing to substantial clinical and methodological heterogeneity, findings were synthesised narratively. Results: Twenty-eight studies were included: 22 on DLBCL and six on AML. DLBCL research was dominated by PET/CT radiomics, deep imaging, digital pathology, and imaging-clinical-molecular fusion. Internally evaluated diagnostic models reported area under the curve values as high as 0.999, whereas externally validated prognostic models achieved values of 0.66-0.71 and showed inconsistent incremental improvement over the International Prognostic Index. AML studies mainly integrated genomic, transcriptomic, epigenomic, single-cell, proteomic, metabolic, and functional drug-response data. Prognostic models reported concordance indices of 0.72-0.81 and time-dependent area under the curve values of 0.795-0.899. The most frequent methodological concerns were retrospective sampling, high-dimensional modelling in modest cohorts, incomplete calibration reporting, and limited independent validation. Treatment-response models in both diseases remained retrospective or exploratory, and none demonstrated improved outcomes through AI-guided treatment allocation. Conclusion: AI and multimodal data approaches show greatest maturity for prognostic stratification, but diagnostic replacement and treatment selection remain unproven. Prospective, multicentre clinical-impact validation is the principal requirement for translation into routine care.

Purpose To compare lower extremity soft tissue injury and revision surgery rates for patients with anorexia nervosa (AN) and bulimia nervosa (BN) compared with matched controls. Methods This retrospective cohort study used a deidentified claims database. Patients were included if they carried an International Classification of Diseases code for AN or BN. Respective matched cohorts for AN and BN were created using propensity score matching. Primary and revision surgeries for anterior cruciate ligament (ACL) reconstruction, posterior cruciate ligament reconstruction, knee collateral ligament reconstruction, meniscus repair or meniscectomy, and any ankle ligament reconstruction were identified by their CPT codes. Patients over the age of 40 and without a minimum 2‐year follow‐up after primary surgery were excluded. Differences in prevalence and revision rates were analyzed. Results A total of 56,146 patients with AN and 42,630 patients with BN were included in this study with equal numbers in respective matched cohorts. Patients with BN showed an increased risk of ACL injury (relative risk = 1.32, P = .019), medial collateral ligament injury (1.17, 0.04), calcaneofibular sprain (1.92, <0.001), deltoid sprain (1.41, 0.004), and unspecified ankle sprain (1.44, <0.001). Patients with AN showed an increased risk for calcaneofibular sprain (1.25, 0.007), deltoid sprain (1.28, 0.015), and unspecified ankle sprain (1.17, <0.001). Patients with BN were more likely to have revision ACL repair (1.89, 0.02), partial meniscus revision (3.44, <0.001) and any meniscus revision (4.74, <0.001) while patients with AN were more likely to have an ACL revision (2.81, <0.001), partial meniscus (4.37, <0.001), and any meniscus (4.52, <0.001). Conclusions In this study, patients with AN and BN had a significantly increased risk for various knee and ankle injuries and revision surgeries compared with matched controls. Additionally, patients with AN and BN who sustained these injuries were more likely to undergo a revision surgical procedure within the first 5 years of the primary procedure. Level of Evidence Level III, retrospective comparative study.

Ear, nose, and throat (ENT) surgeons often perform multiple daily procedures requiring sustained postures while wearing headlights or loupes, increasing the risk of work-related musculoskeletal disorders (WMSDs). This in situ case study aimed to (1) evaluate ENT surgeon workload and (2) introduce ergonomic interventions through workflow changes, education, and personal protective equipment. Three trained ergonomists observed the intraoperative workflow of three ENT surgeons at a tertiary academic hospital, identifying awkward postures. Surgeons received education on surgical microbreaks and OR-Stretch before trialing passive exoskeletons. Exoskeleton effectiveness was evaluated using interviews and surveys. Workflow interventions improved neck posture. One surgeon reported reduced body-part discomfort but increased subjective workload when using the exoskeleton, while interviews identified aesthetic concerns. This exploratory case study identified workflow issues and introduced ergonomic interventions. Although one surgeon reported reduced discomfort with an exoskeleton, larger studies are needed to establish quantitative trends.

Age-related gastrointestinal dysfunction is common, but the mechanisms of aging-associated smooth muscle failure remain unclear. We show that aging in mice slows whole gut and colonic transit, increases regional stiffness, and reduces smooth muscle contractility. Inducible smooth muscle cell (SMC)– specific deletion of Piezo1 preserved youthful transit and force generation, whereas Piezo1 activation in young mice phenocopied aging-associated transit delay. Single-cell transcriptomics, RNA velocity, stiffness-controlled cell and tissue cultures, and pharmacologic studies revealed that Piezo1 couples increased stiffness to Ca 2+ –calcineurin–NFAT signaling, loss of contractile gene programs, leading to age- related contractile loss and contractile-to-synthetic SMC remodeling and gut wall stiffening. Human intestinal SMCs supported conservation of this pathway, and PIEZO1 gain-of-function carriers showed a trend toward delayed colonic transit. Thus, maladaptive SMC Piezo1 mechanotransduction is a targetable mechanism of aging-associated gut dysmotility. Aging alters organ structure, yet how these changes drive functional decline remains poorly defined. We show that progressive stiffening of the gut with age activates the mechanosensitive ion channel Piezo1 in smooth muscle cells, initiating a maladaptive response that impairs contractility and slows intestinal transit. On the other hand, deletion of smooth muscle Piezo1 prevents age-related gut dysmotility. These findings reveal that age-related physical shifts actively drive functional decline through mechanotransduction pathways. By identifying Piezo1 as a critical link between tissue mechanics and organ aging, this work provides a framework for understanding how mechanical cues contribute to age-related dysfunction in the gut and possibly other smooth muscle organs.

Health care organizations are rapidly adopting artificial intelligence (AI)-enabled tools, yet nurse leaders often lack a clear framework to evaluate, govern, and safely scale these technologies. This article presents a practical, system-level AI governance model grounded in risk mitigation, interdisciplinary partnership, and nursing leadership decision rights commonly enacted through nursing professional governance structures. We outline core components of an effective governance structure, including clinical usefulness, safety and reliability, fairness and inclusiveness, transparency and explainability, privacy and security, and organizational accountability. Real-world examples illustrate how nurse executives can guide responsible AI adoption to reduce cognitive load, improve documentation efficiency, and enhance patient outcomes. The framework equips nursing leaders with actionable strategies and practical workflow checklist to lead AI transformation in complex health care environments.

Outcomes of kidney-alone transplantation (KAT) in former simultaneous liver-kidney (SLK) transplant candidates after liver waitlist delisting are not well defined. Using Scientific Registry of Transplant Recipients (SRTR) data, we identified adult recipients who underwent KAT between 2005 and 2025 after prior SLK listing (RLD-KAT), which was matched 1:5 to primary KAT recipients without liver disease by age, transplant year, and diabetes status. Patient and graft survival were evaluated using the Kaplan-Meier method and multivariable Cox proportional hazards models. We identified 163 RLD-KAT recipients matched to 815 controls. Unadjusted Kaplan-Meier analyses demonstrated lower patient survival in RLD-KAT (p = 0.020), whereas death-censored and overall graft survival were similar (p &gt; 0.05). In multivariable models, death-censored graft survival (HR 0.89; 95% CI 0.51–1.53), overall graft survival (HR 1.00; 95% CI 0.73–1.36), and patient survival (HR 1.07; 95% CI 0.76–1.5) did not differ significantly. Six RLD-KAT recipients (3.7%) subsequently underwent liver transplantation. Kidney-alone transplantation in prior SLK candidates was associated with acceptable patient and graft outcomes and a low incidence of subsequent liver transplantation.