Citations

Purpose This study aimed to develop and validate a tool to predict the primary tumor site in patients with metastatic cancer of unknown primary using demographic and clinical variables, including imaging-derived sites of metastasis, without pathology or laboratory data. Methods In this population-based study, data were extracted from the SEER database. Patients diagnosed between 2010 and 2020 with a known primary cancer site, metastatic staging, and metastasis in the bone, liver, brain, and lungs were included. Patients were randomly split into training (70%) and/or testing (30%) sets. A total of 27 primary tumor sites were included. A gradient boosting model was trained to predict the primary tumor site, with random forest and classification tree models evaluated as comparators. Random guess and frequency-weighted guessing models were used for baseline comparison. Results A total of 689,715 patients were included from 9,208,295 queried. The most common primary cancer sites were non–small cell lung cancer (NSCLC) (n = 211,338), intestines (n = 64,187), and pancreas (n = 60,310). The baseline models achieved Top-5 accuracies of 0.179 for a random guess and 0.476 for a frequency-weighted guess. The gradient boosting model achieved Top-1, Top-3, and Top-5 accuracies of 0.40 ± 0.001, 0.680 ± 0.001, and 0.790 ± 0.001, respectively, across 100 Monte-Carlo replicates. Top-5 accuracy was highest for primary NSCLC (0.990 ± 0.001) and intestinal cancer (0.900 ± 0.003). Our model was most influenced by sex (gain = 0.27) and metastasis to bone (gain = 0.20). A web app was constructed: primarycancerpredictor.netlify.app. Conclusion This study developed and evaluated a gradient boosting machine learning model and a user-friendly web tool to aid in the diagnosis of cancer of unknown primary.

Surgeons are at high risk of developing long-term Work-Related Musculoskeletal Disorders (WMSDs) due to awkward sustained postures. Passive spine-supporting exoskeletons are a potential intervention to improve posture and reduce fatigue. The NekSpine ® was evaluated by 21 surgeons (15 male) across two hospital sites within a quaternary academic hospital system. Each surgeon performed at least two comparable procedures, one with the exoskeleton and one without. Surgeons completed pre- and postoperative surveys assessing NASA-TLX workload, usability, body-part discomfort, overall fatigue, and workflow disruptions. Eighty-two cases were evaluated (43 exoskeleton cases). Compared with baseline cases, surgeons reported reduced neck and upper back discomfort and lower overall fatigue when using the exoskeleton. The NekSpine ® exoskeleton may reduce spinal discomfort and fatigue during surgery, supporting its potential as an ergonomic intervention for surgeons.

Robotic surgery offers advantages over traditional open, laparoscopic, and endoscopic approaches, including faster patient recovery and reduced surgeon fatigue. The da Vinci 5 (DV5), is the newest system in the most widely used family of surgical robots. This pilot study examined the usability of the DV5 compared with the da Vinci Xi (DV Xi) from the perspective of the surgical team. A consulting surgeon, trainees, Certified Surgical Assistants (CSAs), and Certified Surgical Technicians (CSTs) were recruited during colorectal surgery cases using the DV5 or DV Xi. Team members completed pre- and postoperative surveys assessing discomfort, workload, and usability. Objective postural data were collected from the consulting surgeon and trainee. Nine cases were evaluated (DV5 = 5). The DV5 improved neck posture for surgeons and trainees, with no workload differences for other team members. The DV5 significantly improved physical ergonomic usability for the surgeon at the console.

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.

Hospital practitioners have a high prevalence of work-related musculoskeletal disorders due to manual patient transfers. Reducing patient transfers can improve safety for staff and patients, especially those with unstable spines. A study at our academic hospital with the Safe TrAnsfer Tray prototype (STAT Tray V1) found transfers could be reduced to the two unavoidable transfers at the beginning and end of care. Surveys from 37 practitioners identified clinical challenges. User feedback informed design requirements for STAT Tray V2. Candidate materials were tested for MRI and CT compatibility, and pressure mapping evaluated padding combinations to reduce pressure-related injuries. STAT Tray V2 was designed for MRI and CT compatibility, current lift systems, and patients ranging from the 5th percentile female to the 95th percentile male while reducing pressure injury risk. Following manufacturing, usability testing will evaluate performance in the Emergency Department, imaging, operating suite, and ICU.

Background/Objectives: Novel vision-language models (VLMs) can integrate patient textual data with image data to support medical diagnosis. Recent studies reported conflicting results regarding the performance of multimodal VLMs compared to other models and physician performance. This systematic review aims to assess the diagnostic performance of multimodal VLMs integrating both patient textual and image data across diverse real-world hospital settings. Methods: We performed comprehensive searches of eight resources, including Embase, MEDLINE, and SCOPUS, on 17 December 2025. Eligible studies reporting diagnostic performance of VLMs integrating both image and patient history textual data from real-world adult patients compared to that of other models and physicians were included. The review adhered to the Preferred Reporting Items for Systematic Reviews and Meta-Analyses (PRISMA) guidelines. The Prediction model study Risk Of Bias Assessment Tool + AI (PROBAST + AI) was used to assess the quality and risk of bias. The study protocol was registered in the PROSPERO database (CRD420251244054). This review received no external funding. Results: We screened 11,026 records, of which 18 studies met the inclusion criteria. Six studies comparing multimodal and unimodal models demonstrated the consistent superiority of the multimodal models. Four studies evaluating VLM accuracy as standalone agents compared with physician performance reported conflicting evidence. One study assessing VLMs as a clinical copilot demonstrated higher accuracy from the group of physicians using VLM assistance. A meta-analysis could not be performed due to the heterogeneity across study populations and outcomes. The majority of the studies were assessed as having a high risk of bias due to dataset quality. Primary limitations identified across studies include small sample size, a lack of external validation, and the need for prospective clinical deployment studies. No study provided documented considerations regarding model safety or data security. Conclusions: This systematic review suggests that multimodal VLMs consistently outperform unimodal models with access to only image or text. While model performance as standalone agents compared to humans remains inconclusive, a copilot model has demonstrated high diagnostic accuracy. Given substantial methodological concerns across studies, cautious interpretation is required, No firm clinical recommendation can be made regarding the use of standalone VLMs. Further research employing high-quality datasets is needed to ensure the reliability and clinical applicability of future VLMs.

ABSTRACT First‐line therapy for mantle cell lymphoma (MCL) represents a critical opportunity for clinical benefit via sustained complete response. We conducted a phase 2 multicenter trial in the academic and community cancer research united (ACCRU) network, testing a multitargeted 1st line regimen. CARiBOU (ACCRU‐LY‐1804) employs alternating VR‐CAP and R‐cytarabine with continuous acalabrutinib, in six 21‐day cycles, for previously untreated MCL. The primary endpoint was complete metabolic response (CMR) rate. Secondary endpoints included safety, feasibility of stem cell collection, proportion proceeding to ASCT, and progression‐free (PFS) and overall survival (OS). Peripheral blood measurable residual disease (MRD) was tested using the ClonoSEQ assay (Adaptive Biotechnologies). Of 41 patients enrolled, 39 (95%) responded to therapy, including 37 patients achieving CMR (90%). Two nonresponders discontinued therapy for toxicity early, prior to study‐defined restaging, and received alternate therapy. Undetectable MRD at a 10 6 threshold was achieved in 26/33 tested patients (79%), and 94% at 10 5 . 18‐month estimated PFS is 79% (95% CI 64%–97%), and OS is 96% (95% CI 88%–100%). Toxicities were primarily hematologic (grade 3 hematologic AE in 32 patients, [78%]). Twelve required platelet transfusions, and one grade 3 bleeding event occurred. Febrile neutropenia occurred in 4 patients, and 6 (14%) experienced SAEs. There were no treatment‐related deaths. CARiBOU is an efficient, highly effective outpatient 1st line MCL regimen, employing intermediate‐dose cytarabine and continuous acalabrutinib for 6 cycles. This multitargeted regimen addresses the biologic heterogeneity of MCL and permits flexible MRD‐guided decisions on consolidation and maintenance. Trial Registration: ClinicalTrials.gov identifier: NCT04626791

Abstract Background Sepsis is a life-threatening condition in which delayed recognition and treatment are associated with increased mortality. While predictive models such as Epic’s Early Detection of Sepsis Model (ESM) were developed to support early intervention, their real-world impact after integration into clinical workflows remains difficult to evaluate. Objectives To evaluate the real-world impact of ESM integrated into clinical workflow on clinical outcomes, antibiotic use, and harm-benefit tradeoffs. Methods We conducted a quasi-experimental study in a single healthcare system using encounter-level data from inpatient settings. Inpatient mortality, prolonged hospitalization, antibiotic use, and sepsis prevalence were compared between the pre-implementation period (3 June 2023 to 20 August 2024) and the online period (21 August 2024 to 26 December 2024) when the model became visible to clinicians. We also applied a counterfactual framework using models trained on pre-implementation data to estimate expected outcomes without ESM and to quantify harms related to overtreatment and delayed treatment. Results Among 101,138 encounters, 86,884 occurred during the pre-implementation period and 14,254 during the online period. In unadjusted analyses, the online period had lower inpatient mortality, prolonged hospitalization, antibiotic use, and sepsis prevalence (all p≤0.002). In the counterfactual analyses, observed outcomes were lower than expected without ESM for mortality (1.21% vs 1.82%; p<0.001), prolonged hospitalization (5.56% vs 7.95%; p<0.001), and antibiotic use (43.52% vs 47.04%; p<0.001). False positive harm (37.72% vs 41.68%; p<0.001) was also lower than expected. Conclusions Integration of ESM into clinical workflow was associated with improved patient outcomes, reduced antibiotic use, and decreased harm from overtreatment, without evidence of increased harm from delayed treatment, supporting a positive net clinical benefit and the safety and effectiveness of ESM under Software as a Medical Device principles.

TPS7101 Background: Patients with high-risk CLL/SLL not achieving a complete response (CR) after ≥ 12 months of BTK inhibitor (BTKi) monotherapy remain at risk for early progression due to residual disease and BTKi resistance. A BCL-2 inhibitor (BCL-2i) introduces a complementary, BCR-independent apoptotic mechanism that may deepen responses and prolong progression-free survival (PFS). Lisaftoclax, a selective oral BCL-2i with a short half-life (4-6 h), enables once-daily dosing and is approved in China as second-line CLL therapy. Lisaftoclax monotherapy has demonstrated overall response rates (ORRs) of 67% in relapsed/refractory CLL and 62.5% in BTKi-refractory disease, including del(17p)/ TP53 -mutated cases. Lisaftoclax combined with acalabrutinib achieved ORRs >97% with favorable tolerability. This study evaluates whether lisaftoclax plus BTKi (acalabrutinib, zanubrutinib, or ibrutinib) improves PFS and/or overall survival (OS) (vs continued BTKi monotherapy) in patients with CLL/SLL and residual disease after prolonged BTKi treatment. Methods: This study will enroll approximately 440 patients randomly allocated to receive lisaftoclax plus BTKi or BTKi alone. Eligible patients have CLL/SLL and, after ≥12 months of BTKi monotherapy (lines 1-3), have achieved neither CR nor progressive disease (PD). Randomization is stratified by del(17p)/ TP53 status. Key inclusion criteria include age ≥18 years, ECOG PS 0-2, and residual disease with either high-risk features (del(17p)/ TP53 mutation, unmutated IGHV , or complex karyotype [≥5 abnormalities]), or measurable residual disease with lymph nodes ≥2.5 cm in the absence of high-risk features. Exclusion criteria include prior BCL-2i therapy or Richter transformation. Patients in the investigational arm will undergo a 5-day oral lisaftoclax ramp-up to 400 mg once daily plus physician's choice of BTKi in 28-day cycles until progression or toxicity. Control patients continue their current BTKi monotherapy. Safety and disease assessments (CT/MRI) will occur regularly. The primary endpoint is PFS by independent review committee (iwCLL 2018); key secondary endpoint OS; and other secondary endpoints, PFS by investigator, ORR, duration of response, MRD negativity, and safety. Enrollment is ongoing across 126 sites in 18 countries (ClinicalTrials.gov ID: NCT06104566). Clinical trial information: NCT06104566 .