Liver stiffness measurement is important for assessing chronic liver disease (CLD). MR elastography (MRE) requires specialized hardware and expertise. Non-invasive deep learning (DL) models using multiparametric abdominal MRI may provide an accessible alternative. We sought to develop and validate a DL model for predicting continuous liver shear stiffness from non-contrast multiparametric abdominal MRI and electronic health record (EHR) data across multiple sites and vendors. This was a retrospective, multi-institutional study. We analyzed 3680 abdominal MRI examinations from 3376 patients with confirmed or suspected CLD. Non-contrast T1-weighted (T1w), T2-weighted (T2w), and diffusion-weighted imaging (DWI) with EHR data were used as inputs. MRE-derived liver shear stiffness served as the reference. A transformer-based multi-channel DL model was trained using multi-site 10-fold cross-validation and evaluated on temporally held-out internal (n = 1224) and independent external (n = 365) test sets. Performance was measured by Pearson’s correlation coefficient (r); residual analysis assessed bias. In cross-validation, the model achieved an r of 0.78 (95
PURPOSE:To provide evidence-based recommendations for patients with stage IV non-small cell lung cancer with driver alterations. METHODS:This ASCO living guideline offers continually updated recommendations based on an ongoing systematic review of randomized controlled trials (RCTs), with the latest time frame spanning March-October 2025. An Expert Panel of medical oncology, pulmonary, community oncology, research methodology, and advocacy experts was convened. The literature search included systematic reviews, meta-analyses, and RCTs. Outcomes of interest include efficacy and safety. Expert Panel members used available evidence and informal consensus to develop evidence-based guideline recommendations. RESULTS:This guideline consolidates all previous updates and reflects the body of evidence informing this guideline topic. Thirteen studies were identified in the latest search of literature to date. RECOMMENDATIONS:Evidence-based recommendations were updated to address first, second, and subsequent treatment options for patients with driver alterations.Additional information is available at www.asco.org/thoracic-cancer-guidelines.
As cancer survivors live longer, technologies improve, and reirradiation (reRT) becomes more common, standardised methods for the assessment and reporting of cumulative radiation doses are needed to allow treatment optimisation and integration with other medical specialties managing these complex patients. This consensus statement, developed by an international collaboration of radiation oncologists, physicists, and other experts in the Reirradiation Collaborative Group, proposes a framework for consistent evaluation, documentation, reporting, and clinical decision making in reRT. This paper outlines practical strategies for dose accumulation from multiple courses of radiation therapy with the use of both image registration-based and point dose-based methods, accounting for uncertainties in data availability, physiological organ recovery, and anatomical changes. The emphasis of the consensus statement is on institutional workflows, improved software tools, and better capture of longitudinal patient outcomes. We also highlight the need for improved biological models, data infrastructure, and cross-specialty collaboration. Ultimately, reRT is framed as a transformative challenge for oncology, demanding interdisciplinary innovation across science, clinical care, and health systems. Widespread adoption of these recommendations could accelerate progress toward improved outcomes for patients receiving reRT worldwide.
BACKGROUND:Head and neck cancer represents the seventh most common cancer diagnosis globally. Maintaining sufficient nutrition is important for preventing malnutrition (undernutrition) and muscle wasting, which contribute to worse outcomes, although many patients are unable to maintain adequate oral intake throughout treatment. This guideline provides practice guidance on nutrition care for patients with head and neck cancer. METHODS:An interdisciplinary team developed key questions and scanned results from a systematic search of the PubMed, EMBASE, CINAHL, and Cochrane Central databases back to 2001. Recommendations were created for key questions concerning timing and duration of nutrition support (early vs delayed enteral nutrition [EN], postoperative feeding, and perioperative dietitian intervention), frequency of dietitian and speech pathology consultations, nutrition screening and assessment, macronutrient requirements, enteral access devices, adjunctive strategies (appetite stimulants and continuation of oral intake alongside EN), specialized nutrients (arginine, glutamine, ω-3, and immunonutrition), and interdisciplinary care. RESULTS:Ninety-two studies were included. Recommendations were made supporting early initiation of EN when oral intake is inadequate, nutrition within 24 h after surgery, weekly consultation with a dietitian during radiotherapy, malnutrition screening and assessment with validated tools, interdisciplinary models of care, dietitian involvement before and after surgery, and when to consider use of specialized nutrients. Recommendations are also provided for protein intake (1.2-1.5 g/kg/day) and energy intake (≥30 kcal/kg/day). CONCLUSION:This guideline provides guidance for the nutrition care of patients with head and neck cancer, identifies research gaps, and calls for standardized outcome reporting to further the state of the evidence. This paper was approved by the ASPEN Board of Directors.
Importance:Plain radiography offers limited diagnostic value in maxillofacial trauma and is considered low-value care. Yet, when imaging is indicated, plain radiography remains commonly used despite guidelines favoring computed tomography (CT). Objective:To examine national trends in, factors associated with, and consequences of low-value plain radiography use in the initial imaging of adults with maxillofacial trauma. Design, Setting, and Participants:This retrospective cohort study used a population-based sample of administrative claims data from the Merative MarketScan Commercial Claims and Encounters Database from January 1, 2013, to December 31, 2022. Participants were adults aged 18 years or older with an International Classification of Diseases, Ninth Revision (ICD-9) or International Statistical Classification of Diseases and Related Health Problems, Tenth Revision (ICD-10) diagnosis of facial trauma who received either plain radiography (nose, face, or orbit) or CT of the face or orbit within 7 days of diagnosis. Individuals with mandibular trauma, mandibular imaging, or prior facial imaging were excluded. Data were analyzed from December 2024 to June 2025. Exposure:Initial imaging modality for facial trauma: plain radiography (nose, face, or orbit) or CT (face or orbit). Main Outcomes and Measures:The primary outcome was prevalence of low-value (plain radiography) imaging. Secondary outcomes included patient and practitioner characteristics associated with radiography use and downstream outcomes, including follow-up CT, diagnostic delays, and imaging-related costs. Multivariable logistic regression identified factors associated with low-value imaging. Results:Among 281 421 patients (mean [SD] age, 38.9 [15.0] years; 51.6% female), 72 125 (25.6%) received low-value plain radiography as their initial imaging. Plain radiography use declined from 32.9% of cases in 2013 to 18.0% in 2022. Female vs male sex (odds ratio [OR], 1.50; 95% CI, 1.47-1.54), being seen in an urgent care vs office-based setting (OR, 1.76; 95% CI, 1.67-1.87), and being seen by a family medicine practitioner vs an internist (OR, 1.43; 95% CI, 1.33-1.54) were associated with low-value imaging. In contrast, being seen by a surgical specialist vs internist (OR, 0.09; 95% CI, 0.08-0.11) or in an emergency department vs office setting (OR, 0.07; 95% CI, 0.07-0.07) were associated with significantly lower odds of receiving low-value imaging. In all, 5.5% of radiograph recipients underwent follow-up CT within 7 days, and 7.6% experienced a diagnostic delay. Although median total costs were lower for plain radiography ($56 [IQR, $29-$139]) than CT ($378 [IQR, $89-$845]), radiograph vs CT represented a greater proportion of total (mean [SD], 26% [24%] vs 21% [21%]) and out-of-pocket (mean [SD], 22% [30%] vs 15% [24%]) costs in low-acuity settings. Conclusions and Relevance:In this cohort study of adults with maxillofacial trauma, low-value plain radiography was frequently used despite clear guidelines favoring CT. Targeted interventions to reduce low-value imaging may improve diagnostic accuracy, reduce unnecessary costs, and advance value-based care.
