Citations

Study objectives To evaluate and compare the performance of two proprietary frontier large language models (LLMs), ChatGPT-5 and Grok-4, on diagnostic reasoning and foundational knowledge tasks within the specialty domain of sleep medicine. Methods The models were evaluated on two tasks: case-based reasoning using 79 clinical vignettes from the AASM Case Book of Sleep Medicine and knowledge assessment using 897 multiple-choice questions (MCQs) from board review materials. For vignettes, final diagnosis was scored by concept-level exact match, and differential diagnosis (DDx) was scored on a fixed top-5 output using concept-level matching with synonym normalization to compute precision, recall, and F 1-score. MCQ performance was the proportion correct. Inter-model performance was compared using the Mann–Whitney U test. Results Both models achieved high accuracy for final diagnosis (92.4% for both; 95% CI 86.4, 98.4) and MCQs (ChatGPT-5: 93.0%; Grok-4: 92.8%). However, performance on generating a comprehensive differential diagnosis was suboptimal, with modest F 1-scores for both ChatGPT-5 (0.55 ± 0.20) and Grok-4 (0.59 ± 0.20). There were no statistically significant differences in performance between the two models across any metric ( p > 0.05). Conclusions Frontier LLMs demonstrated high accuracy in sleep medicine tasks requiring knowledge recall and direct pattern recognition but showed more limited performance in complex clinical reasoning tasks such as generating a comprehensive differential diagnosis. These findings suggest that current general-purpose models may be more reliable for focused knowledge support than for broad hypothesis generation. Future studies should evaluate whether domain-adapted models or clinician-in-the-loop workflows can improve real-world diagnostic usefulness and safety.

Background Respiratory allergic diseases are experiencing changes influenced by genetic factors, environmental shifts, and social and demographic elements. These evolving patterns, together with rapid advances in diagnosis and treatment, require a thorough review of emerging trends. Objective To examine future directions in managing respiratory allergic diseases, focusing on changing disease patterns, environmental factors, diagnostic innovations, and therapeutic advances toward precision medicine. A literature search was conducted in PubMed and Scopus databases covering 2015–2025. Studies addressing human populations with allergic rhinitis or asthma were included, emphasizing emerging patterns, environmental factors, diagnostic technologies, and therapeutic innovations, while reviews, conference proceedings, case reports, and studies without clinical relevance were excluded. Initial screening identified 52 studies, and 21 additional studies were identified through complementary searches, resulting in 73 studies in the final analysis. Summary of findings Climate change is a key factor affecting disease patterns, with pollen seasons starting 10–40 days earlier and yearly emissions increasing by up to 200%. Regarding pathogenesis, early-life rhinovirus C infections with IgE sensitization significantly increase asthma risk (HR = 4.06), while severe asthma shows 40–84% eosinophilic patterns, depending on the assessment approach. On the diagnostic front, advances include multiplex platforms, proteomic biomarkers, and microRNAs. Therapeutically, innovations encompass biologics combined with allergen immunotherapy, nanobody-based therapeutics, and microbiota interventions. Conclusions These developments point toward personalized management of respiratory allergic diseases. However, challenges remain in research with underrepresented populations and accessibility. Moving forward, the key priority is integrating this diverse knowledge into practical strategies that advance precision medicine in respiratory allergic diseases.

Retrieval-augmented generation (RAG) is rapidly emerging as a transformative paradigm for large language models (LLMs), especially in high-stakes domains like oncology that demand precision, factual grounding, and up-to-date knowledge. By pairing LLMs with external knowledge repositories, RAG systems explicitly ground model outputs in relevant retrieved documents, helping to reduce hallucinations and ensure responses reflect current evidence. In oncology, where clinical knowledge evolves continually with new research and drug approvals, RAG offers a way to integrate the latest data (e.g., trial results, guidelines, genomic databases) into decision-making. This review synthesizes the technical foundations of RAG, including its architecture and key components, and examines current applications in oncology such as clinical decision support, patient education, radiology reporting, pathology analysis, and genomics-driven precision medicine. We highlight recent studies that demonstrate RAG’s potential—for instance, improving treatment recommendations by incorporating genetic profiles and literature, and enhancing diagnostic accuracy by integrating guidelines. We also discuss emerging developments like multimodal RAG (combining text with imaging or other data), ensemble model approaches, and new explainability tools that trace model outputs to sources. Finally, we critically analyze the limitations and challenges of deploying RAG in healthcare, including computational costs, retrieval errors, noise or conflicts in retrieved information, and ethical and regulatory considerations. While RAG-based systems show promise in augmenting oncologists’ expertise with timely knowledge, careful implementation, high-quality curation of knowledge bases, and human oversight will be crucial for safe and effective adoption in clinical practice.

Abstract Background The IEC exposure index (EI), deviation index (DI), and target exposure index (EI T ), represent critical standardized metrics for the evaluation of exposure and quality in radiographic imaging. Purpose This work develops and validates a systematic procedure to estimate the EI T for eight of the most common radiography imaging protocols utilizing automatic exposure control (AEC) from measurements acquired under reference conditions. Methods A model was developed to define the relationship between a systems AEC logic, and an estimation of the EI under flat‐field conditions (EIFFC). Separately, clinical data and acquisition protocol information for resultant EI during patient studies were also collected for the eight protocols studied: Chest posteroanterior (PA), Chest lateral, Abdomen anteroposterior (AP), Pelvis AP, L‐Spine AP, C‐Spine AP, T‐Spine AP, and Ribs AP. Data were collected from 41 x‐ray units spanning seven institutions. For each protocol on each unit the EIFFC was computed based on the acquisition protocol, as well as median EI from clinical exams to produce a scaling factor (SF). Kruskal–Wallis statistical tests were used to compare SF's between vendors and AEC cell configurations. Results SFs for eight radiographic imaging protocols have been produced per vendor and per AEC cell selection. A workflow has been established for end‐users to follow to apply these SFs to flat‐field measurements taken at their own locations to establish local EI T . Conclusions The study results show that in seven of the eight imaging protocols, the SFs for most units included in the study report SFs within 1 DI (± 25%) of their respective final vendor reported SF (218/228). The ribs protocol is the exception to this finding (n = 26). SFs have high utility for establishing EI T values on individual x‐ray units and normalizing EI value distributions for quality assurance purposes.

Abstract Additive manufacturing (AM), commonly referred to as 3D printing, has been broadly used in the field of medical imaging and radiotherapy. In medical imaging applications, patient‐specific anatomic models have been used to aid in preoperative planning, patient communication, imaging technique assessment and optimization, and medical education. Within the field of radiation therapy, 3D printing finds significance in fabricating patient‐specific immobilization devices, custom bolus devices, anthropomorphic phantoms, brachytherapy devices, and electron therapy devices. Consistent with standard medical physics practices there is a need to establish quality assurance and quality control (QA/QC) protocols, tolerances, and testing frequencies. The diversity of 3D printing technologies and products poses challenges for medical adoption and thus requires guidelines in workflow standardization and establishment of testing procedures. This report is centered around providing comprehensive vendor‐neutral implementation guidelines and recommendations for QC and QA processes. The scope of this report encompasses diverse requirements within medical imaging and radiation therapy settings, serving both clinical and research purposes. Brief overview of 3D printing technology, common materials, and potential clinical applications is provided. QA team, infrastructure, measurement techniques and challenges are discussed. QA processes for each step in 3D printing are discussed in great detail and baseline and action limits are recommended. This report also touched on regulatory considerations. Key recommendations are summarized at the end of the report.

Background: Given the faster onset and shorter duration of action of ultra-rapid insulin lispro-aabc (URLi, Lyumjev™ insulin), compared with insulin lispro (a rapid-acting insulin [RAI]), the present study investigated the safety and glycemic outcomes of MiniMed™ 780G advanced hybrid closed-loop (AHCL) use with URLi in youths and adults with T1D. Methods: This 19-site, single-arm, clinical trial enrolled children and adolescents (aged 7–17 years) and adults (aged 18–80 years) with T1D who underwent a run-in period (∼2 weeks) using open loop or automated basal only with an RAI (aspart or lispro), followed by a 3-month study period using URLi with AHCL (AHCL + URLi). End-of-study glycemic metrics and A1c were compared to predefined thresholds and to data from baseline/run-in. Use of recommended optimal settings (ROS, 100 mg/dL glucose target with an active insulin time [AIT] of 2 h) was also assessed. Results: In an intention-to-treat population ( N = 101 pediatric and N = 110 adult participants), percentage of time in range (%TIR) during the last ∼6 weeks of the study period was significantly greater than the predefined thresholds for both the pediatric and adult participants. A1c was unchanged in the pediatric cohort but significantly reduced in the adult cohort (from 7.4 ± 0.9% to 6.9 ± 0.6% [ P < 0.001]). Compared with run-in, study period %TIR and percentage of time in tight target range (%TITR) were significantly increased (pediatric mean %TIRΔ [17.4%] and %TITRΔ [16.0%], respectively, and adult mean %TIRΔ [10.6%] and %TITRΔ [11.6%], respectively; P < 0.001 for all). Additionally, % time above range for both groups was significantly reduced. Use of ROS allowed more participants to achieve recommended glycemic targets. There were no severe hypoglycemia or diabetic ketoacidosis events. Most caregivers agreed that mealtime versus premeal URLi delivery simplified pediatric meal management. Conclusions: Similar to previous studies investigating automated URLi delivery, URLi use in the MiniMed™ 780G system was safe, and glycemic outcomes were favorable for pediatric and adult participants.

ABSTRACT Objective Identifying and addressing pediatric hearing loss is critical to supporting a child's development. School‐based hearing screening is a mainstay of timely identification of hearing loss. The objectives of this study were to characterize the current hearing screening practices in public, charter, and private elementary schools in Minnesota. Methods This was a cross‐sectional survey with data collected between March and June 2023. Surveys assessed the presence of standardized hearing screening processes and compliance with American Academy of Audiology (AAA) or Minnesota Department of Health (MDH) guidelines. Results About 146 public schools, 43 charter schools, and 60 private schools met inclusion criteria and responded to the survey. There was a statistically significant difference in the rate of standardized screening between school types ( χ 2 = 18.06; p < 0.001). Only 10.44% ( n = 26) of schools completed hearing screenings per AAA guidelines, and even fewer, 4.82% ( n = 12), completed hearing screenings according to MDH guidelines. The odds of screening per AAA or MDH guidelines were 3.50 times higher in charter schools compared to public schools (95% CI: 1.14, 10.73) and 4.61 times higher in private schools compared to public schools (95% CI: 1.73, 12.26). Conclusion There is a lack of standardization in hearing screening processes in Minnesota elementary schools. Adherence to screening per AAA or MDH recommendations is low in all types of elementary schools. Charter and private schools were more likely than public schools to screen per AAA or MDH guidelines. Overall, our data demonstrate an opportunity for improvement in school‐based hearing screening. Level of Evidence N/A.

Abstract We present chromosome-level, phased diploid genome assemblies of two widely used human fibroblast cell lines: BJ (46,XY) and IMR-90 (46,XX). Using Oxford Nanopore, PacBio HiFi, and Hi-C sequencing data, we generated assemblies spanning 5.9 and 6.0 Gbp with diploid quality values exceeding QV 60. To validate structural integrity, we developed KaryoScope, an alignment-free tool for generating computational karyograms from k-mer feature databases. We identify &gt;50 000 structural variants relative to T2T-CHM13v2.0, the majority of which are heterozygous and cell-line-specific. Combining reference-based and de novo gene annotation, we uncover a previously unreported 1 Mbp homozygous duplication at the 16p11.2 locus in BJ, demonstrating that even karyotypically normal cell lines can harbor clinically relevant submicroscopic rearrangements. We show that mapping publicly available short-read, RNA-seq, and ChIP-seq data to sample-matched diploid assemblies substantially improves read alignment and enables haplotype phasing of 23%–28% of short reads. The BJ and IMR-90 assemblies and associated variant calls are publicly available as a resource for the research community.

Background Failure of conventional imaging to detect pancreatic ductal adenocarcinoma (PDA) at its visually occult pre-diagnostic stage is a primary barrier to improving its otherwise poor rate of survival. Objective To develop and validate the Radiomics-based Early Detection MODel (REDMOD), an AI framework to identify subvisual radiomic signatures of pre-diagnostic PDA on standard-of-care CT. Designs REDMOD was trained on a multi-institutional cohort (n=969; 156 pre-diagnostic, 813 control) and tested on an independent set (n=493; 63 pre-diagnostic, 430 control), simulating a low prevalence (~1:6) early detection paradigm. The fully automated framework couples AI-driven segmentation with a heterogeneous ensemble architecture trained on a 40-feature radiomic signature derived from Synthetic Minority Over-sampling Technique (SMOTE)-balanced data. A tunable Youden Index-optimised classification threshold enables performance calibration without retraining. Validation included direct comparison with radiologists, longitudinal test–retest analysis and external specificity validation across two independent cohorts (n=539 and n=80). Results On an independent test set (n=493), REDMOD identified occult PDA (AUC 0.82; 73.0% sensitivity) at a median 475-day lead time. This represented nearly twofold higher sensitivity than radiologists (38.9%; p<0.001), which grew to nearly threefold (68.0% vs 23.0%) at >24 months lead time. REDMOD showed strong longitudinal stability (90–92% concordance) and generalisable specificity across multi-institutional (81.3%; n=539) and public (87.5%; n=80) datasets. Mechanistic analyses confirmed predictive power derived principally from multi-scale wavelet-filtered textural features (90% of selected signature), which outperformed unfiltered features (AUC 0.82 vs 0.74; p=0.007) in capturing subvisual architectural disruptions. Conclusions REDMOD is an automated, mechanistically grounded, longitudinally stable, externally validated AI that surpasses radiologists for PDA detection at its visually occult pre-diagnostic stage. These attributes position it for prospective validation in high-risk cohorts, a necessary step towards shifting the paradigm from late-stage symptomatic diagnosis to proactive pre-clinical interception.