Citations

Current clinical care relies heavily on complex, rule-based systems for tasks like diagnosis and treatment. However, these systems can be cumbersome and require constant updates. This study explores the potential of the large language model (LLM), LLaMA 2, to address these limitations. We tested LLaMA 2′s performance in interpreting complex clinical process models, such as Mayo Clinic Care Pathway Models (CPMs), and providing accurate clinical recommendations. LLM was trained on encoded pathways versions using DOT language, embedding them with SentenceTransformer, and then presented with hypothetical patient cases. We compared the token-level accuracy between LLM output and the ground truth by measuring both node and edge accuracy. LLaMA 2 accurately retrieved the diagnosis, suggested further evaluation, and delivered appropriate management steps, all based on the pathways. The average node accuracy across the different pathways was 0.91 (SD ± 0.045), while the average edge accuracy was 0.92 (SD ± 0.122). This study highlights the potential of LLMs for healthcare information retrieval, especially when relevant data are provided. Future research should focus on improving these models’ interpretability and their integration into existing clinical workflows.

Background/Objectives: Adherence to sports-specific nutritional guidelines can help optimize athlete performance and health. However, adolescent athletes may not have adequate nutrition knowledge and understanding of specific nutritional requirements. The objective of the current study was to examine the nutrition knowledge and perceived dietary requirements of adolescent athletes. Methods: Male (n = 29, age: 15.7 ± 1.3 yrs.; height: 178.9 ± 8.3 cm; body mass: 74.7 ± 17.2 kg; body fat %: 13.9 ± 7.9%) and female (n = 15, age: 16.5 ± 1.4 yrs.; height: 169.9 ± 6.5 cm; body mass: 63.3 ± 4.5 kg; body fat %: 23.7 ± 3.8%) secondary school student-athletes completed body composition testing (hydrostatic weighing) and electronic surveys (Abridged Sports Nutrition Knowledge Questionnaire (ASNKQ); self-perception of dietary energy and macronutrient requirements). Results: Athletes demonstrated poor sports nutrition knowledge, with no differences observed between sexes for the number of questions answered correctly (males: 45.1 ± 9.8% vs. females: 43.1 ± 12.7%; p = 0.57). No relationships were observed between ASNKQ scores and body composition parameters or between ASNKQ scores and self-reported perception of dietary energy and macronutrient requirements (p > 0.05). Athletes self-reported a lower perceived energy (−560 ± 1272 kcal/d; p = 0.014) and carbohydrate intake (−73 ± 376 g/d; p = 0.014) requirement compared to calculated nutritional recommendations. Athletes self-reported a higher perceived protein intake (263 ± 586 g/d; p = 0.026) requirement compared to calculated nutritional requirements. Conclusions: The current sample of adolescent athletes from the secondary school level appears to have a poor level of sports nutrition knowledge and understanding of energy and macronutrient requirements.

ABSTRACT Background and Purpose In idiopathic normal pressure hydrocephalus (iNPH) patients, cerebrospinal fluid (CSF) flow is typically evaluated with a cardiac‐gated two‐dimensional (2D) phase‐contrast (PC) MRI through the cerebral aqueduct. This approach is limited by the evaluation of a single location and does not account for respiration effects on flow. In this study, we quantified the cardiac and respiratory contributions to CSF movement at multiple intracranial locations using a real‐time 2D PC‐MRI and evaluated the diagnostic value of CSF dynamics biomarkers in classifying iNPH patients. Methods This study included 37 participants: 16 iNPH, 10 Alzheimer's disease (AD), and 11 cognitively unimpaired (CU) controls. Anatomical and real‐time (non‐gated) PC images were acquired in a 3T Philips scanner. CSF flow was assessed at the foramen magnum, fourth ventricle, Sylvian fissure, lateral ventricle, and cerebral aqueduct. We calculated three CSF dynamics biomarkers: mean velocity amplitude, cardiac signal power, and respiratory signal power. Biomarkers from each location were evaluated for classifying iNPH versus AD and CU using support vector machine (SVM). A p ‐value of 0.05 or less was considered statistically significant. Results The velocity amplitude and cardiac signal power were significantly reduced in iNPH compared to CU ( p < 0.005) and AD ( p < 0.05) at the lateral ventricle. The SVM model using biomarkers from the lateral ventricle performed significantly better at classifying iNPH than the other locations in terms of accuracy ( p < 0.005) and diagnostic odds ratio ( p < 0.05). Conclusion Evaluation of CSF movement beyond the cerebral aqueduct may aid in identifying patients with and understanding the pathophysiology of iNPH.

ABSTRACTBackgroundThe role of Intravascular ultrasound (IVUS) and optical coherence tomography (OCT) is still unclear in patients with STEMI undergoing PCI in the current second‐generation DES era.AimsThis study aimed to evaluate the trends and outcomes of IVUS‐guided PCI in patients with STEMI.MethodsWe used the National Inpatient Sample (NIS) database from 2016 to 2021. The primary endpoint of this study is all‐cause in‐hospital mortality. Secondary endpoints include trends of PCI hospitalizations, trends of mortality, length of stay, and cost of hospitalization.ResultsThere were data for 819,645 hospitalizations for STEMI, of which 91.2% (n = 74,7860) utilized angiography‐guided PCI, 8.4% (n = 68,985) utilized IVUS‐guided PCI and 0.3% (n = 2800) utilized OCT‐guided PCI. In‐hospital mortality for IVUS‐guided PCI was 4.6% (n = 3190) versus 6.0% (n = 44,935) for angiography‐guided PCI with an adjusted OR 0.75 (0.68–0.81, p < 0.001). In‐hospital mortality for OCT‐guided PCI was 3.4% (n = 95) versus 6.0% (n = 44,935) for angiography‐guided PCI with an adjusted OR 0.67 (0.43–1.06, p = 0.09).ConclusionsIVUS/OCT‐guidance was increasingly utilized over the years and was associated with a significantly reduced adjusted odds of in‐hospital mortality. Large‐scale, long‐term randomized data are needed to better ascertain where IVUS/OCT may be best utilized for optimization of PCI for STEMI.

ABSTRACTObjectivesThis study aimed to compared Patient‐Reported Outcomes Measurement Information System (PROMIS) anxiety, depression, and anger item bank among Korean, US and Dutch general population.MethodsBetween December 2021 and January 2022, we surveyed representative Korean participants (N = 2699). Then we compared the mean T‐scores of PROMIS anxiety, depression, and anger full items bank among Korean, US (N = 1696) and the Dutch (N = 1002) populations. Differential item‐functioning (DIF) analyses were also performed. We also compared each score by age group, sex, presence of comorbidities, and general health status.ResultsIn Korean, the mean T‐scores for anxiety, depression, and anger were 45.3 (standard deviation [SD] = 11.6), 48.4 (SD = 11.2), and 44.9 (SD = 12.6), respectively. Among the general population in Korea, patients aged 35–44 years and those with comorbidities had higher anxiety, depression, and anger scores. In the DIF analyses between the US and Korean populations, 28%, 32%, and 45% were flagged for uniform or non‐uniform DIF in anxiety, depression and anger, respectively.ConclusionsConsidering the cultural differences, we recommend using a harmonized approach that includes country‐specific reference values while retaining a standardized core set of items to enable cross‐country comparability.

Abstract INTRODUCTION Diffusion‐weighted magnetic resonance imaging (dMRI) is sensitive to the microstructural properties of brain tissues and shows great promise in detecting the effects of degenerative diseases. However, many approaches analyze single measures averaged over regions of interest without considering the underlying fiber geometry. METHODS We propose a novel macrostructure‐informed normative tractometry (MINT) framework to investigate how white matter (WM) microstructure and macrostructure are jointly altered in mild cognitive impairment (MCI) and dementia. We compared MINT‐derived metrics with univariate diffusion tensor imaging (DTI) metrics to examine how fiber geometry may impact the interpretation of microstructure. RESULTS In two multisite cohorts from North America and India, we find consistent patterns of microstructural and macrostructural anomalies implicated in MCI and dementia; we also rank diffusion metrics' sensitivity to dementia. DISCUSSION We show that MINT, by jointly modeling tract shape and microstructure, has the potential to disentangle and better interpret the effects of degenerative disease on the brain's neural pathways. Highlights Changes in diffusion tensor imaging metrics may be due to macroscopic changes. Normative models encode normal variability of diffusion metrics in healthy controls. Variational autoencoder applied on tractography can learn patterns of fiber geometry. WM microstructure and macrostructure are modeled with multivariate methods. Transfer learning uses pretraining and fine‐tuning for increased efficiency.

This review article represents a collaborative effort across continents, bringing together the latest developments in neuro-ophthalmology with a focus on innovative diagnostic and therapeutic modalities that are shaping the future of the field. Among the most significant advancements is the rise of optical coherence tomography (OCT), now recognized as an indispensable tool in neuro-ophthalmological research, providing unparalleled insights into optic nerve and central nervous system pathologies. Gene therapy, particularly for conditions such as Leber's hereditary optic neuropathy, marks a new frontier in personalized medicine, offering hope for previously untreatable conditions. The article also examines the transformative role of telemedicine and artificial intelligence (AI) in clinical practice, which are revolutionizing patient care and enhancing diagnostic precision. Furthermore, it highlights the impact of novel serological biomarkers on the understanding and management of immune-mediated optic neuritis, and discusses the introduction of new therapeutic agents like Tocilizumab and Teprotumumab, which are redefining treatment paradigms. Collectively, these advancements reflect the profound influence of modern medicine on neuro-ophthalmology, paving the way for improved patient outcomes and fostering new avenues for research and clinical practice.

Abstract Myelodysplastic syndromes/neoplasms (MDSs) are heterogeneous stem cell malignancies characterized by poor prognosis and no curative therapies outside of allogeneic hematopoietic stem cell transplantation. Despite some recent approvals by the US Food and Drug Administration, (eg, luspatercept, ivosidenib, decitabine/cedazuridine, and imetelstat), there has been little progress in the development of truly transformative therapies for the treatment of patients with MDS. Challenges to advancing drug development in MDS are multifold but may be grouped into specific categories, including criteria for risk stratification and eligibility, response definitions, time-to-event end points, transfusion end points, functional assessments, and biomarker development. Strategies to address these challenges and optimize future clinical trial design for patients with MDS are presented here.