Citations

Abstract Purpose The purpose of this systematic review was to compare the inter‐ and intra‐observer reliability of Kellgren–Lawrence (KL) grading versus minimum joint space width (mJSW) measurement on knee radiographs, and to examine the influence of rater type, radiographic view and atlas‐based training. Methods A systematic search of PubMed/MEDLINE, Embase, Scopus and Web of Science was conducted through July 2025 following Preferred Reporting Items for Systematic reviews and Meta‐Analyses (PRISMA) guidelines. Studies reporting inter‐ and/or intra‐observer reliability for KL or mJSW on standard knee radiographs were included. Extracted data included kappa ( κ ) and intraclass correlation coefficient (ICC) values, rater expertise, radiographic view and atlas usage. Raters were categorized as expert, trainee/non‐expert or artificial intelligence (AI)‐assisted/automated. Results Twenty‐four studies (10,394 radiographs) met the inclusion criteria. Inter‐observer reliability was generally higher for mJSW (mean ICC = 0.82 ± 0.17) compared with KL (mean k = 0.72 ± 0.17), with similar trends observed for intra‐observer reliability. Experts and AI‐assisted systems outperformed trainees/non‐experts for both metrics. Reliability improved with semiflexed posteroanterior/Rosenberg views and atlas‐guided training. Conclusion This systematic review demonstrates that mJSW measurement generally shows higher reproducibility than KL grading. Reliability improved with expertise, standardized imaging and structured training, and AI‐assisted approaches performed comparably to expert raters. Quantitative mJSW should complement KL grading, particularly when combined with alignment measures, to enhance consistency and clinical relevance of radiographic assessment. Level of Evidence Level III.

Background: We aimed to develop automated data extraction pipelines with large language models (LLMs) to extract registry data from total hip arthroplasty (THA) operative notes and compare the performance with that of existing natural language processing (NLP) algorithms. Methods: We randomly sampled 1,000 primary THA cases from our institutional registry. Two human annotators manually reviewed each operative note for 3 data points: surgical approach, bearing surface, and fixation technique. All labeled THA notes were split into the development set (n = 239) and the testing set (n = 719). We developed a custom data extraction pipeline for each data point by combining an iteratively customized prompt with an LLM. The performance was compared with that of existing rules-based NLP algorithms. Results: The accuracy of LLMs was superior to that of NLP algorithms for all data points: surgical approach (96% compared with 94%), bearing surface (89% compared with 74%), and fixation technique (96% compared with 95%). Furthermore, the LLM accurately inferred the bearing surface for 80% of the notes that were ambiguous about the bearing surface. Conclusions: We developed LLM pipelines for extracting 3 registry-relevant data points from THA operative notes, demonstrating superior performance to existing NLP algorithms. Clinical Relevance: LLMs have the potential to impact clinical care, including the evaluation of electronic medical record free-text data. As registries serve as a cornerstone of orthopaedic evidence, this work demonstrates promise for LLMs to simplify, improve, and democratize the construction of registry databases from operative notes.

Introduction/Objective: As fewer physicians enter primary care, Advanced Practice Providers (APPs) play an increasingly important role in meeting the demand for patient care. Factors contributing to work status changes among primary care APPs are not well studied. We aimed to evaluate differences in primary care APP work status across electronic health record (EHR) workload measures. Methods: We conducted a retrospective cohort study within a Midwestern healthcare system from 2020 to 2022, evaluating the relationship between primary care APP work status defined as retention at current full-time equivalent (FTE), reduction of FTE within primary care, or relocation outside of primary care and 3 time-based EHR workload metrics. Descriptive statistics, univariate, and multivariable analyses were reported. Results: There were no differences between work status (retained, reduced, or relocated) across the EHR workload measurements of in-basket time per appointment, system time per appointment and note time per appointment ( P > .05) on univariate analysis. With multivariable analysis, there was no difference in likelihood of combined relocation/reduction adjusting for EHR workload variables ( P > .05). Conclusion: The EHR workload was not associated with work status changes for primary care APPs in our study. Further exploration is needed to identify factors that may contribute to reduction in primary care APP workforce capacity.

Introduction: Manual measurement of leg length (LL) and offset can be tedious. This study developed an automated algorithm for measuring LL and offset from pre- and postoperative AP pelvis radiographs in a large cohort of THA patients. Methods: Using a deep learning model trained on 1100 total AP pelvis radiographs, an algorithm was developed to calculate LL and offset. Algorithm measurements were compared with manual measurements by 4 raters on a sample of 100 pre- and postoperative image pairs. Inter- and intra-rater consistency was calculated using the intraclass correlation coefficient (ICC). The algorithm was applied to calculate the pre- and postoperative LL and offset discrepancies and the change in LL and offset bilaterally in a cohort of 15,951 image pairs. Results: ICC values between the algorithm and human raters ranged from 0.83 to 0.88 for offset measurements and 0.92 to 0.97 for LL measurements. Human raters demonstrated good-to-excellent inter-rater ICC and uniformly excellent intra-rater ICC. Entire database measurements demonstrated shorter LLs for arthritic joints versus the contralateral leg preoperatively and reduced LL discrepancy post-arthroplasty. Conclusions: We present a deep learning algorithm for calculating LL and offset using AP pelvis radiographs. This tool can support population-level studies and may assist operative management.

ABSTRACT Background Sunlight has profound impacts on physical and mental health, beyond vision, including effects on circadian rhythms, alertness, mood, and sleep. A family history of any mood disorders is strongly associated with psychiatric disorders including bipolar disorder. The purpose of this study was to evaluate the association between a family history of any mood disorder in patients with bipolar I disorder and solar insolation at varied international onset locations. Methods Data for this analysis were available from 5842 patients with a diagnosis of bipolar I disorder obtained at 83 collection sites in both hemispheres. This included 4752 patients from 71 collection sites in the northern hemisphere and 1090 patients from 12 collection sites in the southern hemisphere. Patient data variables were obtained from records or interviews. Solar insolation data were obtained from The National Aeronautics and Space Administration (NASA) Power database for each onset location, and the ratio of the mean monthly minimum/mean monthly maximum solar insolation was calculated. Typically, the ratio is largest near the equator (little yearly change in solar insolation) and smallest near the poles (large yearly change in solar insolation). Results A significant relationship was found between a family history of any mood disorder, the ratio of the mean monthly minimum/mean monthly maximum solar insolation, and gender. The odds of a family history of mood disorder increased as patient location nears the poles and decreased near the equator. Female gender also increased the odds of having a family history of a mood disorder. Conclusions This study highlighted the association between family history, solar insolation, and gender in international patients with bipolar I disorder. Given the profound effects of sunlight on human health, the family of patients with bipolar disorder who live in the same location with the same solar insolation, and especially females, may be at increased risk for a mood disorder.

Importance The choice of induction agent during rapid sequence intubation (RSI) of critically ill adults may affect clinical outcomes. Although ketamine and etomidate are frequently used for RSI, their comparative effectiveness remains controversial. Objective To compare the safety of etomidate vs ketamine for emergency RSI in critically ill adults. Design, Setting, and Participants This cohort study used a target trial emulation with observational data collected between March 1, 2022, and April 30, 2024, from 18 emergency departments across Brazil, with data from the Brazilian Airway Registry Cooperation. Adults who underwent RSI and received either etomidate or ketamine as a sole hypnotic agent were included; those with preintubation cardiac arrest or immediate postintubation transfer were excluded. Exposure Administration of etomidate or ketamine as the induction agent for RSI. Main Outcomes and Measures The primary outcome was 28-day in-hospital mortality. Secondary outcomes included 7-day in-hospital mortality, first-attempt intubation success, and major adverse events (new hemodynamic instability, severe hypoxemia, and cardiac arrest) within 30 minutes after intubation. Inverse probability of treatment weighting was used to adjust for confounding. Risk ratios (RRs) and risk differences (RDs) with 95% CIs were used to compare outcomes between groups. Results Among 1810 patients (median age, 64 years [IQR, 50-74 years]; 1048 men [57.9%]), 514 received ketamine and 1296 received etomidate. The median shock index was higher in the ketamine group than the etomidate group (0.81 [IQR, 0.65-1.01] vs 0.76 [IQR, 0.59-0.99]), and preintubation vasopressor use was more common in the ketamine group than the etomidate group (191 of 514 [37.2%] vs 391 of 1296 [30.2%]). Weighted 28-day mortality was higher with etomidate than ketamine (60.5% [95% CI, 57.2%-63.8%] vs 54.4% [95% CI, 45.0%-63.9%]; RR, 1.14 [95% CI, 1.03-1.27]; RD, 7.6% [95% CI, 2.0%-13.3%]). Seven-day mortality was also higher with etomidate than ketamine (35.2% [95% CI, 32.0%-38.3%] vs 30.1% [95% CI, 23.5%-36.7%]; RR, 1.19 [95% CI, 1.04-1.35]). New hemodynamic instability within 30 minutes after intubation was more frequent with ketamine (24.2% [95% CI, 20.4%-28.0%] vs 18.9% [95% CI, 16.7%-21.0%]; RR, 0.78 [0.64-0.95]). There were no statistically significant differences in the other secondary outcomes. Conclusions and Relevance In this cohort study of critically ill adults undergoing RSI, etomidate use was associated with higher in-hospital mortality at 7 and 28 days compared with ketamine. These findings highlight the need for definitive randomized clinical trials to compare both agents.

Background: Scoliosis has various etiologies, ranging from idiopathic, congenital, to those with spinal cord abnormalities. Advanced imaging is not always feasible and limited by cost, low-yield, and anesthesia risks in children. Given artificial intelligence's potential, we hypothesize that a deep learning (DL)–based image classifier will demonstrate superior performance in radiographic classification of scoliosis etiology compared witht experienced spine surgeons based on spine radiographs. Methods: One thousand thirty-six pediatric patients from single institution with scoliosis diagnosis and paired anterior-posterior - lateral images were included. Patients were manually classified based on their scoliosis etiology from chart review, including previous spine imaging studies when available. Categories included idiopathic, congenital, and spinal cord pathology. Images were randomized and assigned for training, validation, and testing. A DL-classifier using EfficientNet B4 architecture was trained on the radiographs. Accuracy and positive predictive value as defined by precision, recall, and F1-score were calculated to assess final performance metrics. Results: The trained classifier performed well at identifying correct etiologies, with F1-Score (harmonic mean of precision-recall) of 0.97. Model precision was 0.99 for adolescent idiopathic scoliosis, 0.89 for congenital, and 0.78 for spinal cord pathology. Performance was higher on more common classes, with lower performance observed in class with fewer images. The algorithm has highest overall precision (0.96), recall (0.96), and F1 (0.96), while Surgeons 1 and 2 have lower accuracies (precision 0.80, recall 0.79, and F1 0.79 and precision 0.76, recall 0.67, and F10.71, respectively). There was no clear pattern identified regarding the surgeons' errors and poor agreement on which X-rays corresponded to underlying spinal cord pathology. Conclusion: A DL-convolutional-neural-network classifier has been trained to high degree of accuracy to distinguish between 3 scoliosis etiologies on pediatric spine radiographs. This model could provide a novel tool to clinicians to decide when to refer for axial imaging. It had superior diagnostic performance compared with experienced spine surgeons. After further validation and refinement, a clinician could put a patient's X-rays into the predictive tool for analysis and use the results to discuss with the family the risk of finding spinal cord pathology, helping them determine together the best timing for an MRI. Level of Evidence: Level III . See Instructions for Authors for a complete description of levels of evidence.

Artificial intelligence (AI) is increasingly shaping pediatric spine care, leveraging its rapid advancements in healthcare to improve efficiency, accuracy, and disease understanding. Moreover, machine learning and deep learning excel at detecting complex patterns. This holds promise in processing spinal deformity data, with the potential to surpass traditional statistical methods in predictive accuracy. Challenges persist, however, including unclear clinical implementation guidelines, limited model transparency, and ethical concerns surrounding data privacy and bias. Small sample sizes and the need for larger, diverse datasets further complicate integration. In order to realize AI’s transformative potential in pediatric spine care, these critical obstacles must be addressed for effective and ethical clinical adoption. This review examines the role of AI through applications such as image sorting, surgical outcome prediction, forecasting of spinal curve progression, and vertebral volumetric analysis using deep reasoning. It also explores possible intraoperative contributions from AI, including robotics and optimized screw trajectory planning, and the potential of large language models in clinical practice.

Introduction: Diabetes affected 529 million people globally by 2021, largely due to rising obesity contributing to Type 2 diabetes (DM2). In the U.S., it is the seventh leading cause of death and closely linked to cardiovascular disease, the leading cause of mortality in this population. Effective, low-cost strategies to improve glycemic and cardiometabolic health are essential. Psyllium, a viscous soluble fiber, has been shown to lower LDL cholesterol and improve glycemic indices, whereas non-viscous fibers like wheat dextrin lack similar benefits. Emerging lipid markers such as ceramides are associated with cardiometabolic risk but have not been studied in response to fiber. The interaction between fiber and GLP-1 agonists is also unclear. Hypothesis: Psyllium supplementation will improve cardiometabolic markers more than wheat dextrin in people with DM2. Methods: In this randomized trial at Mayo Clinic, adults with DM2 (HbA1c 6.5–10%) were randomized to psyllium or wheat dextrin for 12 weeks. Participants were recruited via electronic health records. Key exclusions: GI disease, bariatric surgery, steroid use, and pregnancy. Follow-up visits occurred at weeks 4, 8, and 12. Primary endpoints were changes in HbA1c and fasting glucose; secondary endpoints included lipids, ceramides, hsCRP, and BMI. An ex post facto analysis evaluated GLP-1 use. Primary analysis was intention-to-treat. Adherence = ≥85% dose completion. Results: Ninety-eight participants enrolled (Psyllium n=50, Dextrin n=48) with similar baseline characteristics. At 12 weeks, psyllium significantly reduced HbA1c (-0.38 ± 0.69, p=0.002). Among adherent users, HbA1c dropped further (-0.41 ± 0.70, p=0.001) with reduced fasting glucose (-14.5 ± 38.2, p=0.013). Wheat dextrin showed no benefit. In subgroup analysis, GLP-1 users on psyllium saw greater HbA1c reductions than non-users (-0.45 vs. -0.23), while GLP-1 users on dextrin had no change (+0.06). No significant changes were found in ceramides, lipids, or BMI in any analysis. CRP trended lower in adherent psyllium users (p=0.055). Conclusion: Psyllium significantly reduced HbA1c over 12 weeks in DM2, especially in adherent and GLP-1–treated groups. Effects may be attributed to psyllium's ability to form a gel in the gastrointestinal tract, modulating nutrient absorption. No effects were seen on ceramides or lipids, likely due to low baseline levels in the latter. Psyllium appears to be a safe, accessible adjunct for glycemic control in DM2.