We present an automated method for measuring the sagittal vertical axis (SVA) from lateral radiography of whole spine using a convolutional neural network for keypoint detection (ResUNet) with our improved localization method. The algorithm is robust to various clinical conditions, such as degenerative changes or deformities. The ResUNet was trained and evaluated on 990 standing lateral radiographs taken at Chang Gung Memorial Hospital, Linkou and performs SVA measurement with median absolute error of 1.183 ± 0.166 mm. The 5-mm detection rate of the C7 body and the sacrum are 91% and 87%, respectively. The SVA calculation takes approximately 0.2 s per image. The intra-class correlation coefficient of the SVA estimates between the algorithm and physicians of different years of experience ranges from 0.946 to 0.993, indicating an excellent consistency. The superior performance of the proposed method and its high consistency with physicians proved its usefulness for automatic measurement of SVA in clinical settings.

The aim of our study was to investigate the association between global spinal alignment, spinopelvic parameters, and outcomes of osteoporotic vertebral compression fractures (OVCF). Patients with vertebral compression fractures seen at our hospital between October 2017 and November of 2018 with a bone mineral density (BMD) T-score < −2.5 were recruited for the study. Surgical intervention was performed after eight weeks of conservative treatment depending on clinical symptoms and the willingness of patients. Spinopelvic and sagittal alignment parameters were compared between patients who had surgery and those that did not. Seventy-nine patients were included in the study. Twenty-five patients (31.6%, mean age: 73.28 ± 9.78 years) received surgery, and 54 (68.3%, mean age: 73 ± 8.58 years) conservative treatment only. Pelvic tilt, pelvic incidence, and local kyphotic angle were statistically different between the groups (all p < 0.05). A sagittal vertical axis ≥ 50 mm, distance between the C7 plumb line and the center of the fractured vertebra (DSVA) ≥ 60 mm, pelvic incidence outside of the range of 44 to 62°), and pelvic tilt ≥ 27° were associted with the need for surgical intervention. Measurement of spinopelvic parameters can predict the need for surgery in patients with OVCF.

Tuberculosis is one of devastating infectious diseases in the world, and early diagnosis and treatment can help overcome this global burden. In this work, a new detection platform combining smartphone-assisted fluorescent analysis and highly sensitive fluorescent copper nanoprobes (CuNPs) in a specific nucleic acid amplification test (NAAT) for the diagnosis of tuberculosis (TB) was demonstrated and validated using clinical samples. To enhance the precision and accuracy of detection, polymerase chain reaction (PCR), padlock probe (PLP) ligation, and rolling circle amplification (RCA) were combined. Long poly(thymine) (polyT) single-stranded DNA was synthesized through RCA, and polyT-CuNPs were formed by adding copper(II) ions and sodium ascorbate as reducing agents; subsequently, the results were visualized through the excitation from a UV transilluminator and quantified with just a smartphone. After optimization, this proposed platform was validated by testing 18 residual DNA samples after TB PCR, including 8 TB-negative and 10 TB-positive samples, and exhibited a detection limit of 5 fg/μL. The findings indicate the potential of this platform for practical application, where it can be combined with a smartphone for image analysis to achieve accurate on-site detection of TB, especially in resource-limited settings.

Background: Tibial plateau fractures represent a diverse group of intra-articular injuries that can be difficult to detect and characterize on initial imaging. The aim of the present study was to develop an artificial intelligence (AI) diagnostic tool for identifying tibial plateau fractures on radiographs. Methods: In this retrospective study, we analyzed radiographs that had been made from January 2018 to December 2020 for 1,809 patients, with an equal distribution of male and female adults. A total of 3,821 anteroposterior and lateral knee radiographs were evaluated with use of the EfficientNet B3 AI model, with computed tomography (CT) images being used as the ground truth. Evaluation metrics focused on the area under the receiver operating characteristic curve (AUC) and positive predictive values across different subgroups. Results: Our AI model attained AUCs of 0.98 and 0.97 for detecting tibial plateau fractures in the test and external validation datasets, respectively. Subgroup analysis revealed diverse positive predictive values across different Schatzker types and 3-column classifications. Conclusions: Our deep learning model exhibits newfound ability for identifying tibial plateau fractures. However, we encountered several limitations, such as imbalances among the sizes of various subgroups in the dataset and an inability to identify radiographs containing foreign objects or other defects. Level of Evidence: Diagnostic Level III . See Instructions for Authors for a complete description of levels of evidence.

Background: Systematic reviews represent the foundation of evidence-based orthopedic practice, yet their methodological rigor relies heavily on accurate and consistent methodological quality assessment. This step remains time-consuming, labor-intensive, and prone to subjectivity. Recent advances in large language models (LLMs) suggest potential for automating parts of evidence synthesis. Purpose: This study examined whether LLMs can perform AMSTAR-1–based methodological quality assessment evaluations in orthopedic systematic reviews with accuracy comparable to human experts. Methods: Ten sports medicine knee reviews were analyzed using three LLMs—GPT-4o, GPT-5, and GPT Consensus—and their binary responses were compared against expert AMSTAR-1 ratings from a published umbrella review (110 decisions). An external validation set of four reviews published between 2022 and 2025 was included to assess generalizability and safeguard against information leakage. Results: Agreement with human reviewers reached 87% for GPT-4o, 89% for GPT-5, and 90% for GPT Consensus; all models achieved 84% agreement in the validation set. Concordance was strongest for structured, explicitly reported domains such as a priori design, literature search, and study characteristics, and lowest for judgment-based items including grey literature inclusion, publication bias, and conflict of interest. Conclusions: LLMs cannot yet replace human reviewers, they can serve as reliable adjunct tools to enhance efficiency, transparency, and reproducibility in systematic review workflows within orthopedic research.