Linjun Yang

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.

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.

Background: Orthopaedic surgeons routinely delay surgical management of femoral neck fractures in patients taking direct oral anticoagulants (DOACs) to decrease perioperative bleeding and associated complications. However, this practice contradicts the principles of hip fracture management, as early surgery is associated with morbidity and mortality benefits. The purpose of this study was to quantify the association of DOAC use and perioperative outcomes in patients who underwent hemiarthroplasty (HA) or total hip arthroplasty (THA) for femoral neck fractures. We hypothesized that early surgical intervention on a patient taking a DOAC medication would not lead to worse perioperative outcomes. Methods: A retrospective cohort study was conducted on 2,833 patients who underwent primary THA or HA for femoral neck fractures between December 31, 2017, and January 29, 2024, across our hospital system. The patients taking a DOAC were divided into 3 groups based on the time since the last DOAC intake: 1 day, 2 days, and ≥3 days. Propensity matching was performed 1:1, accounting for age, sex, Elixhauser Comorbidity Index, preoperative chronic kidney disease stage, preoperative hemoglobin, body mass index, and hospital type. Subanalyses utilizing linear and conditional logistic regression models were performed to assess differences in outcomes between the groups that had a DOAC withheld and the control groups. Results: The mean age of all patients was 81 ± 10 years, 1,805 patients (64%) were women, and 207 patients (7%) were taking a DOAC prior to surgery. Despite comparable preoperative and postoperative hemoglobin levels between the groups that had a DOAC withheld and the control groups (all p > 0.05), the patients who had a DOAC withheld for 1 day were more likely to receive a postoperative blood transfusion (23.1% compared with 0%; p = 0.002). This difference in transfusion rate was not observed in other cohorts. There were no differences in medical complications, reoperation, discharge disposition, or mortality between the groups that had a DOAC withheld and the matched controls at any time point. Conclusions: Delaying surgical management due to DOAC medications may be unnecessary in patients undergoing arthroplasty for femoral neck fractures. Consideration should be given to adjusting transfusion triggers to reduce unwarranted blood transfusions in patients taking a DOAC. Level of Evidence: Therapeutic Level III. See Instructions for Authors for a complete description of levels of evidence.

Background/Objectives: Accurate assessment of spinal bone density is essential for evaluating bone health, particularly in preoperative planning. Conventional manual methods for Hounsfield unit (HU) measurements rely on single-slice measurements within the region of interest, limiting their precision and reproducibility in patients with severe vertebral deformities. We hypothesize that a novel deep-reasoning and learning model (DR-AI) can fully automate spinal bone density assessment volumetrically, with high correlations to spinal bone mineral density (BMD) obtained from dual-energy X-ray absorptiometry (DXA), as well as to the T- and Z-scores. Methods: A cross-sectional study was conducted on patients who had BMD assessment of their lumbar spine and lumbar CT scans within 1 year. The fully-automated DR model was utilized to analyze the soft-tissue window of the lumbar vertebrae CT scans. Spearman correlation coefficients were calculated to assess the strength of relationships between the computed volumetric HUs and the BMD, T-, and Z-scores from each vertebra. Results: 84 patients (67 females, mean age 74.1 ± 10.3 years; 17 males, mean age 68.1 ± 12.4 years) meeting inclusion criteria. Correlation analyses for L1 to L4 showed significant positive relationships (p < 0.0001), with the strongest correlation at L2 between HU and BMD (ρ = 0.75). Conclusions: the DR model for automated assessment of volumetric HUs offers a highly reliable, efficient, and precise alternative to DXA measurements.