Mulford, Kellen L.

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: 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.

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.

As artificial intelligence (AI) advances in healthcare, encompassing robust applications for the diagnosis and prognostication of musculoskeletal diseases, clinicians must increasingly understand the implications of machine learning and deep learning in their practice. This review article explores computer vision algorithms and patient-specific, multimodal prediction models; provides a simple framework to guide discussion on the limitations of AI model development; and introduces the field of generative AI.

Abstract Purpose Developing large‐scale, standardized radiographic registries for anterior cruciate ligament (ACL) injuries with artificial intelligence (AI) tools can enhance personalized orthopaedics. We propose deploying Artificial Intelligence for Knee Imaging Registration and Analysis (AKIRA), a trio of deep learning (DL) algorithms, to automatically classify and annotate radiographs. We hypothesize that algorithms can efficiently organize radiographs based on laterality, projection, identify implants and classify osteoarthritis (OA) grade. Methods A collection of 20,836 knee radiographs from all time points of treatment (mean orthopaedic follow‐up 70.7 months; interquartile range [IQR]: 6.8–172 months) were aggregated from 1628 ACL‐injured patients (median age 26 years [IQR: 19–42], 57% male). Three DL algorithms (EfficientNet, YOLO [You Only Look Once] and Residual Network) were employed. Radiograph laterality and projection (anterior‐posterior [AP], lateral, sunrise, posterior‐anterior, hip–knee–ankle and Camp‐Coventry intercondylar [notch]) were labelled by a DL model. Manually provided labels of metal fixation implants were used to develop a DL object detection algorithm. The degree of OA, both as measured by specific Kellgren–Lawrence (KL) grades, as well as based on a binarized label of OA (defined as KL Grade ≥2), on standing AP radiographs were classified using a DL algorithm. Individual model performances were evaluated on a subset of images prior to the deployment of AKIRA to registry construction using all ACL radiographs. Results The classification algorithms showed excellent performance in classifying radiographic laterality (F1 score: 0.962–0.975) and projection (F1 score: 0.941–1.0). The object detection algorithm achieved high precision–recall (area under the precision‐recall curve: 0.695–0.992) for identifying various metal fixations. The KL classifier reached concordances of 0.39–0.40, improving to 0.81–0.82 for binary OA labels. Sequential deployment of AKIRA following internal validation processed and labelled all 20,836 images with the appropriate views, implants, and the presence of OA within 88 min. Conclusion AKIRA effectively automated the classification and object detection in a large radiograph cohort of ACL injuries, creating an AI‐enabled radiographic registry with comprehensive details on laterality, projection, implants and OA. Study Design Cross‐sectional study. Level of Evidence Level IV.

Background/Objectives: The burden of scoliosis care extends beyond treatment costs and includes missed school for patients and lost income for parents. Chronic absenteeism, defined as more than 18 days of missed school, can have a significant impact on a child’s educational progression, but missed school and work due to scoliosis treatment are not well quantified in the literature. This study investigates absenteeism among scoliosis patients and their caregivers. Methods: We conducted a retrospective comparative study of survey results based on surgery timing and surgery type. Patients and caregivers presenting for clinic visits for scoliosis treatment at a single large tertiary care center from 2014 to 2022 were queried. Results: We collected 2772 surveys from 1104 unique patients. Of these, 223 surveys from 132 patients were within one year of surgery: 140 post-fusion surveys, 71 post-nonfusion surveys, and 11 post-halo/multistage surgery surveys. A total of 2280 surveys were from 1022 nonoperatively treated patients. School absenteeism was significantly higher for surgeries during the school year compared to summer in both the fusion and nonfusion groups, though work absenteeism showed no significant differences. Halo/multistage surgery patients had the highest rates of absenteeism. Conclusions: This study highlights the impacts of scoliosis surgery timing and type on absenteeism among patients and their caregivers. Surgery during summer breaks reduces school absenteeism and academic disruption. Halo/multistage surgery patients face the greatest risk of chronic absenteeism from school, indicating a need for targeted interventions. Optimized surgical timing and planning can help families navigate the educational and financial challenges of scoliosis treatment.