RESUMEN
PURPOSE: To assess direct costs and risks associated with revision operations for distal junctional kyphosis/failure (DJK) following thoracic posterior spinal instrumented fusions (TPSF) for adolescent idiopathic scoliosis (AIS). METHODS: Children who underwent TPSF for AIS by a single surgeon (2014-2020) were reviewed. Inclusion criteria were minimum follow-up of 2 years, thoracolumbar posterior instrumented fusion with a lower instrumented vertebra (LIV) cranial to L2. Patients who developed DJK requiring revision operations were identified and compared with those who did not develop DJK. RESULTS: Seventy-nine children were included for analysis. Of these, 6.3% developed DJK. Average time to revision was 20.8 ± 16.2 months. Comparing index operations, children who developed DJK had significantly greater BMIs, significantly lower thoracic kyphosis postoperatively, greater post-operative lumbar Cobb angles, and significantly more LIVs cranial to the sagittal stable vertebrae (SSV), despite having statistically similar pre-operative coronal and sagittal alignment parameters and operative details compared with non-DJK patients. Revision operations for DJK, when compared with index operations, involved significantly fewer levels, longer operative times, greater blood loss, and longer hospital lengths of stay. These factors resulted in significantly greater direct costs for revision operations for DJK ($76,883 v. $46,595; p < 0.01). CONCLUSIONS: In this single-center experience, risk factors for development of DJK were greater BMI, lower post-operative thoracic kyphosis, and LIV cranial to SSV. As revision operations for DJK were significantly more costly than index operations, all efforts should be aimed at strategies to prevent DJK in the AIS population.
Asunto(s)
Cifosis , Reoperación , Escoliosis , Fusión Vertebral , Vértebras Torácicas , Humanos , Escoliosis/cirugía , Fusión Vertebral/economía , Fusión Vertebral/efectos adversos , Fusión Vertebral/métodos , Cifosis/cirugía , Adolescente , Femenino , Reoperación/economía , Reoperación/estadística & datos numéricos , Masculino , Vértebras Torácicas/cirugía , Niño , Estudios Retrospectivos , Complicaciones Posoperatorias/economía , Complicaciones Posoperatorias/epidemiología , Complicaciones Posoperatorias/etiologíaRESUMEN
PURPOSE: To (1) analyze trends in the publishing of statistical fragility index (FI)-based systematic reviews in the orthopaedic literature, including the prevalence of misleading or inaccurate statements related to the statistical fragility of randomized controlled trials (RCTs) and patients lost to follow-up (LTF), and (2) determine whether RCTs with relatively "low" FIs are truly as sensitive to patients LTF as previously portrayed in the literature. METHODS: All FI-based studies published in the orthopaedic literature were identified using the Cochrane Database of Systematic Reviews, Web of Science Core Collection, PubMed, and MEDLINE databases. All articles involving application of the FI or reverse FI to study the statistical fragility of studies in orthopaedics were eligible for inclusion in the study. Study characteristics, median FIs and sample sizes, and misleading or inaccurate statements related to the FI and patients LTF were recorded. Misleading or inaccurate statements-defined as those basing conclusions of trial fragility on the false assumption that adding patients LTF back to a trial has the same statistical effect as existing patients in a trial experiencing the opposite outcome-were determined by 2 authors. A theoretical RCT with a sample size of 100, P = .006, and FI of 4 was used to evaluate the difference in effect on statistical significance between flipping outcome events of patients already included in the trial (FI) and adding patients LTF back to the trial to show the true sensitivity of RCTs to patients LTF. RESULTS: Of the 39 FI-based studies, 37 (95%) directly compared the FI with the number of patients LTF. Of these 37 studies, 22 (59%) included a statement regarding the FI and patients LTF that was determined to be inaccurate or misleading. In the theoretical RCT, a reversal of significance was not observed until 7 patients LTF (nearly twice the FI) were added to the trial in the distribution of maximal significance reversal. CONCLUSIONS: The claim that any RCT in which the number of patients LTF exceeds the FI could potentially have its significance reversed simply by maintaining study follow-ups is commonly inaccurate and prevalent in orthopaedic studies applying the FI. Patients LTF and the FI are not equivalent. The minimum number of patients LTF required to flip the significance of a typical RCT was shown to be greater than the FI, suggesting that RCTs with relatively low FIs may not be as sensitive to patients LTF as previously portrayed in the literature; however, only a holistic approach that considers the context in which the trial was conducted, potential biases, and study results can determine the merits of any particular RCT. CLINICAL RELEVANCE: Surgeons may benefit from re-examining their interpretation of prior FI reviews that have made claims of substantial RCT fragility based on comparisons between the FI and patients LTF; it is possible the results are more robust than previously believed.
RESUMEN
PURPOSE: To (1) review definitions and concepts necessary to interpret applications of deep learning (DL; a domain of artificial intelligence that leverages neural networks to make predictions on media inputs such as images) and (2) identify knowledge and translational gaps in the literature to provide insight into specific areas for improvement as adoption of this technology continues. METHODS: A comprehensive search of the literature was performed in December 2023 for articles regarding the use of DL in sports medicine. For each study, information regarding the joint of focus, specific anatomic structure/pathology to which DL was applied, imaging modality utilized, source of images used for model training and testing, data set size, model performance, and whether the DL model was externally validated was recorded. A numerical scale was used to rate each DL model's clinical impact, with 1 corresponding to proof-of-concept studies with little to no direct clinical impact and 5 corresponding to practice-changing clinical impact and ready for clinical deployment. RESULTS: Fifty-five studies were identified, all of which were published within the past 5 years, while 82% were published within the past 3 years. Of the DL models identified, 84% were developed for classification tasks, 9% for automated measurements, and 7% for segmentation. A total of 62% of studies utilized magnetic resonance imaging as the imaging modality, 25% radiographs, and 7% ultrasound, while 1 study each used computed tomography, arthroscopic images, or arthroscopic video. Sixty-five percent of studies focused on the detection of tears (anterior cruciate ligament [ACL], rotator cuff [RC], and meniscus). The diagnostic performance of ACL tears, as determined by the area under the receiver operator curve (AUROC), ranged from 0.81 to 0.99 for ACL tears (excellent to near perfect), 0.83 to 0.94 for RC tears (excellent), and from 0.75 to 0.96 for meniscus tears (acceptable to excellent). In addition, 3 studies focused on detection of cartilage lesions had AUROC ranging from 0.90 to 0.92 (excellent performance). However, only 4 (7%) studies externally validated their models, suggesting that they may not be generalizable or may not perform well when applied to populations other than that used to develop the model. Finally, the mean clinical impact score was 2 (range, 1-3) on scale of 1 to 5, corresponding to limited clinical applicability. CONCLUSIONS: DL models in orthopaedic sports medicine show generally excellent performance (high internal validity) but require external validation to facilitate clinical deployment. In addition, current models have low clinical applicability and fail to advance the field due to a focus on routine tasks and a narrow conceptual framework. LEVEL OF EVIDENCE: Level IV, scoping review of Level I to IV studies.
RESUMEN
PURPOSE: To assess the ability of ChatGPT-4, an automated Chatbot powered by artificial intelligence, to answer common patient questions concerning the Latarjet procedure for patients with anterior shoulder instability and compare this performance with Google Search Engine. METHODS: Using previously validated methods, a Google search was first performed using the query "Latarjet." Subsequently, the top 10 frequently asked questions (FAQs) and associated sources were extracted. ChatGPT-4 was then prompted to provide the top 10 FAQs and answers concerning the procedure. This process was repeated to identify additional FAQs requiring discrete-numeric answers to allow for a comparison between ChatGPT-4 and Google. Discrete, numeric answers were subsequently assessed for accuracy on the basis of the clinical judgment of 2 fellowship-trained sports medicine surgeons who were blinded to search platform. RESULTS: Mean (± standard deviation) accuracy to numeric-based answers was 2.9 ± 0.9 for ChatGPT-4 versus 2.5 ± 1.4 for Google (P = .65). ChatGPT-4 derived information for answers only from academic sources, which was significantly different from Google Search Engine (P = .003), which used only 30% academic sources and websites from individual surgeons (50%) and larger medical practices (20%). For general FAQs, 40% of FAQs were found to be identical when comparing ChatGPT-4 and Google Search Engine. In terms of sources used to answer these questions, ChatGPT-4 again used 100% academic resources, whereas Google Search Engine used 60% academic resources, 20% surgeon personal websites, and 20% medical practices (P = .087). CONCLUSIONS: ChatGPT-4 demonstrated the ability to provide accurate and reliable information about the Latarjet procedure in response to patient queries, using multiple academic sources in all cases. This was in contrast to Google Search Engine, which more frequently used single-surgeon and large medical practice websites. Despite differences in the resources accessed to perform information retrieval tasks, the clinical relevance and accuracy of information provided did not significantly differ between ChatGPT-4 and Google Search Engine. CLINICAL RELEVANCE: Commercially available large language models (LLMs), such as ChatGPT-4, can perform diverse information retrieval tasks on-demand. An important medical information retrieval application for LLMs consists of the ability to provide comprehensive, relevant, and accurate information for various use cases such as investigation about a recently diagnosed medical condition or procedure. Understanding the performance and abilities of LLMs for use cases has important implications for deployment within health care settings.
RESUMEN
Explorative data analysis (EDA) is a critical step in scientific projects, aiming to uncover valuable insights and patterns within data. Traditionally, EDA involves manual inspection, visualization, and various statistical methods. The advent of artificial intelligence (AI) and machine learning (ML) has the potential to improve EDA, offering more sophisticated approaches that enhance its efficacy. This review explores how AI and ML algorithms can improve feature engineering and selection during EDA, leading to more robust predictive models and data-driven decisions. Tree-based models, regularized regression, and clustering algorithms were identified as key techniques. These methods automate feature importance ranking, handle complex interactions, perform feature selection, reveal hidden groupings, and detect anomalies. Real-world applications include risk prediction in total hip arthroplasty and subgroup identification in scoliosis patients. Recent advances in explainable AI and EDA automation show potential for further improvement. The integration of AI and ML into EDA accelerates tasks and uncovers sophisticated insights. However, effective utilization requires a deep understanding of the algorithms, their assumptions, and limitations, along with domain knowledge for proper interpretation. As data continues to grow, AI will play an increasingly pivotal role in EDA when combined with human expertise, driving more informed, data-driven decision-making across various scientific domains. Level of Evidence: Level V - Expert opinion.
RESUMEN
Deep learning is a subset of artificial intelligence (AI) with enormous potential to transform orthopaedic surgery. As has already become evident with the deployment of Large Language Models (LLMs) like ChatGPT (OpenAI Inc.), deep learning can rapidly enter clinical and surgical practices. As such, it is imperative that orthopaedic surgeons acquire a deeper understanding of the technical terminology, capabilities and limitations associated with deep learning models. The focus of this series thus far has been providing surgeons with an overview of the steps needed to implement a deep learning-based pipeline, emphasizing some of the important technical details for surgeons to understand as they encounter, evaluate or lead deep learning projects. However, this series would be remiss without providing practical examples of how deep learning models have begun to be deployed and highlighting the areas where the authors feel deep learning may have the most profound potential. While computer vision applications of deep learning were the focus of Parts I and II, due to the enormous impact that natural language processing (NLP) has had in recent months, NLP-based deep learning models are also discussed in this final part of the series. In this review, three applications that the authors believe can be impacted the most by deep learning but with which many surgeons may not be familiar are discussed: (1) registry construction, (2) diagnostic AI and (3) data privacy. Deep learning-based registry construction will be essential for the development of more impactful clinical applications, with diagnostic AI being one of those applications likely to augment clinical decision-making in the near future. As the applications of deep learning continue to grow, the protection of patient information will become increasingly essential; as such, applications of deep learning to enhance data privacy are likely to become more important than ever before. Level of Evidence: Level IV.
Asunto(s)
Aprendizaje Profundo , Cirujanos Ortopédicos , Humanos , Inteligencia Artificial , Privacidad , Sistema de RegistrosRESUMEN
PURPOSE: To review the existing literature to (1) determine the diagnostic efficacy of artificial intelligence (AI) models for detecting scaphoid and distal radius fractures and (2) compare the efficacy to human clinical experts. METHODS: PubMed, OVID/Medline, and Cochrane libraries were queried for studies investigating the development, validation, and analysis of AI for the detection of scaphoid or distal radius fractures. Data regarding study design, AI model development and architecture, prediction accuracy/area under the receiver operator characteristic curve (AUROC), and imaging modalities were recorded. RESULTS: A total of 21 studies were identified, of which 12 (57.1%) used AI to detect fractures of the distal radius, and nine (42.9%) used AI to detect fractures of the scaphoid. AI models demonstrated good diagnostic performance on average, with AUROC values ranging from 0.77 to 0.96 for scaphoid fractures and from 0.90 to 0.99 for distal radius fractures. Accuracy of AI models ranged between 72.0% to 90.3% and 89.0% to 98.0% for scaphoid and distal radius fractures, respectively. When compared to clinical experts, 13 of 14 (92.9%) studies reported that AI models demonstrated comparable or better performance. The type of fracture influenced model performance, with worse overall performance on occult scaphoid fractures; however, models trained specifically on occult fractures demonstrated substantially improved performance when compared to humans. CONCLUSIONS: AI models demonstrated excellent performance for detecting scaphoid and distal radius fractures, with the majority demonstrating comparable or better performance compared with human experts. Worse performance was demonstrated on occult fractures. However, when trained specifically on difficult fracture patterns, AI models demonstrated improved performance. CLINICAL RELEVANCE: AI models can help detect commonly missed occult fractures while enhancing workflow efficiency for distal radius and scaphoid fracture diagnoses. As performance varies based on fracture type, future studies focused on wrist fracture detection should clearly define whether the goal is to (1) identify difficult-to-detect fractures or (2) improve workflow efficiency by assisting in routine tasks.
Asunto(s)
Inteligencia Artificial , Fracturas del Radio , Hueso Escafoides , Fracturas de la Muñeca , Humanos , Fracturas del Radio/diagnóstico por imagen , Hueso Escafoides/lesiones , Fracturas de la Muñeca/diagnóstico por imagenRESUMEN
INTRODUCTION: Technological advancements in implant design and surgical technique have focused on diminishing complications and optimizing performance of reverse shoulder arthroplasty (RSA). Despite this, there remains a paucity of literature correlating prosthetic features and clinical outcomes. This investigation utilized a machine learning approach to evaluate the effect of select implant design features and patient-related factors on surgical complications after RSA. METHODS: Over a 16-year period (2004 - 2020), all primary RSA performed at a single institution for elective and traumatic indications with a minimum follow-up of 2 years were identified. Parameters related to implant design evaluated in this study included inlay vs onlay humeral bearing design, glenoid lateralization (medialized or lateralized), humeral lateralization (medialized, minimally lateralized, or lateralized), global lateralization (medialized, minimally lateralized, lateralized, highly lateralized, or very highly lateralized), stem to metallic bearing neck shaft angle (NSA), and polyethylene NSA. Machine learning models predicting surgical complications were constructed for each patient and Shapley additive explanation (SHAP) values were calculated to quantify feature importance. RESULTS: A total of 3,837 RSAs were identified, of which 472 (12.3%) experienced a surgical complication. Those experiencing a surgical complication were more likely to be current smokers (Odds ratio [OR] = 1.71; P = .003), have prior surgery (OR = 1.60; P < .001), have an underlying diagnosis of sequalae of instability (OR = 4.59; P < .001) or non-union (OR = 3.09; P < .001), and required longer OR times (98 vs. 86 minutes; P < .001). Notable implant design features at an increased odds for complications included an inlay humeral component (OR = 1.67; P < .001), medialized glenoid (OR = 1.43; P = .001), medialized humerus (OR = 1.48; P = .004), a minimally lateralized global construct (OR = 1.51; P < .001), and glenohumeral constructs consisting of a medialized glenoid and minimally lateralized humerus (OR = 1.59; P < .001), and a lateralized glenoid and medialized humerus (OR = 2.68; P < .001). Based on patient- and implant-specific features, the machine learning model predicted complications after RSA with an area under the receiver operating characteristic curve (AUC ROC) of 0.61. CONCLUSIONS: This study demonstrated that patient-specific risk factors had a more substantial effect than implant design configurations on the predictive ability of a machine learning model on surgical complications after RSA. However, certain implant features appeared to be associated with a higher odd of surgical complications.
RESUMEN
BACKGROUND: Based in part on the results of randomized controlled trials (RCTs) that suggest a beneficial effect over alternative treatment options, the use of platelet-rich plasma (PRP) for the management of knee osteoarthritis (OA) is widespread and increasing. However, the extent to which these studies are vulnerable to slight variations in the outcomes of patients remains unknown. PURPOSE: To evaluate the statistical fragility of conclusions from RCTs that reported outcomes of patients with knee OA who were treated with PRP versus alternative nonoperative management strategies. STUDY DESIGN: Systematic review and meta-analysis; Level of evidence, 2. METHODS: All RCTs comparing PRP with alternative nonoperative treatment options for knee OA were identified. The fragility index (FI) and reverse FI were applied to assess the robustness of conclusions regarding the efficacy of PRP for knee OA. Meta-analyses were performed to determine the minimum number of patients from ≥1 trials included in the meta-analysis for which a modification on the event status would change the statistical significance of the pooled treatment effect. RESULTS: In total, this analysis included outcomes from 1993 patients with a mean ± SD age of 58.0 ± 3.8 years. The mean number of events required to reverse significance of individual RCTs (FI) was 4.57 ± 5.85. Based on random-effects meta-analyses, PRP demonstrated a significantly higher rate of successful outcomes when compared with hyaluronic acid (P = .002; odds ratio [OR], 2.19; 95% CI, 1.33-3.62), as well as higher rates of patient-reported symptom relief (P = .019; OR, 1.55; 95% CI, 1.07-2.24), not requiring a reintervention after the initial injection treatment (P = .002; OR, 2.17; 95% CI, 1.33-3.53), and achieving the minimal clinically important difference (MCID) for pain improvement (P = .007; OR, 6.19; 95% CI, 1.63-23.42) when compared with all alternative nonoperative treatments. Overall, the mean number of events per meta-analysis required to change the statistical significance of the pooled treatment effect was 8.67 ± 4.50. CONCLUSION: Conclusions drawn from individual RCTs evaluating PRP for knee OA demonstrated slight robustness. On meta-analysis, PRP demonstrated a significant advantage over hyaluronic acid as well as improved symptom relief, lower rates of reintervention, and more frequent achievement of the MCID for pain improvement when compared with alternative nonoperative treatment options. Statistically significant pooled treatment effects evaluating PRP for knee OA are more robust than approximately half of all comparable meta-analyses in medicine and health care. Future RCTs and meta-analyses should consider reporting FIs and fragility quotients to facilitate interpretation of results in their proper context.
RESUMEN
Purpose: To compare the cost-effectiveness of an initial trial of nonoperative treatment to that of early arthroscopic debridement for stable osteochondritis dissecans (OCD) lesions of the capitellum. Methods: A Markov Chain Monte Carlo probabilistic model was developed to evaluate the outcomes and costs of 1,000 simulated patients undergoing nonoperative management versus early arthroscopic debridement for stable OCD lesions of the capitellum. Health utility values, treatment success rates, and transition probabilities were derived from the published literature. Costs were determined on the basis of the typical patient undergoing each treatment strategy at our institution. Outcome measures included costs, quality-adjusted life-years (QALYs), and the incremental cost-effectiveness ratio (ICER). Results: Mean total costs resulting from nonoperative management and early arthroscopic debridement were $5,330 and $21,672, respectively. On average, early arthroscopic debridement produced an additional 0.64 QALYS, resulting in an ICER of $25,245/QALY, which falls well below the widely accepted $50,000 willingness-to-pay (WTP) threshold. Overall, early arthroscopic debridement was determined to be the preferred cost-effective strategy in 69% of patients included in the microsimulation model. Conclusion: Results of the Monte Carlo microsimulation and probabilistic sensitivity analysis demonstrated early arthroscopic debridement to be a cost-effective treatment strategy for the majority of stable OCD lesions of the capitellum. Although early arthroscopic debridement was associated with higher total costs, the increase in QALYS that resulted from early surgery was enough to justify the cost difference based on an ICER substantially below the $50,000 WTP threshold. Level of Evidence: Level III, economic computer simulation model.
RESUMEN
Purpose: The present study reviews the available scientific literature on artificial intelligence (AI)-assisted ultrasound-guided regional anaesthesia (UGRA) and evaluates the reported intraprocedural parameters and postprocedural outcomes. Methods: A literature search was performed on 19 September 2023, using the Medline, EMBASE, CINAHL, Cochrane Library and Google Scholar databases by experts in electronic searching. All study designs were considered with no restrictions regarding patient characteristics or cohort size. Outcomes assessed included the accuracy of AI-model tracking, success at the first attempt, differences in outcomes between AI-assisted and unassisted UGRA, operator feedback and case-report data. Results: A joint adaptive median binary pattern (JAMBP) has been applied to improve the tracking procedure, while a particle filter (PF) is involved in feature extraction. JAMBP combined with PF was most accurate on all images for landmark identification, with accuracy scores of 0.83, 0.93 and 0.93 on original, preprocessed and filtered images, respectively. Evaluation of first-attempt success of spinal needle insertion revealed first-attempt success in most patients. When comparing AI application versus UGRA alone, a significant statistical difference (p < 0.05) was found for correct block view, correct structure identification and decrease in mean injection time, needle track adjustments and bone encounters in favour of having AI assistance. Assessment of operator feedback revealed that expert and nonexpert operator feedback was overall positive. Conclusion: AI appears promising to enhance UGRA as well as to positively influence operator training. AI application of UGRA may improve the identification of anatomical structures and provide guidance for needle placement, reducing the risk of complications and improving patient outcomes. Level of Evidence: Level IV.
RESUMEN
BACKGROUND: Nonoperative management versus early reconstruction for partial tears of the medial ulnar collateral ligament (MUCL) remains controversial, with the most common treatment options for partial tears consisting of rest, rehabilitation, platelet-rich plasma (PRP), and/or surgical intervention. However, whether the improved outcomes reported for treatments such as MUCL reconstruction (UCLR) or nonoperative management with a series of PRP injections justifies their increased upfront costs remains unknown. PURPOSE: To compare the cost-effectiveness of an initial trial of physical therapy alone, an initial trial of physical therapy plus a series of PRP injections, and early UCLR to determine the preferred cost-effective treatment strategy for young, high-level baseball pitchers with partial tears of the MUCL and with aspirations to continue play at the next level (ie, collegiate and/or professional). STUDY DESIGN: Economic and decision analysis; Level of evidence, 2. METHODS: A Markov chain Monte Carlo probabilistic model was developed to evaluate the outcomes and costs of 1000 young, high-level, simulated pitchers undergoing nonoperative management with and without PRP versus early UCLR for partial MUCL tears. Utility values, return to play rates, and transition probabilities were derived from the published literature. Costs were determined based on the typical patient undergoing each treatment strategy at the authors' institution. Outcome measures included costs, acquired playing years (PYs), and the incremental cost-effectiveness ratio (ICER). RESULTS: The mean total costs resulting from nonoperative management without PRP, nonoperative management with PRP, and early UCLR were $22,520, $24,800, and $43,992, respectively. On average, early UCLR produced an additional 4.0 PYs over the 10-year time horizon relative to nonoperative management, resulting in an ICER of $5395/PY, which falls well below the $50,000 willingness-to-pay threshold. Overall, early UCLR was determined to be the preferred cost-effective strategy in 77.5% of pitchers included in the microsimulation model, with nonoperative management with PRP determined to be the preferred strategy in 15% of pitchers and nonoperative management alone in 7.5% of pitchers. CONCLUSION: Despite increased upfront costs, UCLR is a more cost-effective treatment option for partial tears of the MUCL than an initial trial of nonoperative management for most high-level baseball pitchers.
Asunto(s)
Béisbol , Ligamento Colateral Cubital , Análisis Costo-Beneficio , Cadenas de Markov , Humanos , Béisbol/lesiones , Ligamento Colateral Cubital/lesiones , Ligamento Colateral Cubital/cirugía , Técnicas de Apoyo para la Decisión , Plasma Rico en Plaquetas , Modalidades de Fisioterapia/economía , Traumatismos en Atletas/terapia , Traumatismos en Atletas/cirugía , Traumatismos en Atletas/rehabilitación , Traumatismos en Atletas/economía , Adulto Joven , MasculinoRESUMEN
Artificial intelligence's (AI) accelerating progress demands rigorous evaluation standards to ensure safe, effective integration into healthcare's high-stakes decisions. As AI increasingly enables prediction, analysis and judgement capabilities relevant to medicine, proper evaluation and interpretation are indispensable. Erroneous AI could endanger patients; thus, developing, validating and deploying medical AI demands adhering to strict, transparent standards centred on safety, ethics and responsible oversight. Core considerations include assessing performance on diverse real-world data, collaborating with domain experts, confirming model reliability and limitations, and advancing interpretability. Thoughtful selection of evaluation metrics suited to the clinical context along with testing on diverse data sets representing different populations improves generalisability. Partnering software engineers, data scientists and medical practitioners ground assessment in real needs. Journals must uphold reporting standards matching AI's societal impacts. With rigorous, holistic evaluation frameworks, AI can progress towards expanding healthcare access and quality. Level of Evidence: Level V.
RESUMEN
Purpose: To develop a deep learning model for the detection of Segond fractures on anteroposterior (AP) knee radiographs and to compare model performance to that of trained human experts. Methods: AP knee radiographs were retrieved from the Hospital for Special Surgery ACL Registry, which enrolled patients between 2009 and 2013. All images corresponded to patients who underwent anterior cruciate ligament reconstruction by 1 of 23 surgeons included in the registry data. Images were categorized into 1 of 2 classes based on radiographic evidence of a Segond fracture and manually annotated. Seventy percent of the images were used to populate the training set, while 20% and 10% were reserved for the validation and test sets, respectively. Images from the test set were used to compare model performance to that of expert human observers, including an orthopaedic surgery sports medicine fellow and a fellowship-trained orthopaedic sports medicine surgeon with over 10 years of experience. Results: A total of 324 AP knee radiographs were retrieved, of which 34 (10.4%) images demonstrated evidence of a Segond fracture. The overall mean average precision (mAP) was 0.985, and this was maintained on the Segond fracture class (mAP = 0.978, precision = 0.844, recall = 1). The model demonstrated 100% accuracy with perfect sensitivity and specificity when applied to the independent testing set and the ability to meet or exceed human sensitivity and specificity in all cases. Compared to an orthopaedic surgery sports medicine fellow, the model required 0.3% of the total time needed to evaluate and classify images in the independent test set. Conclusions: A deep learning model was developed and internally validated for Segond fracture detection on AP radiographs and demonstrated perfect accuracy, sensitivity, and specificity on a small test set of radiographs with and without Segond fractures. The model demonstrated superior performance compared with expert human observers. Clinical Relevance: Deep learning can be used for automated Segond fracture identification on radiographs, leading to improved diagnosis of easily missed concomitant injuries, including lateral meniscus tears. Automated identification of Segond fractures can also enable large-scale studies on the incidence and clinical significance of these fractures, which may lead to improved management and outcomes for patients with knee injuries.
RESUMEN
STUDY DESIGN: Retrospective comparative study. OBJECTIVE: To compare patient-reported physical activity between anterior thoracic vertebral body tethering and posterior lumbar spine tethering (ATVBT/PLST) and posterior spinal instrumentation and fusion (PSIF) with minimum 2 year follow-up. METHODS: Consecutive skeletally immature patients with idiopathic scoliosis and a thoracic and lumbar curve magnitude ≥40° who underwent either ATVBT/PLST or PSIF from 2015-2019 were included. The primary outcome was rate of returning to sport. Secondary outcomes included ability to bend and satisfaction with sport performance as well as weeks until return to sport, school, physical education (PE) classes, and running. RESULTS: Ten patients underwent ATVBT/PLST and 12 underwent PSIF. ATVBT/PLST patients reported significantly faster return to sport (13.5 weeks vs 27.9 weeks, P = .04), running (13.3 weeks vs 28.8 weeks, P = .02), and PE class (12.6 weeks vs 26.2 weeks, P = .04) compared to PSIF patients. ATVBT/PLST patients reported that they had to give up activities due to their ability to bend at lower rates than PSIF patients while reporting "no changes" in their ability to bend after surgery at higher rates than PSIF patients (0% vs 4% giving up activities and 70% vs 0% reporting no changes in bending ability for ATVBT/PLST and PSIF, respectively, P = .01). Compared to PSIF patients, ATVBT/PLST patients experienced less main thoracic and thoracolumbar/lumbar curve correction at most recent follow-up (thoracic: 41 ± 19% vs 69 ± 18%, P = .001; thoracolumbar/lumbar: 59 ± 25% vs 78 ± 15%, P = .02). No significant differences in the number of revision surgeries were observed between ATVBT/PLST and PSIF patients (4 (40%) and 1 (8%) for ATVBT/PLST and PSIF, respectively, P = .221). CONCLUSIONS: ATVBT/PLST patients reported significantly faster rates of returning to sport, running, and PE. In addition, ATVBT/PLST patients were less likely to have to give up activities due to bending ability after surgery and reported no changes in their ability to bend after surgery more frequently than PSIF patients. However, the overall rate of return to the same or higher level of sport participation was high amongst both groups, with no significant difference observed between ATVBT/PLST and PSIF patients.