Search Results (53)

(1) Background: The exploration of various machine learning (ML) algorithms for classifying the state of Lumbar Intervertebral Discs (IVD) in orthopedic patients is the focus of this study. The classification is based on six key biomechanical features of the pelvis and lumbar spine. Although previous research has demonstrated the effectiveness of ML models in diagnosing IVD pathology using imaging modalities, there is a scarcity of studies using biomechanical features. (2) Methods: The study utilizes a dataset that encompasses two classification tasks. The first task classifies patients into Normal and Abnormal based on their IVDs (2C). The second task further classifies patients into three groups: Normal, Disc Hernia, and Spondylolisthesis (3C). The performance of various ML models, including decision trees, support vector machines, and neural networks, is evaluated using metrics such as accuracy, AUC, recall, precision, F1, Kappa, and MCC. These models are trained on two open-source datasets, using the PyCaret library in Python. (3) Results: The findings suggest that an ensemble of Random Forest and Logistic Regression models performs best for the 2C classification, while the Extra Trees classifier performs best for the 3C classification. The models demonstrate an accuracy of up to 90.83% and a precision of up to 91.86%, highlighting the effectiveness of ML models in diagnosing IVD pathology. The analysis of the weight of different biomechanical features in the decision-making processes of the models provides insights into the biomechanical changes involved in the pathogenesis of Lumbar IVD abnormalities. (4) Conclusions: This research contributes to the ongoing efforts to leverage data-driven ML models in improving patient outcomes in orthopedic care. The effectiveness of the models for both diagnosis and furthering understanding of Lumbar IVD herniations and spondylolisthesis is outlined. The limitations of AI use in clinical settings are discussed, and areas for future improvement to create more accurate and informative models are suggested. Full article

Background: Lumbar disc herniation (LDH) is a common cause of lower back pain and radiculopathy. In recent years, the enhanced recovery after surgery (ERAS) concept has been increasingly applied in orthopedics and gastrointestinal surgery. Purpose: To investigate the effect of using rapid rehabilitation surgical care for lumbar disc herniation by meta-analysis. Data source: Google Scholar, PubMed Medical, Cochrane and Embase databases were used for the analysis. Research selection: An initial search yielded a total of 322 relevant articles. Duplicate pieces of literature were screened using Endnote. In addition, non-randomized controlled trials and studies with a sample size of less than 30 were excluded. A total of seven papers were included in this study. Main outcomes: The Rapid Rehabilitation Surgical Nursing (RRSN) group showed significantly higher patient satisfaction (RR = 1.24; 95% CI: 1.06, 1.26; p < 0.01) and self-assessed health (Total MD = 5.67; 95% CI: 4.27, 7.06; p < 0.01) compared to the Normal Nursing (NN) group. Pain levels (MD = −0.66; 95% CI: −0.97, −0.36; p < 0.01), disability levels (MD = −18.64; 95% CI: −32.53, −4.76; p < 0.01), anxiety risk (SAS-MD = −4.33; 95% CI: −6.23, −2.44; p < 0.01), and depression risk (SDS-MD = −4.29; 95% CI: −7.50, −1.07; p < 0.01) were significantly lower in the RRSN group compared to the NN group. According to the GRADE classification, the certainty for patient satisfaction is high, while the certainty for post-care pain, functional capacity, risk of psychological disorders, and self-assessed health status is moderate. Conclusions: Rapid recovery surgical nursing can significantly improve postoperative recovery of lumbar disc herniation, increase patient satisfaction, reduce the risk of psychological disorders, improve lumbar function, and alleviate patient pain. Full article

One of the most common diseases afflicting humans is knee osteoarthritis (KOA). KOA occurs when the knee joint cartilage breaks down, and knee bones start rubbing together. The diagnosis of KOA is a lengthy process, and missed diagnosis can have serious consequences. Therefore, the diagnosis of KOA at an initial stage is crucial which prevents the patients from Severe complications. KOA identification using deep learning (DL) algorithms has gained popularity during the past few years. By applying knee X-ray images and the Kellgren–Lawrence (KL) grading system, the objective of this study was to develop a DL model for detecting KOA. This study proposes a novel model based on CNN called knee osteoarthritis classification network (KOC_Net). The KOC_Net model contains 05 convolutional blocks, and each convolutional block has three components such as Convlotuioanl2D, ReLU, and MaxPooling 2D. The KOC_Net model is evaluated on two publicly available benchmark datasets which consist of X-ray images of KOA based on the KL grading system. Additionally, we applied contrast-limited adaptive histogram equalization (CLAHE) methods to enhance the contrast of the images and utilized SMOTE Tomek to deal with the problem of minority classes. For the diagnosis of KOA, the classification performance of the proposed KOC_Net model is compared with baseline deep networks, namely Dense Net-169, Vgg-19, Xception, and Inception-V3. The proposed KOC_Net was able to classify KOA into 5 distinct groups (including Moderate, Minimal, Severe, Doubtful, and Healthy), with an AUC of 96.71%, accuracy of 96.51%, recall of 91.95%, precision of 90.25%, and F1-Score of 96.70%. Dense Net-169, Vgg-19, Xception, and Inception-V3 have relative accuracy rates of 84.97%, 81.08%, 87.06%, and 83.62%. As demonstrated by the results, the KOC_Net model provides great assistance to orthopedics in making diagnoses of KOA. Full article

The optimal management of bone tumors requires a multidisciplinary strategy to guarantee high-quality care. At specialized centers, the medical team responsible for managing patients with bone cancer comprises oncologists, surgeons, radiologists, pathologists, and rehabilitation specialists. The goal of treatment is to achieve long-term survival with minimal disability and pain. Postoperative rehabilitation is a fundamental therapeutic approach to enhance functionality and sustain the utmost quality of life following a limb-sparing surgery. Currently, megaprostheses are used for reconstructing bone defects after tumor resection, but in the literature, only a few studies have investigated rehabilitation outcomes in terms of functionality and impact on daily activities. This narrative review explores the functional and quality of life outcomes after the implantation of MUTARS^® prostheses in patients with lower extremity bone tumors. A comprehensive search was conducted on PubMed and Scopus using the following MESH terms: “MUTARS”, “Megaprosthesis”, “bone”, “tumors”, “metastasis”, “lower limb”, “rehabilitation”, “outcome”, and “quality of life”, and 10 studies were included. The most frequent oncological pathology was found to be primitive bone tumors treated with modular prostheses. The outcome measures used were the Henderson et al. classification, Harris Hip Scale, Musculoskeletal Tumor Society score, Visual Analog Scale, Range Of Motion, Karnofsky Performance Scale, and quality of life questionnaire. MUTARS^® is a well-established treatment option after bone tumor resection, although it involves extensive and complex post-resection reconstruction that exposes joints and tissues to substantial mechanical stress. Proper rehabilitation after MUTARS^® surgery is a fundamental therapeutic step, although there is still insufficient evidence in the literature focusing on functional and rehabilitative outcomes. Therefore, more studies and guidelines are needed to define standardized rehabilitation protocols for clinical practice after orthopedic oncologic surgery. Full article

Introduction: Various classifications for osteoporotic vertebral fractures (OVFs) have been introduced to enhance patient care and facilitate clinical communication. However, there is limited evidence of their effectiveness in predicting vertebral collapse, and very few studies have compared this association across different classification systems. This study aims to investigate the association between OVF categories, according to the most widely used classification systems, and vertebral collapse. Patients and Methods: A retrospective single-center study was conducted involving patients diagnosed with acute OVFs at the emergency department of a tertiary-level academic hospital with a minimum follow-up of 6 months. Vertebral fractures were independently classified by two radiologists according to several classification systems, including those proposed by Genant, Sugita, the German Society for Orthopedics and Trauma (DGOU), and the AO Spine. Associations between vertebral collapse and OVF classification systems were analyzed using bivariate and logistic regression analyses. Results: This study included 208 patients (82.7% females; mean age of 72.6 ± 9.2 years). The median follow-up time was 15 months, with L1 being the most common fracture site (47.6%). The most frequent OVF types observed, according to Genant’s morphological, Genant’s quantitative, Sugita ’s, DGOU’s, and AO Spine’s classifications, were biconcave (50%), grade 0.5 (47.6%), bow-shaped (61.5%), OF2 (74%), and A1 (61.5%), respectively. All classifications, except for Genant’s quantitative system, were significantly associated with vertebral collapse in bivariate analyses. Logistic regression analyses showed a significant association (p = 0.002) between the AO Spine classification and vertebral collapse, with 85.7% of A4 fractures developing collapse on follow-up. Conclusions: The AO Spine classification showed the highest predictive capacity for vertebral collapse. Specifically, A4 fracture types showed a very high risk of vertebral collapse, confirming the need for non-conservative management of these fractures. Further multicentric and prospective studies are warranted to confirm these findings. Full article

Knee effusion, a common and important indicator of joint diseases such as osteoarthritis, is typically more discernible on magnetic resonance imaging (MRI) scans compared to radiographs. However, the use of radiographs for the early detection of knee effusion remains promising due to their cost-effectiveness and accessibility. This multi-center prospective study collected a total of 1413 radiographs from four hospitals between February 2022 to March 2023, of which 1281 were analyzed after exclusions. To automatically detect knee effusion on radiographs, we utilized a state-of-the-art (SOTA) deep learning-based classification model with a novel preprocessing technique to optimize images for diagnosing knee effusion. The diagnostic performance of the proposed method was significantly higher than that of the baseline model, achieving an area under the receiver operating characteristic curve (AUC) of 0.892, accuracy of 0.803, sensitivity of 0.820, and specificity of 0.785. Moreover, the proposed method significantly outperformed two non-orthopedic physicians. Coupled with an explainable artificial intelligence method for visualization, this approach not only improved diagnostic performance but also interpretability, highlighting areas of effusion. These results demonstrate that the proposed method enables the early and accurate classification of knee effusions on radiographs, thereby reducing healthcare costs and improving patient outcomes through timely interventions. Full article

Variations of the sciatic nerve and piriformis muscle (SN-PM) relationship must be considered when discussing orthopedic procedures within the region as they may cause increased risk of SN injuries. Thirty-one formalin-embalmed, prosected donors were evaluated using the Beaton and Anson (B&A) classification system (1939). Major landmarks of the SN-PM relationship were identified, including the posterior superior iliac spine (PSIS), ischial tuberosity (IT), greater trochanter (GT), and the middle of the SN as it exits under the PM (S1). Distances measured included: PSIS-IT, PSIS-GT, IT-GT, PSIS-S1, IT-S1, GT-S1, S1-Q (distance of perpendicular line connecting S1 to PSIS-IT), and S1-R (distance of perpendicular line connecting S1 to PSIS-GT). Measurements from 49 lower extremities were evaluated using a two-tailed t-test to compare by sex and laterality; a one-tailed t-test was utilized to compare groups based on anatomical sex. Six donors displayed asymmetric B&A classifications, demonstrating gross anatomical differences within a single individual; however, no measurements were significant when comparing extremities. Seven measurements were statistically significant (p < 0.05) between sexes, indicating notable sex-based differences. These data highlight sex-based differences in the SN-PM relationship, as well as consistencies within measurements among extremities, which can be utilized by clinicians when treating male and female patients needing unilateral or bilateral orthopedic procedures or injections within the gluteal region. Full article

Hyaluronic acid (HA), a naturally occurring polysaccharide, holds immense potential in regenerative medicine due to its diverse biological functions and clinical applications, particularly in gel formulations. This paper presents a comprehensive exploration of HA, encompassing its origins, molecular characteristics, and therapeutic roles in gel-based interventions. Initially identified in bovine vitreous humor, HA has since been found in various tissues and fluids across vertebrate organisms and bacterial sources, exhibiting consistent physicochemical properties. The synthesis of HA by diverse cell types underscores its integral role in the extracellular matrix and its relevance to tissue homeostasis and repair. Clinical applications of HA, particularly in addressing musculoskeletal ailments such as osteoarthritis, are examined, highlighting its efficacy and safety in promoting tissue regeneration and pain relief. Building upon this foundation, a novel classification system for HA-based interventions is proposed, aiming to standardize treatment protocols and optimize patient outcomes. The ViSCNOVAS classification system refers to viscosity, storage, chain, number, origin, volume, amount, and size. This classification is specifically designed for HA-based orthobiologic products used in regenerative medicine, including orthopedics, sports medicine, aesthetics, cosmetic dermatology, and wound healing. It aims to provide clinicians with a structured framework for personalized treatment strategies. Future directions in HA research are also discussed, emphasizing the need for further validation and refinement of the proposed classification system to advance the field of regenerative medicine. Overall, this manuscript elucidates the biological functions of hyaluronic acid and its potential in clinical practice while advocating for standardization to enhance patient care in various regenerative applications. Full article

Preoperative risk biomarkers for delirium may aid in identifying high-risk patients and developing intervention therapies, which would minimize the health and economic burden of postoperative delirium. Previous studies have typically used single omics approaches to identify such biomarkers. Preoperative cerebrospinal fluid (CSF) from the Healthier Postoperative Recovery study of adults ≥ 63 years old undergoing elective major orthopedic surgery was used in a matched pair delirium case–no delirium control design. We performed metabolomics and lipidomics, which were combined with our previously reported proteomics results on the same samples. Differential expression, clustering, classification, and systems biology analyses were applied to individual and combined omics datasets. Probabilistic graph models were used to identify an integrated multi-omics interaction network, which included clusters of heterogeneous omics interactions among lipids, metabolites, and proteins. The combined multi-omics signature of 25 molecules attained an AUC of 0.96 [95% CI: 0.85–1.00], showing improvement over individual omics-based classification. We conclude that multi-omics integration of preoperative CSF identifies potential risk markers for delirium and generates new insights into the complex pathways associated with delirium. With future validation, this hypotheses-generating study may serve to build robust biomarkers for delirium and improve our understanding of its pathophysiology. Full article

Background: The purpose of this study was to investigate temporal trends in gunshot wound (GSW)-associated orthopedic injuries among children, adolescents, and young adults in New York State, and to determine the impact of the onset of the COVID-19 pandemic on the incidence of these injuries. Methods: The New York Statewide Planning and Research Cooperative System (SPARCS) inpatient database was reviewed to identify patients ≤ 21 years of age who presented to a hospital with GSW-associated injuries from January 2016 to December 2020. Patient diagnosis codes were cross-referenced with the list of the International Classification of Diseases Version 10 Clinical Modification (ICD-10-CM) codes for orthopedic injuries to determine the incidence of GSW-associated orthopedic injuries among this cohort. The number of cases was cross-referenced with New York State census population estimates to calculate incidence per million. The geographic incidence was plotted over a map of New York State with sub-division based on facility Zone Improvement Plan (ZIP) codes. Poisson regression was used to compare the injury incidence in 2020 (pandemic onset) versus the preceding years (pre-pandemic). Results: Between 2016 and 2020, there were 548 inpatient admissions for GSW-associated orthopedic injuries, representing an incidence of 5.6 cases per million. Injury incidence decreased from 2016 to 2019, with an increase in 2020 representing almost 28% of the total cases identified. There was a statistically significant difference in the incidence rate ratio for 2020 compared to 2016–2019 (p < 0.001). The majority of patients were male (94%), African–American (73%), and covered by either Medicare (49%) or Managed Care (47%). Most cases were clustered around large metropolitan areas with low incidence in suburban and rural regions of the state. Conclusions: There was a two-fold increase in the incidence of GSW-associated orthopedic injuries among patients ≤ 21 years old in New York State during the onset of the COVID-19 pandemic. Full article

Background and Objectives: This retrospective cohort study analyzes mechanical complications in hip fracture surgery using the Trochanteric Fixation Nail-Advanced (TFNA) implant. It investigates the correlation of these complications with demographic, intraoperative, and radiological factors, aiming to identify associated risk factors and suggest improvements in clinical surveillance and treatment strategies. Materials and Methods: We enrolled 253 patients diagnosed with pertrochanteric hip fractures treated between 2017 and 2021, with 126 meeting the criteria for a minimum 6-month follow-up. Data on demographics, American Anesthesia Association Classification (ASA), comorbidities, AO/OTA [AO (Arbeitsgemeinschaft für Osteosynthesefragen)/OTA (Orthopedic Trauma Association)] fracture classification, procedural details, and time to failure were collected. Radiographs were evaluated for reduction quality, the tip–apex distance (TAD), progressive varus deviation, and identification of mechanical complications. Statistical analysis was performed using SPSS software. Results: The predominant AO/OTA fracture classification was 31A2 in 67 cases (52.7%). Reduction quality was deemed good or acceptable in 123 cases (97.6%). The mean time to failure was 4.5 months (range: 2.2–6). The average TAD was 18 mm (range: 1.2–36), with a mean progressive varus deviation of 2.44° (range: 1.30–4.14). A good or acceptable reduction quality was observed in 97.6% of cases. Mechanical complications occurred in 21.4% of patients, with significant associations found with the lateral cortex fracture, use of a TFNA implant with a 130° angle, open reduction, and absence of prior osteoporosis treatment. Conclusions: The study provides insights into mechanical complications in proximal femur fractures treated with the TFNA nail, emphasizing the need for enhanced clinical and radiographic surveillance, especially in patients without osteoporosis treatment. Our findings support the necessity for further clinical studies comparing these outcomes with other implant designs and underscore the importance of personalized treatment strategies to reduce complication rates. Full article

Currently, medical imaging has largely supplanted traditional methods in the realm of diagnosis and treatment planning. This shift is primarily attributable to the non-invasive nature, rapidity, and user-friendliness of medical-imaging techniques. The widespread adoption of medical imaging, however, has shifted the bottleneck to healthcare professionals who must analyze each case post-image acquisition. This process is characterized by its sluggishness and subjectivity, making it susceptible to errors. The anterior cruciate ligament (ACL), a frequently injured knee ligament, predominantly affects a youthful and sports-active demographic. ACL injuries often leave patients with substantial disabilities and alter knee mechanics. Since some of these cases necessitate surgery, it is crucial to accurately classify and detect ACL injury. This paper investigates the utilization of pre-trained convolutional neural networks featuring residual connections (ResNet) along with image-processing methods to identify ACL injury and differentiate between various tear levels. The ResNet employed in this study is not the standard ResNet but rather an adapted version capable of processing 3D volumes constructed from 2D image slices. Achieving a peak accuracy of 97.15% with a custom split, 96.32% through Monte-Carlo cross-validation, and 93.22% via five-fold cross-validation, our approach enhances the performance of three-class classifiers by over 7% in terms of raw accuracy. Moreover, we achieved an improvement of more than 1% across all types of evaluation. It is quite clear that the model’s output can effectively serve as an initial diagnostic baseline for radiologists with minimal effort and nearly instantaneous results. This advancement underscores the paper’s focus on harnessing deep learning for the nuanced detection and classification of ACL tears, demonstrating a significant leap toward automating and refining diagnostic accuracy in sports medicine and orthopedics. Full article

Background: Femoral neck fractures (FNFs) are frequent orthopedic injuries in elderly patients. Despite improvements in clinical monitoring and advances in surgical procedures, 1-year mortality remains between 15% and 30%. The aim of this study is to identify variables that lead to better outcomes in patients treated with total hip arthroplasty (THA) for FNFs. Methods: All patients who underwent cementless THA for FNF from January 2018 to December 2022 were identified. Patients aged more than 80 years old and with other post-traumatic lesions were excluded. Patient data and demographic characteristics were collected. The following data were also registered: time trauma/surgery, surgical approach, operative time, intraoperative complications, surgeon arthroplasty-trained or not, and anesthesia type. In order to search for any predictive factors of better short- and long-term outcomes, we performed different logistic regression analyses. Results: A total of 92 patients were included. From multivariable logistic regression models, we derived that a direct anterior surgical approach and an American Society of Anesthesiologists (ASA) classification < 3 can predict improved short-term outcomes. Moreover, THAs performed by surgeons with specific training in arthroplasty have a lower probability of revision at 1 year. Mortality at 1 year was ultimately influenced by the ASA classification. Conclusions: A direct anterior approach and specific arthroplasty training of the surgeon appear to be able to improve the short- and long-term follow-up of THA after FNF. Full article

(1) Background: Either pre-operative physical status or unstable hemodynamic changes has been reported to play a potential role in causing vital organ dysfunction. Therefore, we intended to investigate the impact of the American Society of Anesthesiologist (ASA) classification and intraoperative hemodynamic instability on non-surgical complications following orthopedic surgery. (2) Methods: We collected data on 6478 patients, with a mean age of 57.3 ± 16, who underwent orthopedic surgeries between 2018 and 2020. The ASA classification and hemodynamic data were obtained from an anesthesia database. Non-surgical complications were defined as a dysfunction of the vital organs. (3) Results: ASA III/IV caused significantly higher odds ratios (OR) of 17.49 and 40.96, respectively, than ASA I for developing non-surgical complications (p < 0.001). Non-surgical complications were correlated with a 20% reduction in systolic blood pressure (SBP), which was intraoperatively compared to the pre-operative baseline ((OR) = 1.38, p = 0.02). The risk of postoperative complications increased with longer durations of SBP < 100 mmHg, peaking at over 20 min ((OR) = 1.33, p = 0.34). (4) Conclusions: Extended intraoperative hypotension and ASA III/IV caused a significantly higher risk of adverse events occurring within the major organs. The maintenance of hemodynamic stability prevents non-surgical complications after orthopedic surgeries. Full article

Osteoporosis is a common problem in orthopedic medicine, and it has become an important medical issue in orthopedics as Taiwan is gradually becoming an aging society. In the diagnosis of osteoporosis, the bone mineral density (BMD) derived from dual-energy X-ray absorptiometry (DXA) is the main criterion for orthopedic diagnosis of osteoporosis, but due to the high cost of this equipment and the lower penetration rate of the equipment compared to the X-ray images, the problem of osteoporosis has not been effectively solved for many people who suffer from osteoporosis. At present, in clinical diagnosis, doctors are not yet able to accurately interpret X-ray images for osteoporosis manually and must rely on the data obtained from DXA. In recent years, with the continuous development of artificial intelligence, especially in the fields of machine learning and deep learning, significant progress has been made in image recognition. Therefore, it is worthwhile to revisit the question of whether it is possible to use a convolutional neural network model to read a hip X-ray image and then predict the patient’s BMD. In this study, we proposed a hip X-ray image segmentation model and a hip X-ray image recognition classification model. First, we used the U-Net model as a framework to segment the femoral neck, greater trochanter, Ward’s triangle, and the total hip in the hip X-ray images. We then performed image matting and data augmentation. Finally, we constructed a predictive model for osteoporosis using deep learning algorithms. In the segmentation experiments, we used intersection over union (IoU) as the evaluation metric for image segmentation, and both the U-Net model and the U-Net++ model achieved segmentation results greater than or equal to 0.5. In the classification experiments, using the T-score as the classification basis, the total hip using the DenseNet121 model has the highest accuracy of 74%. Full article