ABSTRACT
STUDY DESIGN: A retrospective study. OBJECTIVE: Traumatic cervical spinal cord injury (TSCI) is often associated with disc rupture. It was reported that high signal of disc and anterior longitudinal ligament (ALL) rupture on magnetic resonance imaging (MRI) were the typical signs of ruptured disc. However, for TSCI with no fracture or dislocation, there is still difficult to diagnose disc rupture. The purpose of this study was to investigate the diagnostic efficiency and localization method of different MRI features for cervical disc rupture in patient with TSCI but no any signs of fracture or dislocation. SETTING: Affiliated hospital of University in Nanchang, China. METHODS: Patients who had TSCI and underwent anterior cervical surgery between June 2016 and December 2021 in our hospital were included. All patients received X-ray, CT scan, and MRI examinations before surgery. MRI findings such as prevertebral hematoma, high-signal SCI, high-signal posterior ligamentous complex (PLC), were recorded. The correlation between preoperative MRI features and intraoperative findings was analyzed. Also, the sensitivity, specificity, positive predictive value (PPV), and negative predictive value (NPV) of these MRI features in diagnosing the disc rupture were calculated. RESULTS: A total of 140 consecutive patients, 120 males and 20 females with an average age of 53 years were included in this study. Of these patients, 98 (134 cervical discs) were intraoperatively confirmed with cervical disc rupture, but 59.1% (58 patients) of them had no definite evidence of an injured disc on preoperative MRI (high-signal disc or ALL rupture signal). For these patients, the high-signal PLC on preoperative MRI had the highest diagnostic rate for disc rupture based on intraoperative findings, with a sensitivity of 97%, specificity of 72%, PPV of 84% and NPV of 93%. Combined high-signal SCI with high-signal PLC had higher specificity (97%) and PPV (98%), and a lower FPR (3%) and FNR (9%) for the diagnosis of disc rupture. And combination of three MRI features (prevertebral hematoma, high-signal SCI and PLC) had the highest accuracy in diagnosing traumatic disc rupture. For the localization of the ruptured disc, the level of the high-signal SCI had the highest consistency with the segment of the ruptured disc. CONCLUSION: MRI features, such as prevertebral hematoma, high-signal SCI and PLC, demonstrated high sensitivities for diagnosing cervical disc rupture. High-signal SCI on preoperative MRI could be used to locate the segment of ruptured disc.
Subject(s)
Cervical Cord , Fractures, Bone , Joint Dislocations , Spinal Cord Injuries , Spinal Injuries , Male , Female , Humans , Middle Aged , Spinal Cord Injuries/complications , Spinal Cord Injuries/diagnostic imaging , Spinal Cord Injuries/surgery , Retrospective Studies , Cervical Cord/injuries , Magnetic Resonance Imaging , Fractures, Bone/complications , Cervical Vertebrae/diagnostic imaging , Cervical Vertebrae/surgery , Cervical Vertebrae/injuriesABSTRACT
BACKGROUND: Osteosarcoma (OS) is one of the malignant bone tumors with strong aggressiveness and poor prognosis. Leucine-rich repeats and immunoglobulin-like domains2 (LRIG2) is closely associated with the poor prognosis of a variety of tumors, but the role of LRIG2 in osteosarcoma and the underlying molecular mechanism remains unclear. OBJECTIVE: The aim of this study was to determine the function of LRIG2 in OS and the related molecular mechanism on cell proliferation, apoptosis and migration of OS. METHODS: The mRNA and protein expression of LRIG2 in OS tissues and cells was detected by qRT-PCR, western blot (WB) assay and immunohistochemistry (IHC). The cell counting Kit-8 (CCK-8), clone formation, transwell, TdT-mediated dUTP Nick-End Labeling (TUNEL) and WB assay were applied to determine the proliferation, migration and apoptosis abilities of OS cells and its molecular mechanisms. Spontaneous metastasis xenografts were established to confirm the role of LRIG2 in vivo. RESULTS: LRIG2 exhibited high expression in OS tissues and OS cell lines and the expression of which was significantly correlated with Enneking stage of patients, knockdown LRIG2 expression significantly inhibited OS cell proliferation, migration and enhanced apoptosis. Silencing LRIG2 also suppressed the growth of subcutaneous transplanted tumor in nude mice. Further, the mechanism investigation revealed that the protein level of cell proapoptotic proteins (Bax, caspase9 and caspase3) all increased attributed to LRIG2 deficiency, whereas expression of anti-apoptotic protein BCL2 decreased. LRIG2 silencing led to the decrease phosphorylation of AKT signaling, a decrease expression of vimentin and N-cadherin. Additionally, silencing LRIG2 significantly decreased the rate of tumor growth and tumor size. CONCLUSIONS: LRIG2 acts as an oncogene in osteosarcoma, and it might become a novel target in the treatment of human OS.
Subject(s)
Bone Neoplasms , MicroRNAs , Osteosarcoma , Animals , Apoptosis/genetics , Bone Neoplasms/pathology , Cadherins/metabolism , Cell Line, Tumor , Cell Movement/genetics , Cell Proliferation/genetics , Gene Expression Regulation, Neoplastic , Humans , Leucine/metabolism , Membrane Glycoproteins , Mice , Mice, Nude , MicroRNAs/genetics , Neoplasm Invasiveness/pathology , Osteosarcoma/pathology , Proto-Oncogene Proteins c-akt/metabolism , RNA, Messenger , Vimentin/metabolism , bcl-2-Associated X Protein/metabolismABSTRACT
Osteoporosis is a major public health concern that significantly increases the risk of fractures. The aim of this study was to develop a Machine Learning based predictive model to screen individuals at high risk of osteoporosis based on chronic disease data, thus facilitating early detection and personalized management. A total of 10,000 complete patient records of primary healthcare data in the German Disease Analyzer database (IMS HEALTH) were included, of which 1293 diagnosed with osteoporosis and 8707 without the condition. The demographic characteristics and chronic disease data, including age, gender, lipid disorder, cancer, COPD, hypertension, heart failure, CHD, diabetes, chronic kidney disease, and stroke were collected from electronic health records. Ten different machine learning algorithms were employed to construct the predictive mode. The performance of the model was further validated and the relative importance of features in the model was analyzed. Out of the ten machine learning algorithms, the Stacker model based on Logistic Regression, AdaBoost Classifier, and Gradient Boosting Classifier demonstrated superior performance. The Stacker model demonstrated excellent performance through ten-fold cross-validation on the training set and ROC curve analysis on the test set. The confusion matrix, lift curve and calibration curves indicated that the Stacker model had optimal clinical utility. Further analysis on feature importance highlighted age, gender, lipid metabolism disorders, cancer, and COPD as the top five influential variables. In this study, a predictive model for osteoporosis based on chronic disease data was developed using machine learning. The model shows great potential in early detection and risk stratification of osteoporosis, ultimately facilitating personalized prevention and management strategies.
Subject(s)
Neoplasms , Osteoporosis , Pulmonary Disease, Chronic Obstructive , Humans , Osteoporosis/diagnosis , Osteoporosis/epidemiology , Chronic Disease , Machine Learning , Pulmonary Disease, Chronic Obstructive/diagnosis , Pulmonary Disease, Chronic Obstructive/epidemiologyABSTRACT
Purpose: Human gut microbiota has been shown to be significantly associated with various inflammatory diseases. Therefore, this study aimed to develop an excellent auxiliary tool for the diagnosis of juvenile idiopathic arthritis (JIA) based on fecal microbial biomarkers. Method: The fecal metagenomic sequencing data associated with JIA were extracted from NCBI, and the sequencing data were transformed into the relative abundance of microorganisms by professional data cleaning (KneadData, Trimmomatic and Bowtie2) and comparison software (Kraken2 and Bracken). After that, the fecal microbes with high abundance were extracted for subsequent analysis. The extracted fecal microbes were further screened by least absolute shrinkage and selection operator (LASSO) regression, and the selected fecal microbe biomarkers were used for model training. In this study, we constructed six different machine learning (ML) models, and then selected the best model for constructing a JIA diagnostic tool by comparing the performance of the models based on a combined consideration of area under receiver operating characteristic curve (AUC), accuracy, specificity, F1 score, calibration curves and clinical decision curves. In addition, to further explain the model, Permutation Importance analysis and Shapley Additive Explanations (SHAP) were performed to understand the contribution of each biomarker in the prediction process. Result: A total of 231 individuals were included in this study, including 203 JIA patients and Non-JIA individuals. In the analysis of diversity at the genus level, the alpha diversity represented by Shannon value was not significantly different between the two groups, while the belt diversity was slightly different. After selection by LASSO regression, 10 fecal microbe biomarkers were selected for model training. By comparing six different models, the XGB model showed the best performance, which average AUC, accuracy and F1 score were 0.976, 0.914 and 0.952, respectively, thus being used to construct the final JIA diagnosis model. Conclusion: A JIA diagnosis model based on XGB algorithm was constructed with excellent performance, which may assist physicians in early detection of JIA patients and improve the prognosis of JIA patients.
Subject(s)
Arthritis, Juvenile , Microbiota , Humans , Arthritis, Juvenile/diagnosis , Arthritis, Juvenile/genetics , Biomarkers , ROC Curve , Machine LearningABSTRACT
BACKGROUND: Unplanned reoperation is commonly performed due to postoperative complications. Previous studies have reported the incidence of unplanned reoperation following lumbar spinal surgery. But few study focused on the trend of reoperation rates, and the reasons of unplanned reoperation were not clear. In this study, we conducted a retrospective study to determine the trend of unplanned reoperation rates after degenerative lumbar spinal surgery from 2011 to 2019, and the reasons and risk factors of unplanned reoperation were also determined. METHODS: Data of patients who were diagnosed with degenerative lumbar spinal disease and underwent posterior lumbar spinal fusion surgery in our institution from January 2011 to December 2019 were reviewed. Those who received unplanned reoperation during the primary admission were identified. The demographics, diagnosis, surgical segments and postoperative complications of these patients were recorded. The rates of unplanned reoperation from 2011 to 2019 were calculated, and the reasons of unplanned reoperation were statistically analysed. RESULTS: A total of 5289 patients were reviewed. Of them, 1.91% (n = 101) received unplanned reoperation during the primary admission. The unplanned reoperation rates of degenerative lumbar spinal surgery firstly increased from 2011 to 2014, with a peak rate in 2014 (2.53%). Then, the rates decreased from 2014 to 2019, with the lowest one in 2019 (1.46%). Patients with lumbar spinal stenosis have a higher rate of unplanned reoperation (2.67%) compared with those diagnosed as lumbar disc herniation (1.50%) and lumbar spondylolisthesis (2.04%) (P < 0.05). The main reasons for unplanned reoperation were wound infection (42.57%), followed by wound hematoma (23.76%). Patients who underwent 2-segment spinal surgery had a higher unplanned reoperation rate (3.79%) than those receiving other segments surgery (P < 0.001). And different spine surgeons had different reoperation rates. CONCLUSIONS: The rates of unplanned reoperation after lumbar degenerative surgery increased at first and then decreased during past 9 years. Wound infection was the major reason for unplanned reoperation. 2-segment surgery and surgeon's surgical skills were related to the reoperation rate.
Subject(s)
Spinal Fusion , Wound Infection , Humans , Reoperation , Retrospective Studies , Lumbar Vertebrae/surgery , Spinal Fusion/adverse effects , Postoperative Complications/epidemiology , Postoperative Complications/surgery , Postoperative Complications/etiology , Wound Infection/complicationsABSTRACT
Introduction: It was first reported that germ cell tumor patients suffer from hematologic malignancies 37 years ago. Since then, the number of relevant reports has increased each year, with most cases being mediastinal germ cell tumor. Theories have been proposed to explain this phenomenon, including a shared origin of progenitor cells, the effects of treatment, and independent development. However, up to now, no widely accepted explanation exists. The case with acute megakaryoblastic leukemia and intracranial germ cell tumor has never been reported before and the association is far less known. Methods: We used whole exome sequencing and gene mutation analysis to study the relationship between intracranial germ cell tumor and acute megakaryoblastic leukemia of our patient. Results: We report a patient who developed acute megakaryoblastic leukemia after treatment for an intracranial germ cell tumor. Through whole exome sequencing and gene mutation analysis, we identified that both tumors shared the same mutation genes and mutation sites, suggesting they originated from the same progenitor cells and differentiated in the later stage. Discussion: Our findings provide the first evidence supporting the theory that acute megakaryoblastic leukemia and intracranial germ cell tumor has the same progenitor cells.
ABSTRACT
Purpose: Thoracolumbar fracture is one of the most common fractures of spine. And short-segment posterior fixation including the fractured vertebra (SSPFI) is usually used for the surgical treatment of it. However, the outcomes of SSPFI for different types of thoracolumbar fractures are not clear, and whether it is necessary to perform transpedicular bone grafting is still controversial. This study was conducted to determine the clinical efficacy of SSPFI for the treatment of different types of single-level thoracolumbar fracture, and make clear what kind of fractures need transpedicular bone grafting during the surgery. Methods: Patients with single-level thoracolumbar fracture undergoing SSPFI surgery between January 2013 and June 2020 were included in this study. The operative duration, intraoperative blood loss, anterior vertebral height ratio (AVHR) and anterior vertebral height compressive ratio (AVHC) of the fractured vertebra, local kyphotic Cobb angle (LKA), vertebral wedge angle (VWA) and correction loss during follow up period were recorded. Outcomes between unilateral and bilateral pedicle screw fixation for fractured vertebra, between SSPFI with and without transpedicular bone grafting (TBG), and among different compressive degrees of fractured vertebrae were compared, respectively. Results: A total of 161 patients were included in this study. All the patients were followed up, and the mean follow-upped duration was 25.2 ± 3.1 months (6-52 months). At the final follow-up, the AVHR was greater, and the LKA and VWA were smaller in patients with bilateral fixation (6-screw fixation) than those with unilateral fixation (5-screw fixation) of AO type A3/A4 fractures (P < 0.001). The correction loss of AVHR, LKA and VWA in fractured vertebra were significantly great when preoperative AVHC was >50% (P < 0.05). For patients with AVHC >50%, the correction loss in patients with TBG were less than those without TBG at the final follow-up (P < 0.05). Conclusions: SSPFI using bilateral fixation was more effective than unilateral fixation in maintaining the fractured vertebral height for AO type A3/A4 fractures. For patients with AVHC >50%, the loss of correction was more obvious and it can be decreased by transpedicular bone grafting.
ABSTRACT
OBJECTIVE: To develop a model based on machine learning to predict surgical site infection (SSI) risk in patients after lumbar spinal surgery (LSS). METHODS: Patients who developed postoperative SSI after LSS in the First Affiliated Hospital of Nanchang University between December 2010 and December 2019 were retrospectively reviewed. Preoperative and intraoperative variables, including age, diabetes mellitus, hypertension, body mass index, previous spinal surgery history, surgical duration, number of fused segments, blood loss, and surgical procedure were analyzed. Six machine learning algorithms-logistic regression, multilayer perceptron, decision tree, random forest, gradient boosting machine, and extreme gradient boosting-were used to build prediction models. The performance of the models was evaluated using the area under the curve, accuracy, precision, sensitivity, and F1 score. A web predictor was developed based on the best-performing model. RESULTS: The study included 288 patients who underwent LSS, of whom 144 developed SSI and 144 did not develop SSI. The extreme gradient boosting model offers the best predictive performance among these 6 models (area under the curve = 0.923, accuracy = 0.860, precision = 0.900, sensitivity = 0.834, F1 score = 0.864). An extreme gradient boosting model-based web predictor was developed to predict SSI in patients after LSS. CONCLUSIONS: This study developed a machine learning model and a web predictor for predicting SSI in patients after LSS, which may help clinicians screen high-risk patients, provide personalized treatment, and reduce the incidence of SSI after LSS.
Subject(s)
Machine Learning , Surgical Wound Infection , Algorithms , Humans , Neurosurgical Procedures , Retrospective Studies , Risk Factors , Surgical Wound Infection/diagnosis , Surgical Wound Infection/epidemiology , Surgical Wound Infection/etiologyABSTRACT
OBJECTIVE: This study aimed to develop and validate a machine learning model for predicting bone metastases (BM) in prostate cancer (PCa) patients. METHODS: Demographic and clinicopathologic variables of PCa patients in the Surveillance, Epidemiology and End Results (SEER) database from 2010 to 2017 were retrospectively analyzed. We used six different machine learning algorithms, including Decision tree (DT), Random forest (RF), Multilayer Perceptron (MLP), Logistic regression (LR), Naive Bayes classifiers (NBC), and eXtreme gradient boosting (XGB), to build prediction models. External validation using data from 644 PCa patients of the First Affiliated Hospital of Nanchang University from 2010 to 2016. The performance of the models was evaluated using the area under receiver operating characteristic curve (AUC), accuracy score, sensitivity (recall rate) and specificity. A web predictor was developed based on the best performance model. RESULTS: A total of 207,137 PCa patients from SEER were included in this study. Of whom, 6725 (3.25%) developed BM. Gleason score, Prostate-specific antigen (PSA) value, T, N stage and age were found to be the risk factors of BM. The XGB model offered the best predictive performance among these 6 models (AUC: 0.962, accuracy: 0.884, sensitivity (recall rate): 0.906, and specificity: 0.879). An XGB model-based web predictor was developed to predict BM in PCa patients. CONCLUSION: This study developed a machine learning model and a web predictor for predicting the risk of BM in PCa patients, which may help physicians make personalized clinical decisions and treatment strategy for patients.
ABSTRACT
OBJECTIVES: This study aimed to establish a machine learning prediction model that can be used to predict bone metastasis (BM) in patients with newly diagnosed thyroid cancer (TC). METHODS: Demographic and clinicopathologic variables of TC patients in the Surveillance, Epidemiology, and End Results database from 2010 to 2016 were retrospectively analyzed. On this basis, we developed a random forest (RF) algorithm model based on machine-learning. The area under receiver operating characteristic curve (AUC), accuracy score, recall rate, and specificity are used to evaluate and compare the prediction performance of the RF model and the other model. RESULTS: A total of 17,138 patients were included in the study, with 166 (0.97%) developed bone metastases. Grade, T stage, histology, race, sex, age, and N stage were the important prediction features of BM. The RF model has better predictive performance than the other model (AUC: 0.917, accuracy: 0.904, recall rate: 0.833, and specificity: 0.905). CONCLUSIONS: The RF model constructed in this study could accurately predict bone metastases in TC patients, which may provide clinicians with more personalized clinical decision-making recommendations. Machine learning technology has the potential to improve the development of BM prediction models in TC patients.