Prediction model for spinal cord injury in spinal tuberculosis patients using multiple machine learning algorithms: a multicentric study.

Spinal cord injury (SCI) is a prevalent and serious complication among patients with spinal tuberculosis (STB) that can lead to motor and sensory impairment and potentially paraplegia. This research aims to identify factors associated with SCI in STB patients and to develop a clinically significant predictive model. Clinical data from STB patients at a single hospital were collected and divided into training and validation sets. Univariate analysis was employed to screen clinical indicators in the training set. Multiple machine learning (ML) algorithms were utilized to establish predictive models. Model performance was evaluated and compared using receiver operating characteristic (ROC) curves, area under the curve (AUC), calibration curve analysis, decision curve analysis (DCA), and precision-recall (PR) curves. The optimal model was determined, and a prospective cohort from two other hospitals served as a testing set to assess its accuracy. Model interpretation and variable importance ranking were conducted using the DALEX R package. The model was deployed on the web by using the Shiny app. Ten clinical characteristics were utilized for the model. The random forest (RF) model emerged as the optimal choice based on the AUC, PRs, calibration curve analysis, and DCA, achieving a test set AUC of 0.816. Additionally, MONO was identified as the primary predictor of SCI in STB patients through variable importance ranking. The RF predictive model provides an efficient and swift approach for predicting SCI in STB patients.

Exploring the causal relationship between inflammatory cytokines and inflammatory arthritis: A Mendelian randomization study.

OBJECTIVES: Previous studies have reported an association between inflammatory cytokines and inflammatory arthritis, including Ankylosing spondylitis (AS), rheumatoid arthritis (RA), and psoriatic arthritis (PsA). This study aims to explore the causal relationship between inflammatory cytokines and AS, RA, and PsA using Mendelian randomization (MR). METHODS: We conducted a bidirectional two-sample MR analysis using genetic summary data from a publicly available genome-wide association study (GWAS) that included 41 genetic variations of inflammatory cytokines, as well as genetic variant data for AS, RA, and PsA from the FinnGen consortium. The main analysis method used was Inverse variance weighted (IVW) to investigate the causal relationship between exposure and outcome. Additionally, other methods such as MR Egger, weighted median (WM), simple mode, and weighted mode were employed to strengthen the final results. Sensitivity analysis was also performed to ensure the reliability of the findings. RESULTS: The results showed that macrophage colony-stimulating factor (MCSF) was associated with an increased risk of AS (OR = 1.163, 95 % CI = 1.016-1.33, p = 0.028). Conversely, high levels of TRAIL and beta nerve growth factor (ß-NGF) were associated with a decreased risk of AS (OR = 0.892, 95 % CI = 0.81-0.982, p = 0.002; OR = 0.829, 95 % CI = 0.696-0.988, p = 0.036). Four inflammatory cytokines were found to be associated with an increased risk of PsA: vascular endothelial growth factor (VEGF) (OR = 1.161, 95 % CI = 1.057-1.275, p = 0.002); Interleukin 12p70 (IL12p70) (OR = 1.189, 95 % CI = 1.049-1.346, p = 0.007); IL10 (OR = 1.216, 95 % CI = 1.024-1.444, p = 0.026); IL13 (OR = 1.159, 95 % CI = 1.05-1.28, p = 0.004). Interleukin 1 receptor antagonist (IL-1rα) was associated with an increased risk of seropositive RA (OR = 1.181, 95 % CI = 1.044-1.336, p = 0.008). Similarly, genetic susceptibility to inflammatory arthritis was found to be causally associated with multiple inflammatory cytokines. Lastly, the sensitivity analysis supported the robustness of these findings. CONCLUSIONS: This study provides additional insights into the relationship between inflammatory cytokines and inflammatory arthritis, and may offer new clues for the etiology, diagnosis, and treatment of inflammatory arthritis.

Development and validation of a diagnostic model to differentiate spinal tuberculosis from pyogenic spondylitis by combining multiple machine learning algorithms.

This study focused on the development and validation of a diagnostic model to differentiate between spinal tuberculosis (STB) and pyogenic spondylitis (PS). We analyzed a total of 387 confirmed cases, out of which 241 were diagnosed with STB and 146 were diagnosed with PS. These cases were randomly divided into a training group (n = 271) and a validation group (n = 116). Within the training group, four machine learning (ML) algorithms (least absolute shrinkage and selection operator [LASSO], logistic regression analysis, random forest, and support vector machine recursive feature elimination [SVM-RFE]) were employed to identify distinctive variables. These specific variables were then utilized to construct a diagnostic model. The model's performance was subsequently assessed using the receiver operating characteristic (ROC) curves and the calibration curves. Finally, internal validation of the model was undertaken in the validation group. Our findings indicate that PS patients had an average platelet-to-neutrophil ratio (PNR) of 277.86, which was significantly higher than the STB patients' average of 69.88. The average age of PS patients was 54.71 years, older than the 48 years recorded for STB patients. Notably, the neutrophil-to-lymphocyte ratio (NLR) was higher in PS patients at 6.15, compared to the 3.46 NLR in STB patients. Additionally, the platelet volume distribution width (PDW) in PS patients was 0.2, compared to 0.15 in STB patients. Conversely, the mean platelet volume (MPV) was lower in PS patients at an average of 4.41, whereas STB patients averaged 8.31. Hemoglobin (HGB) levels were lower in PS patients at an average of 113.31 compared to STB patients' average of 121.64. Furthermore, the average red blood cell (RBC) count was 4.26 in PS patients, which was less than the 4.58 average observed in STB patients. After evaluation, seven key factors were identified using the four ML algorithms, forming the basis of our diagnostic model. The training and validation groups yielded area under the curve (AUC) values of 0.841 and 0.83, respectively. The calibration curves demonstrated a high alignment between the nomogram-predicted values and the actual measurements. The decision curve indicated optimal model performance with a threshold set between 2% and 88%. In conclusion, our model offers healthcare practitioners a reliable tool to efficiently and precisely differentiate between STB and PS, thereby facilitating swift and accurate diagnoses.

Identification of spinal tuberculosis subphenotypes using routine clinical data: a study based on unsupervised machine learning.

OBJECTIVE: The identification of spinal tuberculosis subphenotypes is an integral component of precision medicine. However, we lack proper study models to identify subphenotypes in patients with spinal tuberculosis. Here we identified possible subphenotypes of spinal tuberculosis and compared their clinical results. METHODS: A total of 422 patients with spinal tuberculosis who received surgical treatment were enrolled. Clustering analysis was performed using the K-means clustering algorithm and the routinely available clinical data collected from patients within 24 h after admission. Finally, the differences in clinical characteristics, surgical efficacy, and postoperative complications among the subphenotypes were compared. RESULTS: Two subphenotypes of spinal tuberculosis were identified. Laboratory examination results revealed that the levels of more than one inflammatory index in cluster 2 were higher than those in cluster 1. In terms of disease severity, Cluster 2 showed a higher Oswestry Disability Index (ODI), a higher visual analysis scale (VAS) score, and a lower Japanese Orthopedic Association (JOA) score. In addition, in terms of postoperative outcomes, cluster 2 patients were more prone to complications, especially wound infections, and had a longer hospital stay. CONCLUSION: K-means clustering analysis based on conventional available clinical data can rapidly identify two subtypes of spinal tuberculosis with different clinical results. We believe this finding will help clinicians to rapidly and easily identify the subtypes of spinal tuberculosis at the bedside and become the cornerstone of individualized treatment strategies.

Using Machine Learning to Predict Surgical Site Infection After Lumbar Spine Surgery.

Objective: The objective of this study was to utilize machine learning techniques to analyze perioperative factors and identify blood glucose levels that can predict the occurrence of surgical site infection following posterior lumbar spinal surgery. Methods: A total of 4019 patients receiving lumbar internal fixation surgery from an institute were enrolled between June 2012 and February 2021. First, the filtered data were randomized into the test and verification groups. Second, in the test group, specific variables were screened using logistic regression analysis, Lasso regression analysis, support vector machine, and random forest. Specific variables obtained using the four methods were intersected, and a dynamic model was constructed. ROC and calibration curves were constructed to assess model performance. Finally, internal model performance was verified in the verification group using ROC and calibration curves. Results: The data from 4019 patients were collected. In total, 1327 eligible cases were selected. By combining logistic regression analysis with three machine learning algorithms, this study identified four predictors associated with SSI, namely Modic changes, sebum thickness, hemoglobin, and glucose. Using this information, a prediction model was developed and visually represented. Then, we constructed ROC and calibration curves using the test group; the area under the ROC curve was 0.988. Further, calibration curve analysis revealed favorable consistency of nomogram-predicted values compared with real measurements. The C-index of our model was 0.986 (95% CI 0.981-0.994). Finally, we used the validation group to validate the model internally; the AUC was 0.987. Calibration curve analysis revealed favorable consistency of nomogram-predicted values compared with real measurements. The C-index was 0.982 (95% CI 0.974-0.999). Conclusion: Logistic regression analysis and machine learning were employed to select four risk factors: Modic changes, sebum thickness, hemoglobin, and glucose. Then, a dynamic prediction model was constructed to help clinicians simplify the monitoring and prevention of SSI.

Comprehensive AI-assisted tool for ankylosing spondylitis based on multicenter research outperforms human experts.

Introduction: The diagnosis and treatment of ankylosing spondylitis (AS) is a difficult task, especially in less developed countries without access to experts. To address this issue, a comprehensive artificial intelligence (AI) tool was created to help diagnose and predict the course of AS. Methods: In this retrospective study, a dataset of 5389 pelvic radiographs (PXRs) from patients treated at a single medical center between March 2014 and April 2022 was used to create an ensemble deep learning (DL) model for diagnosing AS. The model was then tested on an additional 583 images from three other medical centers, and its performance was evaluated using the area under the receiver operating characteristic curve analysis, accuracy, precision, recall, and F1 scores. Furthermore, clinical prediction models for identifying high-risk patients and triaging patients were developed and validated using clinical data from 356 patients. Results: The ensemble DL model demonstrated impressive performance in a multicenter external test set, with precision, recall, and area under the receiver operating characteristic curve values of 0.90, 0.89, and 0.96, respectively. This performance surpassed that of human experts, and the model also significantly improved the experts' diagnostic accuracy. Furthermore, the model's diagnosis results based on smartphone-captured images were comparable to those of human experts. Additionally, a clinical prediction model was established that accurately categorizes patients with AS into high-and low-risk groups with distinct clinical trajectories. This provides a strong foundation for individualized care. Discussion: In this study, an exceptionally comprehensive AI tool was developed for the diagnosis and management of AS in complex clinical scenarios, especially in underdeveloped or rural areas that lack access to experts. This tool is highly beneficial in providing an efficient and effective system of diagnosis and management.

ZnO Microfiltration Membranes for Desalination by a Vacuum Flow-Through Evaporation Method.

ZnO was deposited on macroporous α-alumina membranes via atomic layer deposition (ALD) to improve water flux by increasing their hydrophilicity and reducing mass transfer resistance through membrane pore channels. The deposition of ZnO was systemically performed for 4-128 cycles of ALD at 170 °C. Analysis of membrane surface by contact angles (CA) measurements revealed that the hydrophilicity of the ZnO ALD membrane was enhanced with increasing the number of ALD cycles. It was observed that a vacuum-assisted 'flow-through' evaporation method had significantly higher efficacy in comparison to conventional desalination methods. By using the vacuum-assisted 'flow-through' technique, the water flux of the ZnO ALD membrane (~170 L m-2 h-1) was obtained, which is higher than uncoated pristine membranes (92 L m-2 h-1). It was also found that ZnO ALD membranes substantially improved water flux while keeping excellent salt rejection rate (>99.9%). Ultrasonic membrane cleaning had considerable effect on reducing the membrane fouling.

Visible-light promoted catalytic activity of dumbbell-like Au nanorods supported on graphene/TiO2 sheets towards hydrogenation reaction.

In this work, the rationally-designed sharp corners on Au nanorods tremendously improved the catalytic activity, particularly in the presence of visible light irradiation, towards the hydrogenation of 4-nitrophenol to 4-aminophenol. A strikingly increased rate constant of 50.6 g-1 s-1 L was achieved in M-Au-3, which was 41.8 times higher than that of parent Au nanorods under dark conditions. The enhanced activities were proportional to the extent of the protruding sharp corners. Furthermore, remarkably enhanced activities were achieved in novel ternary Au/RGO/TiO2 sheets, which were endowed with a 52.0 times higher rate constant than that of straight Au nanorods. These remarkably enhanced activities were even higher than those of previously reported 3-5 nm Au and 3 nm Pt nanoparticles. It was systematically observed that there are three aspects to the synergistic effects between Au and RGO sheets: (i) electron transfer from RGO to Au, (ii) a high concentration of p-nitrophenol close to dumbbell-like Au nanorods on RGO sheets, and (iii) increased local reaction temperature from the photothermal effect of both dumbbell-like Au nanorods and RGO sheets.

Self-assembly of defect-rich graphene oxide nanosheets with Na2Ti3O7 nanowires and their superior absorptive capacity to toxic dyes.

Graphene sheets, a flexible 2D material with excellent absorptive capacity, have great potential as absorbing materials. However, this material has always suffered from irreversible aggregation and thus loses the abundant active sites and large surface area. In this paper, large-scale graphene oxide (GO) sheets were cut and reduced to tiny reduced graphene oxide (RGO) sheets by a cell-break sonicator, for producing numerous defects, which are the center of chemisorption. Furthermore, sodium titanate nanowires functioned as a framework to help to disperse the tiny RGO sheets uniformly. And, in turn, the flexible tiny RGO sheets glued robust nanowires into a free-standing membrane. This novel composite membrane exhibited an ultra-high decoloration efficiency of 99.8% of rhodamine B in a continuous flow mode, and an outstanding absorptive capability of 1.30 × 10-2 mol g-1 correlated to RGO content in batch reaction, which is about two orders of magnitude higher than other reported graphene-based absorbents. In addition, an efficient and feasible method without any heat treatment for regenerating the membrane is illustrated, and the recycled membrane retains superior decoloration efficiency. The excellent absorptive performance indicates the framework-based disperse strategy has great potential for the construction and application of defect-rich graphene.