Development and Validation of a Machine Learning-Based Nomogram for Prediction of Ankylosing Spondylitis

Development and validation of machine learning algorithms for early detection of ankylosing spondylitis using magnetic resonance images

BackgroundAnkylosing spondylitis (AS) is a chronic inflammatory disease affecting the sacroiliac joints and spine, often leading to disability if not diagnosed and treated early.ObjectiveIn this study, we present the development and validation of machine learning (ML) algorithms for AS detection only using Short Tau Inversion Recovery (STIR) sequenced magnetic resonance (MR) images.MethodsThe detection process is based on creating Gray Level Co-occurrence Matrices (GLCM) from MR images, followed by the computation of Haralick features and the training of ML-based models. A total of 696 MR images (AS+: 348, AS-: 348) were utilized for AS detection. Models were trained and tested on 70% of the dataset using a 10-fold cross-validation method to prevent overfitting, while the remaining 30% of the data was used for validation. In addition, care was taken to ensure that different images from the same patient were not split between the training and validation sets during this separation process to prevent potential data leakage.ResultsThe proposed ML-based model demonstrated superior performance during the validation phase (accuracy: 0.885, AUC: 0.941). The results of our study show promising outcomes when compared to previous works employing GLCM-based ML detection models.Conclusions: This study introduces a new perspective on AS detection, focusing on the assignment of ML techniques to STIR-sequenced MR images with a notable absence of literature on interpreting ML models for AS detection. This typology also addresses a lack of knowledge, as most models do not provide practical interpretability or knowledge alongside accurate prediction. The system also offers an effective strategy for early and correct diagnosis of AS, which is important for timely intervention and treatment planning.

Identification of RSAD2 as a Key Biomarker Linking Iron Metabolism and Dendritic Cell Activation in Systemic Lupus Erythematosus Through Bioinformatics and Experimental Validation

Background

Systemic lupus erythematosus (SLE) is characterized by aberrant immune activation and disrupted iron metabolism, yet the molecular mediators that govern both processes remain unclear. This study aims to identify pivotal genes that modulate immune responses and iron metabolism, and to delineate their contributions to SLE pathogenesis.

Methods

Differentially expressed genes related to iron metabolism (IM-DEGs) were identified using datasets (GSE72326, GSE110169, GSE126307, and GSE50772) from the GEO database and the MSigDB. Functional enrichment analyses were performed on the iron metabolism related genes (IM-Genes). A weighted gene co-expression network analysis was constructed to identify hub genes, which were further refined as potential biomarkers using the least absolute shrinkage and selection operator method. The predictive value of these biomarkers was validated using receiver operating characteristic (ROC) curves and the nomogram. CIBERSORT was employed to evaluate immune cell infiltration in SLE. Additionally, the expression and function of RSAD2 were confirmed using RNA interference, quantitative real-time PCR, and Western blotting techniques.

Results

Bioinformatics analyses identified 4 potential biomarkers: RSAD2, MT2A, LCN2, and LTF. RSAD2 exhibited the highest clinical validity (AUC = 0.927) and was closely associated with classic diagnostic indicators. Its diagnostic potential was confirmed through ROC curve and nomogram, highlighting its role in SLE pathogenesis. Elevated RSAD2 expression was observed in peripheral blood mononuclear cells of SLE patients, positively correlating with activated dendritic cells (DCs). Notably, Rsad2 knockdown markedly impaired the function of activated DCs, as evidenced by suppressed expression of inflammatory mediators and iron metabolism-related genes.

Conclusion

Our findings suggest that RSAD2 is a potential diagnostic biomarker and therapeutic target for SLE, elucidating the intricate relationship between immune dysregulation and aberrant iron metabolism in activated DCs, which exacerbates SLE.

Analysis of the predictive postoperative recurrence performance of three lymph node staging systems in patients with colon cancer

Background

Colon cancer remains a major cause of cancer-related deaths worldwide, with recurrence post-surgery, posing a significant challenge. Accurate lymph node (LN) staging is critical for prognosis and treatment decisions, but traditional systems, such as the AJCC TNM, often fail to predict recurrence. This study compares the prognostic performance of three LN staging systems Lymph Node Ratio (LNR), Log Odds of Metastatic Lymph Nodes (LODDS), and pN in colon cancer.

Methods

We retrospectively analyzed data from 812 colon cancer patients who underwent radical surgery at two tertiary hospitals (2010-2019). LNR, LODDS, and pN were calculated, and their ability to predict postoperative recurrence was assessed using C-index, AIC, BIC, and ROC curves. Machine learning models (LASSO, Random Forest, XGBoost) identified the most predictive staging system. A nomogram was developed integrating the best staging system with clinical factors to predict postoperative recurrence.

Results

The study identified LNR as the most predictive staging system for colon cancer. The nomogram based on LNR, along with other variables such as T stage and tumor grade, demonstrated superior predictive performance compared to individual staging systems. In the training cohort, the nomogram achieved an AUC of 0.791 at 1 year, 0.815 at 3 years, and 0.789 at 5 years. The C-index for the nomogram was 0.788, higher than that of LNR (C-index = 0.694) and tumor stage (C-index = 0.665). The nomogram successfully stratified patients into high- and low-risk groups, with higher risk scores correlating with poorer survival outcomes. The validation cohort confirmed the robustness of the model, showing that patients with lower risk scores had better prognoses.

Conclusions

LNR is an effective predictor of recurrence and prognosis in colon cancer. The nomogram developed from LNR and other clinical factors offers superior prognostication and can aid in personalized treatment strategies.

Two-centers machine learning analysis for predicting acid-fast bacilli results in tuberculosis sputum tests

Background

Tuberculosis (TB) is a chronic respiratory infectious disease caused by Mycobacterium tuberculosis, typically diagnosed through sputum smear microscopy for acid-fast bacilli (AFB) to assess the infectivity of TB.

Methods

This study enrolled 769 patients, including 641 patients from the First Affiliated Hospital of Guangxi Medical University as the training group, and 128 patients from Guangxi Hospital of the First Affiliated Hospital of Sun Yat-sen University as the validation group. Among the training cohort, 107 patients were AFB-positive, and 534 were AFB-negative. In the validation cohort, 24 were AFB-positive, and 104 were AFB-negative. Blood samples were collected and analyzed using machine learning (ML) methods to identify key factors for TB diagnosis.

Results

Several ML methods were compared, and support vector machine recursive feature elimination (SVM-RFE) was selected to construct a nomogram diagnostic model. The area under the curve (AUC) of the diagnostic model was 0.721 in the training cohort and 0.758 in the validation cohort. The model demonstrated clinical utility when the threshold was between 38% and 94%, with the NONE line above the ALL line in the decision curve analysis.

Conclusion

We developed a diagnostic model using multiple ML methods to predict AFB results, achieving satisfactory diagnostic performance.

Harnessing Machine Learning and Nomogram Models to Aid in Predicting Progression-Free Survival for Gastric Cancer Patients Post-Gastrectomy with Deficient Mismatch Repair(dMMR)

OBJECTIVE

To assess the effectiveness of a machine learning framework and nomogram in predicting progression-free survival (PFS) post-radical gastrectomy in patients with dMMR.

METHOD

Machine learning models and nomograms to forecast PFS in patients undergoing radical gastrectomy for nonmetastatic gastric cancer with dMMR. Independent risk factors were identified using Cox regression analysis to develop the nomogram. The performance of the models was assessed through C-index, time receiver operating characteristic (T-ROC) curves, calibration curves, and decision curve analysis (DCA) curves. Subsequently, patients were categorized into high-risk and low-risk groups based on the nomogram's risk scores.

RESULTS

Among the 582 patients studied, machine learning models exhibited higher c-index values than the nomogram. Random Survival Forests (RSF) demonstrated the highest c-index (0.968), followed by Extreme Gradient Boosting (XG boosting, 0.945), Decision Survival Tree (DST, 0.924), the nomogram (0.808), and 8th TNM staging (0.757). All models showed good calibration with low integrated Brier scores (< 0.1), although there was calibration drift over time, particularly in the traditional nomogram model. DCA showed an incremental net benefit from all machine learning models compared with conventional models currently used in practice. Age, positive lymph nodes, neural invasion, and Ki67 were identified as key factors and integrated into the prognostic nomogram.

CONCLUSION

Our research has demonstrated the effectiveness of the RSF algorithm in accurately predicting progression-free survival (PFS) in dMMR gastric cancer patients after gastrectomy. The nomogram created from this algorithm has proven to be a valuable tool in identifying high-risk patients, providing clinicians with important information for postoperative monitoring and personalized treatment strategies.

Development and Validation of a Machine Learning-Based Nomogram for Prediction of Unplanned Reoperation Postspinal Surgery Within 30 Days

BACKGROUND

Unplanned reoperation postspinal surgery (URPS) leads to prolonged hospital stays, higher costs, decreased patient satisfaction, and adversely affects postoperative rehabilitation. This study aimed to develop and validate prediction models (nomograms) for early URPS risk factors using machine learning methods, aiding spine surgeons in designing prevention strategies, promoting early recovery, reducing complications, and improving patient satisfaction.

METHODS

Medical records of 639 patients who underwent reoperation postspinal surgery from the First Affiliated Hospital of Air Force Medical University (2018-2022) were collected, including baseline indicators, perioperative indicators, and laboratory indicators. After applying inclusion and exclusion criteria, 122 URPS and 155 non-URPS patients were identified and randomly divided into training (82 URPS and 111 non-URPS) and validation (40 URPS and 44 non-URPS) cohorts. Three machine learning methods (least absolute shrinkage and selection operator regression, Random Forest, and Support Vector Machine Recursive Feature Elimination) were used to select feature variables, and their intersection was used to develop the prediction model, tested on the validation cohort.

RESULTS

Six factors-implant, postoperative suction drainage, gelatin sponge, anticoagulants, antibiotics, and disease type-were identified to construct a nomogram diagnostic model. The area under the curve of this nomogram was 0.829 (95% confidence interval 0.771-0.886) in the training cohort and 0.854 (95% confidence interval 0.775-0.933) in the validation cohort. Calibration curves demonstrated satisfactory agreement between predictions and actual probabilities. The decision curve indicated clinical usefulness with a threshold between 1% and 90%.

CONCLUSIONS

The established model can effectively predict URPS in patients and can assist spine surgeons in devising personalized and rational clinical prevention strategies.

Integrating multiomics and Single-Cell communication analysis to uncover Ankylosing spondylitis mechanisms

BACKGROUND

Ankylosing spondylitis (AS) is a chronic inflammatory joint disorder, necessitating early diagnosis and effective treatment. The specific mechanism of action of Cassia twigs in the treatment of AS is not fully understood.

METHODS

Blood samples and clinical data from 28,458 individuals (6,101 with AS, 22,357 without AS) were collected. To construct a predictive model, we utilized logistic regressions and machine learning techniques to create a dynamic nomogram. Immune cell infiltration was evaluated using the GSE73754 dataset. Subsequently, we obtained vertebral bone marrow blood from AS patients for 10X single-cell sequencing. We also extracted and purified total RNA from hip joint ligament tissue samples from six AS patients and six non-AS patients. The genes related to the expression of AS and Cassia twigs were analyzed comprehensively, and the specific drug targets were identified by molecular docking. The interactions between immune cells through cell communication analysis were elucidated.

RESULTS

We developed a dynamic nomogram incorporating the neutrophil count (NEUT) and other variables. Neutrophil immune responses were confirmed through immune infiltration analysis utilizing GSE73754. We observed the early involvement of neutrophils in the pathology of AS. The CAT-expressing Cassia twigs gene could be used as a drug target for the treatment of AS. Moreover, comprehensive RNA analysis revealed notable CAT expression in neutrophils and various other immune cells.

CONCLUSIONS

Neutrophils play dual roles in AS, regulating inflammation and initiating differentiation signals to other cells. The CAT gene, which is expressed in Cassia twigs, has emerged as a potential therapeutic target for AS treatment.

Comparison of the predictive performance of three lymph node staging systems for late-onset gastric cancer patients after surgery

Introduction

Lymph node (LN) status is a vital prognostic factor for patients. However, there has been limited focus on predicting the prognosis of patients with late-onset gastric cancer (LOGC). This study aimed to investigate the predictive potential of the log odds of positive lymph nodes (LODDS), lymph node ratio (LNR), and pN stage in assessing the prognosis of patients diagnosed with LOGC.

Methods

The LOGC data were obtained from the Surveillance, Epidemiology, and End Results database. This study evaluated and compared the predictive performance of three LN staging systems. Univariate and multivariate Cox regression analyses were carried out to identify prognostic factors for overall survival (OS). Three machine learning methods, namely, LASSO, XGBoost, and RF analyses, were subsequently used to identify the optimal LN staging system. A nomogram was built to predict the prognosis of patients with LOGC. The efficacy of the model was demonstrated through receiver operating characteristic (ROC) curve analysis and decision curve analysis.

Results

A total of 4,743 patients with >16 removed lymph nodes were ultimately included in this investigation. Three LN staging systems demonstrated significant performance in predicting survival outcomes (P < 0.001). The LNR exhibited the most important prognostic ability, as evidenced by the use of three machine learning methods. Utilizing independent factors derived from multivariate Cox regression analysis, a nomogram for OS was constructed.

Discussion

The calibration, C-index, and AUC revealed their excellent predictive performance. The LNR demonstrated a more powerful performance than other LN staging methods in LOGC patients after surgery. Our novel nomogram exhibited superior clinical feasibility and may assist in patient clinical decision-making.

Artificial intelligence: a new cutting-edge tool in spine surgery

The purpose of this narrative review was to comprehensively elaborate the various components of artificial intelligence (AI), their applications in spine surgery, practical concerns, and future directions. Over the years, spine surgery has been continuously transformed in various aspects, including diagnostic strategies, surgical approaches, procedures, and instrumentation, to provide better-quality patient care. Surgeons have also augmented their surgical expertise with rapidly growing technological advancements. AI is an advancing field that has the potential to revolutionize many aspects of spine surgery. We performed a comprehensive narrative review of the various aspects of AI and machine learning in spine surgery. To elaborate on the current role of AI in spine surgery, a review of the literature was performed using PubMed and Google Scholar databases for articles published in English in the last 20 years. The initial search using the keywords "artificial intelligence" AND "spine," "machine learning" AND "spine," and "deep learning" AND "spine" extracted a total of 78, 60, and 37 articles and 11,500, 4,610, and 2,270 articles on PubMed and Google Scholar. After the initial screening and exclusion of unrelated articles, duplicates, and non-English articles, 405 articles were identified. After the second stage of screening, 93 articles were included in the review. Studies have shown that AI can be used to analyze patient data and provide personalized treatment recommendations in spine care. It also provides valuable insights for planning surgeries and assisting with precise surgical maneuvers and decisionmaking during the procedures. As more data become available and with further advancements, AI is likely to improve patient outcomes.

Ankylosing spondylitis prediction using fuzzy K-nearest neighbor classifier assisted by modified JAYA optimizer

The diagnosis of ankylosing spondylitis (AS) can be complex, necessitating a comprehensive assessment of medical history, clinical symptoms, and radiological evidence. This multidimensional approach can exacerbate the clinical burden and increase the likelihood of diagnostic inaccuracies, which may result in delayed or overlooked cases. Consequently, supplementary diagnostic techniques for AS have become a focal point in clinical research. This study introduces an enhanced optimization algorithm, SCJAYA, which incorporates salp swarm foraging behavior with cooperative predation strategies into the JAYA algorithm framework, noted for its robust optimization capabilities that emulate the evolutionary dynamics of biological organisms. The integration of salp swarm behavior is aimed at accelerating the convergence speed and enhancing the quality of solutions of the classical JAYA algorithm while the cooperative predation strategy is incorporated to mitigate the risk of convergence on local optima. SCJAYA has been evaluated across 30 benchmark functions from the CEC2014 suite against 9 conventional meta-heuristic algorithms as well as 9 state-of-the-art meta-heuristic counterparts. The comparative analyses indicate that SCJAYA surpasses these algorithms in terms of convergence speed and solution precision. Furthermore, we proposed the bSCJAYA-FKNN classifier: an advanced model applying the binary version of SCJAYA for feature selection, with the aim of improving the accuracy in diagnosing and prognosticating AS. The efficacy of the bSCJAYA-FKNN model was substantiated through validation on 11 UCI public datasets in addition to an AS-specific dataset. The model exhibited superior performance metrics-achieving an accuracy rate, specificity, Matthews correlation coefficient (MCC), F-measure, and computational time of 99.23 %, 99.52 %, 0.9906, 99.41 %, and 7.2800 s, respectively. These results not only underscore its profound capability in classification but also its substantial promise for the efficient diagnosis and prognosis of AS.

A Stepwise Approach to Analyzing Musculoskeletal Imaging Data With Artificial Intelligence

The digitization of medical records and expanding electronic health records has created an era of "Big Data" with an abundance of available information ranging from clinical notes to imaging studies. In the field of rheumatology, medical imaging is used to guide both diagnosis and treatment of a wide variety of rheumatic conditions. Although there is an abundance of data to analyze, traditional methods of image analysis are human resource intensive. Fortunately, the growth of artificial intelligence (AI) may be a solution to handle large datasets. In particular, computer vision is a field within AI that analyzes images and extracts information. Computer vision has impressive capabilities and can be applied to rheumatologic conditions, necessitating a need to understand how computer vision works. In this article, we provide an overview of AI in rheumatology and conclude with a five step process to plan and conduct research in the field of computer vision. The five steps include (1) project definition, (2) data handling, (3) model development, (4) performance evaluation, and (5) deployment into clinical care.

Machine learning and deep learning for the diagnosis and treatment of ankylosing spondylitis- a scoping review

Background and objectives

Machine Learning (ML) and Deep Learning (DL) are novel technologies that can facilitate early diagnosis of Ankylosing Spondylitis (AS) and predict better patient-specific treatments. We aim to provide the current update on their use at different stages of AS diagnosis and treatment, describe different types of techniques used, dataset descriptions, contributions and limitations of existing work and ed to identify gaps in current knowledge for future works.

Methods

We curated the data of this review from the PubMed database. We searched the full-text articles related to the use of ML/DL in the diagnosis and treatment of AS, for the period 2013-2023. Each article was manually scrutinized to be included or excluded for this review as per its relevance.

Results

This review revealed that ML/DL technology is useful to assist and promote early diagnosis through AS patient characteristic profile creation, and identification of new AS-related biomarkers. They can help in forecasting the progression of AS and predict treatment responses to aid patient-specific treatment planning. However, there was a lack of sufficient-sized datasets sourced from multi-centres containing different types of diagnostic parameters. Also, there is less research on ML/DL-based AS treatment as compared to ML/DL-based AS diagnosis.

Conclusion

ML/DL can facilitate an early diagnosis and patient-tailored treatment for effective handling of AS. Benefits are especially higher in places with a lack of diagnostic resources and human experts. The use of ML/DL-trained models for AS diagnosis and treatment can provide the necessary support to the otherwise overwhelming healthcare systems in a cost-effective and timely way.

Machine learning-based identification of novel hub genes associated with oxidative stress in lupus nephritis: implications for diagnosis and therapeutic targets

BACKGROUND

Lupus nephritis (LN) is a complication of SLE characterised by immune dysfunction and oxidative stress (OS). Limited options exist for LN. We aimed to identify LN-related OS, highlighting the need for non-invasive diagnostic and therapeutic approaches.

METHODS

LN-differentially expressed genes (DEGs) were extracted from Gene Expression Omnibus datasets (GSE32591, GSE112943 and GSE104948) and Molecular Signatures Database for OS-associated DEGs (OSEGs). Functional enrichment analysis was performed for OSEGs related to LN. Weighted gene co-expression network analysis identified hub genes related to OS-LN. These hub OSEGs were refined as biomarker candidates via least absolute shrinkage and selection operator. The predictive value was validated using receiver operating characteristic (ROC) curves and nomogram for LN prognosis. We evaluated LN immune cell infiltration using single-sample gene set enrichment analysis and CIBERSORT. Additionally, gene set enrichment analysis explored the functional enrichment of hub OSEGs in LN.

RESULTS

The study identified four hub genes, namely STAT1, PRODH, TXN2 and SETX, associated with OS related to LN. These genes were validated for their diagnostic potential, and their involvement in LN pathogenesis was elucidated through ROC and nomogram. Additionally, alterations in immune cell composition in LN correlated with hub OSEG expression were observed. Immunohistochemical analysis reveals that the hub gene is most correlated with activated B cells and CD8 T cells. Finally, we uncovered that the enriched pathways of OSEGs were mainly involved in the PI3K-Akt pathway and the Janus kinase-signal transducer and activator of transcription pathway.

CONCLUSION

These findings contribute to advancing our understanding of the complex interplay between OS, immune dysregulation and molecular pathways in LN, laying a foundation for the identification of potential diagnostic biomarkers and therapeutic targets.

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.

Entry point of machine learning in axial spondyloarthritis

Axial spondyloarthritis (axSpA) is a globally prevalent and challenging autoimmune disease. Characterised by insidious onset and slow progression, the absence of specific clinical manifestations and biomarkers often leads to misdiagnosis, thereby complicating early detection and diagnosis of axSpA. Furthermore, the high heterogeneity of axSpA, its complex pathogenesis and the lack of specific drugs means that traditional classification standards and treatment guidelines struggle to meet the demands of personalised treatment. Recently, machine learning (ML) has seen rapid advancements in the medical field. By integrating large-scale data with diverse algorithms and using multidimensional data, such as patient medical records, laboratory examinations, radiological data, drug usage and molecular biology information, ML can be modelled based on real-world clinical issues. This enables the diagnosis, stratification, therapeutic efficacy prediction and prognostic evaluation of axSpA, positioning it as an emerging research topic. This study explored the application and progression of ML in the diagnosis and therapy of axSpA from five perspectives: early diagnosis, stratification, disease monitoring, drug efficacy evaluation and comorbidity prediction. This study aimed to provide a novel direction for exploring rational diagnostic and therapeutic strategies for axSpA.

Construction of a predictive model for blood transfusion in patients undergoing total hip arthroplasty and identification of clinical heterogeneity

A precise forecast of the need for blood transfusions (BT) in patients undergoing total hip arthroplasty (THA) is a crucial step toward the implementation of precision medicine. To achieve this goal, we utilized supervised machine learning (SML) techniques to establish a predictive model for BT requirements in THA patients. Additionally, we employed unsupervised machine learning (UML) approaches to identify clinical heterogeneity among these patients. In this study, we recruited 224 patients undergoing THA. To identify factors predictive of BT during the perioperative period of THA, we employed LASSO regression and the random forest (RF) algorithm as part of supervised machine learning (SML). Using logistic regression, we developed a predictive model for BT in THA patients. Furthermore, we utilized unsupervised machine learning (UML) techniques to cluster THA patients who required BT based on similar clinical features. The resulting clusters were subsequently visualized and validated. We constructed a predictive model for THA patients who required BT based on six predictive factors: Age, Body Mass Index (BMI), Hemoglobin (HGB), Platelet (PLT), Bleeding Volume, and Urine Volume. Before surgery, 1 h after surgery, 1 day after surgery, and 1 week after surgery, significant differences were observed in HGB and PLT levels between patients who received BT and those who did not. The predictive model achieved an AUC of 0.899. Employing UML, we identified two distinct clusters with significantly heterogeneous clinical characteristics. Age, BMI, PLT, HGB, bleeding volume, and urine volume were found to be independent predictors of BT requirement in THA patients. The predictive model incorporating these six predictors demonstrated excellent predictive performance. Furthermore, employing UML enabled us to classify a heterogeneous cohort of THA patients who received BT in a meaningful and interpretable manner.

Development and validation of a machine learning-based nomogram for predicting HLA-B27 expression

BACKGROUND

HLA-B27 positivity is normal in patients undergoing rheumatic diseases. The diagnosis of many diseases requires an HLA-B27 examination.

METHODS

This study screened totally 1503 patients who underwent HLA-B27 examination, liver/kidney function tests, and complete blood routine examination in First Affiliated Hospital of Guangxi Medical University. The training cohort included 509 cases with HLA-B27 positivity whereas 611 with HLA-B27 negativity. In addition, validation cohort included 147 cases with HLA-B27 positivity whereas 236 with HLA-B27 negativity. In this study, 3 ML approaches, namely, LASSO, support vector machine (SVM) recursive feature elimination and random forest, were adopted for screening feature variables. Subsequently, to acquire the prediction model, the intersection was selected. Finally, differences among 148 cases with HLA-B27 positivity and negativity suffering from ankylosing spondylitis (AS) were investigated.

RESULTS

Six factors, namely red blood cell count, human major compatibility complex, mean platelet volume, albumin/globulin ratio (ALB/GLB), prealbumin, and bicarbonate radical, were chosen with the aim of constructing the diagnostic nomogram using ML methods. For training queue, nomogram curve exhibited the value of area under the curve (AUC) of 0.8254496, and C-value of the model was 0.825. Moreover, nomogram C-value of the validation queue was 0.853, and the AUC value was 0.852675. Furthermore, a significant decrease in the ALB/GLB was noted among cases with HLA-B27 positivity and AS cases.

CONCLUSION

To conclude, the proposed ML model can effectively predict HLA-B27 and help doctors in the diagnosis of various immune diseases.

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.

To infer the probability of cervical ossification of the posterior longitudinal ligament and explore its impact on cervical surgery

The ossification of the posterior longitudinal ligament (OPLL) in the cervical spine is commonly observed in degenerative changes of the cervical spine. Early detection of cervical OPLL and prevention of postoperative complications are of utmost importance. We gathered data from 775 patients who underwent cervical spine surgery at the First Affiliated Hospital of Guangxi Medical University, collecting a total of 84 variables. Among these patients, 144 had cervical OPLL, while 631 did not. They were randomly divided into a training cohort and a validation cohort. Multiple machine learning (ML) methods were employed to screen the variables and ultimately develop a diagnostic model. Subsequently, we compared the postoperative outcomes of patients with positive and negative cervical OPLL. Initially, we compared the advantages and disadvantages of various ML methods. Seven variables, namely Age, Gender, OPLL, AST, UA, BMI, and CHD, exhibited significant differences and were used to construct a diagnostic nomogram model. The area under the curve (AUC) values of this model in the training and validation groups were 0.76 and 0.728, respectively. Our findings revealed that 69.2% of patients who underwent cervical OPLL surgery eventually required elective anterior surgery, in contrast to 86.8% of patients who did not have cervical OPLL. Patients with cervical OPLL had significantly longer operation times and higher postoperative drainage volumes compared to those without cervical OPLL. Interestingly, preoperative cervical OPLL patients demonstrated significant increases in mean UA, age, and BMI. Furthermore, 27.1% of patients with cervical anterior longitudinal ligament ossification (OALL) also exhibited cervical OPLL, whereas this occurrence was only observed in 6.9% of patients without cervical OALL. We developed a diagnostic model for cervical OPLL using the ML method. Our findings indicate that patients with cervical OPLL are more likely to undergo posterior cervical surgery, and they exhibit elevated UA levels, higher BMI, and increased age. The prevalence of cervical anterior longitudinal ligament ossification was also significantly higher among patients with cervical OPLL.

Application of machine learning in prediction of bone cement leakage during single-level thoracolumbar percutaneous vertebroplasty

BACKGROUND

In the elderly, osteoporotic vertebral compression fractures (OVCFs) of the thoracolumbar vertebra are common, and percutaneous vertebroplasty (PVP) is a common surgical method after fracture. Machine learning (ML) was used in this study to assist clinicians in preventing bone cement leakage during PVP surgery.

METHODS

The clinical data of 374 patients with thoracolumbar OVCFs who underwent single-level PVP at The First People's Hospital of Chenzhou were chosen. It included 150 patients with bone cement leakage and 224 patients without it. We screened the feature variables using four ML methods and used the intersection to generate the prediction model. In addition, predictive models were used in the validation cohort.

RESULTS

The ML method was used to select five factors to create a Nomogram diagnostic model. The nomogram model's AUC was 0.646667, and its C value was 0.647. The calibration curves revealed a consistent relationship between nomogram predictions and actual probabilities. In 91 randomized samples, the AUC of this nomogram model was 0.7555116.

CONCLUSION

In this study, we invented a prediction model for bone cement leakage in single-segment PVP surgery, which can help doctors in performing better surgery with reduced risk.

Classification and prediction of spinal disease based on the SMOTE-RFE-XGBoost model

Spinal diseases are killers that cause long-term disturbance to people with complex and diverse symptoms and may cause other conditions. At present, the diagnosis and treatment of the main diseases mainly depend on the professional level and clinical experience of doctors, which is a breakthrough problem in the field of medicine. This article proposes the SMOTE-RFE-XGBoost model, which takes the physical angle of human bone as the research index for feature selection and classification model construction to predict spinal diseases. The research process is as follows: two groups of people with normal and abnormal spine conditions are taken as the research objects of this article, and the synthetic minority oversampling technique (SMOTE) algorithm is used to address category imbalance. Three methods, least absolute shrinkage and selection operator (LASSO), tree-based feature selection, and recursive feature elimination (RFE), are used for feature selection. Logistic regression (LR), support vector machine (SVM), parsimonious Bayes, decision tree (DT), random forest (RF), gradient boosting tree (GBT), extreme gradient boosting (XGBoost), and ridge regression models are used to classify the samples, construct single classification models and combine classification models and rank the feature importance. According to the accuracy and mean square error (MSE) values, the SMOTE-RFE-XGBoost combined model has the best classification, with accuracy, MSE and F1 values of 97.56%, 0.1111 and 0.8696, respectively. The importance of four indicators, lumbar slippage, cervical tilt, pelvic radius and pelvic tilt, was higher.

Identification of clinical heterogeneity and construction of a novel subtype predictive model in patients with ankylosing spondylitis: An unsupervised machine learning study

BACKGROUND

Accurate classification of patients with ankylosing spondylitis (AS) is the premise of precision medicine so as to perform different medical interventions for different patient types. AS pathology is closely related to the changes in the immune microenvironment. In this study, we used unsupervised machine learning (UML) to classify patients with AS based on clinical characteristics. We then constructed a novel subtype predictive model for AS based on the clinical classification, after which we investigated the difference in the immune microenvironment to unravel the AS pathogenesis.

METHODS

Overall, 196 patients with AS were enrolled. UML was used to cluster AS patients by similar clinical characteristics. Functional ability, disease status, and grading of radiologic features were assessed to verify the accuracy and heterogeneity of UML clustering. Least Absolute Shrinkage and Selection Operator (LASSO) regression and Random Forest algorithm were used to screen and identify predictive factors for the novel subtype of AS. Logistic regression was also performed to construct a predictive model of this novel subtype. Datasets were downloaded from the Gene Expression Omnibus database to assess immune cell infiltration, and the results were validated using data of routine blood tests from 3671 AS patients and 5720 non-AS patients. The differential expression of Fat Mass and Obesity-Associated Protein (FTO), an m⁶A regulator, between AS patients and healthy control subjects was confirmed using immunohistochemistry.

RESULTS

UML clustering identified two clusters. The clinical characteristics of the two clusters were significantly heterogeneous. For the novel subtype of AS identified in UML clustering, a predictive model was built using three predictive factors, namely, C-reactive protein (CRP), absolute value of neutrophils (NEU), and absolute value of monocytes (MONO). The area under the curve of the predictive model was 0.983. Heterogeneity in the neutrophil and monocyte counts in AS was verified through immune cell infiltration analysis. Data from routine blood tests revealed that NEU and MONO were significantly higher in AS patients than in non-AS patients (p < 0.001). FTO expression was negatively correlated with both NEU and MONO. Immunohistochemistry analysis confirmed the downregulated expression of FTO.

CONCLUSIONS

UML provides an explicable and remarkable classification of a heterogeneous cohort of AS patients. A novel subtype of AS was identified in UML clustering. CRP, NEU, and MONO were the independent predictive factors for the novel subtype of AS. FTO expression was correlated with immune cell infiltration in AS patients.

From past to future: Bibliometric analysis of global research productivity on nomogram (2000-2021)

Background

Nomogram, a visual clinical predictive model, provides a scientific basis for clinical decision making. Herein, we investigated 20 years of nomogram research responses, focusing on current and future trends and analytical challenges.

Methods

We mined data of scientific literature from the Core Collection of Web of Science, searching for the original articles with title "Nomogram^*/Parton Table^*/Parton Nomogram^*", published within January 1st, 2000 to December 30th, 2021. Data records were validated using HistCite Version and analyzed with a transformable statistical method, the Bibliometrix 3.0 package of R Studio.

Results

In total, 4,176 original articles written by 19,158 authors were included from 915 sources. Annually, Nomogram publications are continually produced, which have rapidly grown since 2018. China published the most articles; however, its total citations ranked second after the United States. Both total citations and average article citations in the United States rank first globally, and a high degree of cooperation exists between countries. Frontiers in Oncology published the most papers (238); this number has grown rapidly since 2019. Journal of Urology had the highest H-index, with an average increase in publications over the past 20 years. Most research topics were tumor-related, among which tumor risk prediction and prognostic evaluation were the main contents. Research on prognostic assessment is more published and advanced, while risk prediction and diagnosis have good developmental prospects. Furthermore, nomogram of the urinary system has been highly developed. Following advancements in nomogram modeling, it has recently been applied to non-oncological subjects.

Conclusion

This bibliometric analysis provides a comprehensive overview of the current nomogram status, which could enable better understanding of its development over the years, and provide global researchers a comprehensive analysis and structured information to help identify hot spots and gaps in future research.