Using Predictive Modeling and Supervised Machine Learning to Identify Patients at Risk for Venous Thromboembolism Following Posterior Lumbar Fusion

Machine learning approach to predict venous thromboembolism among patients undergoing multi-level spinal posterior instrumented fusion

Background

The absence of consensus for prophylaxis of venous thromboembolism (VTE) in spine surgery underscores the importance of identifying patients at risk. This study incorporated machine learning (ML) models to assess key risk factors of VTE in patients who underwent posterior spinal instrumented fusion.

Methods

Data was collected from the IBM MarketScan Database [2009-2021] for patients ≥18 years old who underwent spinal posterior instrumentation (3-6 levels), excluding traumas, malignancies, and infections. VTE incidence (deep vein thrombosis and pulmonary embolism) was recorded 90-day post-surgery. Risk factors for VTE were investigated and compared through several ML models including logistic regression, linear support vector machine (LSVM), random forest, XGBoost, and neural networks.

Results

Among the 141,697 patients who underwent spinal fusion with posterior instrumentation (3-6 levels), the overall 90-day VTE rate was 3.81%. The LSVM model demonstrated the best prediction with an area under the curve (AUC) of 0.68. The most important features for prediction of VTE included remote history of VTE, diagnosis of chronic hypercoagulability, metastatic cancer, hemiplegia, and chronic renal disease. Patients who did not have these five key risk factors had a 90-day VTE rate of 2.95%. Patients who had an increasing number of key risk factors had subsequently higher risks of postoperative VTE.

Conclusions

The analysis of the data with different ML models identified 5 key variables that are most closely associated with VTE. Using these variables, we have developed a simple risk model with additive odds ratio ranging from 2.80 (1 risk factor) to 46.92 (4 risk factors) over 90 days after posterior spinal fusion surgery. These findings can help surgeons risk-stratify their patients for VTE risk, and potentially guide subsequent chemoprophylaxis.

Revolutionizing Cardiology through Artificial Intelligence-Big Data from Proactive Prevention to Precise Diagnostics and Cutting-Edge Treatment-A Comprehensive Review of the Past 5 Years

BACKGROUND

Artificial intelligence (AI) can radically change almost every aspect of the human experience. In the medical field, there are numerous applications of AI and subsequently, in a relatively short time, significant progress has been made. Cardiology is not immune to this trend, this fact being supported by the exponential increase in the number of publications in which the algorithms play an important role in data analysis, pattern discovery, identification of anomalies, and therapeutic decision making. Furthermore, with technological development, there have appeared new models of machine learning (ML) and deep learning (DP) that are capable of exploring various applications of AI in cardiology, including areas such as prevention, cardiovascular imaging, electrophysiology, interventional cardiology, and many others. In this sense, the present article aims to provide a general vision of the current state of AI use in cardiology.

RESULTS

We identified and included a subset of 200 papers directly relevant to the current research covering a wide range of applications. Thus, this paper presents AI applications in cardiovascular imaging, arithmology, clinical or emergency cardiology, cardiovascular prevention, and interventional procedures in a summarized manner. Recent studies from the highly scientific literature demonstrate the feasibility and advantages of using AI in different branches of cardiology.

CONCLUSIONS

The integration of AI in cardiology offers promising perspectives for increasing accuracy by decreasing the error rate and increasing efficiency in cardiovascular practice. From predicting the risk of sudden death or the ability to respond to cardiac resynchronization therapy to the diagnosis of pulmonary embolism or the early detection of valvular diseases, AI algorithms have shown their potential to mitigate human error and provide feasible solutions. At the same time, limits imposed by the small samples studied are highlighted alongside the challenges presented by ethical implementation; these relate to legal implications regarding responsibility and decision making processes, ensuring patient confidentiality and data security. All these constitute future research directions that will allow the integration of AI in the progress of cardiology.

Machine Learning-Based Predictive Models for Patients with Venous Thromboembolism: A Systematic Review

BACKGROUND

 Venous thromboembolism (VTE) is a chronic disorder with a significant health and economic burden. Several VTE-specific clinical prediction models (CPMs) have been used to assist physicians in decision-making but have several limitations. This systematic review explores if machine learning (ML) can enhance CPMs by analyzing extensive patient data derived from electronic health records. We aimed to explore ML-CPMs' applications in VTE for risk stratification, outcome prediction, diagnosis, and treatment.

METHODS

 Three databases were searched: PubMed, Google Scholar, and IEEE electronic library. Inclusion criteria focused on studies using structured data, excluding non-English publications, studies on non-humans, and certain data types such as natural language processing and image processing. Studies involving pregnant women, cancer patients, and children were also excluded. After excluding irrelevant studies, a total of 77 studies were included.

RESULTS

 Most studies report that ML-CPMs outperformed traditional CPMs in terms of receiver operating area under the curve in the four clinical domains that were explored. However, the majority of the studies were retrospective, monocentric, and lacked detailed model architecture description and external validation, which are essential for quality audit. This review identified research gaps and highlighted challenges related to standardized reporting, reproducibility, and model comparison.

CONCLUSION

 ML-CPMs show promise in improving risk assessment and individualized treatment recommendations in VTE. Apparently, there is an urgent need for standardized reporting and methodology for ML models, external validation, prospective and real-world data studies, as well as interventional studies to evaluate the impact of artificial intelligence in VTE.

Venous Thromboembolism: Review of Clinical Challenges, Biology, Assessment, Treatment, and Modeling

Venous thromboembolism (VTE) is a massive clinical challenge, annually affecting millions of patients globally. VTE is a particularly consequential pathology, as incidence is correlated with extremely common risk factors, and a large cohort of patients experience recurrent VTE after initial intervention. Altered hemodynamics, hypercoagulability, and damaged vascular tissue cause deep-vein thrombosis and pulmonary embolism, the two permutations of VTE. Venous valves have been identified as likely locations for initial blood clot formation, but the exact pathway by which thrombosis occurs in this environment is not entirely clear. Several risk factors are known to increase the likelihood of VTE, particularly those that increase inflammation and coagulability, increase venous resistance, and damage the endothelial lining. While these risk factors are useful as predictive tools, VTE diagnosis prior to presentation of outward symptoms is difficult, chiefly due to challenges in successfully imaging deep-vein thrombi. Clinically, VTE can be managed by anticoagulants or mechanical intervention. Recently, direct oral anticoagulants and catheter-directed thrombolysis have emerged as leading tools in resolution of venous thrombosis. While a satisfactory VTE model has yet to be developed, recent strides have been made in advancing in silico models of venous hemodynamics, hemorheology, fluid-structure interaction, and clot growth. These models are often guided by imaging-informed boundary conditions or inspired by benchtop animal models. These gaps in knowledge are critical targets to address necessary improvements in prediction and diagnosis, clinical management, and VTE experimental and computational models.

Limitations in Evaluating Machine Learning Models for Imbalanced Binary Outcome Classification in Spine Surgery: A Systematic Review

Clinical prediction models for spine surgery applications are on the rise, with an increasing reliance on machine learning (ML) and deep learning (DL). Many of the predicted outcomes are uncommon; therefore, to ensure the models' effectiveness in clinical practice it is crucial to properly evaluate them. This systematic review aims to identify and evaluate current research-based ML and DL models applied for spine surgery, specifically those predicting binary outcomes with a focus on their evaluation metrics. Overall, 60 papers were included, and the findings were reported according to the PRISMA guidelines. A total of 13 papers focused on lengths of stay (LOS), 12 on readmissions, 12 on non-home discharge, 6 on mortality, and 5 on reoperations. The target outcomes exhibited data imbalances ranging from 0.44% to 42.4%. A total of 59 papers reported the model's area under the receiver operating characteristic (AUROC), 28 mentioned accuracies, 33 provided sensitivity, 29 discussed specificity, 28 addressed positive predictive value (PPV), 24 included the negative predictive value (NPV), 25 indicated the Brier score with 10 providing a null model Brier, and 8 detailed the F1 score. Additionally, data visualization varied among the included papers. This review discusses the use of appropriate evaluation schemes in ML and identifies several common errors and potential bias sources in the literature. Embracing these recommendations as the field advances may facilitate the integration of reliable and effective ML models in clinical settings.

Using Machine Learning (ML) Models to Predict Risk of Venous Thromboembolism (VTE) Following Spine Surgery

STUDY DESIGN

A retrospective cohort study.

OBJECTIVES

Venous thromboembolism (VTE) is a potentially high-risk complication for patients undergoing spine surgery. Although guidelines for assessing VTE risk in this population have been established, development of new techniques that target different aspects of the medical history may prove to be of further utility. The goal of this study was to develop a predictive machine learning (ML) model to identify nontraditional risk factors for predicting VTE in spine surgery patients.

SUMMARY OF BACKGROUND DATA

A cohort of 63 patients was identified who had undergone spine surgery at a single center from 2015 to 2021. Thirty-one patients had a confirmed VTE, while 32 had no VTE. A total of 113 attributes were defined and collected via chart review. Attribute categories included demographics, medications, labs, past medical history, operative history, and VTE diagnosis.

METHODS

The Waikato Environment for Knowledge Analysis (WEKA) software was used in creating and evaluating the ML models. Six classifier models were tested with 10-fold cross-validation and statistically evaluated using t tests.

RESULTS

Comparing the predictive ML models to the control model (ZeroR), all predictive models were significantly better than the control model at predicting VTE risk, based on the 113 attributes ( P <0.001). The Random Forest model had the highest accuracy of 88.89% with a positive predictive value of 93.75%. The Simple Logistic algorithm had an accuracy of 84.13% and defined risk attributes to include calcium and phosphate laboratory values, history of cardiac comorbidity, history of previous VTE, anesthesia time, selective serotonin reuptake inhibitor use, antibiotic use, and antihistamine use. The J48 model had an accuracy of 80.95% and it defined hemoglobin laboratory values, anesthesia time, beta-blocker use, dopamine agonist use, history of cancer, and Medicare use as potential VTE risk factors.

CONCLUSION

Further development of these tools may provide high diagnostic value and may guide chemoprophylaxis treatment in this setting of high-risk patients.

The use of machine learning for predicting candidates for outpatient spine surgery: a review

While spine surgery has historically been performed in the inpatient setting, in recent years there has been growing interest in performing certain cervical and lumbar spine procedures on an outpatient basis. While conducting these procedures in the outpatient setting may be preferable for both the surgeon and the patient, appropriate patient selection is crucial. The employment of machine learning techniques for data analysis and outcome prediction has grown in recent years within spine surgery literature. Machine learning is a form of statistics often applied to large datasets that creates predictive models, with minimal to no human intervention, that can be applied to previously unseen data. Machine learning techniques may outperform traditional logistic regression with regards to predictive accuracy when analyzing complex datasets. Researchers have applied machine learning to develop algorithms to aid in patient selection for spinal surgery and to predict postoperative outcomes. Furthermore, there has been increasing interest in using machine learning to assist in the selection of patients who may be appropriate candidates for outpatient cervical and lumbar spine surgery. The goal of this review is to discuss the current literature utilizing machine learning to predict appropriate patients for cervical and lumbar spine surgery, candidates for outpatient spine surgery, and outcomes following these procedures.

Using machine learning and big data for the prediction of venous thromboembolic events after spine surgery: A single-center retrospective analysis of multiple models on a cohort of 6869 patients

Objective

Venous thromboembolic event (VTE) after spine surgery is a rare but potentially devastating complication. With the advent of machine learning, an opportunity exists for more accurate prediction of such events to aid in prevention and treatment.

Methods

Seven models were screened using 108 database variables and 62 preoperative variables. These models included deep neural network (DNN), DNN with synthetic minority oversampling technique (SMOTE), logistic regression, ridge regression, lasso regression, simple linear regression, and gradient boosting classifier. Relevant metrics were compared between each model. The top four models were selected based on area under the receiver operator curve; these models included DNN with SMOTE, linear regression, lasso regression, and ridge regression. Separate random sampling of each model was performed 1000 additional independent times using a randomly generated training/testing distribution. Variable weights and magnitudes were analyzed after sampling.

Results

Using all patient-related variables, DNN using SMOTE was the top-performing model in predicting postoperative VTE after spinal surgery (area under the curve [AUC] =0.904), followed by lasso regression (AUC = 0.894), ridge regression (AUC = 0.873), and linear regression (AUC = 0.864). When analyzing a subset of only preoperative variables, the top-performing models were lasso regression (AUC = 0.865) and DNN with SMOTE (AUC = 0.864), both of which outperform any currently published models. Main model contributions relied heavily on variables associated with history of thromboembolic events, length of surgical/anesthetic time, and use of postoperative chemoprophylaxis.

Conclusions

The current study provides promise toward machine learning methods geared toward predicting postoperative complications after spine surgery. Further study is needed in order to best quantify and model real-world risk for such events.

Venous Thromboembolism Rates Have Not Decreased in Elective Lumbar Fusion Surgery from 2011 to 2020

STUDY DESIGN

Retrospective cohort study.

OBJECTIVES

This study aimed to (1) evaluate for any temporal trends in the rates of VTE, deep venous thrombosis (DVT), pulmonary embolism (PE), and mortality from 2011 to 2020 and (2) identify the predictors of VTE following lumbar fusion surgery.

METHODS

Annual incidences of 30-day VTE, DVT, PE, and mortality were calculated for each of the operation year groups from 2011 to 2020. Multivariable Poisson regression was utilized to test the association between operation year and primary outcomes, as well as to identify significant predictors of VTE.

RESULTS

A total of 121,205 patients were included. There were no statistically significant differences in VTE, DVT, PE, or mortality rates among the operation year groups. Multivariable regression analysis revealed that compared to 2011, operation year 2019 was associated with significantly lower rates of DVT. Age, BMI, prolonged operation time, prolonged length of stay, non-home discharge, anterior fusion, smoking status, functional dependence, and chronic steroid use were identified as independent predictors of VTE following lumbar fusion. Female sex, Hispanic ethnicity, and outpatient surgery setting were identified as protective factors from VTE in this cohort.

CONCLUSIONS

Rates of VTE after lumbar fusion have remained mostly unchanged between 2011 and 2020. Older age, higher BMI, longer operation time, prolonged length of stay, non-home discharge, anterior fusion, smoking, functional dependence, and steroid use were independent predictors of VTE after lumbar fusion, while female sex, Hispanic ethnicity, and outpatient surgery were the protective factors.

Automatic detection and voxel‐wise mapping of lumbar spine Modic changes with deep learning

Background

Modic changes (MCs) are the most prevalent classification system for describing magnetic resonance imaging (MRI) signal intensity changes in the vertebrae. However, there is a growing need for novel quantitative and standardized methods of characterizing these anomalies, particularly for lesions of transitional or mixed nature, due to the lack of conclusive evidence of their associations with low back pain. This retrospective imaging study aims to develop an interpretable deep learning‐based detection tool for voxel‐wise mapping of MCs.

Methods

Seventy‐five lumbar spine MRI exams that presented with acute‐to‐chronic low back pain, radiculopathy, and other symptoms of the lumbar spine were enrolled. The pipeline consists of two deep convolutional neural networks to generate an interpretable voxel‐wise Modic map. First, an autoencoder was trained to segment vertebral bodies from T₁‐weighted sagittal lumbar spine images. Next, two radiologists segmented and labeled MCs from a combined T₁‐ and T₂‐weighted assessment to serve as ground truth for training a second autoencoder that performs segmentation of MCs. The voxels in the detected regions were then categorized to the appropriate Modic type using a rule‐based signal intensity algorithm. Post hoc, three radiologists independently graded a second dataset with the aid of the model predictions in an artificial (AI)‐assisted experiment.

Results

The model successfully identified the presence of changes in 85.7% of samples in the unseen test set with a sensitivity of 0.71 (±0.072), specificity of 0.95 (±0.022), and Cohen's kappa score of 0.63. In the AI‐assisted experiment, the agreement between the junior radiologist and the senior neuroradiologist significantly improved from Cohen's kappa score of 0.52 to 0.58 (p < 0.05).

Conclusions

This deep learning‐based approach demonstrates substantial agreement with radiologists and may serve as a tool to improve inter‐rater reliability in the assessment of MCs.

Artificial Intelligence-Driven Prediction Modeling and Decision Making in Spine Surgery Using Hybrid Machine Learning Models

Healthcare systems worldwide generate vast amounts of data from many different sources. Although of high complexity for a human being, it is essential to determine the patterns and minor variations in the genomic, radiological, laboratory, or clinical data that reliably differentiate phenotypes or allow high predictive accuracy in health-related tasks. Convolutional neural networks (CNN) are increasingly applied to image data for various tasks. Its use for non-imaging data becomes feasible through different modern machine learning techniques, converting non-imaging data into images before inputting them into the CNN model. Considering also that healthcare providers do not solely use one data modality for their decisions, this approach opens the door for multi-input/mixed data models which use a combination of patient information, such as genomic, radiological, and clinical data, to train a hybrid deep learning model. Thus, this reflects the main characteristic of artificial intelligence: simulating natural human behavior. The present review focuses on key advances in machine and deep learning, allowing for multi-perspective pattern recognition across the entire information set of patients in spine surgery. This is the first review of artificial intelligence focusing on hybrid models for deep learning applications in spine surgery, to the best of our knowledge. This is especially interesting as future tools are unlikely to use solely one data modality. The techniques discussed could become important in establishing a new approach to decision-making in spine surgery based on three fundamental pillars: (1) patient-specific, (2) artificial intelligence-driven, (3) integrating multimodal data. The findings reveal promising research that already took place to develop multi-input mixed-data hybrid decision-supporting models. Their implementation in spine surgery may hence be only a matter of time.