Construction and verification of a nomogram predicting the risk of preoperative deep vein thrombosis progression after elective spine surgery

Building and Verifying a Prediction Model for Deep Vein Thrombosis Among Spinal Cord Injury Patients Undergoing Inpatient Rehabilitation

OBJECTIVE

To explore the relevant variables that contribute to deep vein thrombosis (DVT) among spinal cord injury (SCI) patients undergoing inpatient rehabilitation and to build and validate a nomogram model that predicts DVT risk.

METHODS

By convenience sampling, 558 SCI patients who were hospitalized at a tertiary-level Grade A general hospital in Anhui Province, China between January 2017 and March 2022 were chosen as the study subjects. They were split into 2 groups at random, one for training (n = 446) and the other for validation (n = 112). The ratio was 8:2. The clinical information of patients was gathered, including sociodemographic characteristics, data about disease characteristics, and examinations pertaining to laboratories. The related factors of DVT among SCI patients undergoing inpatient rehabilitation were analyzed using both univariate and multivariate logistic regression. Using the variables identified by the multivariate logistic regression analysis, we constructed a predictive nomogram model with the aid of the R software. The model's predictive accuracy for assessing the risk of DVT was validated through the use of receiver operating characteristic curves and calibration plots.

RESULTS

Prothrombin time, D-dimer, age, and Caprini score were independent related factors for DVT among SCI patients undergoing inpatient rehabilitation, according to multivariate logistic regression analysis (odds ratio > 1, P < 0.05). These 4 variables selected by the multivariate logistic regression analysis were used to build a nomogram risk model, which was found to have strong predictive capacity for predicting the risk of DVT among SCI patients undergoing inpatient rehabilitation. The nomogram model's area under the receiver operating characteristic curve in the training group and validation group was 0.793 and 0.905, and the 95% confidence intervals were 0.750∼0.837 and 0.830∼0.980, separately, indicating good discrimination of the nomogram model. A good calibration of the model was shown by the calibration curve, which was well consistent between the model's predicted probability and the actual frequency of DVT in both the training and validation groups.

CONCLUSIONS

Prothrombin time, D-dimer level, age, and Caprini score are independent related factors for DVT among SCI patients undergoing inpatient rehabilitation. According to the variables mentioned previously, a nomogram model was constructed that can accurately and easily predict DVT risk among SCI patients undergoing inpatient rehabilitation. This facilitates the early identification of high-risk groups and the timely implementation of prevention, treatment, rehabilitation, and nursing strategies by clinical medical staff.

Construction and verification of a machine learning-based prediction model of deep vein thrombosis formation after spinal surgery

BACKGROUND

Deep vein thromboembolism (DVT) is a common postoperative complication with high morbidity and mortality rates. However, the safety and effectiveness of using prophylactic anticoagulants for preventing DVT after spinal surgery remain controversial. Hence, it is crucial to predict whether DVT occurs in advance following spinal surgery. The present study aimed to establish a machine learning (ML)-based prediction model of DVT formation following spinal surgery.

METHODS

We reviewed the medical records of patients who underwent elective spinal surgery at the Third Affiliated Hospital of Zunyi Medical University (TAHZMU) from January 2020 to December 2022. We ultimately selected the clinical data of 500 patients who met the criteria for elective spinal surgery. The Boruta-SHAP algorithm was used for feature selection, and the SMOTE algorithm was used for data balance. The related risk factors for DVT after spinal surgery were screened and analyzed. Five ML algorithm models were established. The data of 150 patients treated at the Affiliated Hospital of Zunyi Medical University (AHZMU) from July 2023 to October 2023 were used for external verification of the model. The area under the curve (AUC), geometric mean (G-mean), sensitivity, accuracy, specificity, and F1 score were used to evaluate the performance of the models.

RESULTS

The results revealed that activated partial thromboplastin time (APTT), age, body mass index (BMI), preoperative serum creatinine (Crea), anesthesia time, rocuronium dose, and propofol dose were the seven important characteristic variables for predicting DVT after spinal surgery. Among the five ML models established in this study, the random forest classifier (RF) showed superior performance to the other models in the internal validation set.

CONCLUSION

Seven preoperative and intraoperative variables were included in our study to develop an ML-based predictive model for DVT formation following spinal surgery, and this model can be used to assist in clinical evaluation and decision-making.

Nomogram for predicting venous thromboembolism after spinal surgery

PURPOSE

This study aimed to establish a nomogram to predict the risk of venous thromboembolism (VTE), identifying potential risk factors, and providing theoretical basis for prevention of VTE after spinal surgery.

METHODS

A retrospective analysis was conducted on 2754 patients who underwent spinal surgery. The general characteristics of the training group were initially screened using univariate logistic analysis, and the LASSO method was used for optimal prediction. Subsequently, multivariate logistic regression analysis was performed to identify independent risk factors for postoperative VTE in the training group, and a nomogram for predict risk of VTE was established. The discrimination, calibration, and clinical usefulness of the nomogram were separately evaluated using the C-index, receiver operating characteristic curve, calibration plot and clinical decision curve, and was validated using data from the validation group finally.

RESULTS

Multivariate logistic regression analysis identified 10 independent risk factors for VTE after spinal surgery. A nomogram was established based on these independent risk factors. The C-index for the training and validation groups indicating high accuracy and stability of the model. The area under the receiver operating characteristic curve indicating excellent discrimination ability; the calibration curves showed outstanding calibration for both the training and validation groups. Decision curve analysis showed the clinical net benefit of using the nomogram could be maximized in the probability threshold range of 0.01-1.

CONCLUSION

Patients undergoing spinal surgery with elevated D-dimer levels, prolonger surgical, and cervical surgery have higher risk of VTE. The nomogram can provide a theoretical basis for clinicians to prevent VTE.

Comparative study of two models predicting the risk of deep vein thrombosis progression in spinal trauma patients after operation

OBJECTIVE

Patients with preoperative deep vein thrombosis (DVT) exhibit a notable incidence of postoperative deep vein thrombosis progression (DVTp), which bears a potential for silent, severe consequences. Consequently, the development of a predictive model for the risk of postoperative DVTp among spinal trauma patients is important.

METHODS

Data of 161 spinal traumatic patients with preoperative DVT, who underwent spine surgery after admission, were collected from our hospital between January 2016 and December 2022. The least absolute shrinkage and selection operator (LASSO) combined with multivariable logistic regression analysis was applied to select variables for the development of the predictive logistic regression models. One logistic regression model was formulated simply with the Caprini risk score (Model A), while the other model incorporated not only the previously screened variables but also the age variable (Model B). The model's capability was evaluated using sensitivity, specificity, positive predictive value, negative predictive value, accuracy, F1 score, and receiver operating characteristic (ROC) curve. Nomograms simplified and visually presented Model B for the clinicians and patients to understand the predictive model. The decision curve was used to analyze the clinical value of Model B.

RESULTS

A total of 161 DVT patients were enrolled in this study. Postoperative DVTp occurred in 48 spinal trauma patients, accounting for 29.81% of the total patient enrolled. Model A inadequately predicted postoperative DVTp in spinal trauma patients, with ROC AUC values of 0.595 for the training dataset and 0.593 for the test dataset. Through the application of LASSO regression and multivariable logistic regression, a screening process was conducted for seven risk factors: D-dimer, blood platelet, hyperlipidemia, blood group, preoperative anticoagulant, spinal cord injury, lower extremity varicosities. Model B demonstrated superior and consistent predictive performance, with ROC AUC values of 0.809 for the training dataset and 0.773 for the test dataset. According to the calibration curves and decision curve analysis, Model B could accurately predict the probability of postoperative DVTp after spine surgery. The nomograms enhanced the interpretability of Model B in charts and graphs.

CONCLUSIONS

In summary, we established a logistic regression model for the accurate predicting of postoperative deep vein thrombosis progression in spinal trauma patients, utilizing D-dimer, blood platelet, hyperlipidemia, blood group, preoperative anticoagulant, spinal cord injury, lower extremity varicosities, and age as predictive factors. The proposed model outperformed a logistic regression model based simply on CRS. The proposed model has the potential to aid frontline clinicians and patients in identifying and intervening in postoperative DVTp among traumatic patients undergoing spinal surgery.

Analysis of risk factors for deep vein thrombosis after spinal infection surgery and construction of a nomogram preoperative prediction model

Objective

To investigate the differences in postoperative deep venous thrombosis (DVT) between patients with spinal infection and those with non-infected spinal disease; to construct a clinical prediction model using patients' preoperative clinical information and routine laboratory indicators to predict the likelihood of DVT after surgery.

Method

According to the inclusion criteria, 314 cases of spinal infection (SINF) and 314 cases of non-infected spinal disease (NSINF) were collected from January 1, 2016 to December 31, 2021 at Xiangya Hospital, Central South University, and the differences between the two groups in terms of postoperative DVT were analyzed by chi-square test. The spinal infection cases were divided into a thrombotic group (DVT) and a non-thrombotic group (NDVT) according to whether they developed DVT after surgery. Pre-operative clinical information and routine laboratory indicators of patients in the DVT and NDVT groups were used to compare the differences between groups for each variable, and variables with predictive significance were screened out by least absolute shrinkage and operator selection (LASSO) regression analysis, and a predictive model and nomogram of postoperative DVT was established using multi-factor logistic regression, with a Hosmer- Lemeshow goodness-of-fit test was used to plot the calibration curve of the model, and the predictive effect of the model was evaluated by the area under the ROC curve (AUC).

Result

The incidence of postoperative DVT in patients with spinal infection was 28%, significantly higher than 16% in the NSINF group, and statistically different from the NSINF group (P < 0.000). Five predictor variables for postoperative DVT in patients with spinal infection were screened by LASSO regression, and plotted as a nomogram. Calibration curves showed that the model was a good fit. The AUC of the predicted model was 0.8457 in the training cohort and 0.7917 in the validation cohort.

Conclusion

In this study, a nomogram prediction model was developed for predicting postoperative DVT in patients with spinal infection. The nomogram included five preoperative predictor variables, which would effectively predict the likelihood of DVT after spinal infection and may have greater clinical value for the treatment and prevention of postoperative DVT.

Development and validation of a nomogram to predict the risk of surgical site infection within 1 month after transforaminal lumbar interbody fusion

OBJECTIVE

Surgical site infection (SSI), a common serious complication within 1 month after transforaminal lumbar interbody fusion (TLIF), usually leads to poor prognosis and even death. The objective of this study is to investigate the factors related to SSI within 1 month after TLIF. We have developed a dynamic nomogram to change treatment or prevent infection based on accurate predictions.

MATERIALS AND METHODS

We retrospectively analyzed 383 patients who received TLIF at our institution from January 1, 2019, to June 30, 2022. The outcome variable in the current study was the occurrence of SSI within 1 month after surgery. Univariate logistic regression analysis was first performed to assess risk factors for SSI within 1 month after surgery, followed by inclusion of significant variables at P < 0.05 in multivariate logistic regression analysis. The independent risk variables were subsequently utilized to build a nomogram model. The consistency index (C-index), calibration curve and receiver operating characteristic curve were used to evaluate the performance of the model. And the decision curve analysis (DCA) was used to analyze the clinical value of the nomogram.

RESULTS

The multivariate logistic regression models further screened for three independent influences on the occurrence of SSI after TLIF, including lumbar paraspinal (multifidus and erector spinae) muscles (LPM) fat infiltration, diabetes and surgery duration. Based on the three independent factors, a nomogram prediction model was built. The area under the curve for the nomogram including these predictors was 0.929 in both the training and validation samples. Both the training and validation samples had high levels of agreement on the calibration curves, and the nomograms C-index was 0.929 and 0.955, respectively. DCA showed that if the threshold probability was less than 0.74, it was beneficial to use this nomograph to predict the risk of SSI after TLIF. In addition, the nomogram was converted to a web-based calculator that provides a graphical representation of the probability of SSI occurring within 1 month after TLIF.

CONCLUSION

A nomogram including LPM fat infiltration, surgery duration and diabetes is a promising model for predicting the risk of SSI within 1 month after TLIF. This nomogram assists clinicians in stratifying patients, hence boosting decision-making based on evidence and personalizing the best appropriate treatment.