An abbreviated Caprini model for VTE risk assessment in trauma

Development and validation of a novel screening tool for deep vein thrombosis in patients with spinal cord injury: A five-year cross-sectional study

STUDY DESIGN

Cross-sectional study.

OBJECTIVES

Deep vein thrombosis (DVT) presents a significant risk of complication in patients with spinal cord injury (SCI), necessitating accurate screening methods. While the Caprini Risk Assessment Model (Caprini RAM) has seen extensive use for DVT screening, its efficacy remains under scrutiny.

SETTING

First Affiliated Hospital of China University of Science and Technology.

METHODS

We created and evaluated three nomograms for their effectiveness in DVT screening. Model 1 incorporated variables such as age, D-dimer level, red blood cell (RBC) counts, platelet counts, presence of type 2 diabetes mellitus, high blood pressure, mode and level of injury, degree of impairments, and Caprini scores. Model 2 was derived from Caprini scores alone, and Model 3 focused on independent risk factors. We assessed these models using the area under the curve (AUC) of the receiver operating characteristic (ROC), calibration curves, and decision curve analysis (DCA), employing bootstrap resampling tests (500 iterations) to determine their accuracy, discriminative ability, and clinical utility. Internal validation was performed on a separate cohort. Nomogram was established with well-fitted calibration curves for model 1, 2 and 3(AUC = 0.808, 0.751 and 0.797; 95%CI = 0.76-0.86, 0.70-0.80 and 0.75-0.84; respectively), indicating model 1 outperformed the others in prediction DVT risk, followed by model 3 and 2. These findings were consistent in the validation cohort, with DCA further corroborating our conclusions.

CONCLUSION

A nomogram integrating clinical data with Caprini RAM provides a superior option for DVT screening in SCI patients within rehabilitation settings, outperforming Caprini RAM.

Identification of key risk factors for venous thromboembolism in urological inpatients based on the Caprini scale and interpretable machine learning methods

PURPOSE

To identify the key risk factors for venous thromboembolism (VTE) in urological inpatients based on the Caprini scale using an interpretable machine learning method.

METHODS

VTE risk data of urological inpatients were obtained based on the Caprini scale in the case hospital. Based on the data, the Boruta method was used to further select the key variables from the 37 variables in the Caprini scale. Furthermore, decision rules corresponding to each risk level were generated using the rough set (RS) method. Finally, random forest (RF), support vector machine (SVM), and backpropagation artificial neural network (BPANN) were used to verify the data accuracy and were compared with the RS method.

RESULTS

Following the screening, the key risk factors for VTE in urology were "(C1) Age," "(C2) Minor Surgery planned," "(C3) Obesity (BMI > 25)," "(C8) Varicose veins," "(C9) Sepsis (< 1 month)," (C10) "Serious lung disease incl. pneumonia (< 1month) " (C11) COPD," "(C16) Other risk," "(C18) Major surgery (> 45 min)," "(C19) Laparoscopic surgery (> 45 min)," "(C20) Patient confined to bed (> 72 h)," "(C18) Malignancy (present or previous)," "(C23) Central venous access," "(C31) History of DVT/PE," "(C32) Other congenital or acquired thrombophilia," and "(C34) Stroke (< 1 month." According to the decision rules of different risk levels obtained using the RS method, "(C1) Age," "(C18) Major surgery (> 45 minutes)," and "(C21) Malignancy (present or previous)" were the main factors influencing mid- and high-risk levels, and some suggestions on VTE prevention were indicated based on these three factors. The average accuracies of the RS, RF, SVM, and BPANN models were 79.5%, 87.9%, 92.6%, and 97.2%, respectively. In addition, BPANN had the highest accuracy, recall, F1-score, and precision.

CONCLUSIONS

The RS model achieved poorer accuracy than the other three common machine learning models. However, the RS model provides strong interpretability and allows for the identification of high-risk factors and decision rules influencing high-risk assessments of VTE in urology. This transparency is very important for clinicians in the risk assessment process.

A Nomogram Model to Predict Deep Vein Thrombosis Risk After Surgery in Patients with Hip Fractures

Aims

This study aimed to establish a nomogram model for predicting the probability of postoperative deep vein thrombosis (DVT) risk in patients with hip fractures.

Methods

504 patients were randomly assigned to the training set and validation set, and then divided into a DVT group and a non-DVT group. The study analysed the risk factors for DVT using univariate and multivariate analyses. Based on these parameters, a nomogram model was constructed and validated. The predicting performance of nomogram was evaluated by discrimination, calibration, and clinical usefulness.

Results

The predictors contained in the nomogram model included age, surgical approach, 1-day postoperative D-dimer value and admission ultrasound diagnosis of the lower limb vein. Furthermore, the area under the ROC curve (AUC) for the specific DVT risk-stratification nomogram model (0.815; 95% CI 0.746-0.884) was significantly higher than the current model (Caprini) (0.659; 95% CI 0.572-0.746, P < 0.05). According to the calibration plots, the prediction and actual observation were in good agreement. In the range of threshold probabilities of 0.2-0.8, the predictive performance of the model on DVT risk could be maximized.

Conclusions

The current predictive model could serve as a reliable tool to quantify the possibility of postoperative DVT in hip fractures patients.

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.

A Prospective Study Evaluating Patterns of Responses to the Caprini Score to Prevent Venous Thromboembolism After Interventional Treatment for Varicose Veins

Background

Venous thromboembolism (VTE) is a critical complication of varicose vein treatments. The Caprini Score (CS) is an established tool to assess patients’ VTE risks. One disadvantage is the number of questions required, some of them referring to a low incidence of disease, even lower in patients seeking an elective procedure. These elements take time and may result in filling errors if the CS is not filled out by a properly trained health professional.

Objective

To establish a response pattern in CS, with emphasis on questions that usually have a negative answer and propose a simpler adaptative digital version without changing the original structure of the tool.

Methods

two hundred and twenty-seven patients in the pre-surgical treatment of varicose veins were enrolled prospectively and submitted to the CS evaluation.

Results

The pattern of dichotomous responses could be divided arbitrarily into four subgroups considering the percentage of positive responses: none (11 items), less than 3% (13 items), between 3% and 20% (5 items), and more than 20% (8 items). Of the 12 CS questions related to illnesses that occurred in the last month, ten had had no responses, and 2 were less than 3%.

Conclusion

There is a pattern in the CS responses of patients with an indication of surgical treatment of varicose veins. Many of the CS questions are not helpful in this scenario and may result in filling errors performed by untrained providers. An adaptative version of the CS might benefit varicose veins surgery VTE risk stratification