Caprini score and surgical times linked to the risk for venous thromboembolism after robotic-assisted radical prostatectomy

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.

Predictive accuracy of boosted regression model in estimating risk of venous thromboembolism following minimally invasive radical surgery in pharmacological prophylaxis-naïve men with prostate cancer

BACKGROUND

Venous thromboembolism (VTE) is a potentially life-threatening but preventable complication after urological surgery. Physicians are faced with the challenges of weighing the risks and benefits of thromboprophylaxis given scanty evidence for or against and practice variation worldwide.

OBJECTIVE

The primary objective of the study was to explore the possibility of a risk-stratified approach for thromboembolism prophylaxis following radical prostatectomy.

DESIGN, SETTING, AND PARTICIPANTS

A prospective database was accessed to cross-link venous thromboembolism events in 522 men who underwent minimally invasive prostatectomy between February 2010 and October 2021. A deterministic data linkage method was used to record events through electronic systems. Community Health Index (CHI) numbers were used to identify patients via electronic health records. Patient demographics and clinical characteristics such as age, comorbidities, Gleason staging, and readmission details accrued.

OUTCOMES

VTE within 90 days and development of a risk-stratified scoring system. All statistical analysis was performed using R-Statistical Software and the risk of VTE within 90 days of surgery was estimated via gradient-boosting decision trees (BRT) model.

RESULTS AND LIMITATIONS

1.1% (6/522) of patients developed deep vein thrombosis or pulmonary embolism within 3 months post-minimally invasive prostatectomy. Statistical analysis demonstrated a significant difference in the body mass index (p = 0.016), duration of hospital stay (p < 0.001), and number of readmissions (p = 0.036) between patients who developed VTE versus patients who did not develop VTE. BRT analysis found 8 variables that demonstrated relative importance in predicting VTE. The receiver operating curves (ROC) were constructed to assess the discrimination power of a new model. The model showed an AUC of 0.97 (95% confidence intervals [CI]: 0.945,0.999). For predicting VTE, a single-center study is a limitation.

CONCLUSIONS

The incidence of VTE post-minimally invasive prostatectomy in men who did not receive prophylaxis with low molecular weight heparin is low (1.1%). The proposed risk-scoring system may aid in the identification of higher-risk patients for thromboprophylaxis. In this report, we looked at the outcomes of venous thromboembolism following minimally invasive radical prostatectomy for prostate cancer in consecutive men. We developed a new scoring system using advanced statistical analysis. We conclude that the VTE risk is very low and our model, if applied, can risk stratify men for the development of VTE following radical surgery for prostate cancer.

Construction and verification of risk predicting models to evaluate the possibility of hydrocephalus following aneurysmal subarachnoid hemorrhage

BACKGROUND

Hydrocephalus following a ruptured aneurysm portends a poor prognosis. The authors aimed to establish a nomogram to predict the risk of hydrocephalus after aneurysmal subarachnoid hemorrhage (aSAH).

METHODS

A total of 421 patients with aSAH who were diagnosed by digital subtraction angiography in The General Hospital of Northern Theater Command center from January 2020 to June 2021 were screened to establish the training cohort. An additional 135 patients who enrolled between July 2021 and May 2022 were used for the validation cohort. Variate difference analysis and stepwise logistic regression (model A) and univariate and multivariate logistic regressions (model B) were respectively used to construct two models. Then, the net reclassification improvement (NRI), integrated discrimination improvement (IDI), and receiver operating characteristic (ROC) curve were used to compare the predictive abilities of the two models. Finally, two nomograms were constructed and externally validated.

RESULTS

After screening, 556 patients were included. The area under the ROC curve of models A and B in the training cohort were respectively 0.884 (95 % confidence interval [CI]: 0.847-0.921) and 0.834 (95 % CI: 0.787-0.881). The prediction ability of the model A was superior to model B (NRI > 0, IDI > 0, p < 0.05). The C-index of models A and B was 0.8835 and 0.8392, respectively. Regarding clinical usefulness, the two models offered a net benefit with a threshold probability of between 0.12 and 1 in the decision curve analysis, suggesting that the two models can accurately predict hydrocephalus events.

CONCLUSIONS

Both models have good prediction accuracy. Compared with model B, model A has better discrimination and calibration. Further, the easy-to-use nomogram can help neurosurgeons to make rapid clinical decisions and apply early treatment measures in high-risk groups, which ultimately benefits patients.

External Validation of the ICU-Venous Thromboembolism Risk Assessment Model in Adult Critically Ill Patients

BACKGROUND

Currently, no universally accepted standardized VTE risk assessment model (RAM) is specifically designed for critically ill patients. Although the ICU-venous thromboembolism (ICU-VTE) RAM was initially developed in 2020, it lacks prospective external validation.

OBJECTIVES

To evaluate the predictive performance of the ICU-VTE RAM in terms of VTE occurrence in mixed medical-surgical ICU patients.

METHODS

We prospectively enrolled adult patients in the ICU. The ICU-VTE score and Caprini or Padua score were calculated at admission, and the incidence of in-hospital VTE was investigated. The performance of the ICU-VTE RAM was evaluated and compared with that of Caprini or Padua RAM using the receiver operating curve.

RESULTS

We included 269 patients (median age: 70 years; 62.5% male). Eighty-three (30.9%) patients experienced inpatient VTE. The AUC of the ICU-VTE RAM was 0.743 (95% CI, 0.682-0.804, P < 0.001) for mixed medical-surgical ICU patients. Comparatively, the performance of the ICU-VTE RAM was superior to that of the Pauda RAM (AUC: 0.727 vs 0.583, P < 0.001) in critically ill medical patients and the Caprini RAM (AUC: 0.774 vs 0.617, P = 0.128) in critically ill surgical patients, although the latter comparison was not statistically significant.

CONCLUSIONS

The ICU-VTE RAM may be a practical and valuable tool for identifying and stratifying VTE risk in mixed medical-surgical critically ill patients, aiding in managing and preventing VTE complications.

The Thresholds of Caprini Score Associated With Increased Risk of Venous Thromboembolism Across Different Specialties: A Systematic Review

OBJECTIVE

Estimation of the specific thresholds of the Caprini risk score (CRS) that are associated with the increased incidence of venous thromboembolism (VTE) across different specialties, including identifying the highest level of risk.

BACKGROUND

Accurate risk assessment remains an important but often challenging aspect of VTE prophylaxis. One well-established risk assessment model is CRS, which has been validated in thousands of patients from many different medical and surgical specialties.

METHODS

A search of MEDLINE and the Cochrane Library was performed in March 2022. Manuscripts that reported on (1) patients admitted to medical or surgical departments and (2) had their VTE risk assessed by CRS and (3) reported on the correlation between the score and VTE incidence, were included in the analysis.

RESULTS

A total of 4562 references were identified, and the full text of 202 papers was assessed for eligibility. The correlation between CRS and VTE incidence was reported in 68 studies that enrolled 4,207,895 patients. In all specialties, a significant increase in VTE incidence was observed in patients with a CRS of ≥5. In most specialties thresholds of ≥7, ≥9, and ≥11 to 12 were associated with dramatically increased incidences of VTE. In COVID-19, cancer, trauma, vascular, general, head and neck, and thoracic surgery patients with ≥9 and ≥11 to 12 scores the VTE incidence was extremely high (ranging from 13% to 47%).

CONCLUSION

The Caprini score is being used increasingly to predict VTE in many medical and surgical specialties. In most cases, the VTE risk for individual patients increases dramatically at a threshold CRS of 7 to 11.

Construction and Verification of Risk Predicting Models to Evaluate the Possibility of Venous Thromboembolism After Robot-Assisted Radical Prostatectomy

Background

Venous thromboembolism (VTE) is the second leading cause for death of radical prostatectomy. We aimed to establish new nomogram to predict the VTE risk after robot-assisted radical prostatectomy (RARP).

Methods

Patients receiving RARP in our center from November 2015 to June 2021, were enrolled in study. They were randomly divided into training and testing cohorts by 8:2. Univariate and multivariate logistic regression (model A) and stepwise logistic regression (model B) were used to fit two models. The net reclassification improvement (NRI), integrated discrimination improvement (IDI), and receiver operating characteristic (ROC) curve were used to compare predictive abilities of two new models with widely used Caprini risk assessment (CRA) model. Then, two nomograms were constructed and received internal validation.

Results

Totally, 351 patients were included. The area under ROC of model A and model B were 0.967 (95% confidence interval: 0.945–0.990) and 0.978 (95% confidence interval: 0.960–0.996), which also were assayed in the testing cohorts. Both the prediction and classification abilities of the two new models were superior to CRA model (NRI > 0, IDI > 0, p < 0.05). The C-index of Model A and Model B were 0.968 and 0.978, respectively. For clinical usefulness, the two new models offered a net benefit with threshold probability between 0.08 and 1 in decision curve analysis, suggesting the two new models predict VTE events more accurately.

Conclusions

Both two new models have good prediction accuracy and are superior to CRA model. Model A has an advantage of less variable. This easy-to-use model enables rapid clinical decision-making and early intervention in high-risk groups, which ultimately benefit patients.

Supplementary Information

The online version contains supplementary material available at 10.1245/s10434-022-11574-5.

Predicting the occurrence of venous thromboembolism: construction and verification of risk warning model

Background

The onset of venous thromboembolism is insidious and the prognosis is poor. In this study, we aimed to construct a VTE risk warning model and testified its clinical application value.

Methods

Preliminary construction of the VTE risk warning model was carried out according to the independent risk warning indicators of VTE screened by Logistic regression analysis. The truncated value of screening VTE was obtained and the model was evaluated. ROC curve analysis was used to compare the test of Caprini risk assessment scale and VTE risk warning model. The cut-off value of the VTE risk warning model was used to evaluate the test effectiveness of the model for VTE patients with validation data set.

Results

The VTE risk warning model is p = e^x / (1+ e^x), x = − 4.840 + 2.557 • X₁₀₍₁₎ + 1.432 • X₁₄₍₁₎ + 2.977 • X₁₅₍₁₎ + 3.445 • X₁₈₍₁₎ + 1.086 • X₂₅₍₁₎ + 0.249 • X₃₄ + 0.282 • X₄₁. ROC curve results show that: AUC (95%CI), cutoff value, sensitivity, specificity, accuracy, Youden index, Caprini risk assessment scale is 0.596 (0.552, 0.638), 5, 26.07, 96.50, 61.3%, 0.226, VTE risk warning model is 0.960 (0.940, 0.976), 0.438, 92.61, 91.83, 92.2%, 0.844, respectively, with statistically significant differences (Z = 14.521, P < 0.0001). The accuracy and Youden index of VTE screening using VTE risk warning model were 81.8 and 62.5%, respectively.

Conclusions

VTE risk warning model had high accuracy in predicting VTE occurrence in hospitalized patients. Its test performance was better than Caprini risk assessment scale. It also had high test performance in external population.