Comparison of 2013 and 2009 versions of Caprini risk assessment models for predicting VTE in Chinese cancer patients: a retrospective study

Shang, Meimei; Yan, Rong; Wang, Xingli; Gong, Weipeng; Guo, Zhenqing

doi:10.1007/s11239-020-02038-2

Cited by 15 publications

(14 citation statements)

References 25 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Kawaler et al 22 used information automatically elicited from EHRs in combination with the genetic data of patients to predict the post-hospitalisation risk of DVT and PTE among 720 patients from different inpatient departments. Their results indicated that the learned models had higher AUC values than the conventional Sanofi 30 and Chicago 31 risk assessment questionnaires and achieved a high prediction accuracy despite the lack of prior knowledge about relevant risk factors.…”

Section: Discussionmentioning

confidence: 99%

Artificial Intelligence-Based Prediction of Lower Extremity Deep Vein Thrombosis Risk After Knee/Hip Arthroplasty

Wang

Geng

et al. 2023

Clin Appl Thromb Hemost

View full text Add to dashboard Cite

Deep vein thrombosis (DVT) is a common postoperative complication of knee/hip arthroplasty. There is a continued need for artificial intelligence-based methods of predicting lower extremity DVT risk after knee/hip arthroplasty. In this study, we performed a retrospective study to analyse the data from patients who underwent primary knee/hip arthroplasty between January 2017 and December 2021 with postoperative bilateral lower extremity venous ultrasonography. Patients’ features were extracted from electronic health records (EHRs) and assigned to the training (80%) and test (20%) datasets using six models: eXtreme gradient boosting, random forest, support vector machines, logistic regression, ensemble, and backpropagation neural network. The Caprini score was calculated according to the Caprini score measurement scale, and the corresponding optimal cut-off Caprini score was calculated according to the largest Youden index. In total, 6897 cases of knee/hip arthroplasty were included (average age, 65.5 ± 8.9 years; 1702 men), among which 1161 (16.8%) were positive and 5736 (83.2%) were negative for deep vein thrombosis. Among the six models, the ensemble model had the highest area under the curve [0.9206 (0.8956, 0.9364)], with a sensitivity, specificity, positive predictive value, negative predictive value, and F1 score of 0.8027, 0.9059, 0.6100, 0.9573 and 0.7003, respectively. The corresponding optimal cut-off Caprini score was 10, with an area under the curve, sensitivity, specificity, positive predictive value, and negative predictive values of 0.5703, 0.8915, 0.2491, 0.1937, 0.9191, and 0.3183, respectively. In conclusion, machine learning models based on EHRs can help predict the risk of deep vein thrombosis after knee/hip arthroplasty.

show abstract

Section: Discussionmentioning

confidence: 99%

Artificial Intelligence-Based Prediction of Lower Extremity Deep Vein Thrombosis Risk After Knee/Hip Arthroplasty

Wang

Geng

et al. 2023

Clin Appl Thromb Hemost

View full text Add to dashboard Cite

show abstract

“…19,20 The best performance (AUCs) for the RAMs were obtained in studies with modest numbers of high-risk patients, often fewer than1,000. [21][22][23] The two RAMs have also been compared previously 5,20,[23][24][25][26][27] , with the Caprini RAM showing better prediction for mortality, 20 and a higher AUC to predict VTE (0.77 vs. 0.62 for Padua RAM, p<0.05). 24 Conversely, an analysis of acutely ill medical patients reported low predictive abilities from both, the Caprini (AUC=0.60) and Padua (AUC=0.64) RAMs.…”

Section: Discussionmentioning

confidence: 99%

Ability of Caprini and Padua Risk-Assessment Models to Predict Venous Thromboembolism in a Nationwide Study

Hayssen

Sahoo

Nguyen

et al. 2023

Preprint

View full text Add to dashboard Cite

Background: Venous thromboembolism (VTE) is a preventable complication of hospitalization. Risk-stratification is the cornerstone of prevention. The Caprini and Padua are the most commonly used risk-assessment models to quantify VTE risk. Both models perform well in select, high-risk cohorts. While VTE risk-stratification is recommended for all hospital admissions, few studies have evaluated the models in a large, unselected cohort of patients. Methods: We analyzed consecutive first hospital admissions of 1,252,460 unique surgical and non-surgical patients to 1,298 VA facilities nationwide between January 2016 and December 2021. Caprini and Padua scores were generated using the VA's national data repository. We first assessed the ability of the two RAMs to predict VTE within 90 days of admission. In secondary analyses, we evaluated prediction at 30 and 60 days, in surgical versus non-surgical patients, after excluding patients with upper extremity DVT, in patients hospitalized {greater than or equal to}72 hours, after including all-cause mortality in the composite outcome, and after accounting for prophylaxis in the predictive model. We used area under the receiver-operating characteristic curves (AUC) as the metric of prediction. Results: A total of 330,388 (26.4%) surgical and 922,072 (73.6%) non-surgical consecutively hospitalized patients (total n=1,252,460) were analyzed. Caprini scores ranged from 0-28 (median, interquartile range: 4, 3-6); Padua scores ranged from 0-13 (1, 1-3). The RAMs showed good calibration and higher scores were associated with higher VTE rates. VTE developed in 35,557 patients (2.8%) within 90 days of admission. The ability of both models to predict 90-day VTE was low (AUCs: Caprini 0.56 [95% CI 0.56-0.56], Padua 0.59 [0.58-0.59]). Prediction remained low for surgical (Caprini 0.54 [0.53-0.54], Padua 0.56 [0.56-0.57]) and non-surgical patients (Caprini 0.59 [0.58-0.59], Padua 0.59 [0.59-0.60]). There was no clinically meaningful change in predictive performance in patients admitted for {greater than or equal to}72 hours, after excluding upper extremity DVT from the outcome, after including all-cause mortality in the outcome, or after accounting for ongoing VTE prophylaxis. Conclusions: Caprini and Padua risk-assessment model scores have low ability to predict VTE events in a cohort of unselected consecutive hospitalizations. Improved VTE risk-assessment models must be developed before they can be applied to a general hospital population.

show abstract

“…In our study, the Caprini RAM showed a better predictive ability and accuracy than PPS. Caprini RAM had been validated e ciently in more than 200 studies, especially for surgical patients [15,27,28]. The better prediction performance of Caprini RAM was attributed mostly to the comprehensive risk factors it incorporated.…”

Section: Discussionmentioning

confidence: 99%

“…At present, the PPS still lacks of external validation in Chinese population currently, whereas the Caprini RAM has been validated effectively in hospitalized patients of internal medicine [5,14,15]. Several casecontrol studies in China have compared the capabilities of Caprini RAM and the PPS in medical and surgical inpatients to evaluate which model can predict VTE risk better.…”

Section: Introductionmentioning

confidence: 99%

“…Caprini RAM was developed based on expert consensus and clinical experience, consisted of 39 independent VTE risk factors that were given 1 to 5 points each and used a point-scoring system [12]. It was suggested for the 9th edition of the ACCP guidelines that the Caprini RAM was used to assess the VTE risk in non-orthopedic surgical patients [13,14] .At present, the PPS still lacks of external validation in Chinese population currently, whereas the Caprini RAM has been validated effectively in hospitalized patients of internal medicine [5,14,15]. Several casecontrol studies in China have compared the capabilities of Caprini RAM and the PPS in medical and surgical inpatients to evaluate which model can predict VTE risk better.…”

mentioning

confidence: 99%

See 1 more Smart Citation

Padua Prediction Score was Inappropriate for Venous Thromboembolism Risk Assessment in Acute Medical Inpatients: A Cohort Study

Yang

Zhang

Jiao

et al. 2022

Preprint

View full text Add to dashboard Cite

Background Padua Prediction Score (PPS) still lacks of effectively external validation in Chinese population. To assess the accuracy of PPS to predict venous thromboembolism (VTE) risk in acute medical inpatients, and to compare the predictive value with Caprini risk assessment model (RAM). Methods This consecutive cohort study included acute internal medicine inpatients in Beijing Institute of Respiratory Medicine, Beijing, China from January to August 2019. The PPS and Caprini RAM were assessed for all the patients. The occurrence rate of VTE predicted by PPS and Caprini RAM was compared using Chi-squared test. Discrimination was evaluated by the area under curve using the Delong tests. Reclassification parameters were also used to compare the PPS's clinical utility with that of the Caprini RAM. Results: A total of 1647 inpatients of internal medicine were retrospectively registered. The overall incidence of VTE during hospitalization was 13.2%. The incidence of VTE in low-risk patients was 6.5% assessed by PPS, which was significantly higher than that by Caprini RAM (2.6%, p < 0.001). The area under the receiver operating characteristic curve (ROC) for PPS and Caprini RAM was 0.747 (95%CI, 0.725–0.768) and 0.773 (95%CI, 0.752–0.793), respectively (p = 0.0453). Based on the best cut-off, the specificity of the PPS appeared higher than that of the Caprini RAM (82.45 vs 60.07, p < 0.001), but its sensitivity was lower (59.45 vs 83.87, p < 0.001). Compared with Caprini RAM, the net reclassification index was estimated at 0.094 (p = 0.016) and integrated discrimination improvement was 0.037 (p = 0.098) by PPS. The ROC curve of the Caprini RAM and PPS in the subgroup of patients without pharmacological prophylaxis during their hospitalization was 0.776 of the Caprini RAM, which was significantly higher than that of the PPS (p = 0.005). Conclusions PPS seems inappropriately to predict VTE risk in acute internal medicine inpatients. It has limitations not only in the performance of identifying “VTE high-risk” patients, but also in the ability of discrimination. An accurate, widely applicable, validated RAM for prediction of the VTE risk needs to be further constructed in Chinese hospitalized medical patients.

show abstract

Comparison of 2013 and 2009 versions of Caprini risk assessment models for predicting VTE in Chinese cancer patients: a retrospective study

Cited by 15 publications

References 25 publications

Artificial Intelligence-Based Prediction of Lower Extremity Deep Vein Thrombosis Risk After Knee/Hip Arthroplasty

Artificial Intelligence-Based Prediction of Lower Extremity Deep Vein Thrombosis Risk After Knee/Hip Arthroplasty

Ability of Caprini and Padua Risk-Assessment Models to Predict Venous Thromboembolism in a Nationwide Study

Padua Prediction Score was Inappropriate for Venous Thromboembolism Risk Assessment in Acute Medical Inpatients: A Cohort Study

Contact Info

Product

Resources

About