Machine learning-based prediction of the post-thrombotic syndrome: Model development and validation study

Yu, Tao; Shen, Runnan; You, Guochang; Li, Lin; Kang, Shimao; Wang, Xiaoyan; Xu, Jiatang; Zhu, Dongxi; Xia, Zuqi; Zheng, Junmeng

doi:10.3389/fcvm.2022.990788

Cited by 8 publications

(14 citation statements)

References 46 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The nding of new biomarkers will provide data for the construction of models for predicting and preventing post-thrombotic syndrome, as is already being built with technology using machine learning models aimed at post-thrombotic syndrome. 29 However, our results cannot be interpreted as a biomarker diagnostic panel, as it would require a greater number of participants in the study to rule out type I statistical error. There are risks of bias inherent to cross-sectional studies and risks of selection bias besides inability to generalize the ndings to different populations at this moment.…”

Section: Discussionmentioning

confidence: 94%

Evaluation of expression of genes associated with post-thrombotic syndrome

Barros,

Herenio,

Maximiano

et al. 2023

Preprint

View full text Add to dashboard Cite

The prediction of post-thrombotic syndrome (PTS) development among patients with deep venous thrombosis (DVT) is currently based on clinical characteristics alone; reliable biomarkers are unavailable. In this study, the expression of myeloperoxidase (MPO), Fms-related tyrosine kinase 4 (FLT4), and coagulation Factor XIII A chain (F13A1) was evaluated to identify novel biomarkers of PTS. F13A1 of the clotting cascade stabilizes the thrombus; MPO interacts with the endothelium; and FLT4 encodes a vascular endothelium-derived growth factor receptor that participates in angiogenesis. This study evaluated nine patients stratified into three different groups. The control group included three healthy patients; the second group included three patients with DVT without PTS (group II); and the third group included three patients with PTS (group III). The expression of MPO, FLT4, and F13A1 was evaluated in the three groups. A significant decrease in FLT4 expression (ΔCt -2.71; gene expression 0.03, p=0.11 in group II; ΔCt -2.44; gene expression 0.01, p=0.05 in group III) and a non-significant difference in MPO gene expression were found among the three groups; however, there was a notable progressive increase in F13A1 expression (ΔCt 6.54; gene expression 3.5, p=0.02). Despite the low sampling rate in the present study, the decreased FLT4expression and increased of F13A1 expression may represent biomarkers of PTS.

show abstract

Section: Discussionmentioning

confidence: 94%

Evaluation of expression of genes associated with post-thrombotic syndrome

Barros,

Herenio,

Maximiano

et al. 2023

Preprint

View full text Add to dashboard Cite

show abstract

“…The c statistic of this model was 0.825 (95% CI: 0.774-0.877), and the c statistic of internal validation and temporal verification were 0.816 and 0.773 respectively (14). The second model was built from 23 clinical variables entered into four machine learning algorithms (15). External validation of this model found an AUROC of 0.83 (95% CI:0.76-0.89) (15).…”

Section: Discussionmentioning

confidence: 97%

“…Two other models were recently developed and seem to have promising accuracy (14,15). The predictors for the first model include ilio-femoral location of index DVT, active cancer, history of chronic venous insufficiency, prior VTE, and chronic kidney disease (14).…”

Section: Discussionmentioning

confidence: 99%

“…The second model was built from 23 clinical variables entered into four machine learning algorithms (15). External validation of this model found an AUROC of 0.83 (95% CI:0.76-0.89) (15). lack of definition of chronic venous insufficiency and chronic kidney disease for the first model and machine learning methods from the second model made impossible assessing and comparing these models in the SAVER dataset.…”

Section: Discussionmentioning

confidence: 99%

“…Two other models were recently developed and seem to have promising accuracy. 14 15 The predictors for the first model include ilio-femoral location of index DVT, active cancer, history of chronic venous insufficiency, prior VTE, and chronic kidney disease. 14 The c-statistic of this model was 0.825 (95% CI: 0.774–0.877), and the c-statistic values of internal validation and temporal verification were 0.816 and 0.773, respectively.…”

Section: Discussionmentioning

confidence: 99%

See 2 more Smart Citations

Performance and Head-to-Head Comparison of Three Clinical Models to Predict Occurrence of Postthrombotic Syndrome: A Validation Study

et al. 2023

View full text Add to dashboard Cite

Objective: The SOX-PTS, Amin, and Méan models are three different clinical prediction scores stratifying the risk for post-thrombotic syndrome (PTS) development in patients with acute deep vein thrombosis (DVT) of the lower limbs. Herein, we aimed to assess and compare these scores in the same cohort of patients. Methods: We retrospectively applied the three scores in a cohort of 181 patients (196 limbs) who participated in the SAVER pilot trial for an acute DVT. Patients were stratified into PTS-risk groups using positivity thresholds for high-risk patients as proposed in the derivation studies. All patients were assessed for PTS 6 months after index DVT using the Villalta scale. We calculated the predictive accuracy for PTS and area under receiver operating characteristic (AUROC) curve for each model. Results: The Méan model was the most sensitive (Sensitivity 87.7%; 95% CI: 77.2-94.5) with the highest negative predictive value (87.5%; 95% CI: 76.8-94.4) for PTS. The SOX-PTS was the most specific score (Specificity 97.5 %; 95% CI: 92.7-99.5) with the highest positive predictive value (72.7%; 95% CI: 39.0-94.0). The SOX-PTS and Méan models performed well for PTS prediction (AUROC 0.72; 95% CI: 0.65-0.80 and 0.74; 95% CI: 0.67-0.82), whereas the Amin model did not (AUROC 0.58; 95% CI: 0.49-0.67). Conclusions: Our data support the SOX-PTS and Méan models have good accuracy to stratify the risk for PTS.

show abstract

Unsupervised and Supervised Machine Learning to Identify Variability of Tumor-Educated Platelets and Association with Pan-Cancer: A Cross-National Study

Chen,

Shen,

et al. 2023

Fundamental Research

View full text Add to dashboard Cite

Machine learning-based prediction of the post-thrombotic syndrome: Model development and validation study

Abstract: and Huang K (2022) Machine learning-based prediction of the post-thrombotic syndrome: Model development and validation study.

Cited by 8 publications

References 46 publications

Evaluation of expression of genes associated with post-thrombotic syndrome

Evaluation of expression of genes associated with post-thrombotic syndrome

Performance and Head-to-Head Comparison of Three Clinical Models to Predict Occurrence of Postthrombotic Syndrome: A Validation Study

Unsupervised and Supervised Machine Learning to Identify Variability of Tumor-Educated Platelets and Association with Pan-Cancer: A Cross-National Study

Contact Info

Product

Resources

About