Back

Analysis of Risk Factors and the Establishment of a Predictive Model for Thrombosis in Patients with immune thrombocytopenia

Liang, H.; Duan, L.; Long, M.; Tie, S.; Sun, C.; Ma, S.; Wang, J.; Wang, S.

2024-08-22 rheumatology
10.1101/2024.08.21.24312388 medRxiv
Show abstract

ObjectivesTo explore the risk factors for thrombi occurring in patients with immune thrombocytopenia (ITP) and establish a risk prediction model to better predict the risk of thrombosis in patients with ITP. MethodsWe retrospectively analyzed 350 ITP patients who had been hospitalized in The First Peoples Hospital of Yunnan Province between February to June 2024. For all patients, we recorded demographic characteristics and clinical data, analyzed the risk factors for thrombosis in ITP patients and then developed a risk prediction model. ResultsStepwise logistic regression analysis indicated that a high complement D-dimer level, a low PLT and a high Padua score were independent risk factors for thrombosis in ITP patients. According to multivariate analysis, a predictive model for thrombus risk was successfully established; the area under the ROC curve(AUC) was 0.673 (95% CI: 0.615-0.730) and the maximum Youden index, sensitivity and specificity were 0.272, 47.0% and 80.2%, respectively. ConclusionA high complement D-dimer level, low PLT level, and a high Padua score were shown to be independent risk factors for thrombosis in ITP patients. We developed a risk prediction model based on these three risk factors that could predict the risk of thrombosis in ITP patients to some extent.

Matching journals

The top 5 journals account for 50% of the predicted probability mass.

50% of probability mass above

"Similar papers" are the closest papers from that journal in the model's embedding space. They show what the match is built on, but the ranking comes mostly from a classifier over the whole training set, not from these examples alone.