Prediction of Major Bleeding in Anticoagulated Patients for Venous Thromboembolism: Comparison of the RIETE and the VTE-BLEED Scores

Jiménez, Laura; Ruiz-Artacho, Pedro; Nieto, José Antonio; Ruíz-Giménez, Nuria; Visonà, Adriana; Skride, Andris; Moustafa, Farès; Trujillo, J.; Monreal, Manuel; Investigators, Riete

doi:10.1055/s-0041-1729171

Cited by 7 publications

(3 citation statements)

References 26 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Most of these clinical variables have been identified and validated in the literatuire as independent risk factors for bleeding in patients with VTE. [27][28][29] Interestingly however, only NLR, anemia and renal insufficiency independently predicted the risk for major bleeding. Moreover, both NLR and SII independently predicted the risk of death.…”

Section: Discussionmentioning

confidence: 96%

Cellular Indices and Outcome in Patients with Acute Venous Thromboembolism

Siddiqui

García-Ortega

Kantarcıoğlu

et al. 2022

Clin Appl Thromb Hemost

Self Cite

View full text Add to dashboard Cite

Background Cellular indices provide integrative information about systemic inflammation status which is readily available from routine laboratory parameters. This study aimed to evaluate the prognostic role of three cellular indices in patients with venous thromboembolism (VTE). Methods The RIETE registry database was used to determine the association between the baseline neutrophil-to-lymphocyte-ratio (NLR), platelet-to-lymphocyte-ratio (PLR) and systemic-immune-inflammation-index (SII) for 90-day adverse outcomes in patients with acute VTE. Results From January 2020 to April 2021, 4487 patients with acute VTE were recruited in the RIETE registry. Of these, 2683 presented with symptomatic pulmonary embolism (PE); 283 with incidental PE; 1129 with lower-limb deep vein thrombosis (DVT); 175 with upper-limb DVT; 69 with splanchnic vein thrombosis; 142 with superficial vein thrombosis and 20 with retinal vein thrombosis. Mean values were: NLR 5.9 ± 7.1, PLR 190 ± 158 and SII 1459 ± 2028. During the first 90-days, 38 patients (0.8%) developed recurrent DVT, 45 (1.0%) had recurrent PE, 152 (3.4%) suffered major bleeding, and 484 (11%) died. On multivariable analysis, patients with NLR >4.41 were at an increased risk for major bleeding and patients with NLR >4.96 were at the risk of death, while those with SII >1134.5 were at increased risk for death. Conclusions This study reports the results of a large cohort to date which evaluate the prognostic value of three cellular indices simultaneously in patients with acute VTE. Results support that none of the three baseline cellular indices were sufficient for prediction of VTE recurrences in acute VTE patients. The patients with higher baseline NLR values were at an increased risk of major bleeding or death, those with high SII values were only at an increased risk for mortality.

show abstract

Section: Discussionmentioning

confidence: 96%

Cellular Indices and Outcome in Patients with Acute Venous Thromboembolism

Siddiqui

García-Ortega

Kantarcıoğlu

et al. 2022

Clin Appl Thromb Hemost

Self Cite

View full text Add to dashboard Cite

show abstract

“…This is unsurprising as bleeding history is a component of bleeding risk strati cation tools for other clinical settings such as HAS-BLED, RIETE, and VTE-BLEED. 29,37 Further, this evidenced the importance of evaluating predisposing risk factors to bleeding prior to SSRI prescribing. Socioeconomic status was identi ed as a clinically important feature cluster in the uoxetine cohort and the combined SSRI cohort.…”

Section: Discussionmentioning

confidence: 99%

Using Machine Learning to Develop a Clinical Prediction Model for SSRI-associated bleeding: a feasibility study

Goyal

Zhang

et al. 2023

Preprint

View full text Add to dashboard Cite

Introduction: Adverse drug events (ADEs) are associated with poor outcomes and increased costs but may be prevented with prediction tools. With the National Institute of Health All of Us (AoU) database, we employed machine learning (ML) to predict selective serotonin reuptake inhibitor (SSRI)-associated bleeding. Methods: The AoU program, beginning in 05/2018, continues to recruit ≥18 years old individuals across the United States. Participants completed surveys and consented to contribute electronic health record (EHR) for research. Using the EHR, we determined participants who were exposed to SSRIs (citalopram, escitalopram, fluoxetine, fluvoxamine, paroxetine, sertraline, vortioxetine). Features (n=88) were selected with clinicians’ input and comprised sociodemographic, lifestyle, comorbidities, and medication use information. We identified bleeding events with validated EHR algorithms and applied logistic regression, decision tree, random forest, and extreme gradient boost to predict bleeding during SSRI exposure. We assessed model performance with area under the receiver operating characteristic curve statistic (AUC) and defined clinically significant features as resulting in >0.01 decline in AUC after removal from the model, in three of four ML models. Results: There were 10,362 participants exposed to SSRIs, with 9.6% experiencing a bleeding event during SSRI exposure. For each SSRI, performance across all four ML models was relatively consistent. AUCs from the best models ranged 0.632–0.698. Clinically significant features included health literacy for escitalopram, and bleeding history and socioeconomic status for all SSRIs. Conclusions: We demonstrated feasibility of predicting ADEs using ML. Incorporating genomic features and drug interactions with deep learning models may improve ADEprediction.

show abstract

“…Prior bleeding history was identified as clinically significant in almost all drug cohorts, except escitalopram, although bleeding history remains arguably important as significant changes in AUC were found in two out of its four ML escitalopram models. This is unsurprising as bleeding history is a component of bleeding risk stratification tools for other clinical settings such as HAS-BLED, RIETE, and VTE-BLEED [ 29 , 38 ]. Further, this evidenced the importance of evaluating predisposing risk factors to bleeding prior to SSRI prescribing.…”

Section: Discussionmentioning

confidence: 99%

Using machine learning to develop a clinical prediction model for SSRI-associated bleeding: a feasibility study

Goyal

Zhang

et al. 2023

BMC Med Inform Decis Mak

View full text Add to dashboard Cite

Introduction Adverse drug events (ADEs) are associated with poor outcomes and increased costs but may be prevented with prediction tools. With the National Institute of Health All of Us (AoU) database, we employed machine learning (ML) to predict selective serotonin reuptake inhibitor (SSRI)-associated bleeding. Methods The AoU program, beginning in 05/2018, continues to recruit ≥ 18 years old individuals across the United States. Participants completed surveys and consented to contribute electronic health record (EHR) for research. Using the EHR, we determined participants who were exposed to SSRIs (citalopram, escitalopram, fluoxetine, fluvoxamine, paroxetine, sertraline, vortioxetine). Features (n = 88) were selected with clinicians’ input and comprised sociodemographic, lifestyle, comorbidities, and medication use information. We identified bleeding events with validated EHR algorithms and applied logistic regression, decision tree, random forest, and extreme gradient boost to predict bleeding during SSRI exposure. We assessed model performance with area under the receiver operating characteristic curve statistic (AUC) and defined clinically significant features as resulting in > 0.01 decline in AUC after removal from the model, in three of four ML models. Results There were 10,362 participants exposed to SSRIs, with 9.6% experiencing a bleeding event during SSRI exposure. For each SSRI, performance across all four ML models was relatively consistent. AUCs from the best models ranged 0.632–0.698. Clinically significant features included health literacy for escitalopram, and bleeding history and socioeconomic status for all SSRIs. Conclusions We demonstrated feasibility of predicting ADEs using ML. Incorporating genomic features and drug interactions with deep learning models may improve ADE prediction.

show abstract

Prediction of Major Bleeding in Anticoagulated Patients for Venous Thromboembolism: Comparison of the RIETE and the VTE-BLEED Scores

Cited by 7 publications

References 26 publications

Cellular Indices and Outcome in Patients with Acute Venous Thromboembolism

Cellular Indices and Outcome in Patients with Acute Venous Thromboembolism

Using Machine Learning to Develop a Clinical Prediction Model for SSRI-associated bleeding: a feasibility study

Using machine learning to develop a clinical prediction model for SSRI-associated bleeding: a feasibility study

Contact Info

Product

Resources

About