Cookie-Einstellungen
     
 
 
新闻
Thrombosis and Haemostasis | Author Interview 2022-06-12
1647254456249.jpg

Thrombosis and Haemostasis

Author Interview

Stroke, Systemic or Venous Thromboembolism

Bleeding Risk Assessment in End-Stage Kidney Disease: Validation of Existing Risk Scores and Evaluation of a Machine Learning-Based Approach

Stephan NoppClemens P. SpielvogelSabine SchmaldienstRenate Klauser-BraunMatthias LorenzBenedikt N. BauerIngrid PabingerMarcus SäemannOliver KönigsbrüggeCihan Ay

Thromb Haemost
DOI: 10.1055/a-1754-7551

T&H


Why did you (and your colleagues) write this paper? What was its main purpose?

STEPHAN NOPP

When initiating the VIVALDI study in 2014, we wanted to better understand the risk of thromboembolism and bleeding in patients with end-stage kidney disease on hemodialysis. The bleeding rate in these patients has been reported to be high, around 9 per 100 patient-years. However, no valid approach to assess the individual risk of bleeding in this high risk population has been established. Therefore, the main purpose of the work presented in this paper was to improve bleeding risk prediction in this special patient population.

T&H


What are the main conclusions? 

STEPHAN NOPP

Taken together, both currently existing bleeding risk scores, which have been predominantly developed and used in a broader population of patients, and our machine learning-based approach, which incorporated patient demographics, clinical characteristics, and laboratory measurements, failed to predict major bleeding in patients with end-stage kidney disease on hemodialysis. 

T&H


What are the paper's implications? - to the public? -to medical professionals?

STEPHAN NOPP

Patients on hemodialysis are at high risk for bleeding and bleeding risk assessment could guide clinical decision-making with regard to anticoagulation strategies or dialysis treatment modalities. However, no current approach to bleeding risk prediction in hemodialysis patients is reliable and more research effort is needed to better characterize the risk of bleeding in these patients.  

T&H


Are the findings clinically significant? Should the findings change practice? 

STEPHAN NOPP

Patients on hemodialysis represent a unique patient population in which current bleeding risk scores and standard clinical parameters fail to predict the risk of bleeding, unlike in the general non-dialysis population. Importantly, no current approach to bleeding risk prediction in patients on hemodialysis can be recommended to date, and physicians need to generally take the very high bleeding risk in this patient population into account. More work needs to be done to identify risk factors for bleeding in this special patient population at high baseline risk for bleeding to advance the field.