Development of a clinical prediction model for an international normalised ratio ≥ 4·5 in hospitalised patients using vitamin K antagonists

Abstract

SummaryVitamin K antagonists (VKAs) used for the prevention and treatment of thromboembolic disease, increase the risk of bleeding complications. We developed and validated a model to predict the risk of an international normalised ratio (INR) ≥ 4·5 during a hospital stay. Adult patients admitted to a tertiary hospital and treated with VKAs between 2006 and 2010 were analysed. Bleeding risk was operationalised as an INR value ≥4·5. Multivariable logistic regression analysis was used to assess the association between potential predictors and an INR ≥ 4·5 and validated in an independent cohort of patients from the same hospital between 2011 and 2014. We identified 8996 admissions of patients treated with VKAs, of which 1507 (17%) involved an INR ≥ 4·5. The final model included the following predictors: gender, age, concomitant medication and several biochemical parameters. Temporal validation showed a c statistic of 0·71. We developed and validated a clinical prediction model for an INR ≥ 4·5 in VKA‐treated patients admitted to our hospital. The model includes factors that are collected during routine care and are extractable from electronic patient records, enabling easy use of this model to predict an increased bleeding risk in clinical practice.

Using machine learning to predict the bleeding risk for patients with cardiac valve replacement treated with warfarin in hospitalized

“…However, there are few studies concerned with the risk of bleeding in hospitalized patients. Albert et al 15 used a logistic regression method for predicting INR ≥4.5 in hospitalized patients that the model was achieved an AUC of 0.71. The study population were taking Vitamin K antagonists which included a variety of indications and the model showed a moderate predictive performance.…”

“…There are several bleeding risk prediction scores have been developed, such as the HAS-BLED (hypertension, abnormal renal/liver function, stroke, bleeding history or predisposition, labile international normalized ratio 13 score, ORBIT (older age [age ≥ 75 years], reduced haemoglobin/haematocrit/history of anaemia, bleeding history, insufficient kidney function, and treatment with antiplatelet) 14 and so on. 15,16 These scores were derived from patients with non-valvular atrial fibrillation (NVAF) and focuses on patients in ambulatory care, or ambulatory and followup patients together. However, the risk factors of bleeding during hospitalization are different from outpatients, they were treated in a various physiological and pathological state.…”

“…However, the risk factors of bleeding during hospitalization are different from outpatients, they were treated in a various physiological and pathological state. 15 Studies have also found that patients are more sensitive to warfarin after valve replacement, 17,18 it means that the therapeutic strategy of AF is different from valve replacement, which requires a lower warfarin dose at initial stage. Hence, existing prediction models may not be suitable for predicting bleeding risk in valve replacement patients during a hospital stay.…”

“…Combing with multifactor might be an excellent strategy to identify patients at high bleeding risk. There are several bleeding risk prediction scores have been developed, such as the HAS‐BLED (hypertension, abnormal renal/liver function, stroke, bleeding history or predisposition, labile international normalized ratio [INR], 11 elderly [age ≥ 65 years], drugs/alcohol concomitantly) score, ABC (age, biomarkers, and clinical history) 12 score, ATRIA (Anticoagulation and Risk Factors in Atrial Fibrillation: anemia, renal disease, elderly [age ≥ 75 years], any prior bleeding, hypertension) 13 score, ORBIT (older age [age ≥ 75 years], reduced haemoglobin/haematocrit/history of anaemia, bleeding history, insufficient kidney function, and treatment with antiplatelet) 14 and so on 15,16 . These scores were derived from patients with non‐valvular atrial fibrillation (NVAF) and focuses on patients in ambulatory care, or ambulatory and follow‐up patients together.…”

“…These scores were derived from patients with non‐valvular atrial fibrillation (NVAF) and focuses on patients in ambulatory care, or ambulatory and follow‐up patients together. However, the risk factors of bleeding during hospitalization are different from outpatients, they were treated in a various physiological and pathological state 15 . Studies have also found that patients are more sensitive to warfarin after valve replacement, 17,18 it means that the therapeutic strategy of AF is different from valve replacement, which requires a lower warfarin dose at initial stage.…”