Performance of PRECISE-DAPT and Age-Bleeding-Organ Dysfunction Score for Predicting Bleeding Complication During Dual Antiplatelet Therapy in Chinese Elderly Patients

Abstract

Background: Recently, the Age-Bleeding-Organ Dysfunction (ABO) algorithm was recommended by the Asian Pacific Society of Cardiology Consensus as a binary approach to evaluate bleeding risk. This analysis made comparison of the predictive performances between the PRECISE-DAPT and ABO bleeding score in identifying the risk of 12-months major bleeding in Chinese elderly patients over 65 years old patients who underwent percutaneous coronary intervention (PCI) during dual-antiplatelet therapy period.

Methods: A total of 2,037 elderly coronary artery disease (CAD) patients (≥65 years) receiving dual antiplatelet therapy (DAPT) after PCI were enrolled in the study. The predictive accuracy of the two bleeding risk scores (PRECISE-DAPT and ABO) was compared for identifying the risk of bleeding during the dual-antiplatelet therapy in patients who underwent PCI. Major clinically relevant bleeding events were defined according to the Bleeding Academic Research Consortium (BARC) criteria.

Results: The PRECISE-DAPT score in the no bleeding, BARC = 1 bleeding, BARC ≥ 2 bleeding patients was 23.55 ± 10.46, 23.23 ± 10.03, and 33.54 ± 14.33 (p < 0.001), respectively. Meanwhile, the ABO score in the three groups was 0.72 ± 0.80, 0.69 ± 0.81, and 1.49 ± 0.99 (p < 0.001), respectively. The C-statistic of the PRECISE-DAPT model for prediction of BARC ≥ 2 bleeding in overall patients was 0.717 (95% CI, 0.656-0.777) and 0.720 (95% CI, 0.656-0.784) in acute coronary syndrome (ACS) patients. Similar discriminatory capacity was demonstrated in the ABO risk score [overall, patients, AUC: 0.712 (95% CI, 0.650-0.774); ACS patients, AUC: 0.703 (95% CI, 0.634-0.772)]. No differences were observed when the ABO model was in comparison with the PRECISE-DAPT model, regardless in overall patients (z = -0.199, p = 0.842) or ACS patients (z = -0.605, p = 0.545). The calibration for BARC ≥ 2 bleeding of the PRECISE-DAPT and ABO score were acceptable, regardless in overall patients [goodness-of-fit (GOF) Chi-square = 0.432 and 0.001, respectively; p-value = 0.806 and 0.999, respectively] or ACS patients (GOF Chi-square = 0.008 and 0.580, respectively; p-value = 0.996 and 0.748, respectively).

Conclusion: No matter of clinical presentation in Asian 65-years older patients with DAPT, the PRECISE-DAPT, and ABO scores had the similar discriminative ability for 12-months BARC ≥ 2 bleeding. Considering the simplicity and reliability, the PRECISE-DAPT score might be more clinically applicable in the overall population and ACS patients in bleeding prediction.

Keywords: ABO score; PRECISE-DAPT; bleeding risk scores; dual-antiplatelet therapy; percutaneous coronary intervention.

FIGURE 1

The details of the clinically relevant bleeding types after PCI. Clinically relevant bleeding complications (BARC = type 2–5, excluding BARC 4) including 22 (30%) cases of gastrointestinal hemorrhage, 8 (11%) cases of cerebral hemorrhage, 9 (13%) cases of urinary tract hemorrhage, 25 (34%) cases of skin and mucous membrane hemorrhage, and 9 (12%) cases of pulmonary hemorrhage.

FIGURE 2

The performance of receiver operating characteristic (ROC) curve and calibration plot for PRECISE-DAPT and ABO risk score systems in overall patients with 1-year DAPT after PCI. (A) ROC curve for the prediction of BARC ≥ 2 type bleeding events by PRECISE-DAPT and ABO risk score systems in overall patients with 1-year DAPT after PCI [AUC: 0.717 and 0.712, respectively; (95% CI, 0.656–0.777)and (95% CI, 0.650–0.774), respectively; p < 0.001]. The C-statistics for the two risk models were compared to each other by the DeLong test (z = –0.199, p = 0.842). (B) The calibration plot for PRECISE-DAPT risk score in overall patients (GOF Chi-square = 0.432, p-value = 0.806). (C) The calibration plot for ABO risk score in overall patients (GOF Chi-square = 0.001 p-value = 0.999).

FIGURE 3

The performance of ROC curve and calibration plot for PRECISE-DAPT and ABO risk score systems in ACS patients with 1-year DAPT after PCI. (A) ROC curve for the prediction of BARC ≥ 2 type bleeding events by PRECISE-DAPT and ABO risk score systems in ACS patients with 1-year DAPT after PCI [AUC: 0.720 and 0.703, respectively; (95% CI, 0.656–0.784) and (95% CI, 0.634–0.772), respectively; p < 0.001]. The C-statistics for the two risk models were compared to each other by the DeLong test (z = –0.605, p = 0.545). (B) The calibration plot for the PRECISE-DAPT risk score in ACS patients (GOF Chi-square = 0.008, p-value = 0.996). (C) The calibration plot for the ABO risk score in ACS patients (GOF Chi-square = 0.580 p-value = 0.748).

FIGURE 4

Receiver operating characteristic curve for the prediction of BARC = 3 or 5 type bleeding events by PRECISE-DAPT and ABO risk score systems in overall patients with 1-year DAPT after PCI [AUC: 0.655 and 0.625, respectively; (95% CI, 0.486–0.823) and (95% CI, 0.428–0.823), respectively; p = 0.076 and p = 0.152, respectively). The C-statistics for the two risk models were compared to each other by the DeLong test (z = –0.427, p = 0.670).