Identification of clinical factors predicting warfarin sensitivity after cardiac surgery

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

BACKGROUND

Distinguishing warfarin-related bleeding risk at the bedside remains challenging. Studies indicate that warfarin therapy should be suspended when international normalized ratio (INR) ≥ 4.5, or it may sharply increase the risk of bleeding. We aim to develop and validate a model to predict the high bleeding risk in valve replacement patients during hospitalization.

METHOD

Cardiac valve replacement patients from January 2016 to December 2021 across Nanjing First Hospital were collected. Five different machine-learning (ML) models were used to establish the prediction model. High bleeding risk was an INR ≥4.5. The area under the receiver operating characteristic curve (AUC) was used for evaluating the prediction performance of different models. The SHapley Additive exPlanations (SHAP) was used for interpreting the model. We also compared ML with ATRIA score and ORBIT score.

RESULTS

A total of 2376 patients were finally enrolled in this model, 131 (5.5%) of whom experienced the high bleeding risk after anticoagulation therapy of warfarin during hospitalization. The extreme gradient boosting (XGBoost) exhibited the best overall prediction performance (AUC: 0.882, confidence interval [CI] 0.817-0.946, Brier score, 0.158) compared to other prediction models. It also shows superior performance compared with ATRIA score and ORBIT score. The top 5 most influential features in XGBoost model were platelet, thyroid stimulation hormone, body surface area, serum creatinine and white blood cell.

CONCLUSION

A model for predicting high bleeding risk in valve replacement patients who treated with warfarin during hospitalization was successfully developed by using machine learning, which may well assist clinicians to identify patients at high risk of bleeding and allow timely adjust therapeutic strategies in evaluating individual patient.

Evaluation of Machine Learning Approaches for Predicting Warfarin Discharge Dose in Cardiac Surgery Patients: Retrospective Algorithm Development and Validation Study

BACKGROUND

Warfarin dosing in cardiac surgery patients is complicated by a heightened sensitivity to the drug, predisposing patients to adverse events. Predictive algorithms are therefore needed to guide warfarin dosing in cardiac surgery patients.

OBJECTIVE

This study aimed to develop and validate an algorithm for predicting the warfarin dose needed to attain a therapeutic international normalized ratio (INR) at the time of discharge in cardiac surgery patients.

METHODS

We abstracted variables influencing warfarin dosage from the records of 1031 encounters initiating warfarin between April 1, 2011, and November 29, 2019, at St Michael's Hospital in Toronto, Ontario, Canada. We compared the performance of penalized linear regression, k-nearest neighbors, random forest regression, gradient boosting, multivariate adaptive regression splines, and an ensemble model combining the predictions of the 5 regression models. We developed and validated separate models for predicting the warfarin dose required for achieving a discharge INR of 2.0-3.0 in patients undergoing all forms of cardiac surgery except mechanical mitral valve replacement and a discharge INR of 2.5-3.5 in patients receiving a mechanical mitral valve replacement. For the former, we selected 80% of encounters (n=780) who had initiated warfarin during their hospital admission and had achieved a target INR of 2.0-3.0 at the time of discharge as the training cohort. Following 10-fold cross-validation, model accuracy was evaluated in a test cohort comprised solely of cardiac surgery patients. For patients requiring a target INR of 2.5-3.5 (n=165), we used leave-p-out cross-validation (p=3 observations) to estimate model performance. For each approach, we determined the mean absolute error (MAE) and the proportion of predictions within 20% of the true warfarin dose. We retrospectively evaluated the best-performing algorithm in clinical practice by comparing the proportion of cardiovascular surgery patients discharged with a therapeutic INR before (April 2011 and July 2019) and following (September 2021 and May 2, 2022) its implementation in routine care.

RESULTS

Random forest regression was the best-performing model for patients with a target INR of 2.0-3.0, an MAE of 1.13 mg, and 39.5% of predictions of falling within 20% of the actual therapeutic discharge dose. For patients with a target INR of 2.5-3.5, the ensemble model performed best, with an MAE of 1.11 mg and 43.6% of predictions being within 20% of the actual therapeutic discharge dose. The proportion of cardiovascular surgery patients discharged with a therapeutic INR before and following implementation of these algorithms in clinical practice was 47.5% (305/641) and 61.1% (11/18), respectively.

CONCLUSIONS

Machine learning algorithms based on routinely available clinical data can help guide initial warfarin dosing in cardiac surgery patients and optimize the postsurgical anticoagulation of these patients.

Effect of Early Amiodarone Use on Warfarin Sensitivity, Blood Product Use, and Bleeding in Patients With a Left Ventricular Assist Device

Data are scarce on the effect of amiodarone on warfarin sensitivity and related outcomes after placement of a left ventricular assist device (VAD). This retrospective study compared 30-day outcomes between patients on amiodarone vs no amiodarone after VAD implant. After exclusions, 220 patients received amiodarone and 136 patients did not. Compared to the no amiodarone group, the amiodarone group had a higher warfarin dosing index (0.53 [0.39, 0.79] vs 0.46 [0.34, 0.63]; P = 0.003), incidence of INR ≥ 4 (40.5 vs 23.5%; P = 0.001), incidence of bleeding (24.1 vs 14%; P = 0.021), and use of INR reversal agents (14.5 vs 2.9%, P ≤ 0.001). Amiodarone was associated with bleeding (OR, 1.95; 95% CI, 1.10-3.47; P = 0.022), but not after adjusting for age, estimated glomerular filtration rate, and platelet count (OR, 1.67; 95% CI, 0.92-3.03; P = 0.089). After VAD implant, amiodarone was associated with increased warfarin sensitivity and administration of INR reversal agents.

AM Versus PM Postoperative Administration of Warfarin With a Mechanical Mitral Valve

Background: Currently, there are no guidelines regarding the optimal daily timing of inpatient warfarin administration. Objective: The purpose of this study was to determine whether dosing warfarin in the morning will have a significant impact on therapeutic international normalized ratio (INR) achievement compared with evening administration in mechanical mitral valve patients initiated on warfarin following cardiac surgery. Methods: This was a single-center, pre- and post-retrospective cohort conducted between 2014 and 2018. One-hundred fifty-four adult patients who underwent a mechanical mitral valve replacement or alternative cardiac surgery with a history of a mechanical mitral valve were enrolled. The primary outcome was achievement of therapeutic INR at any time point after initiation of warfarin. Pre-intervention administration timing was 6 pm and post-intervention timing was 10 am. Results: Baseline characteristics including age, sex, and race were similar between the 2 groups (P = NS for each characteristic). Therapeutic INR achievement was significantly improved at all time points following 10 am warfarin administration compared with 6 pm (hazard ratio = 1.69; P = .005). Mean time-to-therapeutic INR was 7.37 days in the post-intervention group and 8.39 days in the pre-intervention group (P = .073). There were no significant differences in INR >4, bleeding, or thrombotic complications between groups. Conclusion and Relevance: This retrospective analysis suggests that there may be a postoperative benefit in therapeutic INR achievement in mechanical valve patients when dosing warfarin in the morning compared with evening administration. Large-scale studies should be conducted to further elucidate the potential benefit across more heterogeneous populations.