Search Results (2)

Background: Warfarin pharmacogenomics is critical due to its narrow therapeutic index and significant interpatient variability. While machine learning (ML) can predict anticoagulation control status (ACS), its “black-box” nature limits clinical translatability. Explainable Artificial Intelligence (XAI) addresses this by providing interpretable insights. This study applied ML and XAI to a warfarin pharmacogenomic dataset to predict poor ACS and explain model decisions. Methods: A post hoc analysis was conducted on a cross-sectional dataset of 232 patients receiving warfarin for ≥6 months. Data included age, gender, interacting drugs, SAMe-TT2R2 score, and genotypes for CYP2C9, VKORC1, and CYP4F2. Poor ACS was defined as time in therapeutic range (TTR) < 70%. The dataset was split into training (70%) and testing (30%) cohorts. Three models, Random Forest, XGBoost, and Logistic Regression, were developed and evaluated using AUC-ROC, sensitivity, and specificity. XAI techniques, including permutation importance and SHapley Additive exPlanations (SHAP), were employed for global and local interpretability. Results: Of 232 patients, 141 (60.8%) had poor ACS. XGBoost and Random Forest demonstrated comparable predictive accuracy (AUC-ROC: 0.67), outperforming Logistic Regression. Sensitivity was 0.83 and 0.79 for XGBoost and Random Forest, respectively. However, specificity was modest for both ensemble methods (Random Forest: 0.48; XGBoost: 0.41) and extremely low for Logistic Regression (0.04), indicating poor discrimination, particularly for identifying patients with adequate anticoagulation control. Globally, important predictors included the age, SAMe-TT2R2 score, CYP2C9 (*2/*2), female gender, and VKORC1 (C/T). XAI revealed predictions were primarily driven by VKORC1, CYP4F2, SAMe-TT2R2 scores, and drug interactions. Concordance between XAI predictions and actual ACS was 78% for adequate and 88.6% for poor ACS. SHAP analysis showed VKORC1 provided a stable risk signal (mean absolute SHAP: 1.44 ± 0.49 in concordant cases), while CYP2C9 was a high-variance, high-impact driver of discordance (mean SHAP: 3.44 ± 3.79 in discordant cases). Conclusions: ML models, particularly ensemble methods, show modest ability to predict poor warfarin control with limited ability to correctly identify patients with adequate control from our dataset. XAI transforms these models into interpretable tools, with SHAP analysis attributing predictions to specific genetic and clinical features. While predictive accuracy remains modest, this approach enhances transparency and provides a foundation for generating hypotheses that may ultimately support clinical decision-making in pharmacogenomic-guided warfarin therapy. Full article

Background: Warfarin requires regular monitoring with the time in therapeutic range (TTR), a common indicator of control and TTR > 70% is indicative of efficient anticoagulation. The SAMe-TT₂R₂ (sex, age, medical history, treatment, tobacco use, race) model has been utilised as a predictor of warfarin control, with a score ≥ 2 indicative of poor control. However, it has been suggested that race may be over-represented in this model. To date, no Australian studies have applied this model, possibly because race is not routinely recorded. Therefore, the aim of this study was to apply the SAMe-TT₂R₂ model in an Australian population on warfarin managed by both a warfarin care program (WCP) and general practitioner (GP). Methods: Retrospective data was collected for patients receiving warfarin via a WCP in Queensland and whilst being managed by a GP. Patient data was used to calculate the SAMe-TT₂R₂ score and the TTR for each patient. Mean TTR was used for analysis and comparison with the categorised SAMe-TT₂R₂ score. Results: Of the 3911 patients managed by a WCP, there was a significantly lower mean TTR for patients with a SAMe-TT₂R₂ score ≥ 2 compared to 0–1 (78.6 ± 10.7% vs. 80.9 ± 9.5%, p < 0.0001). Of these patients, 200 were analysed whilst managed by a GP and the categorised SAMe-TT₂R₂ score did not result in a statistically different mean TTR (69.3 ± 16.3% with 0–1 vs. 63.6 ± 15.0% with ≥2, p = 0.089), but a score ≥2 differentiated patients with a TTR less than 65%. Conclusions: The SAMe-TT₂R₂ model differentiated Australian patients with reduced warfarin control, despite the exclusion of race. In Australia, the SAMe-TT₂R₂ score could assist clinicians in identifying Australian patients who may obtain reduced warfarin control and benefit from additional interventions such as a dedicated WCP. Full article