Transformer-Based Deep Learning Model for Predicting Hemoglobin Response to Mircera® in Hemodialysis Patients

Anemia management in hemodialysis (HD) depends on individualized erythropoiesis-stimulating agent (ESA) dosing to achieve and maintain target hemoglobin (Hgb) levels. However, predicting individual Hgb responses remains a significant challenge due to nonlinear erythropoietic dynamics and patient heterogeneity. Here, we developed a machine learning-based approach to predict individual Hgb response to ESA therapy in HD patients.

We included adult patients undergoing HD at Sanderling clinics who received intravenous (IV) ESA (Mircera®) and IV elemental iron and had ≥ 5 qualifying dosing events with associated post-dose Hgb measurements. Clinical, dialysis, and laboratory data were structured into an event-based dataset, where each event included pre-dose Hgb, contemporaneous Mircera® and iron doses, and follow-up Hgb 7-21 days later. Pharmacokinetically informed features, including cumulative and time-weighted Mircera® dosing were engineered to capture delayed erythropoietic effects. A transformer-based neural network was trained using sequences of five consecutive events. Model performance was assessed using patient-level train-test split, with mean absolute percentage error (MAPE) as the primary metric. The MAPE was calculated as the average absolute percentage error between the predicted future Hgb and the observed future Hgb. To illustrate clinical utility, we conducted simulation-based forecasting of 30-day Hgb trajectories under varying hypothetical Mircera® doses (0-200 µg) in four representative patients. In addition, simulation error was summarized at the cohort level across all eligible patients to assess overall forecasting performance under hypothetical dosing scenarios.

Among 728 HD patients, the mean age was 63 ± 14 years, with dialysis vintage 2.1 ± 1.8 years. Of these 43% were female and 40% had diabetes. Patients received 114± 56 mg/week of IV iron and 149± 92 µg /month of IV Mircera®. Mean Hgb was 10.1 ± 0.9 g/dL, transferrin saturation (TSAT) 31± 10%, and ferritin level of 703± 452 ng/mL. The transformer model predicted future Hgb with a MAPE of ~6.0%. Simulation-based forecasting in representative patients, together with cohort-level summary of simulation error (MAPE 6.29%), demonstrated the model's ability to project individualized Hgb trajectories under varying Mircera® dosing scenarios.

Our results showed the promising performance of a transformer-based machine learning model in predicting future Hgb levels within 6% of observed levels in HD patients being treated with Mircera® and IV iron. These findings suggest the potential for personalized ESA dosing strategies informed by sequential clinical data. Future studies should focus on refining these models and evaluate their real-world clinical utility with the goal of personalized ESA dosing to maximize on-target Hgb levels.