Search research articles

ABOUT JoVE

Overview Leadership Blog JoVE Help Center

AUTHORS

Publishing Process Editorial Board Scope & Policies Peer Review FAQ Submit

LIBRARIANS

Testimonials Subscriptions Access Resources Library Advisory Board FAQ

RESEARCH

JoVE Journal Methods Collections JoVE Encyclopedia of Experiments Archive

EDUCATION

JoVE Core JoVE Business JoVE Science Education JoVE Lab Manual Faculty Resource Center Faculty Site

Terms & Conditions of Use

Search research articles

Related Experiment Video

Updated: Jul 10, 2026

Predicting Treatment Response to Image-Guided Therapies Using Machine Learning: An Example for Trans-Arterial Treatment of Hepatocellular Carcinoma

Predicting Treatment Response to Image-Guided Therapies Using Machine Learning: An Example for Trans-Arterial Treatment of Hepatocellular Carcinoma

Published on: October 10, 2018

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

Siwei Zhao, Yunfei Luo, Joseph Mahaffy

Blood Purification

|July 8, 2026

Summary

This summary is machine-generated.

Related Concept Videos

Hemodialysis I: Introduction

Hemodialysis I: Introduction

Hemodialysis (HD) is a medical treatment that artificially removes waste products, excess fluids, and toxins from the blood when the kidneys are no longer able to perform these functions effectively. In this process, blood is filtered through a semipermeable membrane, allowing for the selective removal of waste while preserving necessary components like blood cells and proteins. Hemodialysis is typically performed in patients with end-stage renal disease (ESRD) or severe kidney...

You might also read

Related Articles

Articles linked to this work by shared authors, journal, and citation graph.

Sort by

Same author

Tuning Chemo- and Regioselectivity by the Noncoordinating Chloro Group in Rh-Catalyzed C-H Active [3+2] Annulation Reactions of Imines and Alkynes.

Organic letters·2026

Same author

Recurrent IgG4 Disease-Related Tubulointerstitial Nephritis Treated With Rituximab As Maintenance Therapy.

Cureus·2026

Same author

Increased Risk of Intraocular Pressure-Lowering Treatment in Patients with End-Stage Renal Disease Undergoing Hemodialysis.

Ophthalmology. Glaucoma·2026

Same author

Benzoxazine-Promoted Copper Catalyst for the Activation of the Benzylic C-O Bond: A Homolytic Cleavage without Light.

Organic letters·2026

Same author

Cutaneous Microvascular Functional Reserve is Associated with Kidney Function and Histopathologic Injury in CKD: The MAP-CKD Study.

medRxiv : the preprint server for health sciences·2026

Same author

Static magnetic fields promote osteogenesis via the lncRNA Gas5/miR-182/PKR molecular axis in rat osteoblasts and femoral defect models.

Connective tissue research·2026

Machine learning accurately predicts hemoglobin (Hgb) response to erythropoiesis-stimulating agent (ESA) therapy in hemodialysis (HD) patients. This approach enables personalized ESA dosing strategies to optimize Hgb levels.

Area of Science:

Artificial Intelligence in Medicine
Machine Learning for Clinical Prediction
Nephrology and Hematology

Background:

Anemia management in hemodialysis (HD) requires precise erythropoiesis-stimulating agent (ESA) dosing for target hemoglobin (Hgb) levels.
Predicting individual Hgb response to ESA is challenging due to complex erythropoietic dynamics and patient variability.
A machine learning (ML) approach was developed to forecast individual Hgb response to ESA therapy in HD patients.

Purpose of the Study:

To develop and validate an ML model for predicting individual Hgb response to ESA therapy in HD patients.
To assess the model's ability to forecast Hgb trajectories under different dosing scenarios.
To explore the potential for personalized ESA dosing strategies using ML-driven predictions.

Main Methods:

Related Experiment Videos

Last Updated: Jul 10, 2026

Predicting Treatment Response to Image-Guided Therapies Using Machine Learning: An Example for Trans-Arterial Treatment of Hepatocellular Carcinoma

Predicting Treatment Response to Image-Guided Therapies Using Machine Learning: An Example for Trans-Arterial Treatment of Hepatocellular Carcinoma

Published on: October 10, 2018

A transformer-based neural network was trained on sequential clinical and laboratory data from HD patients receiving Mircera® and IV iron.
Pharmacokinetically informed features, including cumulative and time-weighted dosing, were engineered to capture delayed effects.
Model performance was evaluated using mean absolute percentage error (MAPE) on a patient-level train-test split, with simulation-based forecasting to demonstrate clinical utility.

Main Results:

The transformer model achieved a mean absolute percentage error (MAPE) of approximately 6.0% in predicting future Hgb levels.
Simulation-based forecasting demonstrated the model's capability to project individualized Hgb trajectories under varying Mircera® doses.
Cohort-level analysis confirmed the model's forecasting performance with a MAPE of 6.29% across hypothetical dosing scenarios.

Conclusions:

A transformer-based ML model shows promising performance in predicting Hgb levels in HD patients treated with Mircera® and IV iron.
The model's accuracy suggests potential for personalized ESA dosing strategies informed by sequential clinical data.
Future research should focus on refining these models and evaluating their real-world clinical utility for optimizing Hgb levels.