LAPSE:2022.0094
Published Article
LAPSE:2022.0094
Hemoglobin Response Modeling under Erythropoietin Treatment: Physiological Model-Informed Machine Learning Method
Zhongyu Zhang, Zukui Li*
October 21, 2022
Patients with renal anemia (RA) are usually treated with recombinant human erythropoietin (EPO) because of insufficient renal EPO secretion. The establishment of a good hemoglobin (Hgb) response model is a necessary condition for dose optimization design. The purpose of this paper is to apply physics-informed neural networks (PINN) to build the Hgb response model under EPO treatment. Neural network training is guided by physiological model to avoid overfitting problem. During the training process, the parameters of the physiological model can be estimated simultaneously. To handle differential equations with impulse inputs and time delays, we propose approximate analytical expressions for the pharmacokinetic (PK) model and weighted formulations for the pharmacology (PD) model, respectively. The improved PK/PD model was incorporated into PINN for training. Tests on simulated data show that the proposed method has good performance.
Keywords
Erythropoietin Therapy, Parameter Identification, Physics-Informed Neural Networks, Renal Anemia
Suggested Citation
Zhang Z, Li Z. Hemoglobin Response Modeling under Erythropoietin Treatment: Physiological Model-Informed Machine Learning Method. (2022). LAPSE:2022.0094
Author Affiliations
Zhang Z: University of Alberta
Li Z*: University of Alberta
* Corresponding Author
[Login] to see author email addresses.
Journal Name
CSChE Systems & Control Transactions
Volume
2
First Page
35
Last Page
41
Year
2022
Publication Date
2022-10-21
Version Comments
Original Submission
Download
Files
[Download 1v1.pdf] (828 kB)
Oct 21, 2022
Main Article
License
CC BY 4.0
Meta
Record Statistics
Record Views
402
Version History
[v1] (Original Submission)
Oct 21, 2022
 
Verified by curator on
Nov 1, 2022
This Version Number
v1
Citations
Most Recent
This Version
URL Here
https://psecommunity.org/LAPSE:2022.0094
 
Original Submitter
Mina Naeini