(163a) Deriving Personalized and Optimized Estrogen Dosage Profile for Optimal Endometrium Thickness in IVF Patients | AIChE

(163a) Deriving Personalized and Optimized Estrogen Dosage Profile for Optimal Endometrium Thickness in IVF Patients

Authors 

Diwekar, U., Vishwamitra Research Institute /stochastic Rese
Introduction:

Assisted Reproductive Technologies (ART) are defined as treatments for infertility that handle eggs or embryos (“What is Assisted Reproductive Technology?”). The most commonly recommended ART treatment is in vitro fertilization (IVF), a treatment in which egg cells, also known as oocytes, are fertilized by sperm in a laboratory and then inserted back into the uterus of the patient. In vitro fertilization occurs in four stages: superovulation, egg retrieval, fertilization, and embryo transfer (Diwekar et al., 2020). In the last stage of embryo transfer or implantation of the embryo into the uterus, the embryo attaches to the endometrial lining of the uterus. A correlation exists between endometrial thickness and the success of embryo implantation. Thinner endometriums often have lower implantation success rates (Eftekhar & Mehrjardi, 2019). Daily estrogen dose is given to develop the endometrium for implantation. There are general recommendations for estrogen dosing, but the dosage is not personalized or optimized for each patient. In this work, we use the first principle-based model to link estrogen doses to endometrium thickness and a nonlinear programming (NLP) based approach to obtain a personalized and optimized dosage profile for each patient to have optimal endometrium thickness.

Objective: To personalize and optimize the estrogen dose profile to reach the optimal endometrium thickness for the endometrium preparation phase of in vitro fertilization treatment.

Model and Methods: We derive a first principle-based model and personalize it for each patient using the patient's initial days data. Then, we use an NLP optimization method to derive the optimal control profile of estrogen doses for each patient.

Expected Results: We have collected daily data from two hospitals in India on the implantation cycle for frozen embryos. The personalized model will be validated for each patient. This model will then be used to obtain the optimal estrogen profile. We will compare the thickness resulting from optimization with the suggested optimal value (8 mm at the end of the cycle). Total estrogen dosage will also be compared with the current dosage.

References:

Diwekar, Urmila, et al. “Customized modeling and optimal control of superovulation stage in in vitro fertilization (IVF) treatment.” Control Applications for Biomedical Engineering Systems, edited by Ahmad Taher Azar, Elsevier Science, 2020.

Eftekhar, Maryam, and Sara Zare Mehrjardi. “The correlation between endometrial thickness and pregnancy outcomes in fresh ART cycles with different age groups: a retrospective study - Middle East Fertility Society Journal.” Middle East Fertility Society Journal, 18 December 2019, https://mefj.springeropen.com/articles/10.1186/s43043-019-0013-y#citeas.

Kovacs, Gabor, and Lois Salamonsen, editors. How to Prepare the Endometrium to Maximize Implantation Rates and IVF Success. Cambridge University Press, 2019.

Prato, Luca Dal et al. “Endometrial preparation for frozen-thawed embryo transfer with or without pretreatment with gonadotropin-releasing hormone agonist” Fertility and Sterility, Volume 77, Issue 5, 956 - 960

“What is Assisted Reproductive Technology? | Reproductive Health | CDC.” Centers for Disease Control and Prevention, https://www.cdc.gov/art/whatis.html.