Use of Artificial Intelligence for Clinical Assessment of Assisted Reproductive Techniques and IVF Outcomes

ART, Infertility, in Vitro Fertilization (IVF)

Artificial Intelligence

The use of machine learning techniques using an artificial intelligence tool is proposed to analyze clinical data to predict best possible IVF/ART outcomes. This tool has been utilized to accurately predict embryo quality here at Cornell. Utilizing this tool to assess objective clinical findings and predict outcomes of assisted reproductive techniques is sought, with the ultimate goal of an automated tool to reduce implicit physician bias. Within this goal, using this tool to objectively and accurately assess baseline ovarian reserve at the start of an ART cycle is proposed, using 3D sonography to image the ovary and artificial intelligence tool to objectively identify baseline antral follicle counts.

This study will collect prospective data, specifically 3D transvaginal ultrasound of ovaries at time of baseline evaluation at beginning of an ART cycle. All participants will be asked to give written consent to be included in the study. At the time of initial ultrasound that is routinely done on the first day of the ART cycle, the physician performing the ultrasound will use a 3D ultrasound transvaginal probe to perform the ultrasound and capture both 2D and 3D images. 3D ultrasound is performed routinely for patients undergoing ART and is not an investigative procedure, however is not uniformly performed at the time of the baseline ultrasound. As per standard practice, the baseline antral follicle count will be documented by the performing physician, as well as a 3D image saved to be analyzed later using AI. Information about the medical history, treatment and outcomes will be collected as part of the study. Data maintained in the medical record as a result of standard of care monitoring for IVF and IUI will also be used for this study. This will include semen analysis (male partners if applicable) and pregnancy outcomes. For male partners, the semen analysis record will be part of the fertility history and semen analysis will be performed as standard of care with semen processing for fertilization. Additional data related to the treatment and outcomes will be collected from the medical record from the time of consent through the end of the treatment (including pregnancy outcomes). The time commitment for subjects may take up to 1 month (time from consent signing to 3D ultrasound) and to the time of delivery if pregnant (up to 9 months). No further procedures will be performed in the study group.

No related papers found yet.

United States