16 Sep In-Vitro Fertilization: AI Improves Ability to Pick Embryos With Best Chance of Success
MedicalResearch.com Interview with:
Hadi Shafiee, PhD
Assistant Professor, Harvard Medical School
Brigham and Women’s Hospital
Department of Medicine
MedicalResearch.com: What is the background for this study? What are some of the characteristics that AI uses to identify blastocysts witha better chance of successful implantation?
Response: In-vitro fertilization (IVF), while a solution to many infertile couples is still extremely inefficient with a success rate of nearly 30% and is both mentally, physically, and economically taxing to patients. The IVF process involves the insemination of eggs and the culture of embryos externally in a fertility lab before transferring the developed embryo to the mother.
A major challenge in the field is deciding on the embryos that need to be transferred during IVF, such that chances of a healthy birth are maximal and any complications for both mother and child are minimal. Currently, the tools available to embryologists when making such are extremely limited and expensive, and thus, most embryologists are required to make these life-altering decisions using only their observational skills and expertise. In such scenarios, their decision-making process is extremely subjective and tends to be variable.
MedicalResearch.com What are the main findings?
Response: Using thousands of embryo image examples, an AI system was developed as part of a collaborative effort between the MGH fertility center and Brigham and Women’s Hospital, to identify and select embryos of the highest quality by looking at look at singular embryo images.
Firstly, it was identified that the embryos selected by the AI were of a similar developmental quality to those that may have been selected by an embryologist, deeming suitable for clinical utility.
Secondly, the developed AI system was observed to potentially possess an ability to identify embryos that will eventually lead to a successful outcome, better than embryologists.
Finally, even among the highest quality genetically-screened embryos, where the visually observable differences between embryos is extremely subtle, the AI system was able to differentiate and identify those with the highest potential for success significantly better than 15 experienced embryologists from 5 different fertility centers across the United States.
MedicalResearch.com: What should readers take away from your report?
Response: Overall, the developed AI system has a tremendous potential to improve clinical decision making, reduce human errors, and can lead to faster pregnancies for patients, while improving access to care. Aside from the direct benefits to the field of reproductive medicine, this technology could also be of benefit to clinical, biological, and industrial process management where the simplicity, reliability, and accuracy of the technology in identifying the subtle differences in cell morphology can lead to improved and early outcome predictions.
MedicalResearch.com: What recommendations do you have for future research as a result of this work?
Response: We will need to perform prospective clinical trials to get FDA approvals.
Performance of a deep learning based neural network in the selection of human blastocysts for implantation Charles L Bormann, Manoj Kumar Kanakasabapathy, Prudhvi Thirumalaraju, Raghav Gupta, Rohan Pooniwala, Hemanth Kandula, Eduardo Hariton, Irene Souter, Irene Dimitriadis, Leslie B Ramirez, Carol L Curchoe, Jason E Swain, Lynn M Boehnlein, Hadi Shafiee
eLife 2020;9:e55301 DOI: 10.7554/eLife.55301
The information on MedicalResearch.com is provided for educational purposes only, and is in no way intended to diagnose, cure, or treat any medical or other condition. Always seek the advice of your physician or other qualified health and ask your doctor any questions you may have regarding a medical condition. In addition to all other limitations and disclaimers in this agreement, service provider and its third party providers disclaim any liability or loss in connection with the content provided on this website.
Last Updated on September 16, 2020 by Marie Benz MD FAAD