June 19th, 2019

The Reproductive Science Center of SF Bay Area uses AI to Treat Infertility

RSS icon RSS Category: Community, Customer, Data Science, Driverless AI, Use Cases, Yield Prediction

Having your own baby may be a dream that many people have but some cannot realize until they seek specialized help. The Reproductive Science Center of SF Bay Area is one of the pioneer organizations conducting in-vitro fertilization. They strive to produce healthy babies for their patients. However, every patient has their own set of obstacles and favorable or unfavorable embryotic traits that affect their chances of having a baby. This makes it difficult to select the particular embryos that have the highest chance to produce a healthy baby.

For a patient this may sound discouraging, but with new AI and machine learning technology a patient’s dream of having a baby is more tangible. Data scientists at RSC have been able to collect a large amount of data from past medical records and genetic testing, they can analyze data on what factors make a successful embryo. They consider factors like ideal pH, genetic information, number of chromosomes, and many other factors that would affect the outcome.

Instead of considering just one or two factors, now the data scientists can build a predictive model with H2O Driverless AI, an automatic machine learning platform, that incorporates approximately 300 factors in order to predict favorable outcomes. This is much more accurate and personalized to the specific patient. RSC uses this to focus on the factors  that are most likely to result in a healthy baby for that patient. Now, instead of comparing the patient’s chances of having a baby to averages, RSC can predict a probability that is patient-specific.

H2O Driverless AI is instrumental in RSC’s function because it helps determine the chances of embryo survival based on the different factors. Oleksii Barash, the IVF Laboratory Supervisor, emphasizes “one of the best techniques [to predict embryotic outcomes] has been using H2O Driverless AI. We actually always use Driverless AI as a benchmark measured against traditional techniques. It doesn’t take any time, it’s just plug and play and we get accurate results.” Driverless AI has helped RSC deliver accurate and personalized results to their patients.

A patient’s dream to have a baby, which was previously just a shot in the dark, is now reliant on a highly advanced machine learning algorithms. Data scientists can determine the right factors to make a favorable embryo resulting in one healthy baby.

And who knows? Maybe the resulting baby will one day become an excellent data scientist.

Leave a Reply

How a Passion for Numbers Turned This Mechanical Engineer into a Kaggle Grandmaster

In conversation with Sudalai Rajkumar: A Kaggle Double Grandmaster and a Data Scientist at H2O.ai It

January 23, 2020 - by Parul Pandey
How H2O propels data scientists ahead of itself: enhancing Driverless AI models with advanced options, recipes and visualizations

H2O.ai engineers continually innovate and introduce new techniques by adopting latest research, working on cutting

January 6, 2020 - by Gregory Kanevsky
H2O Release 3.28 (Yu)

There’s a new major release of H2O, and it’s packed with new features and fixes! Among

December 20, 2019 - by Michal Kurka
Why you should care about debugging machine learning models

This blog post was originally published here. Authors: Patrick Hall and Andrew Burt For all the excitement about machine learning

December 12, 2019 - by Patrick Hall
Interview with Arno Candel | AutoML | Physics | H2O.ai | CTDS.Show

In this episode, Sanyam Bhutani interviews Dr. Arno Candel: CTO at H2O.ai They talk about Arno’s

December 12, 2019 - by Sanyam Bhutani
How to Effectively Employ an AI Strategy in your Business

Artificial Intelligence has evolved from being a buzz word to a reality today. Companies with

December 11, 2019 - by Parul Pandey

Join the AI Revolution

Subscribe, read the documentation, download or contact us.

Subscribe to the Newsletter

Start Your 21-Day Free Trial Today

Get It Now
Desktop img