:quality(75))
- The Reproductive Science Center of SF Bay Area used H2O Driverless AI to build a predictive model incorporating approximately 300 factors affecting embryo outcomes.
- Data scientists at RSC considered factors like ideal pH, genetic information, and chromosome count to predict which embryos were most likely to succeed, per the post.
- Oleksii Barash, RSC's IVF Laboratory Supervisor, said in the post that Driverless AI is used as a benchmark against traditional techniques because it is fast and accurate.
- The post says Driverless AI let RSC predict a patient-specific probability of success rather than comparing a patient only to population averages.
- The post credits Driverless AI's automatic machine learning approach with making personalized fertility predictions more accurate for RSC's patients.
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.