Celmatix, a US-based startup, are beginning clinical trials for their Big Data technology in the field of fertility treatment. Their technology Polaris, so-named for the guiding star in astronomy, computes massive amounts of data to better predict which fertility treatments a particular patient will respond to best. Polaris will initially be piloted in five clinics across the US, and eventually be rolled out in ten.

So what model are Celmatix using to predict their patients’ response to treatments? The answer may surprise you. “We took over large sets of electronic medical records from our different research partner clinics and we started to use the same kind of analytics that Google uses for what shoe you want to buy to determine why someone is responding to treatments when someone else was not,” Dr. Piraye Yurttas Beim, Celmatix’s founder explains. In other words, in a similar fashion to the way Google harnesses data to make personalised shopping recommendations, Polaris uses personal biological metrics to tailor fertility treatment recommendations.

Another advantage of Polaris’ big-data approach is greater knowledge for the patients. The more time someone stays on a particular course of fertility treatment, the more likely they are to conceive. But women and couples are often disenchanted by the lack of information or measurable results, and stop a course of treatment, assuming it was ‘unsuccessful’. “Emotional stress and lack of clarity are big drivers of discontinuation of therapy,” says Beim. “Most of us in a certain age group experience this.” Polaris offers patients greater clarity of knowledge, decreasing the chance of discontinuation and increasing the likelihood of a positive result.

Looking forward, Celmatix are also excited by the prospect of using the information available to help women begin planning their pregnancies. For now though, they are primarily focused on women and couples who have experienced trouble conceiving, a broad and pressing issue in the US. According to the U.S. Centers for Disease Control, 6.7 million women in the US have impaired ability to conceive. Technologies such as Polaris have the ability to change millions of lives, and start millions of families.

Read more here.
(Photo credit: Celmatix website)

Project Data Sphere (PDS), an online platform sharing clinical trial data for use in cancer research, announced its official opening earlier this week. The goal of the project is to accelerate drug discovery and research to improve the lives of cancer patients around the world.

9 data sets are being used for this project. The companies currently involved are AstraZeneca, Pfizer, Memorial Sloan Kettering Cancer Center, Sanofi U.S., Bayer, Celgene, Janssen Research and Development (part of Johnson & Johnson).

Charles Hugh-Jones (Chief Medical Office at Sanofi) and Robert J. Hugin (CEO of Roundtable on Cancer) commented on the new platform yesterday, respectively.

“Using clinical trial datasets collaboratively is a big leap forward in the cancer drug discovery process. 8.2 million people still die of cancer every year while the attrition rate for clinical testing of promising compounds can be as high as 95%.  This could become substantially lower once researchers in both academia and industry share clinical trial data. We’re excited to be working with world-class partners like SAS, SAGE Bionetworks, academia, many in industry and importantly patient groups to bring this free resource to researchers globally.” 

“Data sharing through initiatives such as the Project Data Sphere initiative has the potential to accelerate the speed with which clinical trials are conducted, improve the efficiency of trial designs and assist with the development of data standards applicable to all cancer types,” said Robert J. Hugin, member, CEO Roundtable on Cancer and Chairman and Chief Executive Officer of Celgene.”

(Image Credit: Bill Lyon)

Preventive Medicine, a medical journal, has published an article suggesting that tweets indicating certain risky actions are very good proxies for existing statistics on HIV outbreaks. When comparing the location data of the tweets with existing statistics researchers from UCLA and Virginia Tech found a high correlation. Over 550 million tweets were evaluated over a 6 month period, 10 000 of which contained words associated with risky behavior. This is a further step in using social media and big data to predict changes affecting the health. A few years ago Google managed to do something similar with flu outbreaks.