OR WAIT 15 SECS
IBM Watson Health's Peter Brandsetter talks about how analytics, IoT and artficial intelligence are moving from buzz words to real-world solutions with benefits that weren't possible just a few years ago.
At this month's AMPLEXOR Life Sciences’ “Be The Expert” conference in Dubrovnik, Croatia, IBM Watson Health's Peter Brandsetter talked about how analytics, IoT and artficial intelligence are moving from buzz words to real-world solutions with benefits that weren't possible just a few years ago. In a conversation with PharmExec, Brandsetter underlined how this process is progressing.
Peter Brandstetter: We are definitely at this point. In my presentation I referenced research that IBM does every year, and the most recent showed that already something like I think 20% or 30% of pharmaceutical companies are already started with projects using artificial intelligence technology. And all through the conference there were speakers talking about using AI, how you can use it and real world examples of organizations doing so.
One example is this box for patient data that IBM is developing in the pharmacovigilance space. It makes the whole process easier when a person with a reaction comes in, as it makes assessing it much faster - a pharmaceutical company needs to react to this within fifteen days. They need to analyse what the event was, what was the cause of it, was it something that could be repeated? They need to put a lot of things together. This is known as a literature research and this for example, the literature research is supported by what's called patient safety, a natural language processing artificial intelligence technology.
Rather than several people reading hundreds of documents, you press a button and get results much faster. Then the person must go and deep, dive but this the AI computing at the literature research phase can be invaluable.
Well, one challenge is that generally in this industry organizations are usually not that fast in adopting new technology. It's a highly regulated industry, so every technology that is innovative also needs to prove that it's really working. This is especially so when you use artificial intelligence, but it is also harder, as we can't use the traditional approaches where you put in A and B comes out. Because in artificial intelligence you train the system similarly to how you would a human being, so it's not that obvious what is really coming out.
This is also something that we are working on with clients - getting new insights from existing data. For example for one muscular skeletal disease, we are working together with a client on data that's been around for twenty years, and has been used by many researchers and many pharma companies already. We’ve applied machine learning and after working just three or four weeks, we already found some new insights. This is a good example of where such technology can really help us, because machine learning is really good when you have thousands of parameters that you need to combine and you need to look and to find patterns.
Machine learning is a deep neural network and this is something that a human with traditional statistical methods cannot do as fast.
AI is already a reality for many in the industry, but we are still in something of a pilot phase. But as soon as the early adopters start to show good results, then the whole industry will follow. This will take two years and when we are sitting here in 2020, then I think we can talk about many more companies using AI and really starting to see the right results.
There are several tools that IBM is currently developing. One example that’s particularly interesting and promising is this image processing where you can use x-ray images, processing technology and neuro matter technology to identify if an x-ray might be a cancer or not. IBM research is working very hard in this area and they already have some good examples that are even better than the best radiologist.