 From around the globe, it's theCUBE with digital coverage of AWS re-invent 2020. Sponsored by Intel and AWS. Welcome back to theCUBE's ongoing coverage of AWS re-invent virtual. theCUBE has gone virtual too. We're going to talk about machine intelligence, cloud and transformation in healthcare, an industry that is rapidly evolving and reinventing itself to provide better quality care, faster and more accurate diagnoses. And this has to be done at lower cost. And with me to talk about this is Dr. Taha Pasput, who's the director of machine learning at Amazon Web Services. Dr. Good to see you again. Thanks for coming on. Thank you so much. Good to see you, Dave. Yeah, last time we talked, I think it was a couple of years ago. We remember we were talking about Amazon Comprehend Medical. And of course you've been so called raising the bar so to speak over the past 24 months. You made some announcements today including Amazon HealthLake, which we're going to talk about. Tell us about it. Well, we're really excited about it. And so are our customers. Amazon HealthLake, a new HIPAA eligible service for healthcare providers, health insurance companies, and pharmaceutical companies to securely store, transform, query and analyze health data in the cloud at petabyte scale. Amazon HealthLake uses machine learning models trained to automatically understand context and extract meaningful medical data from raw disparate information such as medications, procedures, and diagnoses. Therefore, revolutionizing a process that was traditionally manual, error prone, and highly costly. Requires a lot of expertise on teams within these organizations. What HealthLake does is it tags and indexes every piece of information and then structure it in an open standard, the fire standard, or that's the fast healthcare and our operability resources in order to provide a complete view, 360 degree view of each patient in a consistent way so you'll be able to query and share that data securely. It also integrates with other machine learning services, analytic services that AWS offers such as Amazon QuickSight or Amazon SageMaker in order to visualize and understand the relationships in the data, identify trends, and also make predictions. The other great benefit is since the Amazon HealthLake automatically structures all the healthcare and organizations data into an open standard, the fire industry format, the information now can be easily and securely shared between systems, health systems, and with third party applications. So, providers, healthcare providers will enjoy the ability to collaborate more effectively with each other but also allowing patients and federal access to their medical information. I think so, one of the things that people are gonna ask is okay, wait a minute, HIPAA eligible, is that like cable ready or HD ready? But people need to understand that it's a shared responsibility model. You can't come out of the box and be HIPAA compliant. There are a number of things and processes that your customer has to do. Maybe you could explain that a little bit. Absolutely, let me unpack this a little bit. This is a very, very important thing and it's something that we're really fully baked into the service and how we built also the service, especially dealing with healthcare information. First off, AWS as you know, is vigilant about customers privacy and security. It is job zero for us. Your data and the health lake is secure, compliant and audible. Data versioning is enabled to protect this data against any accidental deletion for example and per fire specification. If you are to delete one piece of data, it will be versioned. It will be only hidden from analysis as a result, not deleted from the service. So your data is always encrypted and using your own customer managed key in a single tenant architecture is another added benefit to provide that additional level of protection when the data is accessed and searched. For example, every time you query a value, for example, someone's glucose level, the data is encrypted and decrypted and so on and so forth. So additionally, this sits in a single tenant architecture so that way the same key is not shared across multiple customers. So you're tamed full ownership and control of your data along with the ability to encrypt, protect, move it, delete it in alignment with organization, security and policies. Now a little bit about the HIPAA eligibility, it's a term that AWS uses for customers storing protected health information or PHI. AWS buy its business associate agreement and also business associate amendment to require customers to encrypt data, address and transit when they're using AWS services. There are over a hundred services to date that are HIPAA eligible including the Amazon Health Lake. This is very important, especially for enabling these covered entities and their business associate subject to HIPAA regulations and is be able to kind of in this shared model between what AWS protection and services and how it can process and store and manage PHI. But there's additional level of compliance is required on the customer side about anywhere from physical security to how each application can be built which is no different than how you manage it. For example, today in your own data center, why not? But this is why many cost grown number of healthcare providers, payers as well as IT professionals are using AWS utility based cloud services today to process, store and transmit PHI. So tell us more about who is going to benefit from this new capability? What types of organizations and maybe some of the outcomes for patients? Absolutely, every healthcare provider today or a payer like a health insurance company or a life science company such as a pharma company is just trying to solve the problem of organizing instruction and data. Because if you do, you make better sense of this information from better patient support decisions, design better clinical trials, operate more efficiently and understand population health trends and then be able then to share that data securely. It's really all starts with making sense of that data and those are the ultimate customers that we're trying to empower with the Amazon, Amazon health lake. Well, and of course there's downstream benefits for the patient. Absolutely. That's ultimately what we're trying to get to. I mean, I mean, I set up front. I mean, it's everybody feels the pain of high healthcare costs. A lot of times you're trying to get to see a doctor and it takes a long time now, especially with COVID. So and much of this oftentimes it's even hard to get access to your own data. So I think you're really trying to attack that problem, aren't you? So I'm gonna give you a couple of examples. Like, I mean, today the most widely used clinical models in practice to predict, let's say someone's disease risk, lack personalization, you and I can be lumped in the same bucket, for example, based on few attributes that are common data elements or data points, which is problematic also because the resulting models produce are imprecise. However, if you look at an individual's medical record, for example, a type two diabetic patient, if you look at the entire history and from all this information coming to them, whether it's doctor nose, medication, dosages, which line of treatment, the second line treatment, continuous monitoring of glucose and that sort of thing, there's over a hundred, there are hundreds of thousands of data points in their entire medical history, but none of this is used today at the point of care. And you want all this information to be organized, aggregated, structured in a way that you'll be able to build even better models, easily queried this information and then observe the health of that individual in comparison with the rest of the population. Because at that point, you'll be able to make those personalized decisions and then also for patient engagement with the health lake ability to now emit data back and share securely via APIs that conform to the FHIR standard. So third-party applications can be built also to provide the access, whether that's for analytics or digital health application, for example, of patient access and that information. All of that is very important because ultimately you wanna get at better care of these populations, better enrollment clinical trials, reduced duplicative tests and waste and healthcare systems. All that comes when you have your entire information available in a way that is structured and normalized and be able to query and analyze. And then the seamless integration between the health lake and the rest of the services like Amazon SageMaker, you can really start, understand relationships and meaning of the information, build better decision support models and predictive models at the individual and the population level. Yeah, right. You talked about all this data that's not really used and it's because it's not accessible, I presume. It's not in one place that somebody can analyze, it's not standardized, it's not normalized. Yeah. Is that right? That is the biggest challenge for every healthcare provider, payer or life science organization today. If you look at this data, it's difficult to work with. Medical health data is really different. Data is siloed, is spread out across multiple systems and is stored in incompatible formats. If you look at the last decade, I mean, one of the greatest things is we witness a great transformation healthcare towards digitization of the record. But your data is scattered across many of these systems anywhere from your family history, the clinical observation, diagnosis and treatments. Where you see the vast majority of that data is contained in unstructured medical records like doctor notes, PDFs of insurance of laboratory reports or insurance claims and forms with COVID, we've seen a quite a bit of uptake of digital sort of delivery of care, such as telemedicine and recorded audios and videos, X-rays and images, the large propagation of digital health apps and digital assistants and wearables and as well as these sort of monitors like glucose monitor and whatnot, data come in all shape and form and format and store across all these things. It's a huge heavy lift for any healthcare organization to be able to aggregate, normalize, store securely and then also be able to kind of analyze this information and structure in a way that's easy to scale with regards to the kind of problems that you're going after. Well, Dr. Koss, we have to leave it there. Thank you so much. I mean, I've been saying for years in the CUBE, when is it that machines are going to be able to make better diagnoses than doctors? Maybe that's the wrong question. Maybe it's machines helping doctors make faster and more accurate diagnoses and lowering our costs. Thanks so much for coming back. Thank you very much. I appreciate it. Thank you. All right, and thank you for watching everybody. Keep it right there. This is Dave Vellante. We'll be back with more coverage of AWS re-invent 2020 and CUBE virtual right after this short break.