- Amazon Web Services (AWS) launched this week its Amazon Comprehend Medical machine learning service that enables healthcare professionals and developers to mine unstructured medical text and patient data, such as diagnosis, treatments, dosages, symptoms, and other signs of disease.
The new service helps healthcare professionals improve clinical decision support, streamline revenue cycle and clinical trials management, and better meet data privacy and HIPAA requirements.
Amazon Comprehend Medical uses natural language processing to simplify the process of using machine learning to extract pertinent information from unstructured medical text, such as medical notes, prescriptions, interview transcripts, and pathology and radiology reports. It then determines the relationship among the data analyzed.
“Comprehend Medical can identify medical conditions, anatomic terms, medications, details of medical tests, treatments and procedures. Ultimately, this richness of information may be able to one day help consumers with managing their own health, including medication management, proactively scheduling care visits, or empowering them to make informed decisions about their health and eligibility,” wrote Dr. Taha A. Kass-Hout, a senior leader of Amazon’s healthcare and AI-related initiatives, and Dr. Matt Wood, general manager of deep learning and AI at AWS, in a blog post.
AWS said it is working with the Fred Hutchinson Cancer Research Center in Seattle to identify patients for clinical trials who could benefit from certain cancer therapies. The center used Amazon Comprehend Medical to evaluate millions of clinical notes in order to extract and index medical conditions, medications, and cancer therapeutic options. This reduced the process time for each document from hours to second, Kass-Hout and Wood related.
They explained that no data would be stored on AWS servers or used for training.
“For cancer patients and the researchers dedicated to curing them, time is the limiting resource. The process of developing clinical trials and connecting them with the right patients requires research teams to sift through and label mountains of unstructured medical record data,” said Fred Hutchinson Cancer Research Center CIO Matthew Trunnell.
“Amazon Comprehend Medical will reduce this time burden from hours per record to seconds. This is a vital step toward getting researchers rapid access to the information they need when they need it so they can find actionable insights to advance lifesaving therapies for patients,” Trunnell added.
Another customer, Roche Diagnostics, is using the service to extract patient data from hospitals to provide decision support and analytics.
With petabytes of unstructured data being generated in hospital systems every day, our goal is to take this information and convert it into useful insights that can be efficiently accessed and understood,” said Roche Director of Software Engineering Anish Kejariwal.
“Amazon Comprehend Medical provides the functionality to help us with quickly extracting and structuring information from medical documents, so that we can build a comprehensive, longitudinal view of patients, and enable both decision support and population analytics,” Kejariwal added.
AWS presaged the launch of the new service earlier this month when it announced that its Amazon Comprehend, along with Amazon Transcribe and Amazon Translate, were HIPAA eligible services.
Amazon Transcribe is a speech-to-text service automatically creates text transcripts from audio files, which would allow healthcare organizations to created transcripts of patient calls.
Amazon Translate is a neural machine translation service that provides fast and reliable language translation, which could enable an organization to translate documents and other text as well as communication with patients in their preferred language.
Medical care search company Zocdoc is using AWS machine learning services in the healthcare sector. “At Zocdoc, our focus has been making it easier for patients to find the right doctor and book an appointment at the most convenient time and location. You can imagine the ML use cases. There is a lot of excitement among Zocdoc engineers around how easy it is to quickly build and deploy a model using Amazon SageMaker,” Zocdoc said in a statement.
“Many healthcare customers are exploring new ways use the power of ML to advance their current workloads and transform how they provide care to patients, all while meeting the requirements of HIPAA,” AWS concluded.