Amazon Web Services, the tech giant's cloud computing arm, announced this week that Textract, a service using machine learning to extract information from any type of document, will be rolled out to all AWS customers.
Rather than blindly culling text and data using basic character recognition, Textract's artificial intelligence "reads" the contents of a form, table or document and identifies context to compile only the most relevant information into lists and databases. The service requires no previous machine learning training and is able to automatically extract data from "virtually any document," per Amazon, including hospital claims, patient forms and more, no matter the format or file type.
Textract is already in use by several AWS customers and, beginning with several regions in the U.S. and Ireland this week, will soon be made available to all global users.
Among those already using the service is Healthfirst, a nonprofit managed care organization based in New York City. With Textract, Healthfirst is vastly scaling up its efforts to "turn scanned medical charts into useful clinical information to improve care coordination, drive quality outcomes, and ensure appropriate reimbursement for members under our coverage," Steve Prewitt, the company's chief analytics officer, said in a statement.
More articles about AI:
Samsung, Stanley Black & Decker invest in countertop AI medication reminder tool
Verily's AI predicts disease biomarkers 'significantly better' than existing models
Physician viewpoint: AI will reduce healthcare costs, improve physician wellbeing