Data and Analytics - eBook (TC)

Everest-Report

Issue link: https://read.uberflip.com/i/1496578

Contents of this Issue

Navigation

Page 5 of 13

6 Proprietary & Confidential. © 2022, Everest Global, Inc. | EGR-2022-45-E-5054 Everest Group PEAK Matrix ® for Cloud for Healthcare – Data Platform Vendors 2022 AWS | healthcare cloud data platforms profile (page 2 of 5) Case studies Case study 1 Implemented an image recognition model through a cloud solution Business challenge UC San Diego Health needed help in setting up a system for applying an image recognition model in a clinical setting that would enable medical practitioners to use the information for diagnosis and treatment The goal was to implement a system that could take in X-rays from a clinical setting, run the model on them, and return results quickly to assist with triage and diagnosis Solution and impact Amazon Elastic Compute Cloud (Amazon EC2) instances and Amazon SageMaker were used to connect the clinical imaging system to receive images and output them directly into patients' files AWS provided the client with a scalable solution that could impact clinical decision-making by 20% of the time The image recognition model was able to help the client process over 65,000 X-rays, each in 3-4 minutes, within six months Case study 2 Migrated EHR data to AWS for compliance and insights Business challenge MEDHOST provides enterprise information technology and Electronic Health Record (EHR) solutions to full-service community hospitals MEDHOST wanted to migrate their data onto the cloud to leverage analytics and ensure that all its clients were compliant with the interoperability rule Solution and impact MEDHOST engaged with the AWS Data Lab team to build a working prototype of its end-to-end data pipeline The MEDHOST team was able to leverage FHIR Works on AWS that enabled multi-tenancy to support multiple customers from a single deployment Amazon Athena was used to query the clinical data using standard SQL. This allowed the clinical data to be searched, with multiple FHIR resource types joined together for full insights of patients within the client's data store NOT EXHAUSTIVE

Articles in this issue

view archives of Data and Analytics - eBook (TC) - Everest-Report