How to use AWS HealthScribe API to automatically generate clinical notes from patient-clinician conversations in a serverless architecture.
Amazon API Gateway receives the HTTP POST request which triggers the AWS Lambda function.
The AWS Lambda function calls AWS HealthScribe
start_medical_scribe_job API using boto3 library. The audio content to be analysed is stored in an Amazon S3 bucket.AWS HealthScribe transcription job analyses the patient-clinician conversations audio content and generates clinical notes from it.
The output is uploaded into the Amazon S3 bucket.
< Back to all patterns
Clone repo
git clone https://github.com/aws-samples/serverless-patterns/cd serverless-patterns/apigw-lambda-healthscribe-samDeploy
sam deploy --guidedbash create_lambda_layer.shTesting
See the GitHub repo for detailed testing instructions.
Cleanup
Delete the Amazon S3 bucket content:
aws s3 rm s3://{TranscribeNotesBucket} --recursiveDelete the stack:
sam delete.Delete Lambda Layer stack:
bash delete_lambda_layer.sh.Created by:
