Real-Time, Serverless Predictions With Google Cloud Healthcare API (Cloud Next '19)

preview_player
Показать описание
There is no shortage of opportunities for clinical decision support and cognitive assistance in healthcare. In this session, review a serverless architecture for generating real-time clinical predictions using FHIR in Cloud Healthcare API and built with Cloud Machine Learning Engine, Cloud Pub/Sub, and Cloud Functions. Also, hear how FHIR-based, machine learning tools are deployed into live clinical environments.

Watch more:

Speaker(s): Kurt Ericson, David Burdick

Session ID: MLAI219
product:Cloud Healthcare,Cloud Healthcare Service,Cloud ML Engine,APIs,TensorFlow,Cloud; fullname:Kurtis Ericson; event: Google Cloud Next 2019; re_ty: Publish; product: Cloud - General; fullname: Kurt Ericson, David Burdick; event: Google Cloud Next 2019;
  1. Google Cloud Tech
  2. type: Conference Talk (Full production);
  3. pr_pr: Google Cloud Next
  4. purpose: Educate
Рекомендации по теме
Real-Time, Serverless Predictions 0:39:32

Real-Time, Serverless Predictions With Google Cloud Healthcare API (Cloud Next '19)

Serverless in Real 0:41:01

Serverless in Real Life: A Case Study in the Travel Industry (Cloud Next '19)

How to get 0:06:27

How to get predictions from an ML model

How to build 0:16:07

How to build a serverless real-time credit card fraud detection solution

Streaming Analytics: Generating 0:35:24

Streaming Analytics: Generating Real Value From Real Time (Cloud Next '19)

Serverless Computing with 0:10:04

Serverless Computing with Google Cloud

Back to Basics: 0:01:00

Back to Basics: Deploy Your Machine Learning Model for Real-Time Predictions #aws #cloudcomputing

Dataflow for real-time 0:04:56

Dataflow for real-time IoT analytics

Dataflow for Real-time 0:04:52

Dataflow for Real-time Clickstream Analytics

Doing More with 0:34:31

Doing More with Less: Serverless Events (Cloud Next '18)

Serverless Machine Learning: 0:45:13

Serverless Machine Learning: a beginner's guide by Bret McGowen and Yufeng Guo

Serverless and Open-Source 0:36:30

Serverless and Open-Source Machine Learning at Sling Media (Cloud Next '19)

The Shift to 0:01:58

The Shift to Serverless is Real

Things I Wish 0:37:37

Things I Wish I Knew Before Building Serverless ML Solutions (Cloud Next '19)

What's new in 0:36:05

What's new in Serverless Spark

Tutorial 6 :Deployment 0:15:17

Tutorial 6 :Deployment of Machine Learning Models in Google Cloud Platform

Webinar: Taking Serverless 0:58:09

Webinar: Taking Serverless and AI to the Next Level

MLess at Scale 0:07:22

MLess at Scale (Best in Show) - Google Cloud Easy as Pie Serverless Hackathon

Run your Business 0:43:46

Run your Business with Real-time Insights from Data (Cloud Next '18)

Dataflow for Real-time 0:03:47

Dataflow for Real-time Marketing Intelligence

Build a Demand 0:29:26

Build a Demand Forecasting Model with Google Cloud Platform

What's your #GoogleCloudPrediction? 0:00:55

What's your #GoogleCloudPrediction? #Shorts

AWS Summit ANZ 0:26:37

AWS Summit ANZ 2022 - Real-time churn prediction with AI powered contact centres (ENTH6)

Serving Real-time scikit-learn 0:31:56

Serving Real-time scikit-learn and XGBoost Predictions on Google Cloud ML Engine part2

Комментарии
Автор

Thank you. Would be great to showcase more cases of data conversion from HL7 or CCD to FHIR store

daverajsiva
Автор

The problem for tech guys would be to annotate by hand the medical data, which would require assistance from the medical personal having medical know-how.As pre-trained healthcare models are not available due to lack of publicly available healthcare dataset (compliance of sensitive data handling being one bottleneck in public healthcare dataset availability). Waiting for a release in future where we would get to select and use already trained models for usage in radiology, oncology etc for the general good. :)

inimitableHarish
Автор

This is something the whole world needs!

aiwithr
Автор

This is incredible! Thanks for the video.

jaredfiacco