Presentation is loading. Please wait.

Presentation is loading. Please wait.

MongoDB PostgreSQL SaaS Quality Measure Storage

Similar presentations


Presentation on theme: "MongoDB PostgreSQL SaaS Quality Measure Storage"— Presentation transcript:

1 MongoDB PostgreSQL SaaS http://www.checkqm.com Quality Measure Storage
User entered data Screen Shots SaaS Amazon EC2

2 January, 2012 EMR Generated Data TDS (Legacy System) HL7 Feed
RN Documentation Provider Documentation TDS (Legacy System) 22 Years Patient Data 1.2M Patients 9M Records Orders Labs Transcribed Results Patient Record HL7 Feed Lab Results Physiological Monitors Ventilators Transcribed Reports Radiology Results Endoscopy Results Orders External Data Home Monitoring Personal Health Record Social Media *Twitter *Foursquare *Yelp *RSS & Blog

3 Big Data = Complete Data
The Electronic Medical Record is primarily transactional taking feeds from source systems via an interface engine. The Enterprise Data Warehouse is a collection of data from the EMR and various source systems in the enterprise. In both cases decisions are made concerning data acquisition. Hadoop is capable of ingesting and storing healthcare data in total.

4 Big Data = Infrastructure
Low Cost of Entry & Scalable Open Source Commodity Hardware UCI Hadoop Ecosystem 8 nodes 4 terabytes Yahoo Hadoop Ecosystem 60K nodes 160 petabytes Cloud Ready

5 Big Data = Interoperability
An Ecosystem that Supports Hadoop (HDFS) MongoDB (NoSQL) Neo 4j (Graph Database) Relational Data Base MapReduce JBoss Drools Mahout

6 Limits of Current Ecosystem
The Electronic Medical Record is not up to the task of handling complex operations such as anomaly detection, machine learning, building complex algorithms or pattern set recognition. Enterprise Data Warehouses (EDW) suffer from a latency factor of up to 24 hours. The EDW serves clinicians, operations, quality and research retrospectively as opposed to real time.

7 Data Information Knowledge Wisdom
Saritor Data Information Knowledge Wisdom A healthcare information ecosystem built on “Big Data” technologies capable of serving the needs of clinicians, operations, quality and research in real time and in one environment. Able to ingest all healthcare generated data both internal and external. Platform for advanced analytics such as early detection of sepsis & hospital acquired conditions. Prediction of potential readmissions. Complex algorithm and machine learning platform.

8 Health Care Data Sources
Legacy Systems All HL7 Feeds (EMR source systems) All EMR Initiated Data Device Data (in one minute intervals) Physiological Monitors Ventilators Smart Pumps Real Time Location System Hospital Sensors Genomic Data Home Monitoring Social Media Healthcare Organization Sentiment Analysis Patient Engagement

9 Saritor Initial Functionality
Integration with EMR to View Legacy Data 30 Day Readmit Prediction (UCI Centric) Early Sepsis Detection & Notification Integration with UCI Clinical Intelligence Applications Chronic Disease Scorecards Home Monitoring Analytics Social Media Sentiment Analysis

10

11 Algorithm Management Available Data Set
Input Data Attributes, Rules, Parameters Input Data Attributes, Rules, Parameters Training Data Set Test Data Set Hypothesis / Algorithm Model (Core Engine with the Equations / Analysis) Statistical Techniques Hypothesis / Algorithm Model (Core Engine with the Equations/ Analysis) Statistical Techniques Output / Results (Actual) Output / Results (Actual) Analyze Output for Model Behavior (Actual versus Desired) Analyze Output for Model Behavior (Actual versus Desired) Not Satisfactory Satisfactory Result Not Satisfactory Satisfactory Result Identify Improvements Matches Expectation Identify Improvements Matches Expectation Feedback and Refine the Model Release for Testing the Model Feedback and Refine the Model Baseline the Pattern Publish new version to Repository Diagnosis Patterns Repository

12 Quantified Self Personal Informatics mHealth

13 PHR Centric Health HIE Saritor EMR

14

15 The difference between a vision and a hallucination
is that other people can see the vision. Marc Andreessen

16 Charles Boicey cboicey@uci.edu @N2InformaticsRN


Download ppt "MongoDB PostgreSQL SaaS Quality Measure Storage"

Similar presentations


Ads by Google