Rapid Deployment and Adoption of Health Information Technology for

Real Time Biosurveillance

Primary support: NCI, NLM, CDC, and the DF/HCC

Outline

Overview of the SPIN Architecture

Lessons Learned for Rapid National Deployment

SPIN enabled Biosurveillance

Summary

SPIN addresses (3) pervasive issues

1. Linking existing patient care systems 2. Protecting patient privacy3. Ensuring that hospitals remain in control

… and has been deployed for: • Cancer Research Requiring Human

Specimens• Public Health Biosurveillance• With the potential for other clinical

applications

How SPIN works

1. Link existing databases• Extract from existing hospital systems • Transform patient encounters into HIPAA-safe vocabulary • Load into hospital controlled “SPIN peer”

2. Protect Patient Privacy per HIPAA• De-Identified: Statistical Level query

• Limited: When authorized for individual cases

• PHI is rarely used, and only with permission from each IRB

3. Hospital Control • No central governing body• Remain in control over disclosures at all times

(1) Linking routine care systems

Extract from routine care delivery systems Databases or XML

Transform free text reports “Scrub” patient identifiers (per HIPAA) Autocode into controlled vocabularies such as

UMLS

Load into the hospital controlled PEER database Assign a randomly generated ID to each case

(2) Protecting Patient Privacy

Increasing levels of investigator access commensurate

with investigator need and hospital policy.

SPIN has enabled Statistical Queries Limited Dataset Identified

Cancer Research Feasibility Studies Case Selection Specimens

Biosurveillance Automated Analysis Investigation Emergencies

Potential Applications Clinical Aggregates QA/QC Informed Care

(3) Hospitals remain in control

Each hospital (Peer) chooses who to share with

And what to share (Clinical Reports, ED feeds, .. )

SPIN Applications & Timeline

(2001 – Present) Translational Research (cancer)

(2006 – Present) Biosurveillance

(2007 - Present) Harvard CTSA

SPIN enabled Translational Research

Motivation:

Vast collections of human specimens and clinical data exist all over the country, yet are infrequently shared for cancer research.

Results:National prototype including 14 sites Virtual Specimen Locator (all HMS hospitals)UMLS/scrubber adopted by caBIG (caTIES)Direct influence on Markle’s CFH Common Framework

Sites Participating in the National Demonstration

1. Brigham & Women's Hospital*2. Beth Israel Deaconess Medical Center*3. Cedars-Sinai Medical Center 4. Dana-Farber Cancer Institute*5. Children's Hospital Boston* 6. Harvard Medical School* 7. Massachusetts General Hospital*8. National Institutes of Health 9. National Cancer Institute 10.Olive View Medical Center 11.Regenstrief Institute 12.University of California at Los Angeles Medical Center 13.University of Pittsburgh Medical Center 14.VA Greater LA Healthcare System

* Participate in ongoing “Virtual Specimen Locator” collaboration

Lessons Learned for Rapid National Deployment

We have the principles, now here are the challenges:

For each participant and for each type of data exchange, we need to map heterogeneous databases

Building agreement to share: IRBs and the political will

Lessons Learned for Rapid National Deployment

mapping heterogeneous DBs

VS

Start SMALL : Grow the number of common terms!

Lessons Learned for Rapid National Deployment

Applying lessons learned: mapping heterogeneous DBs

1. Request for Capabilities (What is available?) 2. Availability limits scope of the vocabulary 3. What big questions can be asked with only a few data elements?

Pathology: age, gender, collection, free text “diagnosis”Public Health: age, gender, location, free text “complaint”CTSA: age, gender, …………, free text mining

4. Parallel tracks: autocoding and standard vocabulary approach Different low hanging fruit: diagnosis vs MRN

5. Quick End-To-End lifecyles Question, development, research, new question

Lessons Learned for Rapid National Deployment

Agreement to share: IRBs and political will

SPIN has addressed the “Distributed IRB” issue

Statistical level queries easy are OK by IRBs

Difficulty arises going to the next stepHIPAA limited data setProtected Health Information

2006 to present: SPIN enabled Biosurveillance

Motivation: Detect infectious disease outbreaksTrack the spread of influenzaProvide early warning signs of bioterrorismRe-identify patients as fast as possible during public health emergency

AEGIS:Automated Epidemiologic Geotemporal Integrated

Surveillance

2006 to present: SPIN enabled Biosurveillance

(1) Link Routine Care Delivery Systems

Extract Emergency Department visits from each siteWrite a simple SQL statement & set routine extraction time

TransformAutocode free text of the “Chief Complaint”Anonymize (blur) home addresses & preserve spatial clusters

Load into local SPIN peerGenerate the random linked identifier Peer database is encrypted ( key does NOT live on disk! )

2006 to present: SPIN enabled Biosurveillance

Preserving both spatial clusters & patient privacy

Calculate latitude/longitude for each patient address.

Skew the latitude/longitude with respect to the underlying population density.

Return only the anonymized coordinates during routine analysis

Return real address during emergencies

2006 to present: SPIN enabled Biosurveillance

(1) Link Routine Care Delivery Systems Extract Emergency Department visits from each site Anonymize patient addresses & Autocode “Chief

complaint” Generate random identifier and load into local SPIN peer

(2) Patient Privacy: Increasing levels of investigator access

Statistical query (Automated routine analysis) Limited Disclosure (Alarm Investigation ) Patient Re-Identification (Emergency Investigation)

(3) Hospital Control Which public health agencies do I trust? (CDC, DPH) What do I want to allow in each investigation scenario?

2006 to present: SPIN enabled Biosurveillance

DPH/CDC is responsible for assigning Identity Role Each Hospital is responsible for assigning Role Policy

2006 to present: SPIN enabled Biosurveillance

Routine Analysis Alarm Investigation Emergency InvestigationVisit ID Anonymize Permit PermitGender Permit Permit PermitChief Complaint Permit Permit PermitLocation Anonymize Anonymize PermitDisposition Permit PermitTemperature Permit PermitCheckin Time Permit PermitDischarge Time Permit PermitMRN Permit

One Example of Hospital Authorization Policies

DPH/CDC is responsible for assigning Identity Role Each Hospital is responsible for assigning Role Policy

2006 to present: SPIN enabled Biosurveillance

2006 to present: Biosurveillance using SPIN & AEGIS

Motivation: Detect infectious disease outbreaksTrack the spread of influenzaProvide early warning signs of bioterrorismRe-identify patients as fast as possible during public health emergency

Results:Fulfills AHIC Biosurveillance Use CaseOne of four federally funded NHIN architecturesEnables our existing biosurveillance application (aegis.chip.org)

Summary

SPIN addresses 3 pervasive issues Linking routine care systems Protecting patient privacy Ensuring that hospitals remain in control

SPIN enables increasing levels of access: Automated real-time biosurveillance Alarm Investigation Emergency Investigation

SPIN is decentralized and builds agreement for timely national adoption