Download presentation
Presentation is loading. Please wait.
Published byLora Hampton Modified over 8 years ago
1
Leveraging Open-Source Matching Tools and Health Information Exchange to Improve Newborn Screening Follow-up Shaun Grannis, MD MS Medical Informatics Research Scientist, Regenstrief Institute Assistant Professor of Family Medicine, I.U. School of Medicine
2
Objective Describe how we leveraged HIE and open tools in a collaborative approach to develop linkage tools necessary to improve NBS follow-up
3
The Problem Not all infants are appropriately screened for harmful or potentially fatal disorders that are otherwise unapparent at birth Although PH can link vital records data with newborn screening results to identify unscreened infants, such processes may be delayed and some cases may remain undetected by this process
4
The Approach Verify that all infants within the Indiana Network for Patient Care (an operational regional HIE) have a newborn screen present To accomplish this, leverage data streams and attempt to match each infant within the INPC to Indiana’s statewide newborn screening registry
5
NBS INPC Test present? Registration Yes/No Clinical Reminders
6
The NBS Platform
7
Matching Inbound NBS Data HL7 Receiver Matching Module “Does patient exist?” (findPatient) NBS Test Data Flow Inbound HL7 “No.” “Add to Patient Table” (createPatient) Add to Matching Table (createPatient)
8
Matching Inbound HIE Data HL7 Receiver Matching Module “Does patient exist?” (findPatient) HIE Data Flow Inbound HL7 “No!!!” “Add to Patient Table” (createPatient) Add to Matching Table (createPatient) Alert!!!
9
Purpose Help address the identity management needs in resource constrained environments reflected by the OpenMRS community
10
Data Access – Methods to access data sources containing records for matching including flat files, relational databases, etc. Analytics – Generates customized parameters for matching weights and other statistical metrics. These parameters are typically calculated and preset prior to matching process. Pair Search/Creation – Creates ‘record pair’ objects by joining entities from one or more data sources Match Scoring – Assigns a match score (using matching analytics) that establishes the likelihood that a ‘record pair’ is a match High Level Overview - Core Matching Functions Data Access Analytics Pair creation Match scoring Core matching functionality
11
High Level Overview - Core Matching Functions Data Access Analytics Pair creation Match scoring Data Access Analytics Pair creation Match scoring
12
High Level Overview – OpenMRS Matching API Data Access Analytics Pair creation Match scoring findDupes updatePatient findPatient createPatient OpenMRS Matching Module API Calls
13
Use Cases Matching Inbound Data De-duplicating patient table Batch mode matching
14
Finding Duplicate Records
15
Batch Mode Record Matching Data Access Analytics Pair creation Match scoring findDupesfindMatchesfindPatient createPatient
16
Results
17
102 un-linked INPC records Riley NBS Lab Data (100,203 records) INPC Data (2,345 records) 2,243 linked INPC records 97,960 un-linked Riley records Newborn Screening
20
Acknowledgements Steve Downs Paul Biondich James Egg Vibha Anand Meena Shelley I Nyoman Ribeka HRSA
21
Leveraging Open-Source Matching Tools and Health Information Exchange to Improve Newborn Screening Follow-up Shaun Grannis, MD MS Medical Informatics Research Scientist, Regenstrief Institute Assistant Professor of Family Medicine, I.U. School of Medicine
Similar presentations
© 2025 SlidePlayer.com. Inc.
All rights reserved.