Welcome and Introductions: Steve Posnack, ONC/Genevieve Morris, ONC

1. Introductions
2. ONC Patient Matching Overview

Patient Matching Algorithm Challenge (PMAC): Adam Culbertson, ONC/MITRE/Challenge Winners

The goals of the ONC Patient Matching Algorithm Challenge (PMAC) were to bring about greater transparency and data on the performance of patient matching algorithms, spur the adoption of performance metrics for patient matching algorithm developers, and positively impact other aspects of patient matching such as deduplication and linking to clinical data.

1. PMAC Overview
2. Outcomes and analyses
3. Determination of winners
4. Feedback, lessons learned, recommendations, and next steps from top-scoring teams
5. Q&A

Break

Gold Standard and Algorithm Testing Pilot: Carmen Smiley, ONC/OCHIN/Kaiser Permanente/MITRE

Despite the increased adoption of electronic health records (EHRs) in recent years and progress made towards interoperability, there is no widely used standard for assessing or reporting the accuracy of patient matching algorithms. The goal of the Gold Standard and Algorithm Testing (GSAT) pilot was to create a gold standard dataset containing thousands of pairs of known duplicate records against which algorithm performance may be evaluated.

1. GSAT Overview
2. Adjudication and creation of gold standard data set
3. Scoring of algorithm
4. Findings, challenges, and recommendations
5. Q&A

Break

Patient Demographic Data Quality: Lee Stevens, ONC

Patient demographic data is the primary key used for matching patient records. Unfortunately, patient demographic data has historically been of poor data quality, resulting in both inaccurate matching of patient records and low match rates, particularly when data is exchanged across organizations. The Patient Demographic Data Quality (PDDQ) initiative worked to establish a standardized framework and guidance aimed at improving the quality of patient demographic data.

1. PDDQ Overview
2. Need for demographic data management
3. PDDQ products developed by ONC
   1. PDDQ Framework
   2. PDDQ Ambulatory Guide
   3. Maturity level assessment and scoring
4. Q&A

Data Quality Framework (DQF) Pilot: Justin Cross, ONC/Carmen Smiley, ONC/OCHIN/Kaiser Permanente

High quality demographic data are particularly critical for preventing or minimizing the creation of duplicate records. The Data Quality Framework (DQF) aimed to streamline and standardize the patient registration process in order to improve the overall quality of patient demographic data and reduce the number of duplicate patient records.

1. DQF Overview
2. Approach

1. Literature Review
2. Data Collection
3. Data Quality Improvement Training

1. Findings, challenges, limitations, and recommendations
2. Q&A

Closing Remarks