A Standard-Based Citywide Health Information Exchange for Public Health in Response to COVID-19: Development Study
Bibliographic record
Abstract
BACKGROUND: Disease surveillance is a critical function of public health, provides essential information about the disease burden and the clinical and epidemiologic parameters of disease, and is an important element of effective and timely case and contact tracing. The COVID-19 pandemic demonstrates the essential role of disease surveillance in preserving public health. In theory, the standard data formats and exchange methods provided by electronic health record (EHR) meaningful use should enable rapid health care data exchange in the setting of disruptive health care events, such as a pandemic. In reality, access to data remains challenging and, even if available, often lacks conformity to regulated standards. OBJECTIVE: We sought to use regulated interoperability standards already in production to generate awareness of regional bed capacity and enhance the capture of epidemiological risk factors and clinical variables among patients tested for SARS-CoV-2. We described the technical and operational components, governance model, and timelines required to implement the public health order that mandated electronic reporting of data from EHRs among hospitals in the Chicago jurisdiction. We also evaluated the data sources, infrastructure requirements, and the completeness of data supplied to the platform and the capacity to link these sources. METHODS: Following a public health order mandating data submission by all acute care hospitals in Chicago, we developed the technical infrastructure to combine multiple data feeds from those EHR systems-a regional data hub to enhance public health surveillance. A cloud-based environment was created that received ELR, consolidated clinical data architecture, and bed capacity data feeds from sites. Data governance was planned from the project initiation to aid in consensus and principles for data use. We measured the completeness of each feed and the match rate between feeds. RESULTS: Data from 88,906 persons from CCDA records among 14 facilities and 408,741 persons from ELR records among 88 facilities were submitted. Most (n=448,380, 90.1%) records could be matched between CCDA and ELR feeds. Data fields absent from ELR feeds included travel histories, clinical symptoms, and comorbidities. Less than 5% of CCDA data fields were empty. Merging CCDA with ELR data improved race, ethnicity, comorbidity, and hospitalization information data availability. CONCLUSIONS: We described the development of a citywide public health data hub for the surveillance of SARS-CoV-2 infection. We were able to assess the completeness of existing ELR feeds, augment those feeds with CCDA documents, establish secure transfer methods for data exchange, develop a cloud-based architecture to enable secure data storage and analytics, and produce dashboards for monitoring of capacity and the disease burden. We consider this public health and clinical data registry as an informative example of the power of common standards across EHRs and a potential template for future use of standards to improve public health surveillance.
Fetched live from OpenAlex and de-inverted. Abstracts are not stored in this database: the inverted indexes are 8.6 GB of the frame’s 9.3 GB of text, and the host has 13 GB free.
How this classification was reachedexpand
Full frame machine prediction
Teacher imitationNot calibrated prevalence, not ground truth. Human validation pending. The Gemma side is a direct model label for every work in the frame, read from the title-only record. The Codex side is a classifier learned from the 10,348 direct Codex labels and calibrated to design-weighted sample rates; fields without enough sample support carry no Codex call. Candidate is the union of the two sides; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels.
Distilled classifier scores by category (both heads)
| Category | Codex | Gemma |
|---|---|---|
| Metaresearch | 0.025 | 0.018 |
| Meta-epidemiology (narrow) | 0.001 | 0.000 |
| Meta-epidemiology (broad) | 0.000 | 0.001 |
| Bibliometrics | 0.002 | 0.002 |
| Science and technology studies | 0.001 | 0.001 |
| Scholarly communication | 0.003 | 0.003 |
| Open science | 0.002 | 0.002 |
| Research integrity | 0.001 | 0.001 |
| Insufficient payload (model declined to judge) | 0.004 | 0.001 |
Machine scores (provisional)
The two teacher heads of the student model, read on this work. A score orders the frame for review; it never asserts a category, and the validation status ships verbatim with every row.
Baseline scores from an immature model (maturity gate not passed, 7 training rounds). Scores rank; they never assert a category.
score_only:v0-immature-baseline · verbatim from the scoring run: score_only means the number may rank works, and no category label ships from itClassification
machine, unvalidatedMachine predicted; a candidate call from one source (direct Gemma or distilled Codex), not a consensus.
How this classification was reached, model by model and score by score, is at the end of the page under "How this classification was reached".