Rapid Deployment of a Free, Privacy-Assured COVID-19 Symptom Tracker for Public Safety During Reopening: System Development and Feasibility Study
Bibliographic record
Abstract
BACKGROUND: Since the emergence of severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2), the number of cases of coronavirus disease (COVID-19) in the United States has exponentially increased. Identifying and monitoring individuals with COVID-19 and individuals who have been exposed to the disease is critical to prevent transmission. Traditional contact tracing mechanisms are not structured on the scale needed to address this pandemic. As businesses reopen, institutions and agencies not traditionally engaged in disease prevention are being tasked with ensuring public safety. Systems to support organizations facing these new challenges are critically needed. Most currently available symptom trackers use a direct-to-consumer approach and use personal identifiers, which raises privacy concerns. OBJECTIVE: Our aim was to develop a monitoring and reporting system for COVID-19 to support institutions conducting monitoring activities without compromising privacy. METHODS: Our multidisciplinary team designed a symptom tracking system after consultation with experts. The system was designed in the Georgetown University AvesTerra knowledge management environment, which supports data integration and synthesis to identify actionable events and maintain privacy. We conducted a beta test for functionality among consenting Georgetown University medical students. RESULTS: The symptom tracker system was designed based on guiding principles developed during peer consultations. Institutions are provided access to the system through an efficient onboarding process that uses clickwrap technology to document agreement to limited terms of use to rapidly enable free access. Institutions provide their constituents with a unique identifier to enter data through a web-based user interface to collect vetted symptoms as well as clinical and epidemiologic data. The website also provides individuals with educational information through links to the COVID-19 prevention recommendations from the US Centers for Disease Control and Prevention. Safety features include instructions for people with new or worsening symptoms to seek care. No personal identifiers are collected in the system. The reporter mechanism safeguards data access so that institutions can only access their own data, and it provides institutions with on-demand access to the data entered by their constituents, organized in summary reports that highlight actionable data. Development of the system began on March 15, 2020, and it was launched on March 20, 2020. In the beta test, 48 Georgetown University School of Medicine students or their social contacts entered data into the system from March 31 to April 5, 2020. One of the 48 users (2%) reported active COVID-19 infection and had no symptoms by the end of the monitoring period. No other participants reported symptoms. Only data with the unique entity identifier for our beta test were generated in our summary reports. CONCLUSIONS: This system harnesses insights into privacy and data sharing to avoid regulatory and legal hurdles to rapid adaption by entities tasked with maintaining public safety. Our pilot study demonstrated feasibility and ease of use. Refinements based on feedback from early adapters included release of a Spanish language version. These systems provide technological advances to complement the traditional contact tracing and digital tracing applications being implemented to limit SARS-CoV-2 transmission during reopening.
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 distilled prediction
Teacher imitationNot calibrated prevalence, not ground truth. Human validation pending. Learned from the 10,348 direct Codex labels and 10,348 direct Gemma labels. Candidate is the union of thresholded teacher heads; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels or direct frontier model labels.
Codex and Gemma teacher scores by category
| Category | Codex | Gemma |
|---|---|---|
| Metaresearch | 0.004 | 0.002 |
| Meta-epidemiology (narrow) | 0.000 | 0.000 |
| Meta-epidemiology (broad) | 0.001 | 0.000 |
| Bibliometrics | 0.000 | 0.001 |
| Science and technology studies | 0.001 | 0.000 |
| Scholarly communication | 0.001 | 0.001 |
| Open science | 0.001 | 0.001 |
| Research integrity | 0.000 | 0.000 |
| Insufficient payload (model declined to judge) | 0.000 | 0.000 |
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 teacher head, 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".