Performance of Digital Contact Tracing Tools for COVID-19 Response in Singapore: Cross-Sectional Study
Bibliographic record
Abstract
BACKGROUND: Effective contact tracing is labor intensive and time sensitive during the COVID-19 pandemic, but also essential in the absence of effective treatment and vaccines. Singapore launched the first Bluetooth-based contact tracing app-TraceTogether-in March 2020 to augment Singapore's contact tracing capabilities. OBJECTIVE: This study aims to compare the performance of the contact tracing app-TraceTogether-with that of a wearable tag-based real-time locating system (RTLS) and to validate them against the electronic medical records at the National Centre for Infectious Diseases (NCID), the national referral center for COVID-19 screening. METHODS: All patients and physicians in the NCID screening center were issued RTLS tags (CADI Scientific) for contact tracing. In total, 18 physicians were deployed to the NCID screening center from May 10 to May 20, 2020. The physicians activated the TraceTogether app (version 1.6; GovTech) on their smartphones during shifts and urged their patients to use the app. We compared patient contacts identified by TraceTogether and those identified by RTLS tags within the NCID vicinity during physicians' 10-day posting. We also validated both digital contact tracing tools by verifying the physician-patient contacts with the electronic medical records of 156 patients who attended the NCID screening center over a 24-hour time frame within the study period. RESULTS: RTLS tags had a high sensitivity of 95.3% for detecting patient contacts identified either by the system or TraceTogether while TraceTogether had an overall sensitivity of 6.5% and performed significantly better on Android phones than iPhones (Android: 9.7%, iPhone: 2.7%; P<.001). When validated against the electronic medical records, RTLS tags had a sensitivity of 96.9% and specificity of 83.1%, while TraceTogether only detected 2 patient contacts with physicians who did not attend to them. CONCLUSIONS: TraceTogether had a much lower sensitivity than RTLS tags for identifying patient contacts in a clinical setting. Although the tag-based RTLS performed well for contact tracing in a clinical setting, its implementation in the community would be more challenging than TraceTogether. Given the uncertainty of the adoption and capabilities of contact tracing apps, policy makers should be cautioned against overreliance on such apps for contact tracing. Nonetheless, leveraging technology to augment conventional manual contact tracing is a necessary move for returning some normalcy to life during the long haul of the COVID-19 pandemic.
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 | 0.002 | 0.006 |
| Meta-epidemiology (narrow) | 0.000 | 0.000 |
| Meta-epidemiology (broad) | 0.000 | 0.001 |
| Bibliometrics | 0.001 | 0.001 |
| Science and technology studies | 0.001 | 0.000 |
| Scholarly communication | 0.001 | 0.001 |
| Open science | 0.001 | 0.001 |
| Research integrity | 0.001 | 0.001 |
| Insufficient payload (model declined to judge) | 0.002 | 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".