Patient safety discourse in a pandemic: a Twitter hashtag analysis study on #PatientSafety
Bibliographic record
Abstract
Background: The digitalization of medicine is becoming a transformative force in modern healthcare systems. This study aims to investigate discussions regarding patient safety, as well as summarize perceived approaches to mitigating risks of adverse events expressed through the #PatientSafety Twitter hashtag during the COVID-19 pandemic. Methods: This research is grounded in the analysis of data extracted from Twitter under the hashtag #PatientSafety between December 1, 2019 and February 1, 2023. Symplur Signals, which represents a tool offering a method to monitor tweets containing hashtags registered with the Symplur Healthcare Hashtag Project, was used for analyzing the tweets shared in the study period. For text analytics of the relevant data, we further used the word cloud generator MonkeyLearn, and VOSviewer. Results: The analysis encompasses 358'809 tweets that were shared by 90'079 Twitter users, generating a total of 1'183'384'757 impressions. Physicians contributed to 18.65% of all tweets, followed by other healthcare professionals (14.31%), and health-focused individuals (10.91%). Geographically, more than a third of tweets (60.90%) were published in the United States. Canada and India followed in second and third positions, respectively. Blocks of trending terms of greater interest to the global Twitter community within the hashtag #PatientSafety were determined to be: "Patient," "Practical doctors," and "Health Care Safety Management." The findings demonstrate the engagement of the Twitter community with COVID-19 and problems related to the training, experience of doctors and patients during a pandemic, communication, the vaccine safety and effectiveness, and potential use of off-label drugs. Noteworthy, in the field of pharmacovigilance, Twitter has the possibility of identifying adverse reactions associated with the use of drugs, including vaccines. The issue of medical errors has been also discussed by Twitter users using the hashtag #PatientSafety. Conclusion: It is clear that various stakeholders, including students, medical practitioners, health organizations, pharmaceutical companies, and regulatory bodies, leverage Twitter to rapidly exchange medical information, data on the disease symptoms, and the drug effects. Consequently, there is a need to further integrate Twitter-derived data into the operational routines of healthcare organizations.
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 | 0.003 | 0.012 |
| Meta-epidemiology (narrow) | 0.000 | 0.000 |
| Meta-epidemiology (broad) | 0.000 | 0.000 |
| Bibliometrics | 0.001 | 0.002 |
| Science and technology studies | 0.002 | 0.002 |
| Scholarly communication | 0.003 | 0.004 |
| Open science | 0.000 | 0.003 |
| Research integrity | 0.001 | 0.001 |
| Insufficient payload (model declined to judge) | 0.003 | 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".