A mixed-methods study on the design of Artificial Intelligence and data science-based strategies to inform public health responses to COVID-19 in different local health ecosystems: A study protocol for COLEV
Bibliographic record
Abstract
<ns4:p> <ns4:bold>Background:</ns4:bold> Artificial Intelligence (AI) and data science research are promising tools to better inform public policy and public health responses, promoting automation and affordability. During the COVID-19 pandemic, AI has been an aid to forecast outbreak spread globally. The overall aim of the study is to contribute to the ongoing public health, socioeconomic, and communication challenges caused by COVID-19. </ns4:p> <ns4:p> <ns4:bold>Protocol:</ns4:bold> COLEV is a five-pronged interdisciplinary mixed methods project based on AI and data science from an inclusive perspective of age and gender to develop, implement, and communicate useful evidence for COVID-19-related response and recovery in Colombia. The first objective is identification of stakeholders’ preferences, needs, and their use of AI and data science relative to other forms of evidence. The second objective will develop locally relevant mathematical models that will shed light on the possible impact, trajectories, geographical spread, and uncertainties of disease progression as well as risk assessment. The third objective focuses on estimating the effect of COVID-19 on other diseases, gender disparities and health system saturation. The fourth objective aims to analyze popular social networks to identify health-related trending interest and users that act as ‘super spreaders’ for information and misinformation. Finally, the fifth objective, aims at designing disruptive cross-media communication strategies to confront mis- and dis-information around COVID-19. To understand stakeholders’ perspectives, we will use semi-structured interviews and ethnographic work. Daily cases and deaths of COVID-19 reported from the National Surveillance System (INS) of Colombia will be used for quantitative analysis, and data regarding the online conversation will be obtained from Facebook and Twitter. </ns4:p> <ns4:p> <ns4:bold>Conclusions:</ns4:bold> COLEV intends to facilitate the dialogue between academia and health policymakers. The results of COLEV will inform on the responsible, safe and ethical use of AI and data science for decision-making in the context of sanitary emergencies in deeply unequal settings. </ns4:p>
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 | 0.090 | 0.029 |
| Meta-epidemiology (narrow) | 0.001 | 0.000 |
| Meta-epidemiology (broad) | 0.001 | 0.000 |
| Bibliometrics | 0.003 | 0.003 |
| Science and technology studies | 0.001 | 0.001 |
| Scholarly communication | 0.001 | 0.000 |
| Open science | 0.003 | 0.006 |
| Research integrity | 0.000 | 0.001 |
| 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; both teacher heads agree on what is shown here.
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".