Leveraging Responsible, Explainable, and Local Artificial Intelligence Solutions for Clinical Public Health in the Global South
Bibliographic record
Abstract
In the present paper, we will explore how artificial intelligence (AI) and big data analytics (BDA) can help address clinical public and global health needs in the Global South, leveraging and capitalizing on our experience with the "Africa-Canada Artificial Intelligence and Data Innovation Consortium" (ACADIC) Project in the Global South, and focusing on the ethical and regulatory challenges we had to face. "Clinical public health" can be defined as an interdisciplinary field, at the intersection of clinical medicine and public health, whilst "clinical global health" is the practice of clinical public health with a special focus on health issue management in resource-limited settings and contexts, including the Global South. As such, clinical public and global health represent vital approaches, instrumental in (i) applying a community/population perspective to clinical practice as well as a clinical lens to community/population health, (ii) identifying health needs both at the individual and community/population levels, (iii) systematically addressing the determinants of health, including the social and structural ones, (iv) reaching the goals of population's health and well-being, especially of socially vulnerable, underserved communities, (v) better coordinating and integrating the delivery of healthcare provisions, (vi) strengthening health promotion, health protection, and health equity, and (vii) closing gender inequality and other (ethnic and socio-economic) disparities and gaps. Clinical public and global health are called to respond to the more pressing healthcare needs and challenges of our contemporary society, for which AI and BDA can help unlock new options and perspectives. In the aftermath of the still ongoing COVID-19 pandemic, the future trend of AI and BDA in the healthcare field will be devoted to building a more healthy, resilient society, able to face several challenges arising from globally networked hyper-risks, including ageing, multimorbidity, chronic disease accumulation, and climate change.
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 | 0.049 | 0.046 |
| Meta-epidemiology (narrow) | 0.001 | 0.001 |
| Meta-epidemiology (broad) | 0.001 | 0.001 |
| Bibliometrics | 0.003 | 0.002 |
| Science and technology studies | 0.005 | 0.022 |
| Scholarly communication | 0.017 | 0.013 |
| Open science | 0.004 | 0.025 |
| Research integrity | 0.006 | 0.010 |
| Insufficient payload (model declined to judge) | 0.008 | 0.002 |
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".