Knowledge and Recommendations of Stakeholders Regarding Ethical Oversight of Data Science Health Research: Protocol for a Qualitative Study
Bibliographic record
Abstract
BACKGROUND: Data science health research (DSHR) uses novel computational methods and high-performance computing to analyze big data from conventional and nonconventional health and related sources to generate novel insights and communications. DSHR creates assets but generates ethical, legal, and social challenges. Key gaps in current ethical oversight of DSHR include blurred boundaries between research and nonresearch data use, inadequate protection of data donors, power imbalances that risk extractive research practices, algorithmic biases, and regulatory inadequacies. Nigeria, a typical low- and middle-income country with rapidly expanding DSHR, exemplifies this environment and concerns. OBJECTIVE: This study will elicit answers from Nigerian DSHR stakeholders and contribute to understanding the ethical, legal, and social implications (ELSI) of DSHR and developing novel ethical oversight frameworks. METHODS: Between October 2024 and January 2025, we conducted Key Informant Interviews with 65 stakeholders of 87 individuals. The Key Informant Interview guide comprised 11 construct-based question domains addressing awareness of policies and laws, ethical oversight processes, ELSI considerations in policy development, experiences addressing DSHR challenges, organizational and procedural frameworks, ideal oversight components, stakeholder roles, research impact on ethics and policy, regulatory influences on research practices, equity-enhancing policies, and balanced regulations. The interviews lasted 60-90 minutes and were transcribed. We analyzed the transcripts using a hybrid deductive-inductive approach. A priori codes derived from research objectives provided the analytical framework while allowing for the identification of emergent concepts. The iterative 3-level coding process involved initial code generation, evaluation, and refinement, with codes grouped into thematic families and semantic networks representing hierarchical concept relationships. Query tools and Boolean operators were used to interrogate the codes to extract findings. RESULTS: Of 87 invited individuals, 22 (25%) were unable to participate. The 65 participants (age: mean 47.9, SD 7.9 years; 50/65, 77% male) included data science health researchers (25/65, 39%), biomedical researchers (17/65, 26%), Health Research Ethics Committee members (12/65, 19%), and policymakers (11/65, 17%). Most held doctoral degrees (38/65, 57%) and were affiliated with academic institutions (45/65, 69%) and government organizations (26/65, 40%), and had received general research ethics training (50/65, 77%). However, only 12% (8/65) had received predominantly short-duration ethics-specific DSHR training, while 92% (60/65) acknowledged the need for specialized DSHR ethics education. As of January 2025, the interview transcripts have been generated, with checking completed, with qualitative analysis scheduled for completion by March 2025 and completion of primary manuscripts by the end of 2025. CONCLUSIONS: This study will generate stakeholder-informed recommendations for ethical oversight of DSHR that address issues relating to broad consent, ELSI, data ownership, benefit-sharing, and donor protection in resource-limited settings. Our findings will inform global DSHR and research ethics communities on the development of contextually appropriate oversight mechanisms that promote equitable partnerships, co-ownership, and tiered data governance. INTERNATIONAL REGISTERED REPORT IDENTIFIER (IRRID): DERR1-10.2196/78557.
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 | 0.094 | 0.104 |
| Meta-epidemiology (narrow) | 0.002 | 0.002 |
| Meta-epidemiology (broad) | 0.003 | 0.002 |
| Bibliometrics | 0.005 | 0.004 |
| Science and technology studies | 0.009 | 0.008 |
| Scholarly communication | 0.006 | 0.007 |
| Open science | 0.005 | 0.007 |
| Research integrity | 0.007 | 0.010 |
| Insufficient payload (model declined to judge) | 0.042 | 0.011 |
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".