Responsible artificial intelligence in clinical decision support systems requires good science: Lessons learned from an international roundtable discussion (Preprint)
Bibliographic record
Abstract
UNSTRUCTURED In healthcare, where increasing efficiency is essential to the demand of scale, there is immense opportunity to incorporate advances in artificial intelligence (AI). However, particularly in healthcare, these technologies must be designed to be both effective and ethical. Our objective in a multidisciplinary international roundtable discussion (Canada, United States, United Kingdom), was to identify concepts, perspectives, and considerations for AI systems in healthcare settings that are designed, developed, and deployed with good intention to empower patients and healthcare providers in a safe, trustworthy, and ethical way. We refer to this notion as responsible AI (RAI). First, we discuss the role and opportunity of AI to support collaborative healthcare (clinicians and patients working together) and increase specialist capacity. Second, we outline risks and ramifications of poorly implemented AI including bias, implications of predictors to support diagnosis, and privacy and security considerations. Third, we discuss how these risks can be mitigated through conducting “good science” by addressing biases such as representative data, probing annotation bias, and the role of the biostatistician. We also outline the need to evaluate fit for purpose through transdisciplinary collaboration to address: explainability, fairness, interpretability, transparency, as well as the role of standards, auditing, and regulatory considerations. Finally, we detail four criteria outlining determinants, considerations and rationale for developing RAI. These determinants and considerations are meant to position new AI-powered healthcare technologies primed for responsible design supporting acceptability, appropriateness, feasibility, and adoption. Future directions should expand on additional factors and monitor responsible AI implementation success to validate these criteria.
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 | 0.214 | 0.144 |
| Meta-epidemiology (narrow) | 0.001 | 0.001 |
| Meta-epidemiology (broad) | 0.001 | 0.003 |
| Bibliometrics | 0.002 | 0.003 |
| Science and technology studies | 0.010 | 0.022 |
| Scholarly communication | 0.037 | 0.029 |
| Open science | 0.006 | 0.012 |
| Research integrity | 0.036 | 0.046 |
| Insufficient payload (model declined to judge) | 0.011 | 0.003 |
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; the direct Gemma label and the distilled Codex classifier 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".