Bibliographic record
Abstract
Clinical decision support systems are AI-based systems utilizing AI methods to assist the decision making process. In recent years, the use of clinical support systems has grown in popularity. In addition to its significant benefits in improving healthcare efficiency, it also raises several ethical questions. In this research, three case studies of real AI applications in the medical field have been investigated. The first one is PainChek®, an AI pain assessment tool utilized in Australian residential care. It is helpful for people, especially those who are not able to speak, to express their pain levels, but issues such as transparency, security, and accuracy are raised. The second example is IDx-DR, an FDA-approved automated method for identifying retinopathy in diabetic patients. Even while it can lower costs, there are still some issues with data management transparency, possible risks, and consequences on human specialists. The last case study discusses a hospital’s deployment of an AI-assisted end-of-life system. Although the system can boost physicians’ confidence and lower treatment costs by improving resource allocation, its shortcomings include bias and trust. To address those challenges, a framework has been developed for tracking ethical dilemmas that arise when developing machine learning models for medical applications. The framework combines policy regulation with model implementation processes. This framework aims to help the AI-based clinical system become more transparent and responsible, enhancing the effectiveness of clinical treatment as well as minimizing ethical risks.
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 | 0.189 | 0.273 |
| Meta-epidemiology (narrow) | 0.001 | 0.001 |
| Meta-epidemiology (broad) | 0.001 | 0.001 |
| Bibliometrics | 0.002 | 0.002 |
| Science and technology studies | 0.009 | 0.028 |
| Scholarly communication | 0.021 | 0.017 |
| Open science | 0.004 | 0.013 |
| Research integrity | 0.017 | 0.015 |
| Insufficient payload (model declined to judge) | 0.004 | 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".