OP30 <u>M</u>odel for <u>AS</u>sessing The Value Of <u>AI</u> In Medical Imaging (MAS-AI)
Bibliographic record
Abstract
Introduction Artificial intelligence (AI) is seen as one of the major disrupting forces in the future healthcare system. However, assessment of the value of these new technologies is still unclear and no agreed international HTA-based guideline exists. Therefore, a Model for ASsessing the value of AI (MAS-AI) in medical imaging was developed by a multidisciplinary group of experts and patient representatives. Methods The MAS-AI guideline is based on four steps. First a literature review of existing guides, evaluations, and assessments of the value of AI in the field of medical imaging (5,890 studies were assessed with 86 studies included in the scoping review). Next, interviews with leading researchers in AI in Denmark. The third step was two workshops where decision-makers, patient organizations and researchers discussed crucial topics when evaluating AI. Between workshops, the multidisciplinary team revised the model according to comments from workshop-participants. Last step is a validation workshop in Canada. Results The MAS-AI guideline has three parts. There are two steps covering nine domains and then advises for the evaluation process. Step 1 contains a description of patients, how the AI-model was developed, and initial ethical and legal considerations. Finishing the four domains in Step 1 is a prerequisite for moving to step 2. In step 2, a multidisciplinary assessment of outcomes of the AI-application is done for the five remaining domains: safety, clinical aspects, economics, organizational aspects and patient aspects. The last part, is five advices to facilitate a good evaluation process. Conclusions We have developed an HTA based framework to support the prospective phase while introducing novel AI technologies into healthcare in medical imaging. MAS-AI can assist HTA organizations (and companies) in selecting the relevant domains and outcome measures in the assessment of AI applications. It is important to ensure uniform and valid decisions regarding the adoption of AI technology with a structured process and tool. MAS-AI can help support these decisions and provide greater transparency for all parties involved.
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 | 0.024 | 0.065 |
| Meta-epidemiology (narrow) | 0.001 | 0.001 |
| Meta-epidemiology (broad) | 0.001 | 0.002 |
| Bibliometrics | 0.008 | 0.005 |
| Science and technology studies | 0.003 | 0.006 |
| Scholarly communication | 0.012 | 0.009 |
| Open science | 0.003 | 0.008 |
| Research integrity | 0.006 | 0.005 |
| Insufficient payload (model declined to judge) | 0.034 | 0.013 |
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".