Applications of artificial intelligence-guided clinical decision support in disaster medicine: an international Delphi study
Bibliographic record
Abstract
Background Since the 1950′s, artificial intelligence (AI) technologies have been beyond the reach of most disaster medicine (DM) practitioners. With the introduction of ChatGPT in 2022, there has been a surge of proposed applications for AI in disaster medicine. However, AI development is largely guided by vendors in high-income countries, and little is known of the needs of practitioners. This study provides an international perspective on the clinical problems that DM practitioners would like to see addressed by AI. Materials and methods A three round online Delphi study was performed by 131 international DM experts. In round one, experts were asked: “What specific clinical questions or problems in Disaster Medicine would you like to see addressed by artificial intelligence guided clinical decision support?” Statements from the first round were analyzed and collated for subsequent rounds where participants rated statements on a 7-point linear scale for importance. Results In round one, 77 participants gave 539 proposed statements which were collated into 47 statements for subsequent rounds. In round two, 89 participants gave 3,008 ratings with no statements reaching consensus. In round three, 63 participants gave 2,942 ratings: five statements reached consensus: distribution of disaster patients within the hospital, estimating the size of the affected population, hazard vulnerability analysis, acquisition and distribution of resources, and transportation routing. Experts tended to disagree with the use of AI for ethics, mental health, cultural sensitivity, or difficult treatment decisions. Conclusions In this online Delphi study DM practitioners expressed a preference for AI tools that would help with the logistical support of their clinical responsibilities. Participants appeared to have much less support for the use of AI in making difficult or critical decisions. Development of AI for clinical decision support should focus on the needs of the users and be guided by an international perspective.
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 distilled prediction
Teacher imitationNot calibrated prevalence, not ground truth. Human validation pending. Learned from the 10,348 direct Codex labels and 10,348 direct Gemma labels. Candidate is the union of thresholded teacher heads; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels or direct frontier model labels.
Codex and Gemma teacher scores by category
| Category | Codex | Gemma |
|---|---|---|
| Metaresearch | 0.002 | 0.001 |
| Meta-epidemiology (narrow) | 0.000 | 0.000 |
| Meta-epidemiology (broad) | 0.001 | 0.000 |
| Bibliometrics | 0.001 | 0.001 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.000 | 0.000 |
| Open science | 0.000 | 0.000 |
| Research integrity | 0.000 | 0.000 |
| Insufficient payload (model declined to judge) | 0.001 | 0.000 |
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 teacher head, 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".