Demonstrating Tactical Combat Casualty Care in Simulated Environments to Enable Passive, Autonomous Documentation: Protocol for a Prospective Simulation-Based Study
Bibliographic record
Abstract
BACKGROUND: The Telemedicine & Advanced Technology Research Center (TATRC) commenced a new research portfolio specifically addressing Autonomous Casualty Care (AC2) in 2023. The first project within this portfolio addresses the current and historical challenges of capturing tactical combat casualty care (TCCC) data in operational settings. OBJECTIVE: The initial autonomous casualty care effort, the Passive Data Collection using Autonomous Documentation research project, conducts systematic, simulated patient and casualty care scenarios, leveraging suites of passive sensor inputs to populate a data repository that will automate future combat care. METHODS: To obtain the required datasets, TATRC will engage care provider participants who provided consent in one of 6 randomized simulated TCCC scenarios leveraging an institutional review board-approved office protocol (#M-11057). These simulations will leverage mannikins (low and high fidelity) and live simulated patients (eg, human actors who provided consent). All consenting participants (eg, both the care providers and live simulated patients) will be equipped with suites of sensors that will passively collect data on care delivery actions and patient physiology. Simulated data is being collected at Fort Detrick, Maryland; Fort Sam Houston, Texas; Fort Indiantown Gap, Pennsylvania; Fort Liberty, North Carolina; and a commercial site in Greenville, North Carolina. RESULTS: Across all research locations, TATRC will collect and annotate approximately 2500 simulation procedures tasks by March 2025. These study data will generate the first machine learning and artificial intelligence algorithms to populate Department of Defense (DD) Form 1380 fields accurately and reliably. Additional data collected past March 2025 will be used to continue to refine and mature the algorithm. CONCLUSIONS: The military health care system (MHS) lacks real-world datasets for TCCC care at the point of injury. Developing a data repository of simulated TCCC data is required as an essential step toward automating TCCC care. If TATRC's research efforts result in the ability to automate care delivery documentation, this will alleviate the cognitive burden of TCCC care providers in austere, chaotic environments. By generating a TCCC data repository through this Autonomous Documentation research project, TATRC will have opportunities to leverage this research data to create machine learning and artificial intelligence models to advance passive, automated medical documentation across the health care continuum. INTERNATIONAL REGISTERED REPORT IDENTIFIER (IRRID): DERR1-10.2196/67673.
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 | 0.038 | 0.049 |
| Meta-epidemiology (narrow) | 0.003 | 0.002 |
| Meta-epidemiology (broad) | 0.002 | 0.003 |
| Bibliometrics | 0.002 | 0.002 |
| Science and technology studies | 0.004 | 0.004 |
| Scholarly communication | 0.004 | 0.003 |
| Open science | 0.004 | 0.003 |
| Research integrity | 0.004 | 0.007 |
| Insufficient payload (model declined to judge) | 0.074 | 0.014 |
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".