Adaption-Based Analytics for Assessment of Human Deconditioning during Deep Space Exploration
Bibliographic record
Abstract
Technological and scientific advancements continue to enable safe prolonged human presence in space, while extending the boundaries of manned exploration from low-Earth orbit into deep space. As humankind prepares to embark on exploration-class missions, to the Moon and Mars, mission objectives, risks and challenges become more complex and vastly different from the majority of human manned space exploration experience known to-date. The potential health risks associated with deep space exploration are expected to amplify, the mitigation of which would necessitate complex and autonomous in-flight medical capacity, which has not been available to-date. The logistics of medical care delivery in-flight have been significantly limited by impracticality of existing biomedical monitoring modalities and retrospective data analytics methods and techniques. Conventionally, physiological health monitoring has been discontinuous and extremely limited, hindering the usability and practicality of the acquired data to support clinical decision-making in-flight. This paper presents an integrated big data framework that utilizes stream computing to support real-time autonomous clinical-decision making in-flight. The proposed framework extends previous research known as the Artemis and Artemis Cloud platforms by integrating multi-source, multi-type data to provide in-depth adaption-based assessment and identify the activity of the various compensatory reactions of regulatory mechanisms, which have been known to impact human health in weightlessness. The instantiation of the proposed big data integrated framework is demonstrated within the context of a ground-based 5-day Dry Immersion study. More specifically, the paper demonstrates the potential to support adaption-based analytics-as-a-service within the context of space medicine. Further to that, adaption-based analytics are enhanced through the introduction of multimodal real-time analytics. The multimodal adaption-based analytics are based on traditional data sampling and a sliding-window approach for analysis of the heart rate variability (HRV) and its features. The introduction of a sliding-window approach offers numerous benefits, including increased sample size, greater stability of numerical estimates, de-trending of the HRV to ensure the observed patterns are attributed to an actual physiological response rather than noise or artefacts. As such, the proposed adaption-based analytics-as-a-service demonstrate great potential to identify unstable physiological states and support proactive prognostics, diagnostics and health management during spaceflight. Additionally, the proposed approach contributes to meaningful use of the acquired physiological data in-flight.
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 | 0.001 | 0.002 |
| Meta-epidemiology (narrow) | 0.001 | 0.000 |
| Meta-epidemiology (broad) | 0.001 | 0.000 |
| Bibliometrics | 0.002 | 0.001 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.001 | 0.001 |
| Open science | 0.001 | 0.001 |
| Research integrity | 0.001 | 0.001 |
| 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 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".