Augmented Reality and Machine Learning in Health: A Systematic Review
Bibliographic record
Abstract
Augmented Reality (AR) is a useful technology for providing an information-rich reality by superimposing digital objects and giving a virtual interpretation of the physical environment. AR has played a key role in reducing cognitive load and the applications of AR have been useful in various fields ranging from manufacturing, advertisement, education, military, and health. AR has also been deployed on various platforms like mobile, computer screens, and head-mounted displays (HMD). In this paper, we systematically reviewed research papers that have applied AR systems with machine learning (ML) in various health-related domains within the past 12 years (2010–2021). We present a review of the state-of-the-art AR implementation and research in the area of health by (1) identifying various AR approaches, (2) uncovering various areas of health where AR have been applied, (3) determining the current trend, gaps, and areas for future work, (4) highlighting the artificial intelligence (AI) and machine learning (ML) algorithms used in the AR systems and how they are used, and (5) comparing the different visualization modalities (web, mobile, and HMD). This review adds to the existing literature by shedding light on the common tools, successful approaches used in implementing previous AR projects, and evaluation methods. We uncover how AI and object tracking was implemented in AR for health. Finally, we identify gaps and offer recommendations for advancing research in this area.
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 | 0.004 | 0.016 |
| Meta-epidemiology (narrow) | 0.001 | 0.001 |
| Meta-epidemiology (broad) | 0.004 | 0.003 |
| Bibliometrics | 0.007 | 0.008 |
| Science and technology studies | 0.000 | 0.001 |
| Scholarly communication | 0.002 | 0.002 |
| Open science | 0.002 | 0.001 |
| Research integrity | 0.002 | 0.001 |
| Insufficient payload (model declined to judge) | 0.007 | 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".