Evaluation of eye-tracking capabilities in Apple Vision Pro for training in hybrid ventricular septal defect procedures
Bibliographic record
Abstract
Three-dimensional visualization of anatomical structures is a crucial skill for ventricular septal defect closure hybrid procedures, a task that takes years of training to master. The use of virtual and augmented reality has recently increased in the medical field to assist with these visualization challenges during surgery. Apple’s Vision Pro is one of the most recent virtual/augmented reality headsets to show promise in this area because it relies on eye-tracking to navigate its interface. This research aims to provide a quantitative assessment of the Vision Pro’s eye-tracking capabilities to determine whether it is an appropriate tool to use for training cardiac surgeons, whose precision skills are of utmost importance. To do so, we recruited a cohort of 44 participants and developed a user study in two parts. The first was a 2D random saccades task which gave a baseline evaluation of the Vision Pro and the second was an evaluation in a more clinical setting involving the selection of anatomical landmarks on a 3D pediatric heart model molded in polyvinyl alcohol cryogel. We obtained an accuracy of 0.59 degrees, an RMS precision of 0.41 degrees, and a standard deviation precision of 0.21 for the first part, and an accuracy of 3.70 degrees, RMS precision of 0.96 degrees, and standard deviation of 0.23 degrees for the second part. The eye tracking capabilities of the Vision Pro are promising for navigation guidance during cardiac surgery, and might provide additional visualization cues such as an overlay of a 3D preoperative model.
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 | 0.001 | 0.000 |
| Meta-epidemiology (narrow) | 0.000 | 0.000 |
| Meta-epidemiology (broad) | 0.000 | 0.000 |
| Bibliometrics | 0.000 | 0.000 |
| 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) | 0.000 | 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".