Surgical Workflow Analysis in Cerebral Aneurysm Coiling
Bibliographic record
Abstract
Minimally‐invasive endovascular procedures have been established as fundamental and incredibly effective interventions in the treatment of aneurysms. Daily operations incorporate thousands of hours of experience sourced from the operating room and extensive literature. In particular, neurointerventional angiography requires extensive hands‐on training under the guidance of an expert interventionalist in order to learn nuanced navigational and procedural strategies. The presence of a high learning curves and inter‐center training variability creates difficulties in developing standardized training and assessment models in this field. Surgical workflow analysis has been gaining traction in recent years as a favorable technical approach to understanding surgical procedures. Through the breakdown of clinical performance into its core steps and events, workflow models allow for the visualization, statistical analysis and standardization of performance from clinically representative arrays of data points. Simulation‐based training in cerebral aneurysm diagnosis and coiling has seen great technical advancement over the last decade, with the production of affordable, tactile computer‐based simulators. Although these tools hold much potential, there is little data supporting the extent of their abilities to teach and standardize clinically‐transferable skills. Using surgical workflow analysis software, we aim to dissect the core steps and events that occur during a cerebral aneurysm coiling procedure in order to identify the average occurrence and length of significant procedural steps and events. Using this data, we aim to develop a standardized model of performance that can be applied as a guide to simulation‐based training and as a performance metric to simulation‐based clinical skills transfer. A total of three video cameras are placed around the Angio Suite focusing on significant areas of clinical importance: (1) the femoral access site and hands of the surgical team, (2) the imaging monitors, and (3) angiography pedals. Video data from 20 patients undergoing a cerebral angiography coiling procedure are collected and analyzed using Annotate. Data analysis will focus on quantitative data, such as event occurrence and length, and summative qualitative data on procedural overview. This data will be used to develop an averaged expert performance model for this procedure. The results of this study will provide important guidelines for translational simulation‐based training work that is representative of the steps performed in the Angio Suite. Workflow analysis in cerebral aneurysm coiling can provide answers to many uncertainties existing in the field, such as metrics for performance among experts, accuracy of simulation‐based training in comparison to clinical practice and potential areas of development in clinical training. Furthermore, the development of a performance model in neurointerventional angiography would create potential for automated workflow analyses and application of statistical data towards the treatment recommendations for novel and difficult cases. Support or Funding Information CIHR‐CGSD
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 | 0.003 | 0.009 |
| Meta-epidemiology (narrow) | 0.001 | 0.000 |
| Meta-epidemiology (broad) | 0.000 | 0.001 |
| Bibliometrics | 0.003 | 0.002 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.002 | 0.001 |
| Open science | 0.001 | 0.001 |
| 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 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".