Comment on ‘Intelligent cataract surgery supervision and evaluation via deep learning’
Bibliographic record
Abstract
We read with great interest the recent article [1] titled 'Intelligent cataract surgery supervision and evaluation via deep learning' published in International Journal of Surgery.This study presented a new approach to assist ophthalmologists in cataract surgery by using deep learning techniques to analyze surgery videos and provide real-time feedback to the surgeon.The authors described the development of an intelligent system that can monitor various surgical parameters and provide feedback to the surgeon in real time.The system was trained using a large dataset of cataract surgery videos and demonstrated high accuracy in evaluating surgical performance.The potential impact of this study on the field of ophthalmology is immense.Cataract surgery is one of the most commonly performed surgeries worldwide, and the ability to have an intelligent system that can evaluate surgical performance and provide feedback to the surgeon in real time can significantly improve patient outcomes.While this study presented a new approach to assist ophthalmologists in cataract surgery by using deep learning techniques, we believe there are some potential concerns that should be addressed.Firstly, we are concerned about the generalizability of the study due to the lack of clarity on the baseline features used for the trained and validated queues.This study reported that the DeepSurgery algorithm was trained on 186 standard cataract surgery videos and validated on two datasets containing 50 and 21 videos, respectively.However, this study does not provide detailed information on the baseline features used for these a
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 | 0.008 | 0.088 |
| Meta-epidemiology (narrow) | 0.001 | 0.001 |
| Meta-epidemiology (broad) | 0.001 | 0.002 |
| Bibliometrics | 0.001 | 0.001 |
| Science and technology studies | 0.002 | 0.004 |
| Scholarly communication | 0.003 | 0.003 |
| Open science | 0.003 | 0.002 |
| Research integrity | 0.033 | 0.031 |
| Insufficient payload (model declined to judge) | 0.008 | 0.010 |
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".