A Modified Dempster Shafer Approach to Classification in Surgical Skill Assessment
Why this work is in the frame
A frame that forgets how it found something cannot be audited. These are the routes that admitted this work.
Bibliographic record
Abstract
Artificial intelligence systems are usually implemented either using machine learning or expert systems. Machine learning methods are usually more accurate and applicable to a broader range of applications. Expert systems, on the other hand, require much less data for training and generate more comprehensible results. These characteristics are typically desired in the fields of surgery and medicine because there isn't much data available. In order to give a machine's decisions a deeper level of semantics, it is also advantageous to incorporate a doctor's expertise into it. Furthermore, it is safer to understand the reasoning behind a machine's choices. In this paper, a Dempster-Shafer Theory (DST) based expert system is suggested for the task of surgical training skill assessment. An interval-based probabilistic feature analysis was applied to the data to assign values to the mass functions. Zhang's rule of combination was applied to handle the conflicting evidence in the prediction phase. The performance of the proposed method was compared to another DST classifier, SVM, and XGBoost. Our method outperforms SVM and other DST classifiers, but it is not as precise as XGBoost. By reducing the size of the dataset, the added benefit of using an expert system as opposed to a machine learning method was explored further. The performance of the suggested method is not adversely affected by the size of the dataset, whereas the XGBoost classifier is.
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.
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 | 0.001 |
| 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 it