A New Strategy of Artificial Intelligence-Based CARS Model Applied to Comparative Analysis of Medical Paper Abstracts in Chinese and English
Bibliographic record
Abstract
Artificial Intelligence (AI) is increasingly used in medical research, especially in the analysis and interpretation of medical data.In this study, based on the traditional CARS model, we built a framework for thesis abstract language step research by categorizing fuzzy steps into optional steps and adding appropriate key steps to the language steps.With the help of artificial intelligence technology, an extraction model of key elements of abstracts incorporating the attention mechanism is constructed, aiming at screening the elemental utterances in abstracts.Finally, by collecting data from medical related papers in CNKI, Web of Science and other databases, the CARS modeling strategy based on artificial intelligence is implemented in the comparative analysis of medical paper abstracts in English and Chinese.Through the comparative analysis, it is found that the number of sentences in English abstracts is concentrated in 6-7 sentences, while the number of sentences in Chinese abstracts is scattered in 2-8 sentences.The percentage of the use of Chinese sentences on English abstract writing is the highest, with an average percentage of 45.24%.The frequency of the first 20 words of fuzzy restrictive phrases in English abstracts was significantly higher than that in Chinese abstracts.The organization of Chinese and English abstracts was mostly in the structure of "introductionmethod-results-discussion", which accounted for 54% and 71%, respectively.In addition, the frequency of steps indicating gaps in the research area is higher in English than Chinese abstracts.
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 | 0.005 | 0.010 |
| Meta-epidemiology (narrow) | 0.001 | 0.000 |
| Meta-epidemiology (broad) | 0.001 | 0.003 |
| Bibliometrics | 0.009 | 0.005 |
| Science and technology studies | 0.001 | 0.001 |
| Scholarly communication | 0.003 | 0.003 |
| Open science | 0.002 | 0.001 |
| Research integrity | 0.001 | 0.001 |
| Insufficient payload (model declined to judge) | 0.004 | 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".