The performance of Covidence: An artificial intelligence-based tool for title and abstract screening in a breast cancer evidence-based clinical practice guideline
Bibliographic record
Abstract
Clinical practice guidelines (CPGs) support evidence-based care but are time-consuming to develop. This study aimed to compare artificial intelligence (AI)-assisted versus manual title and abstract screening (Stage I) in Covidence using data from a published breast-cancer CPG. This systematic review (SR) included 8,774 articles identified through a medical literature search, after removing duplicates. Three article subsets ( n =500, 1,000, and 2,000) were randomly selected from 8,774 articles to perform 30, 30, and 10 trials, respectively, independent Stage I, AI-assisted trials. The primary outcome of each trial is workload savings achieved through AI-assisted identification of 95% and 100% relevant articles (i.e., sensitivity), and 100% of finally-included articles. The secondary outcome is missed finally-included articles when the sensitivity of 95% was reached for each subset. At the sensitivity of 95%, 100% relevant articles and 100% finally-included articles were identified, median (minimum, maximum) workload savings are 40.7% (4.4%, 59.4%), 25.0% (0.4%, 55.2%), 57.6% (6.2%, 76.4%) for n =500; 38.3% (6.2%, 54.0%), 17.3% (0.0%, 39.1%), 63.9% (0.4%, 77.5%) for n =1,000; 16.6% (10.8%, 41.8%), 4.4% (0.3%, 20.9%), 17.9% (0.8%, 64.6%) for n =2,000 respectively. Covidence’s performance does not improve as the size of the subsets increases for a CPG with multiple complicated research questions. A potential positive correlation between the proportion of relevant articles in initial training of Covidence and workload savings at Stage I across all 70 trials. At 95% sensitivity, 5 trials missed 1 article ( n =500); 2 trials missed 2 articles and 1 trial missed 1 article ( n =1,000); 1 trial missed 3 articles, and 5trials missed 1 article ( n =2,000). AI-assistance in Covidence for Stage I screening shows both promise and pitfalls in the SR for a breast cancer CPG on a complex topic. Further prospective research is needed to better understand the performance of AI-assistance in Covidence and the intricacies of CPG topics.
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 | 0.006 | 0.016 |
| 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".