Loon Lens 1.0 Validation: Agentic AI for Title and Abstract Screening in Systematic Literature Reviews
Bibliographic record
Abstract
Abstract Introduction Systematic literature reviews (SLRs) are critical for informing clinical research and practice, but they are time-consuming and resource-intensive, particularly during Title and Abstract (TiAb) screening. Loon Lens, an autonomous, agentic AI platform, streamlines TiAb screening without the need for human reviewers to conduct any screening. Methods This study validates Loon Lens against human reviewer decisions across eight SLRs conducted by Canada’s Drug Agency, covering a range of drugs and eligibility criteria. A total of 3,796 citations were retrieved, with human reviewers identifying 287 (7.6%) for inclusion. Loon Lens autonomously screened the same citations based on the provided inclusion and exclusion criteria. Metrics such as accuracy, recall, precision, F1 score, specificity, and negative predictive value (NPV) were calculated. Bootstrapping was applied to compute 95% confidence intervals. Results Loon Lens achieved an accuracy of 95.5% (95% CI: 94.8–96.1), with recall at 98.95% (95% CI: 97.57–100%) and specificity at 95.24% (95% CI: 94.54–95.89%). Precision was lower at 62.97% (95% CI: 58.39–67.27%), suggesting that Loon Lens included more citations for full-text screening compared to human reviewers. The F1 score was 0.770 (95% CI: 0.734–0.802), indicating a strong balance between precision and recall. Conclusion Loon Lens demonstrates the ability to autonomously conduct TiAb screening with a substantial potential for reducing the time and cost associated with manual or semi-autonomous TiAb screening in SLRs. While improvements in precision are needed, the platform offers a scalable, autonomous solution for systematic reviews. Access to Loon Lens is available upon request at https://loonlens.com/ .
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 | 0.338 | 0.647 |
| Meta-epidemiology (narrow) | 0.004 | 0.005 |
| Meta-epidemiology (broad) | 0.011 | 0.018 |
| Bibliometrics | 0.037 | 0.029 |
| Science and technology studies | 0.004 | 0.004 |
| Scholarly communication | 0.016 | 0.012 |
| Open science | 0.006 | 0.008 |
| Research integrity | 0.005 | 0.003 |
| Insufficient payload (model declined to judge) | 0.053 | 0.009 |
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; the direct Gemma label and the distilled Codex classifier agree on what is shown here.
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".