Performance and usability of machine learning for screening in systematic reviews: a comparative evaluation of three tools
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
BACKGROUND: We explored the performance of three machine learning tools designed to facilitate title and abstract screening in systematic reviews (SRs) when used to (a) eliminate irrelevant records (automated simulation) and (b) complement the work of a single reviewer (semi-automated simulation). We evaluated user experiences for each tool. METHODS: We subjected three SRs to two retrospective screening simulations. In each tool (Abstrackr, DistillerSR, RobotAnalyst), we screened a 200-record training set and downloaded the predicted relevance of the remaining records. We calculated the proportion missed and workload and time savings compared to dual independent screening. To test user experiences, eight research staff tried each tool and completed a survey. RESULTS: Using Abstrackr, DistillerSR, and RobotAnalyst, respectively, the median (range) proportion missed was 5 (0 to 28) percent, 97 (96 to 100) percent, and 70 (23 to 100) percent for the automated simulation and 1 (0 to 2) percent, 2 (0 to 7) percent, and 2 (0 to 4) percent for the semi-automated simulation. The median (range) workload savings was 90 (82 to 93) percent, 99 (98 to 99) percent, and 85 (85 to 88) percent for the automated simulation and 40 (32 to 43) percent, 49 (48 to 49) percent, and 35 (34 to 38) percent for the semi-automated simulation. The median (range) time savings was 154 (91 to 183), 185 (95 to 201), and 157 (86 to 172) hours for the automated simulation and 61 (42 to 82), 92 (46 to 100), and 64 (37 to 71) hours for the semi-automated simulation. Abstrackr identified 33-90% of records missed by a single reviewer. RobotAnalyst performed less well and DistillerSR provided no relative advantage. User experiences depended on user friendliness, qualities of the user interface, features and functions, trustworthiness, ease and speed of obtaining predictions, and practicality of the export file(s). CONCLUSIONS: The workload savings afforded in the automated simulation came with increased risk of missing relevant records. Supplementing a single reviewer's decisions with relevance predictions (semi-automated simulation) sometimes reduced the proportion missed, but performance varied by tool and SR. Designing tools based on reviewers' self-identified preferences may improve their compatibility with present workflows. SYSTEMATIC REVIEW REGISTRATION: Not applicable.
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 | 0.554 | 0.196 |
| Meta-epidemiology (narrow) | 0.001 | 0.000 |
| Meta-epidemiology (broad) | 0.021 | 0.002 |
| Bibliometrics | 0.000 | 0.002 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.000 | 0.001 |
| Open science | 0.001 | 0.000 |
| Research integrity | 0.000 | 0.000 |
| Insufficient payload (model declined to judge) | 0.001 | 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