Evaluation of Applied Machine Learning for Health Misinformation Detection via Survey of Medical Professionals on Controversial Topics in Pediatrics
Bibliographic record
Abstract
In this research, we present an evaluation of a system for detection of health misinformation using applied machine learning. The system incorporates computing automation, information retrieval, and natural language processing in conjunction with evidence-based medicine to generate a veracity score based on consensus from trusted medical knowledge bases. For our study, we pre-computed the veracity scores of controversial topics in pediatrics with our proposed system, and then also solicited evaluations of these topics from medical professionals in the neurodevelopmental field via a quantitative survey. Hence, this work provides a double-blind comparison on the veracity of medical claims between our proposed system's results and medical professionals' responses. The results showed that our system's automated assessment matched professional opinions of medical personnel with 80% precision. The survey also demonstrated the inherent challenge with health misinformation detection, as there was no consensus among the medical professionals for 50% of the controversial statements. Nevertheless, this evaluation shows promising results for using objective trust metrics such as the veracity score, in contrast with subjective trust metrics that rely on potentially biased crowdsourcing, ratings, and pre-trained labelling of data.
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 | 0.020 | 0.060 |
| Meta-epidemiology (narrow) | 0.001 | 0.000 |
| Meta-epidemiology (broad) | 0.001 | 0.000 |
| Bibliometrics | 0.004 | 0.002 |
| Science and technology studies | 0.001 | 0.001 |
| Scholarly communication | 0.002 | 0.002 |
| Open science | 0.001 | 0.001 |
| Research integrity | 0.001 | 0.001 |
| Insufficient payload (model declined to judge) | 0.001 | 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".