Data mining for detecting signals of adverse drug reaction of doxycycline using the Korea adverse event reporting system database
Bibliographic record
Abstract
BACKGROUND: Doxycycline is one of the most prescribed antibiotics by dermatologists. However, the concern regarding adverse events of doxycyline has been rising. OBJECTIVE: To detect the adverse events of doxycycline using the Korea Adverse Events Reporting System (KAERS) database from January 2014 to December 2018 through a data mining method. METHODS: A signal was defined as one satisfying all three indices; a proportional reporting ratio, a reporting odds ratio, and an information component. We further checked whether the detected signals exist in drug labels in Korea and five developed countries, the United States, the United Kingdom, Germany, Canada, and Japan. RESULTS: A total of 3,365,186 adverse event-drug pairs were reported and of which 3,075 were associated with doxycycline. Among the thirty-seven signals, nineteen (malaise, ileus, confusion, malignant neoplasm, ectopic pregnancy, ovarian hyperstimulation, vaginal hemorrhage, bone necrosis, acne, rosacea, seborrheic dermatitis, folliculitis, skin ulceration, crusting, dry skin, paronychia, mottled skin, application site reaction, and application site edema) were not included on any of the drug labels of the six countries. CONCLUSION: We identified nineteen new doxycycline signals that did not appear on drug labels in six countries. Further studies are warranted to evaluate the causality of the adverse events with doxycycline.
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 | 0.004 | 0.011 |
| Meta-epidemiology (narrow) | 0.001 | 0.000 |
| Meta-epidemiology (broad) | 0.001 | 0.001 |
| Bibliometrics | 0.009 | 0.006 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.001 | 0.001 |
| 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".