Machine Learning for Pattern Detection in Cochlear Implant FDA Adverse Event Reports
Bibliographic record
Abstract
ABSTRACT Importance The United States Food & Drug Administration (FDA) passively monitors medical device performance and safety through submitted medical device reports (MDRs) in the Manufacturer and User Facility Device Experience (MAUDE) database. These databases can be analyzed for patterns and novel opportunities for improving patient safety and/or device design. Objectives The objective of this analysis was to use supervised machine learning to explore patterns in reported adverse events involving cochlear implants. Design The MDRs for the top three CI manufacturers by volume from January 1 st 2009 to August 30 th 2019 were retained for the analysis. Natural language processing was used to measure the importance of specific words. Four supervised machine learning algorithms were used to predict which adverse event narrative description pattern corresponded with a specific cochlear implant manufacturer and adverse event type - injury, malfunction, or death. Setting U.S. government public database. Participants Adult and pediatric cochlear patients. Exposure Surgical placement of a cochlear implant. Main Outcome Measure Machine learning model classification prediction accuracy (% correct predictions). Results 27,511 adverse events related to cochlear implant devices were submitted to the MAUDE database during the study period. Most adverse events involved patient injury (n = 16,736), followed by device malfunction (n = 10,760), and death (n = 16). Submissions to the database were dominated by Cochlear Corporation (n = 13,897), followed by MedEL (n = 7,125), and Advanced Bionics (n = 6,489). The random forest, linear SVC, naïve Bayes and logistic algorithms were able to predict the specific CI manufacturer based on the adverse event narrative with an average accuracy of 74.8%, 86.0%, 88.5% and 88.6%, respectively. Conclusions & Relevance Using supervised machine learning algorithms, our classification models were able to predict the CI manufacturer and event type with high accuracy based on patterns in adverse event text descriptions. Level of evidence 3
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 | 0.008 | 0.031 |
| Meta-epidemiology (narrow) | 0.001 | 0.000 |
| Meta-epidemiology (broad) | 0.001 | 0.001 |
| Bibliometrics | 0.007 | 0.003 |
| 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) | 0.002 | 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".