A Neural Collaborative Filtering Model for Adverse Drug Reaction Prediction
Bibliographic record
Abstract
As adverse drug reactions (ADRs) can cause serious consequences to medication treatment, identifying and predicting adverse drug reactions (ADRs) play a crucial role in drug effects and drug use safety. In this paper, we reviewed existing machine learning methods in ADR prediction and proposed a neural collaborative filtering model (NCF) for the prediction of monopharmacy ADRs. NCF is based on dimension reduction by matrix factorization (MF) and combined with an MLP model to enhance prediction performance by handling complex non-linear relationships using MLN. Our NCF model optimizes the MF model by replacing dot product in the MF model with MLP, integrating drug and ADR embeddings from monopharmacy ADR benchmark data and drug-related chemical, physical and biological descriptors in a two-layer deep neural network. The model was tested by using 10-fold cross-validation. On 10-fold cross-validation, the resulting AUC, AUPR, and running time indicated a better performance and higher efficiency on drug-ADR prediction achieved by applying our NCF model.
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 | 0.002 | 0.004 |
| Meta-epidemiology (narrow) | 0.001 | 0.000 |
| Meta-epidemiology (broad) | 0.001 | 0.001 |
| Bibliometrics | 0.001 | 0.001 |
| Science and technology studies | 0.001 | 0.000 |
| Scholarly communication | 0.001 | 0.001 |
| Open science | 0.002 | 0.001 |
| Research integrity | 0.002 | 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".