Identifying indications for novel drugs using electronic health records
Bibliographic record
Abstract
OBJECTIVE: Computational drug re-purposing has received a lot of attention in the past decade. However, methods developed to date focused on established compounds for which information on both, successfully treated patients and chemical and genomic impact, were known. Such information does not always exist for first-in-class drugs under development. METHODS: To identify indications (diseases) for drugs under development we extended and tested several unsupervised computational methods that utilize Electronic Health Record (EHR) data. RESULTS: We tested the methods on known drugs with multiple indications and show that a variant of matrix factorization leads to the best performance for first-in-line drugs improving upon prior methods that were developed for established drugs. The method also identifies novel predictions for key immunology and oncology drugs. Our results show that the performance of re-purposing methods differ greatly between oncology and inflammation/immunology. We hypothesize that the lower performance in oncology can be explained by the fact that many chemotherapies are not targeted therapies. CONCLUSION: Finding new indications for drugs is extremely valuable. Our results explore how to best use EHR data for finding new indications for first in class drugs drug using a phenotypical-similarity driven approach. Our methods can be integrated with others methods using multiple data modalities such as chemical, molecular, genetic 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 | 0.003 | 0.016 |
| Meta-epidemiology (narrow) | 0.001 | 0.000 |
| Meta-epidemiology (broad) | 0.001 | 0.001 |
| Bibliometrics | 0.005 | 0.004 |
| 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) | 0.004 | 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".