Provider-Consumer Anomaly Detection for Healthcare Systems
Bibliographic record
Abstract
Anomaly detection is an important task that has been widely applied to different scenarios. In particular, its application in public healthcare is a crucial management task that can improve the quality of the health services and avoid loss of huge amounts of money. In this work we propose and evaluate, in a real scenario, a method for anomaly detection in healthcare based on a provider-consumer model. Our method is divided into two phases. In the first phase it assigns anomaly scores to the cities (consumers) as a function of their demand, then, in the second phase, it transfers the scores from cities to hospitals (providers). We applied the method to a real database from the Brazilian public healthcare that records medical procedures which cost more than $8.5 billion from 2008 to 2012, and demonstrated our method's ability to find potentially fraudulent hospitals. The method is being adopted by the Brazilian government for selecting anomalous hospitals to be investigated. Our main contributions are (i) a simple and effective method for anomaly detection in healthcare; (ii) our method does not require information about the providers nor medical rules; (iii) the analysis from the consumer perspective allows the detection of anomalies that could not be detected with traditional methods; and (iv) we applied the method to a real database and performed a detailed validation.
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 | 0.013 |
| Meta-epidemiology (narrow) | 0.001 | 0.000 |
| Meta-epidemiology (broad) | 0.001 | 0.001 |
| Bibliometrics | 0.002 | 0.002 |
| Science and technology studies | 0.001 | 0.001 |
| Scholarly communication | 0.002 | 0.003 |
| Open science | 0.002 | 0.001 |
| Research integrity | 0.001 | 0.001 |
| Insufficient payload (model declined to judge) | 0.001 | 0.000 |
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".