Efficient and Privacy-Preserving Decision Tree Classification for Health Monitoring Systems
Bibliographic record
Abstract
Due to the increasing healthcare costs and the advance of wireless technology, health monitoring systems have been widely adopted recently. In health monitoring systems, a hospital outsources a clinical decision model to a cloud service provider, which receives biomedical data from remote clients and produces clinical decisions based on the outsourced model. Due to critical privacy concerns, both the clinical decision model and biomedical data should be protected. In this article, we propose an efficient and privacy-preserving decision tree (PPDT) classification scheme for health monitoring systems. Specifically, we first transform a decision tree classifier (i.e., the clinical decision model) into the Boolean vectors. Then, we leverage symmetric key encryption to encrypt the Boolean vectors as encrypted indices. The PPDT classification is achieved by searching the encrypted indices with encrypted tokens. We formulate a leakage function and provide the security definition and simulation-based proof for PPDT. The performance analyses demonstrate that PPDT is very efficient in terms of computation, communication, and storage. Experimental evaluations show that PPDT only requires microsecond-level execution time, kilobyte-level communication costs, and kilobyte-level storage costs on the test data set.
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 | 0.010 |
| 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 | 0.001 |
| Scholarly communication | 0.001 | 0.003 |
| Open science | 0.001 | 0.002 |
| Research integrity | 0.001 | 0.002 |
| 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".