A classification module in data masking framework for Business Intelligence platform in healthcare
Bibliographic record
Abstract
Healthcare organizations are undergoing tremendous change in analytical computing. The vehicle for this change is implementing a Business Intelligence (BI) platform, which includes On-Line Analytical Processing (OLAP) Cubes, data visualization tools, and integrated data warehouse (DW). Extracting sensitive data (Personally Identifiable Information-PII, Personal Health Information-PHI) from operational databases, then saving them into a consolidated central repository to facilitate efficient analysis are the best solution. This solution demonstrates a good understanding of overall business operational performance and trends as well as improves the business processes through using statistical and data mining methods. Nonetheless, this huge data warehouse (DW) constitutes one of the most serious privacy breach threats that any healthcare organization might face when many internal users of different security levels have access to BI components. Data masking techniques are used to minimize the inadvertent disclosure risk of sensitive data as well as to preserve the basic quality of data analytics (data utility). However, the traditional masking methods fail to maintain the utility of data analysis for reporting and research purposes. In this paper a practical classification component for a built-in data masking framework (IMETU-Identify, Map, Execute, Test, and Utilize) is proposed and focuses on the first two modules. The analyzed health data attributes are based on the Discharge Abstract Database (DAD - Acute Inpatient in Canada). The proposed component is to identify the sensitive data, and select the best masking format to provide more data privacy and protection at rest (i.e., it can accurately be drilled down to a monthly aggregated level). This Module allows sensitive data attributes to be safely used and complies with the privacy regulatory requirements within the healthcare data warehouse by mapping them with the proper irreversible or reversible masking techniques. Native encryption techniques are avoided due to complex calculation and increase storage space.
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 | 0.005 | 0.004 |
| Meta-epidemiology (narrow) | 0.001 | 0.001 |
| Meta-epidemiology (broad) | 0.001 | 0.002 |
| Bibliometrics | 0.002 | 0.001 |
| Science and technology studies | 0.001 | 0.001 |
| Scholarly communication | 0.003 | 0.004 |
| Open science | 0.002 | 0.003 |
| Research integrity | 0.002 | 0.002 |
| Insufficient payload (model declined to judge) | 0.004 | 0.003 |
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".