Novel Solutions for Privacy, Security and Trust in Modern Medical Data Management Systems
Bibliographic record
Abstract
Data and analytics are indispensable parts of any successful business. Despite that, they can lead to serious privacy issues if not used safely. Even though the financial and legal consequences of privacy breaches are profound, the most damaging one, in the long run, is customer distrust. This is particularly the case for hypersensitive data such as personal health information. In recent years, the significance of privacy, security, and trust to the design of successful modern systems are being recognized more than ever before. Nevertheless, the current state of data management systems is far from achieving this goal. Particularly, in medical data management systems, handling sensitive data, mistrust is a barrier to many core processes such as data collection, sharing and analytics. Consequently, it is a primary cause of suboptimal medical services in our time. The primary direction of this thesis is to respond to these concerns of ethical nature by taking data privacy as a fundamental human right into serious consideration in the design of these processes. We highlight the emerging role of the blockchain in health information systems and recognize blockchain's ample opportunities for trust establishment. Consequently, we propose solutions based on this novel technology. More precisely, this thesis proposes a privacy-preserving data market for incentivedriven data collection for the development of reliable mathematical models that accelerate medical research. The blockchain aspect of the platform provides transparency as to the purpose for which the data is used to avoid the perception of data misuse/abuse. Secondly, this thesis proposes flexible blockchain-based access control mechanisms with multiple privacy protection layers for user-centric data sharing. Furthermore, it proposes a distributed machine learning-as-a-service platform for data analytics whose computational integrity can be verified efficiently by users. The strength of this platform lies in mutual privacy protection of user data and service provider intellectual property.
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 | 0.010 | 0.015 |
| Meta-epidemiology (narrow) | 0.000 | 0.001 |
| Meta-epidemiology (broad) | 0.001 | 0.001 |
| Bibliometrics | 0.001 | 0.001 |
| Science and technology studies | 0.003 | 0.004 |
| Scholarly communication | 0.007 | 0.012 |
| Open science | 0.002 | 0.009 |
| Research integrity | 0.004 | 0.005 |
| 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".