| Educational guide School of Engineering |
english |
| Biomedical Data Science (2022) |
 Subjects |
| ETHICS, REGULATION AND PRIVACY |
| Contents |
| IDENTIFYING DATA | 2023_24 |
| Subject | ETHICS, REGULATION AND PRIVACY | Code | 17705112 | |||||
| Study programme |
|
Cycle | 2nd | |||||
| Descriptors | Credits | Type | Year | Period | ||||
| 4.5 | Compulsory | First | 2Q |
|||||
| Competences | Learning outcomes | Contents |
| Planning | Methodologies | Personalized attention |
| Assessment | Sources of information | Recommendations |
| Topic | Sub-topic |
| Ethics | 1. Ethics and moralities 2. Omics Science and 5P Medicine: an overview 3. Values at stake in biomedical data science 4. Challenges in biomedical data science 5. ELSI issues 6. What ethics for Omics and Data Science? 7. Conclusions |
| Regulation | 1. Introduction to quality criteria 2. Use cases of data science in life sciences: genomics, health, clinical trials, manufacturing 3. 21 CFR Part 11 and extensions 4. Data Integrity 5. ALCOA++ applied to big data and cloud technologies 6. Big data designed as a driver for the implementation of the ICH 8 guide, beyond the CQA and CPP 7. Application of ICH 9 in big data and cloud systems 8. Quality systems applied to IT infrastructures 9. Traditional quality systems vs. current requirements for big data and cloud environments 10. IaaS Qualification Guidelines 11. Guides for the validation of IaaS, PaaS, and SaaS 12. Guides for the validation of indexed data, advanced analytics, AI, and Deep Learning on big data 13. Risk analysis in big data and cloud environments 14. Added value in the use of big data technologies applied to environments that require quality management 15. Regulatory approach in the new generation of Life Sciences |
| Privacy | 1. Privacy and Data protection by design 2. Privacy techniques and technologies 3. Privacy in databases 3.1. Basic concepts: risk and utility 3.2. Statistical disclosure control 3.3. Privacy models: k-anonymity and extensions, DP. 4. Privacy in machine learning and deep learning 4.1. Basic concepts 4.2. Membership, Attribute, and Reconstruction attacks 4.3. Privacy mechanisms: differential privacy, PATE, etc. 5. Anonymization software |
