Guardado en:
| Autores principales: | , , , , |
|---|---|
| Formato: | Preprint |
| Publicado: |
2024
|
| Materias: | |
| Acceso en línea: | https://arxiv.org/abs/2405.18430 |
| Etiquetas: |
Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
|
| _version_ | 1866914814984454144 |
|---|---|
| author | Yao, Yixiang Cecil, Joseph Angyan, Praveen Bahroos, Neil Ravi, Srivatsan |
| author_facet | Yao, Yixiang Cecil, Joseph Angyan, Praveen Bahroos, Neil Ravi, Srivatsan |
| contents | Patient datasets contain confidential information which is protected by laws and regulations such as HIPAA and GDPR. Ensuring comprehensive patient information necessitates privacy-preserving entity resolution (PPER), which identifies identical patient entities across multiple databases from different healthcare organizations while maintaining data privacy. Existing methods often lack cryptographic security or are computationally impractical for real-world datasets. We introduce a PPER pipeline based on AMPPERE, a secure abstract computation model utilizing cryptographic tools like homomorphic encryption. Our tailored approach incorporates extensive parallelization techniques and optimal parameters specifically for patient datasets. Experimental results demonstrate the proposed method's effectiveness in terms of accuracy and efficiency compared to various baselines. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2405_18430 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Feasibility of Privacy-Preserving Entity Resolution on Confidential Healthcare Datasets Using Homomorphic Encryption Yao, Yixiang Cecil, Joseph Angyan, Praveen Bahroos, Neil Ravi, Srivatsan Computational Engineering, Finance, and Science Patient datasets contain confidential information which is protected by laws and regulations such as HIPAA and GDPR. Ensuring comprehensive patient information necessitates privacy-preserving entity resolution (PPER), which identifies identical patient entities across multiple databases from different healthcare organizations while maintaining data privacy. Existing methods often lack cryptographic security or are computationally impractical for real-world datasets. We introduce a PPER pipeline based on AMPPERE, a secure abstract computation model utilizing cryptographic tools like homomorphic encryption. Our tailored approach incorporates extensive parallelization techniques and optimal parameters specifically for patient datasets. Experimental results demonstrate the proposed method's effectiveness in terms of accuracy and efficiency compared to various baselines. |
| title | Feasibility of Privacy-Preserving Entity Resolution on Confidential Healthcare Datasets Using Homomorphic Encryption |
| topic | Computational Engineering, Finance, and Science |
| url | https://arxiv.org/abs/2405.18430 |