Affiliation:
1. EEDIS Laboratory, Djillali Liabes University, Sidi Bel Abbès, Algeria
Abstract
Machine learning is a powerful tool to mine useful knowledge from vast databases. Many establishments in the medical area such as hospitals, laboratories want to join their efforts with the ambition to extract models that are more accurate. However, this approach faces problems. Due to the laws protecting patient privacy or other similar concerns, parties are reluctant to share their data. In vast amounts of data, which are useful and pertinent in constructing accurate data mining models? In this article, the researchers deal with these challenges for vertically distributed medical data. They propose an original secure wrapper solution to perform feature selection based on genetic algorithms and distributed Naïve Bayes. Contrary to the previous solutions, the original data is not perturbed. Therefore, the data utility and performance are preserved. They prove that the proposed solution selects relevant attributes to increase performance, preserving patient privacy.
Reference22 articles.
1. Applying data mining techniques to medical time series: an empirical case study in electroencephalography and stabilometry
2. Privacy preserving feature selection for distributed data using virtual dimension
3. Privacy Preserving Naïve Bayes Classification for Vertically Partitioned Biomedical Data in the Semi_honest Model Using Untrusted Cloud.;T.Boudheb;Proceedings of the 3rd International Conference on Networking and Advanced Systems (ICNAS’2017),2017
4. Brownlee, J. (2014, October 6). An Introduction to Feature Selection. Machine Learning Mastery. Retrieved from https://machinelearningmastery.com/an-introduction-to-feature-selection/
5. Chelvan, M., & Perumal, K. (2017). Stable Feature Selection with Privacy Preserving Data Mining Algorithm. In Advanced Informatics for Computing Research (pp. 227-237).