Precision medicine is an emerging approach for disease treatment and prevention that delivers personalized care to individual patients by considering their genetic makeups, medical histories, environments, and lifestyles. One challenge of great importance is the security and privacy of precision health–related data, such as genomic data and electronic health records,which hampers the full potential of machine-learning (ML) algorithms. This paper proposes a generic machine learning with encryption (MLE) framework, which was used to build an ML model that predicts cancer from one of the most recent comprehensive genomics datasets in the field with greater accuracy while preserving the privacy of the cases as required. First, a machine learning with encryption (MLE) framework is proposed that considers the requirements and constraints and facilitates preforming analysis on a real precision healthcare dataset while preserving its privacy. Second, the model’s success is illustrated by considering a case study using the MSK-IMPACT dataset.
Input variables : Genomic patient records extracted from tumor tissue samples
Output Variables : Precision medicine for cancer
Statistical | : | Somers D | Accuracy | Precision and Recall | Confusion Matrix | F1 Score | Roc and Auc | Prevalence | Detection Rate | Balanced Accuracy | Cohen's Kappa | Concordance | Gini Coefficent | KS Statistic | Youden's J Index |
Infrastructure | : | Log Bytes | Logging/User/IAMPolicy | Logging/User/VPN | CPU Utilization | Memory Usage | Error Count | Prediction Count | Prediction Latencies | Private Endpoint Prediction Latencies | Private Endpoint Response Count |
Visit Model : github.com
Additional links : arxiv.org
Model Category | : | Public |
Date Published | : | February, 2021 |
Healthcare Domain | : | Life Sciences |
Code | : | github.com |
Data Privacy |
Deidentification |