Smart disclosure initiatives and new regulations such as GDPR allow individuals to get the control back on their data by gathering their entire digital life in a Personal Data Management Systems (PDMS). Multiple PDMS ar-chitectures exist and differ on their ability to preserve data privacy and to perform collective computations crossing data of multiple individuals (e.g., epidemiological or social studies) but none of them satisfy both objectives. The emergence of Trusted Execution Environments (TEE) changes the game. We propose a solution called Trusted PDMS, combining the TEE and PDMS properties to manage the data of each individual, and a complete framework to execute collective computation on top of them, with strong privacy and fault tolerance guarantees. We demonstrate the practicality of the solution through a real case-study being conducted over 10.000 patients in the healthcare field.