Future Monitor 한국어

Signal Asan Medical Center trained AI on 300,000 records across three hospitals without moving raw data

Summary

The chapter's applied case for the same mathematics is fully homomorphic encryption: in 2024 researchers at Asan Medical Center trained AI models across more than 300,000 patient records held at three hospitals with no institution's raw data leaving its own servers, and the chapter states the resulting models outperformed anything a single institution could have built alone.

Classification

Region menusGlobal
Occurrencescope:country · geo_region:east_asia · country:KR
Impactscope:global
Time horizon0-3 years (2026-07-26)
Last updated2026-07-29 04:49:53

Evidence 2

Part of trends 1

Directly linked issues 0

No objects.

Relation types: supports

Public id: fm-494f596442a2