With the rapid increase
of electronic health records (EHR), machine learning researchers have immense
opportunities to adopt artificial intelligence into diverse clinical
applications. To properly employ artificial intelligence for medicine, Jinsung
Yoon, a Research Scientist at Google, tried to handle the special properties of
the EHR and clinical applications and to construct end-to-end machine learning
frameworks for clinical decision support.
Jinsung proposed various
novel machine learning frameworks that can be applicable to a wide range of
clinical applications in practical settings. Those models are broadly utilized
including cohorts in the intensive care units, wards, and primary care
hospitals. Those works consistently and significantly improved state-of-the-art
models for handling missing data, understanding the trained model, and
generating private synthetic data that is critical for building end-to-end
artificial intelligence models for medicine.
Jinsung’s research
interests are not limited to artificial intelligence for medicine. He is
actively working on diverse and critical research topics in artificial
intelligence, such as anomaly detection, self-and semi-supervised learning, and
time-series modeling. Recently, Google Covid-19 forecasting models, in which
Jinsung participated as the main model developer, got significant attention in
both the United States and Japan. The forecasting models were widely used by
the US state governments and healthcare providers during the Covid-19 pandemic.
As explained above, his endless and passionate innovations would be deeply beneficial
in both industries and academia.