Deep Dive Readings
Completion requirements
View

Reading: Health system-scale language models are all-purpose prediction engines.
By Jiang L.Y. et al.
In the talk with Prof. Levi, we've touched on how Large Language Models can leverage unstructured clinical notes in Electronic Health Records (EHRs). This paper delves deeper into how we can transform this unstructured data into powerful prediction tools. By generating forecasts based on comprehensive patient data, these models can help healthcare professionals make more informed decisions.
Reading time: ~30 min
Reflective questions
- For which tasls were the Large Language Models employed, as reported by the authors?
- Were unstructured text data sufficient to achieve all the clinical and operational outcomes?
Source: Jiang, L.Y., Liu, X.C., Nejatian, N.P. et al. Health system-scale language models are all-purpose prediction engines. Nature 619, 357–362 (2023). Link