Back

Improving postsurgical fall detection for older Americans using LLM-driven analysis of clinical narratives

Pillai, M.; Blumke, T. L.; Studnia, J.; Wang, Y.; Veigulis, Z. P.; Ware, A. D.; Hoover, P. J.; Carroll, I. R.; Humphreys, K.; Osborne, T. F.; Asch, S. M.; Hernandez-Boussard, T.; Curtin, C. M.

2024-06-26 health informatics
10.1101/2024.06.25.24309480 medRxiv
Show abstract

Postsurgical falls have significant patient and societal implications but remain challenging to identify and track. Detecting postsurgical falls is crucial to improve patient care for older adults and reduce healthcare costs. Large language models (LLMs) offer a promising solution for reliable and automated fall detection using unstructured data in clinical notes. We tested several LLM prompting approaches to postsurgical fall detection in two different healthcare systems with three open-source LLMs. The Mixtral-8x7B zero-shot had the best performance at Stanford Health Care (PPV = 0.81, recall = 0.67) and the Veterans Health Administration (PPV = 0.93, recall = 0.94). These results demonstrate that LLMs can detect falls with little to no guidance and lay groundwork for applications of LLMs in fall prediction and prevention across many different settings.

Matching journals

The top 5 journals account for 50% of the predicted probability mass.

50% of probability mass above

"Similar papers" are the closest papers from that journal in the model's embedding space. They show what the match is built on, but the ranking comes mostly from a classifier over the whole training set, not from these examples alone.