LLM-extracted features improved XGBoost's 30-day ED return AUC from 0.74 to 0.76, and an LLM-based explainability layer translated SHAP values into clinician-readable narratives with 99% expert-rated accuracy on a 100-sample review.
History of use, unsure if still using
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.LG 1years
2025 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Explainable AI for Mental Health Emergency Returns: Integrating LLMs with Predictive Modeling
LLM-extracted features improved XGBoost's 30-day ED return AUC from 0.74 to 0.76, and an LLM-based explainability layer translated SHAP values into clinician-readable narratives with 99% expert-rated accuracy on a 100-sample review.