Author

Daniel Palacios

2 papers indexed here

We haven’t gathered this author’s papers yet. Follow them and we’ll fetch their work.

Not the right person? Other researchers publish under this name.

#small language model Preprint Oct 2026

Agentic LLM reasoning in pediatric diabetes outcome prediction from multimodal medical records

Using records from 2,489 youth with type 2 diabetes and 4,018 with type 1 diabetes, CEDAR (Clinical Evidence-Driven Agent for Risk-prediction), an evidence-citing, self-auditing LLM pipeline, outperformed trained machine learning in both cohorts.

Daniel Palacios, Guan-Tong Qi, Anna Kadi et al. · 0 citations

Preprint Aug 2026

Institution-Specific LLM Prompting Recovers PHI That De-identification Systems and Their Gold Standards Both Miss

Well-calibrated ICL resolves both the institutional PHI gap and the precision--recall trade-off in one LLM call per note, with advantages concentrated in contextual categories.

Daniel Palacios, Matthew Neeley, A. A. Otto et al. · 0 citations