Pediatric Sepsis Cohort Detection Using In-Context Pointwise V-Usable Information

Yingya Li, Alon Geva, Steven Bethard, Timothy A. Miller, Kate Madden, Matthew A. Eisenberg, Daniel P. Kelly, Guergana Savova


Abstract
Pediatric sepsis diagnosis remains a major clinical challenge due to non-specific symptoms and a lack of reliable diagnostic criteria. Large language models (LLMs) provide a scalable solution for processing and understanding unstructured text in medical records. However, identifying the most suitable model is non-trivial given the rapid growth of available LLMs. In this work, we proposed using in-context pointwise V-usable information (pvi) to estimate task difficulty and guide model selection for pediatric sepsis cohort detection. We applied in-context pvi to estimate task difficulty and inform model selection across 12 state-of-the-art open LLMs on the task, using electronic medical record data from 507 patient encounters at a U.S. children’s hospital. We compared the performance of the best-fitting LLM to feature-rich baseline models and a fine-tuned transformer. Our results show that the pvi-selected LLM outperforms the baselines, although the feature-rich bag-of-words model with a support vector machine also achieves competitive performance. We believe our approach demonstrates a promising application of current LLM techniques to high-stakes clinical tasks.
Anthology ID:
2026.clinicalnlp-1.37
Volume:
Proceedings of the 8th Workshop on Clinical Natural Language Processing (Clinical NLP) @ LREC 2026
Month:
May
Year:
2026
Address:
Palma, Mallorca (Spain)
Editors:
Asma Ben Abacha, Steven Bethard, Danielle Bitterman, Tristan Naumann, Kirk Roberts
Venues:
ClinicalNLP | WS
SIG:
Publisher:
ELRA Language Resources Association (ELRA)
Note:
Pages:
336–349
Language:
External URL:
https://lrec.elra.info/lrec2026-ws-clinicalnlp-37
DOI:
10.63317/38bj4pwcnt3q
Bibkey:
Cite (ACL):
Yingya Li, Alon Geva, Steven Bethard, Timothy A. Miller, Kate Madden, Matthew A. Eisenberg, Daniel P. Kelly, and Guergana Savova. 2026. Pediatric Sepsis Cohort Detection Using In-Context Pointwise V-Usable Information. In Proceedings of the 8th Workshop on Clinical Natural Language Processing (Clinical NLP) @ LREC 2026, pages 336–349, Palma, Mallorca (Spain). ELRA Language Resources Association (ELRA).
Cite (Informal):
Pediatric Sepsis Cohort Detection Using In-Context Pointwise V-Usable Information (Li et al., ClinicalNLP 2026)
Copy Citation: