Reconstructing Sepsis Trajectories from Clinical Case Reports using LLMs: the Textual Time Series Corpus for Sepsis

Shahriar Noroozizadeh, Jeremy Weiss
Proceedings of the 7th Conference on Health, Inference, and Learning, PMLR 333:10-51, 2026.

Abstract

Clinical case reports and discharge summaries may be the most complete and accurate summarization of patient encounters, yet they are finalized, i.e., timestamped after the encounter. Complementary structured data streams become available sooner but suffer from incompleteness. To train models and algorithms on more complete and temporally fine-grained data, we construct a pipeline to phenotype, extract, and annotate time-localized findings within case reports using large language models. We apply our pipeline to generate an open-access textual time series corpus for Sepsis-3 comprising 2,139 case reports from the PubMed-Open Access (PMOA) Subset. To validate our system, we apply it to PMOA and timeline annotations from i2b2/MIMIC-IV and compare the results to physician-expert annotations. We show high recovery rates of clinical findings (event match rates: GPT-5–0.93, Llama 3.3 70B Instruct–0.76) and strong temporal ordering (concordance: GPT-5–0.965, Llama 3.3 70B Instruct–0.908). Our work characterizes the ability of LLMs to time-localize clinical findings in text, illustrating the limitations of LLM use for temporal reconstruction and providing several potential avenues of improvement via multimodal integration.

Cite this Paper

BibTeX
@InProceedings{pmlr-v333-noroozizadeh26a, title = {Reconstructing Sepsis Trajectories from Clinical Case Reports using LLMs: the Textual Time Series Corpus for Sepsis}, author = {Noroozizadeh, Shahriar and Weiss, Jeremy}, booktitle = {Proceedings of the 7th Conference on Health, Inference, and Learning}, pages = {10--51}, year = {2026}, editor = {Healey, Elizabeth and Fries, Jason and Pollard, Tom and Tang, Shengpu and Zink, Anna and Hartvigsen, Tom and Agrawal, Monica and Finlayson, Sam and Glicksberg, Benjamin and Beaulieu-Jones, Brett and Wang, Kai and Fontalvo, Daseyra and Sarker, Tasmie and Chen, Irene and Alsentzer, Emily}, volume = {333}, series = {Proceedings of Machine Learning Research}, month = {29--30 Jun}, publisher = {PMLR}, pdf = {https://raw.githubusercontent.com/mlresearch/v333/main/assets/noroozizadeh26a/noroozizadeh26a.pdf}, url = {https://proceedings.mlr.press/v333/noroozizadeh26a.html}, abstract = {Clinical case reports and discharge summaries may be the most complete and accurate summarization of patient encounters, yet they are finalized, i.e., timestamped after the encounter. Complementary structured data streams become available sooner but suffer from incompleteness. To train models and algorithms on more complete and temporally fine-grained data, we construct a pipeline to phenotype, extract, and annotate time-localized findings within case reports using large language models. We apply our pipeline to generate an open-access textual time series corpus for Sepsis-3 comprising 2,139 case reports from the PubMed-Open Access (PMOA) Subset. To validate our system, we apply it to PMOA and timeline annotations from i2b2/MIMIC-IV and compare the results to physician-expert annotations. We show high recovery rates of clinical findings (event match rates: GPT-5–0.93, Llama 3.3 70B Instruct–0.76) and strong temporal ordering (concordance: GPT-5–0.965, Llama 3.3 70B Instruct–0.908). Our work characterizes the ability of LLMs to time-localize clinical findings in text, illustrating the limitations of LLM use for temporal reconstruction and providing several potential avenues of improvement via multimodal integration.} }
Endnote
%0 Conference Paper %T Reconstructing Sepsis Trajectories from Clinical Case Reports using LLMs: the Textual Time Series Corpus for Sepsis %A Shahriar Noroozizadeh %A Jeremy Weiss %B Proceedings of the 7th Conference on Health, Inference, and Learning %C Proceedings of Machine Learning Research %D 2026 %E Elizabeth Healey %E Jason Fries %E Tom Pollard %E Shengpu Tang %E Anna Zink %E Tom Hartvigsen %E Monica Agrawal %E Sam Finlayson %E Benjamin Glicksberg %E Brett Beaulieu-Jones %E Kai Wang %E Daseyra Fontalvo %E Tasmie Sarker %E Irene Chen %E Emily Alsentzer %F pmlr-v333-noroozizadeh26a %I PMLR %P 10--51 %U https://proceedings.mlr.press/v333/noroozizadeh26a.html %V 333 %X Clinical case reports and discharge summaries may be the most complete and accurate summarization of patient encounters, yet they are finalized, i.e., timestamped after the encounter. Complementary structured data streams become available sooner but suffer from incompleteness. To train models and algorithms on more complete and temporally fine-grained data, we construct a pipeline to phenotype, extract, and annotate time-localized findings within case reports using large language models. We apply our pipeline to generate an open-access textual time series corpus for Sepsis-3 comprising 2,139 case reports from the PubMed-Open Access (PMOA) Subset. To validate our system, we apply it to PMOA and timeline annotations from i2b2/MIMIC-IV and compare the results to physician-expert annotations. We show high recovery rates of clinical findings (event match rates: GPT-5–0.93, Llama 3.3 70B Instruct–0.76) and strong temporal ordering (concordance: GPT-5–0.965, Llama 3.3 70B Instruct–0.908). Our work characterizes the ability of LLMs to time-localize clinical findings in text, illustrating the limitations of LLM use for temporal reconstruction and providing several potential avenues of improvement via multimodal integration.
APA
Noroozizadeh, S. & Weiss, J.. (2026). Reconstructing Sepsis Trajectories from Clinical Case Reports using LLMs: the Textual Time Series Corpus for Sepsis. Proceedings of the 7th Conference on Health, Inference, and Learning, in Proceedings of Machine Learning Research 333:10-51 Available from https://proceedings.mlr.press/v333/noroozizadeh26a.html.

Related Material