Bridging Large Language Model–Based AI and Conventional Statistics for Retrospective Mortality Risk Assessment in Intra-Abdominal Sepsis and Septic Shock
Applied Biosciences · 28.10.2026 · 5 (4) · 102
DOI: 10.3390/applbiosci5040102 ↗Kurz gefasst
Fachartikel in der Zeitschrift Applied Biosciences, online erschienen am 28.10.2026. Verfasst von Andreea Elena Stan und 9 weiteren Autor:innen. Die Arbeit nennt 74 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).
Abstract (Originalsprache)
Background
Severe intra-abdominal infections are a major cause of sepsis and septic shock in intensive care units (ICUs), with high mortality and heterogeneity. Identifying variables associated with mortality is essential for risk assessment in this population. The potential of artificial intelligence (AI)-assisted analysis using large language models (LLMs) to complement conventional statistics remains underexplored.
Methods
This retrospective, single-center study analyzed 172 adult ICU patients with intra-abdominal sepsis or septic shock, identified among 6674 patients over one year. Conventional statistical methods assessed mortality-related variables. Two LLMs (Google Gemini 3.1 Pro and Claude Sonnet 5) were separately prompted to examine the pseudonymized, outcome-labeled dataset in five runs using structured prompts; their narrative outputs were compared with conventional findings.
Results
Overall in-ICU mortality was 60.5%. APACHE II showed the highest discriminatory capacity for mortality (AUC = 0.695), followed by admission lactate (AUC = 0.636) and SOFA score (AUC = 0.626). LLM outputs most consistently reproduced the direction of findings involving SOFA, APACHE II, and lactate, while coverage of other variables varied between models and runs.
Conclusions
Conventional statistics and AI-assisted LLM analyses yielded largely convergent findings for mortality markers. However, variability across other findings supports AI-assisted analysis as an exploratory, complementary approach. Further validation in larger, independent, multicenter cohorts is required before widespread routine clinical application.
Zitieren
APA
Stan, A. E., Patrascanu, E., Jalloul, W., Ristescu, I. A., Blaj, M., Breabăn, M., Olariu, M., Corduneanu, A., Iftene, A., & Stefanescu, C. (2026). Bridging Large Language Model–Based AI and Conventional Statistics for Retrospective Mortality Risk Assessment in Intra-Abdominal Sepsis and Septic Shock. Applied Biosciences, 5(4), 102. https://doi.org/10.3390/applbiosci5040102
Vancouver
Stan AE, Patrascanu E, Jalloul W, Ristescu IA, Blaj M, Breabăn M, et al. Bridging Large Language Model–Based AI and Conventional Statistics for Retrospective Mortality Risk Assessment in Intra-Abdominal Sepsis and Septic Shock. Applied Biosciences. 2026;5(4):102. doi:10.3390/applbiosci5040102
BibTeX
@article{Stan2026,
author = {Stan, Andreea Elena and Patrascanu, Emilia and Jalloul, Wael and Ristescu, Irina Anca and Blaj, Mihaela and Breabăn, Mihaela and Olariu, Maria-Ecaterina and Corduneanu, Andreia-Florentina and Iftene, Adrian and Stefanescu, Cipriana},
title = {Bridging Large Language Model–Based AI and Conventional Statistics for Retrospective Mortality Risk Assessment in Intra-Abdominal Sepsis and Septic Shock},
journal = {Applied Biosciences},
year = {2026},
volume = {5},
number = {4},
pages = {102},
doi = {10.3390/applbiosci5040102}
}
EUVIMED