Explainable AI unravels sepsis heterogeneity via coagulation-inflammation profiles for prognosis and stratification

Sepsis is a leading cause of hospital mortality, and its significant heterogeneity complicates prognosis and stratification. To address this challenge, we developed an explainable artificial intelligence prognostic model (SepsisFormer, a transformer-based neural network) and an automated risk-stratification tool (SMART) for sepsis. In a multi-center retrospective study of 12,408 sepsis patients, SepsisFormer achieved high predictive accuracy (AUC: 0.9301, sensitivity: 0.9346, and specificity: 0.8312). SMART (AUC: 0.7360) surpassed most established scoring systems. Seven coagulation-inflammatory routine laboratory measurements and patient age were identified to classify patients' four risk levels (mild, moderate, severe, dangerous) and two subphenotypes (CIS1 and CIS2), each with distinct clinical characteristics and mortality rates. Notably, patients with moderate/severe levels or CIS2 derive more significant benefits from anticoagulant treatment. Our work, therefore, offers a set of simple, real-time executable tools for sepsis heterogeneity, demonstrating the potential to enhance sepsis clinical practice globally, particularly in resource-constrained healthcare settings.

Authors

Institutions

Publication Details

Journal
Nature Communications
Published
2025-11-24
DOI
https://doi.org/10.1038/s41467-025-65365-z
Primary Topic
Sepsis Diagnosis and Treatment
Type
article
Field-Weighted Citation Impact
0.00

Funders

Controls
|||
ALL TIME
JAN
FEB
MAR
APR
MAY
JUN
JUL
AUG
SEP
OCT
article

Explainable AI unravels sepsis heterogeneity via coagulation-inflammation profiles for prognosis and stratification

Yangguang Ren, Jialian Wang, Zefeng Yu, Kai Wu et al.
Nature Communications
Sepsis Diagnosis and Treatment
article

Explainable AI unravels sepsis heterogeneity via coagulation-inflammation profiles for prognosis and stratification

Yangguang Ren, Jialian Wang, Zefeng Yu, Kai Wu, Z. Chen, Chongke Hu, Yang Luo, Fei Guo, Linhui Shi, Yue‐qiao Chen, Fan Zhang, Hong Zhang, Jiaying Shen, Li Zhu, Bailin Niu, Lanqi Liu, Tzu‐Ming Liu, Xingyu Tao, Wei Yu, Hongjun Chen, Fen Liu
article en

Abstract

Sepsis is a leading cause of hospital mortality, and its significant heterogeneity complicates prognosis and stratification. To address this challenge, we developed an explainable artificial intelligence prognostic model (SepsisFormer, a transformer-based neural network) and an automated risk-stratification tool (SMART) for sepsis. In a multi-center retrospective study of 12,408 sepsis patients, SepsisFormer achieved high predictive accuracy (AUC: 0.9301, sensitivity: 0.9346, and specificity: 0.8312). SMART (AUC: 0.7360) surpassed most established scoring systems. Seven coagulation-inflammatory routine laboratory measurements and patient age were identified to classify patients' four risk levels (mild, moderate, severe, dangerous) and two subphenotypes (CIS1 and CIS2), each with distinct clinical characteristics and mortality rates. Notably, patients with moderate/severe levels or CIS2 derive more significant benefits from anticoagulant treatment. Our work, therefore, offers a set of simple, real-time executable tools for sepsis heterogeneity, demonstrating the potential to enhance sepsis clinical practice globally, particularly in resource-constrained healthcare settings.

Nature CommunicationsVol. 16(1)
Brigham and Women's Hospital (US), Harvard University (US), Nanchang University (CN), Chongqing University (CN), University of Macau (MO), Kunming Medical University (CN), Second Affiliated Hospital of Kunming Medical College (CN), Ningbo Medical Center Lihuili Hospital (CN), The Affiliated Yongchuan Hospital of Chongqing Medical University (CN), Chongqing Emergency Medical Center (CN), Qilu Hospital of Shandong University (CN), First Affiliated Hospital of Nanchang University (CN), Jiangxi University of Finance and Economics (CN), Chongqing Medical University (CN)
Emory University, National Natural Science Foundation of China, Beihang University, Nanchang University, National Science and Technology Major Project, Fundamental Research Funds for the Central Universities
Openalex Percentile: Top 53%
Sepsis Diagnosis and Treatment
DOIOpen Access PDFOpenAlex
AI Navigator

Ask Laika to Summarize, Analyze, and Connect papers live on the map.

Summarize Papers & Methodologies

Extract key findings, datasets, and comparative methods across publications.

Benchmark Rankings & Visual Analytics

Rank top research institutions, authors, funders, topics, and journals by Field-Weighted Citation Impact (FWCI) and paper volume with instant charts.

Connect Distant Disciplines

Bridge topological clusters on the map to find hidden collaborative intersections.