WANG Jian,SHEN Jianguo,WANG Lisheng,et al.Construction of a traditional Chinese medicine syndrome element prediction model for mortality risk in sepsis patients based on retrospective study[J].Shanghai Journal of Traditional Chinese Medicine,2025,59(11):62-68.
WANG Jian,SHEN Jianguo,WANG Lisheng,et al.Construction of a traditional Chinese medicine syndrome element prediction model for mortality risk in sepsis patients based on retrospective study[J].Shanghai Journal of Traditional Chinese Medicine,2025,59(11):62-68. DOI: 10.16305/j.1007-1334.2025.z20241016002.
Construction of a traditional Chinese medicine syndrome element prediction model for mortality risk in sepsis patients based on retrospective study
To construct a traditional Chinese medicine (TCM) syndrome element prediction model based on retrospective study for the mortality risk in sepsis patients.
Methods
2
Clinical data were collected from 290 sepsis patients, who were divided into a survival group (
n
=151) and a death group (
n
=139) based on whether death occurred within 30 days. First, univariate analysis was performed to initially screen the predictors of mortality in sepsis patients, and multivariate logistic regression analysis was conducted to identify independent predictors and construct the TCM syndrome element prediction model. Second, the model's goodness of fit and discriminative validity were tested, and its stability was assessed through internal validation using Bootstrap. Finally, the prediction model was compared with the SOFA score to evaluate its predictive ability for se
psis mortality.
Results
2
The final model identified five risk factors: age and TCM syndrome elements of the brain, phlegm, blood stasis, and blood deficiency. Based on these factors, the TCM syndrome element prediction model was constructed. Goodness of fit testing indicated that the model performed well statistically (
P
>
0.05). The receiver operating characteristic (ROC) curve analysis showed that the area under the curve (AUC) of the prediction model was 0.765 (
P
<
0.05), indicating moderate discriminative validity. Bootstrap validation revealed that the average AUC of the prediction model was 0.740 across different datasets. Compared with the SOFA score, the prediction model had a higher AUC (
P
<
0.05), and decision curve analysis (DCA) showed that the model provided a higher net benefit.
Conclusion
2
The TCM syndrome element prediction model demonstrates certain stability and effectiveness in assessing the mortality risk of sepsis patients, showing promising clinical application potential.
关键词
Keywords
references
SINGER M , DEUTSCHMAN C S , SEYMOUR C W , et al . The third international consensus definitions for sepsis and septic shock(Sepsis-3) [J]. JAMA , 2016 , 315 ( 8 ): 801 - 810 .
KESHANI M , ALIKIAII B , BABAEI Z , et al . The effects of L‑carnitine supplementation on inflammation,oxidative stress, and clinical outcomes in critically Ⅲ patients with sepsis: a randomized, double-blind, controlled trial [J]. Nutr J , 2024 , 23 ( 1 ): 31 .
PAOLI C J , REYNOLDS M A , SINHA M , et al . Epidemiology and costs of sepsis in the united states-an analysis based on timing of diagnosis and severity level [J]. Crit Care Med , 2018 , 46 ( 12 ): 1889 - 1897 .
GUPTA J , MAJUMDER A K , SENGUPTA D , et al . Investigating computational models for diagnosis and prognosis of sepsis based on clinical parameters:Opportunities, challenges, and future research directions [J]. J Intensive Med , 2024 , 4 ( 4 ): 468 - 477 .
NIKRAVANGOLSEFID N , REDDY S , TRUONG H H , et al . Machine learning for predicting mortality in adult critically ill patients with Sepsis:A systematic review [J]. J Crit Care , 2024 , 84 : 154889 .
PERSSON I , MACURA A , BECEDAS D , et al . Early prediction of sepsis in intensive care patients using the machine learning algorithm NAVOY ® Sepsis, a prospective randomized clinical validation study [J]. J Crit Care , 2024 , 80 : 154400 .
WANG Y , FENG S . A prediction model for 30-day mortality of sepsis patients based on intravenous fluids and electrolytes [J]. Medicine(Baltimore) , 2022 , 101 ( 39 ): e30578 .
ZHANG Y , XU W , YANG P , et al . Machine learning for the prediction of sepsis-related death: a systematic review and meta-analysis [J]. BMC Med Inform Decis Mak , 2023 , 23 ( 1 ): 283 .
RHODES A , EVANS L E , ALHAZZANI W , et al . Surviving sepsis campaign:International guideline for management of sepsis and septic schock: 2016 [J]. Crit Care Med , 2017 , 45 ( 3 ): 486 - 552 .
BURSAC Z , GAUSS C H , WILLIAMS D K , et al . Purposeful selection of variables in logistic regression [J]. Source Code Biol Med , 2008 , 3 : 17 .
SUN C , GONG X , HOU L , et al . A nomogram based on conventional and contrast-enhanced ultrasound radiomics for the noninvasively prediction of axillary lymph node metastasis in breast cancer patients [J]. Front Oncol , 2024 , 14 : 1400872 .
ZHANG Z , GUO L , JIA L , et al . Factors contributing to sepsis-associated encephalopathy:a comprehensive systematic review and meta-analysis [J]. Front Med(Lausanne) , 2024 , 11 : 1379019 .
ARERO A G , VASHEGHANI-FARAHANI A , TIGABU B M , et al . Long-term risk and predictors of cerebrovascular events following sepsis hospitalization: A systematic review and meta-analysis [J]. Front Med(Lausanne) , 2022 , 9 : 1065476 .
ZHU M Y , TANG X K , GAO Y , et al . Impact of heart failure on outcomes in patients with sepsis:A systematic review and meta-analysis [J]. World J Clin Cases , 2023 , 11 ( 15 ): 3511 - 3521 .
SHANKAR-HARI M , AMBLER M , MAHALINGASIVAM V , et al . Evidence for a causal link between sepsis and long-term mortality:a systematic review of epidemiologic studies [J]. Crit Care , 2016 , 20 : 101 .
LI X , XU X , ZHANG J , et al . Review of the therapeutic effects of traditional Chinese medicine in sepsis-associated encephalopathy [J]. J Ethnopharmacol , 2024 , 334 : 118588 .
FAN T H , PREMRAJ L , ROBERTS J , et al . In-hospital neurologic complications, neuromonitoring, and long-term neurologic outcomes in patients with sepsis:A systematic review and meta-analysis [J]. Crit Care Med , 2024 , 52 ( 3 ): 452 - 463 .
PIVA S , BERTONI M , GITTI N , et al . Neurological complications of sepsis [J]. Curr Opin Crit Care , 2023 , 29 ( 2 ): 75 - 84 .
MOSTEL Z , PERL A , MARCK M , et al . Post-sepsis syndrome-an evolving entity that afflicts survivors of sepsis [J]. Mol Med , 2019 , 26 ( 1 ): 6 .
ARSHAD A , AHMED W , REHMAN N , et al . Tackling a deadly global phenomenon:sepsis induced coagulopathy:A narrative review [J]. J Pak Med Assoc , 2024 , 74 ( 5 ): 959 - 966 .
DO S N , DAO C X , NGUYEN T A , et al . Sequential Organ Failure Assessment (SOFA) score for predicting mortality in patients with sepsis in vietnamese intensive care units:a multicentre,cross-sectional study [J]. BMJ Open , 2023 , 13 ( 3 ): e064870 .
Construction and validation of a traditional Chinese medicine clinical prediction model for polycystic ovary syndrome with metabolic syndrome
Establishment and evaluation of a nomogram for predicting traditional Chinese medicine syndromes of menopause⁃like syndrome after endocrine therapy for postoperative breast cancer
Prediction models for cardiovascular diseases in elderly diabetic patients based on artificial intelligence algorithms and traditional Chinese medicine constitution types
Research on traditional Chinese medicine syndromes in prostate cancer based on cluster and factor analysis
Related Author
YU Jinglu
SUN Miao
HOU Lihui
PAN Zimeng
LI Jinyuan
CHEN Chuang
LONG Dile
LIN Dongyi
Related Institution
Department of Obstetrics, First Affiliated Hospital of Heilongjiang University of Chinese Medicine
Department of Gynecology Ⅱ, First Affiliated Hospital of Heilongjiang University of Chinese Medicine
Department of Obstetrics and Gynecology, Shunyi Hospital of Beijing Traditional Chinese Medicine Hospital
Guangxi University of Traditional Chinese Medicine
Jiangxi Ganzhou Nankang District Hospital of Traditional Chinese Medicine