Machine learning for predicting mortality in adult critically ill patients with Sepsis: A systematic review

被引:0
|
作者
Nikravangolsefid, Nasrin [1 ,2 ]
Reddy, Swetha [2 ]
Truong, Hong Hieu [1 ,3 ]
Charkviani, Mariam [1 ]
Ninan, Jacob [4 ]
Prokop, Larry J. [5 ]
Suppadungsuk, Supawadee [1 ]
Singh, Waryaam [1 ]
Kashani, Kianoush B. [1 ,2 ]
Garces, Juan Pablo Domecq [1 ,6 ]
机构
[1] Mayo Clin, Dept Med, Div Nephrol & Hypertens, Rochester, MN USA
[2] Mayo Clin, Dept Med, Div Pulm & Crit Care Med, Rochester, MN USA
[3] St Francis Hosp, Dept Med, Evanston, IL USA
[4] MultiCare Capital Med Ctr, Dept Nephrol & Crit Care, Olympia, WA USA
[5] Mayo Clin, Mayo Clin Lib, Rochester, MN USA
[6] Mayo Clin Hlth Syst, Dept Crit Care Med, Mankato, MN USA
关键词
Sepsis; Mortality; Machine learning; Prediction; HOSPITAL MORTALITY; LOGISTIC-REGRESSION; RISK STRATIFICATION; ACUTE PHYSIOLOGY; VALIDATION; MODELS; ASSOCIATION; DEFINITIONS; TRENDS; SCORE;
D O I
10.1016/j.jcrc.2024.154889
中图分类号
R4 [临床医学];
学科分类号
1002 ; 100602 ;
摘要
Introduction: Various Machine Learning (ML) models have been used to predict sepsis-associated mortality. We conducted a systematic review to evaluate the methodologies employed in studies to predict mortality among patients with sepsis. Methods: Following a pre-established protocol registered at the International Prospective Register of Systematic Reviews, we performed a comprehensive search of databases from inception to February 2024. We included peer-reviewed articles reporting predicting mortality in critically ill adult patients with sepsis. Results: Among the 1822 articles, 31 were included, involving 1,477,200 adult patients with sepsis. Nineteen studies had a high risk of bias. Among the diverse ML models, Logistic regression and eXtreme Gradient Boosting were the most frequently used, in 22 and 16 studies, respectively. Nine studies performed internal and external validation. Compared with conventional scoring systems such as SOFA, the ML models showed slightly higher performance in predicting mortality (AUROC ranges: 0.62-0.90 vs. 0.47-0.86). Conclusions: ML models demonstrate a modest improvement in predicting sepsis-associated mortality. The certainty of these findings remains low due to the high risk of bias and significant heterogeneity. Studies should include comprehensive methodological details on calibration and hyperparameter selection, adopt a standardized definition of sepsis, and conduct multicenter prospective designs along with external validations.
引用
收藏
页数:16
相关论文
共 50 条
  • [21] Machine learning algorithm to predict mortality in critically ill patients with sepsis-associated acute kidney injury
    Xunliang Li
    Ruijuan Wu
    Wenman Zhao
    Rui Shi
    Yuyu Zhu
    Zhijuan Wang
    Haifeng Pan
    Deguang Wang
    Scientific Reports, 13
  • [22] Comparison between traditional logistic regression and machine learning for predicting mortality in adult sepsis patients
    Wu, Hongsheng
    Liao, Biling
    Ji, Tengfei
    Ma, Keqiang
    Luo, Yumei
    Zhang, Shengmin
    FRONTIERS IN MEDICINE, 2025, 11
  • [23] Machine learning algorithm to predict mortality in critically ill patients with sepsis-associated acute kidney injury
    Li, Xunliang
    Wu, Ruijuan
    Zhao, Wenman
    Shi, Rui
    Zhu, Yuyu
    Wang, Zhijuan
    Pan, Haifeng
    Wang, Deguang
    SCIENTIFIC REPORTS, 2023, 13 (01)
  • [24] Mortality prediction in critically ill patients using machine learning score
    Dzaharudin, F.
    Ralib, A. M.
    Jamaludin, U. K.
    Nor, M. B. M.
    Tumian, A.
    Har, L. C.
    Ceng, T. C.
    5TH INTERNATIONAL CONFERENCE ON MECHANICAL ENGINEERING RESEARCH 2019 (ICMER 2019), 2020, 788
  • [25] Predicting Mortality in Critically Ill Patients Reply
    Wijdicks, Eelco F. M.
    Kramer, Andrew A.
    Rohs, Thomas, Jr.
    CRITICAL CARE MEDICINE, 2015, 43 (10) : E472 - E473
  • [26] PREDICTING AMINOGLYCOSIDE DOSAGE IN CRITICALLY ILL PATIENTS WITH SEPSIS
    STEVENS, MR
    CLINICAL PHARMACY, 1987, 6 (04): : 272 - 273
  • [27] EXPLAINABLE MACHINE LEARNING MODEL FOR PREDICTING ACUTE MORTALITY IN CRITICALLY ILL CIRRHOSIS PATIENTSE
    Deshmukh, Farah
    Merchant, Shamel S.
    HEPATOLOGY, 2020, 72 : 134A - 134A
  • [28] Eosinopenia as a marker of sepsis and mortality in critically ill patients
    A Savitskiy
    V Rudnov
    V Bagin
    Critical Care, 19 (Suppl 1):
  • [29] Diagnostic value of procalcitonin and presepsin for sepsis in critically ill adult patients: a systematic review and meta-analysis
    Kondo, Yutaka
    Umemura, Yutaka
    Hayashida, Kei
    Hara, Yoshitaka
    Aihara, Morio
    Yamakawa, Kazuma
    JOURNAL OF INTENSIVE CARE, 2019, 7 (1)
  • [30] Diagnostic value of procalcitonin and presepsin for sepsis in critically ill adult patients: a systematic review and meta-analysis
    Yutaka Kondo
    Yutaka Umemura
    Kei Hayashida
    Yoshitaka Hara
    Morio Aihara
    Kazuma Yamakawa
    Journal of Intensive Care, 7