Development and validation of a machine learning model integrated with the clinical workflow for early detection of sepsis

被引:2
|
作者
Mahyoub, Mohammed A. [1 ,2 ]
Yadav, Ravi R. [1 ]
Dougherty, Kacie [1 ]
Shukla, Ajit [1 ]
机构
[1] Virtua Hlth, Adv Analyt & Solut, Marlton, NJ 08053 USA
[2] SUNY Binghamton, Dept Syst Sci & Ind Engn, Binghamton, NY USA
关键词
sepsis; early detection; machine learning; XGBoost; model interpretability; machine learning deployment; MORTALITY;
D O I
10.3389/fmed.2023.1284081
中图分类号
R5 [内科学];
学科分类号
1002 ; 100201 ;
摘要
BackgroundSepsis is a life-threatening condition caused by a dysregulated response to infection, affecting millions of people worldwide. Early diagnosis and treatment are critical for managing sepsis and reducing morbidity and mortality rates.Materials and methodsA systematic design approach was employed to build a model that predicts sepsis, incorporating clinical feedback to identify relevant data elements. XGBoost was utilized for prediction, and interpretability was achieved through the application of Shapley values. The model was successfully deployed within a widely used Electronic Medical Record (EMR) system.ResultsThe developed model demonstrated robust performance pre-operations, with a sensitivity of 92%, specificity of 93%, and a false positive rate of 7%. Following deployment, the model maintained comparable performance, with a sensitivity of 91% and specificity of 94%. Notably, the post-deployment false positive rate of 6% represents a substantial reduction compared to the currently deployed commercial model in the same health system, which exhibits a false positive rate of 30%.DiscussionThese findings underscore the effectiveness and potential value of the developed model in improving timely sepsis detection and reducing unnecessary alerts in clinical practice. Further investigations should focus on its long-term generalizability and impact on patient outcomes.
引用
收藏
页数:10
相关论文
共 50 条
  • [21] Development and Validation of a Machine Learning Model to Phenotype Surgical Patients at Risk of Developing Postoperative Sepsis
    Walters, Emily
    Hill, Brian
    Cannesson, Maxime
    ANESTHESIA AND ANALGESIA, 2020, 130 : 959 - 959
  • [22] Early Detection of Sepsis Induced Deterioration Using Machine Learning
    Dal Canton, Francesco
    Quinten, Vincent M.
    Wiering, Marco A.
    ARTIFICIAL INTELLIGENCE, BNAIC 2018, 2019, 1021 : 1 - 15
  • [23] Clinical Prediction Model Development and Validation for the Detection of Newborn Sepsis, Diagnostic Research Protocol
    Feleke, Sefineh Fenta
    Mulu, Berihun
    Azmeraw, Molla
    Temesgen, Dessie
    Dagne, Melsew
    Giza, Mastewal
    Yimer, Ali
    Dessie, Anteneh Mengist
    Yenew, Chalachew
    INTERNATIONAL JOURNAL OF GENERAL MEDICINE, 2022, 15 : 8025 - 8031
  • [24] Sepsis prediction, early detection, and identification using clinical text for machine learning: a systematic review
    Yan, Melissa Y.
    Gustad, Lise Tuset
    Nytro, Oystein
    JOURNAL OF THE AMERICAN MEDICAL INFORMATICS ASSOCIATION, 2022, 29 (03) : 559 - 575
  • [25] Clinical ground truth in machine learning for early sepsis diagnosis
    Lindner, Holger A.
    Thiel, Manfred
    Schneider-Lindner, Verena
    LANCET DIGITAL HEALTH, 2023, 5 (06): : E338 - E339
  • [26] Development and validation of a clinical prediction model for glioma grade using machine learning
    Wu, Mingzhen
    Luan, Jixin
    Zhang, Di
    Fan, Hua
    Qiao, Lishan
    Zhang, Chuanchen
    TECHNOLOGY AND HEALTH CARE, 2024, 32 (03) : 1977 - 1990
  • [27] DEVELOPMENT AND VALIDATION OF A NOVEL MACHINE LEARNING ALGORITHM TO PREDICT SEPSIS READMISSIONS
    Wardi, Gabriel
    Shashikumar, Supreeth
    Allen, Thomas
    Nemati, Shamim
    CRITICAL CARE MEDICINE, 2021, 49 (01) : 620 - 620
  • [28] Development and validation of an interpretable machine learning for mortality prediction in patients with sepsis
    He, Bihua
    Qiu, Zheng
    FRONTIERS IN ARTIFICIAL INTELLIGENCE, 2024, 7
  • [29] An early sepsis prediction model utilizing machine learning and unbalanced data processing in a clinical context
    Zhou, Luyao
    Shao, Min
    Wang, Cui
    Wang, Yu
    PREVENTIVE MEDICINE REPORTS, 2024, 45
  • [30] Development and validation of a novel blending machine learning model for hospital mortality prediction in ICU patients with Sepsis
    Zeng, Zhixuan
    Yao, Shuo
    Zheng, Jianfei
    Gong, Xun
    BIODATA MINING, 2021, 14 (01)