Explainable AI for Fair Sepsis Mortality Predictive Model

被引:0
|
作者
Chang, Chia-Hsuan [1 ]
Wang, Xiaoyang [1 ]
Yang, Christopher C. [1 ]
机构
[1] Drexel Univ, Coll Comp & Informat, Philadelphia, PA 19104 USA
基金
美国国家科学基金会;
关键词
Fairness; Explainable artificial intelligence; MIMIC-IV; Sepsis mortality prediction;
D O I
10.1007/978-3-031-66535-6_29
中图分类号
TP18 [人工智能理论];
学科分类号
081104 ; 0812 ; 0835 ; 1405 ;
摘要
Artificial intelligence supports healthcare professionals with predictive modeling, greatly transforming clinical decision-making. This study addresses the crucial need for fairness and explainability in AI applications within healthcare to ensure equitable outcomes across diverse patient demographics. By focusing on the predictive modeling of sepsis-related mortality, we propose a method that learns a performance-optimized predictive model and then employs the transfer learning process to produce a model with better fairness. Our method also introduces a novel permutation-based feature importance algorithm aiming at elucidating the contribution of each feature in enhancing fairness on predictions. Unlike existing explainability methods concentrating on explaining feature contribution to predictive performance, our proposed method uniquely bridges the gap in understanding how each feature contributes to fairness. This advancement is pivotal, given sepsis's significant mortality rate and its role in one-third of hospital deaths. Our method not only aids in identifying and mitigating biases within the predictive model but also fosters trust among healthcare stakeholders by improving the transparency and fairness of model predictions, thereby contributing to more equitable and trustworthy healthcare delivery.
引用
收藏
页码:267 / 276
页数:10
相关论文
共 50 条
  • [1] Explainable AI Enabled Infant Mortality Prediction Based on Neonatal Sepsis
    Shaw, Priti
    Pachpor, Kaustubh
    Sankaranarayanan, Suresh
    COMPUTER SYSTEMS SCIENCE AND ENGINEERING, 2023, 44 (01): : 311 - 325
  • [2] Advances in Explainable, Fair, and Trustworthy AI
    Islam, Sheikh Rabiul
    Russell, Ingrid
    Eberle, William
    Talbert, Douglas
    Hasan, Md Golam Moula Mehedi
    INTERNATIONAL JOURNAL ON ARTIFICIAL INTELLIGENCE TOOLS, 2024, 33 (03)
  • [3] Explainable AI as evidence of fair decisions
    Leben, Derek
    FRONTIERS IN PSYCHOLOGY, 2023, 14
  • [4] A snapshot of AI in predictive toxicology: explainable AI
    Tetko, I. V.
    TOXICOLOGY LETTERS, 2022, 368 : S25 - S26
  • [5] A predictive model for damp risk in english housing with explainable AI
    Gulala Aziz
    Adam Hardy
    Scientific Reports, 15 (1)
  • [6] PREDICTIVE MODEL FOR MORTALITY IN PATIENTS WITH ABDOMINAL SEPSIS
    Osikov, M., V
    Telesheva, Lf
    Konashov, Ag
    Konashov, V. A.
    Gusev, A., V
    Boyko, M. S.
    BULLETIN OF RUSSIAN STATE MEDICAL UNIVERSITY, 2025, (01): : 11 - 18
  • [7] An Explainable AI based Clinical Assistance Model for Identifying Patients with the Onset of Sepsis
    Chakraborty, Snehashis
    Kumar, Komal
    Reddy, Balakrishna Pailla
    Meena, Tanushree
    Roy, Sudipta
    2023 IEEE 24TH INTERNATIONAL CONFERENCE ON INFORMATION REUSE AND INTEGRATION FOR DATA SCIENCE, IRI, 2023, : 297 - 302
  • [8] Explainable AI for Predictive Analytics on Employee Attrition
    Das, Sandip
    Sayan, Chakraborty
    Sajjan, Gairik
    Majumder, Soumi
    Dey, Nilanjan
    Tavares, Joao Manuel R. S.
    SOFT COMPUTING AND ITS ENGINEERING APPLICATIONS, ICSOFTCOMP 2022, 2023, 1788 : 147 - 157
  • [9] Explainable AI in Manufacturing: A Predictive Maintenance Case Study
    Hrnjica, Bahrudin
    Softic, Selver
    ADVANCES IN PRODUCTION MANAGEMENT SYSTEMS: TOWARDS SMART AND DIGITAL MANUFACTURING, PT II, 2020, 592 : 66 - 73
  • [10] Explainable AI (XAI) in Smart Grids for Predictive Maintenance: A survey
    Onu, Peter
    Pradhan, Anup
    Madonsela, Nelson Sizwe
    2024 1ST INTERNATIONAL CONFERENCE ON SMART ENERGY SYSTEMS AND ARTIFICIAL INTELLIGENCE, SESAI 2024, 2024, : 12 - 17