Superhuman performance on sepsis MIMIC-III data by distributional reinforcement learning

被引:6
|
作者
Boeck, Markus [1 ]
Malle, Julien [1 ]
Pasterk, Daniel [1 ]
Kukina, Hrvoje [1 ]
Hasani, Ramin [2 ]
Heitzinger, Clemens [1 ,3 ]
机构
[1] Tech Univ Wien TU Wien, Vienna, Austria
[2] MIT, 77 Massachusetts Ave, Cambridge, MA 02139 USA
[3] TU Wien, CAIML Ctr Artificial Intelligence & Machine Learn, Vienna, Austria
来源
PLOS ONE | 2022年 / 17卷 / 11期
基金
奥地利科学基金会;
关键词
D O I
10.1371/journal.pone.0275358
中图分类号
O [数理科学和化学]; P [天文学、地球科学]; Q [生物科学]; N [自然科学总论];
学科分类号
07 ; 0710 ; 09 ;
摘要
We present a novel setup for treating sepsis using distributional reinforcement learning (RL). Sepsis is a life-threatening medical emergency. Its treatment is considered to be a challenging high-stakes decision-making problem, which has to procedurally account for risk. Treating sepsis by machine learning algorithms is difficult due to a couple of reasons: There is limited and error-afflicted initial data in a highly complex biological system combined with the need to make robust, transparent and safe decisions. We demonstrate a suitable method that combines data imputation by a kNN model using a custom distance with state representation by discretization using clustering, and that enables superhuman decision-making using speedy Q-learning in the framework of distributional RL. Compared to clinicians, the recovery rate is increased by more than 3% on the test data set. Our results illustrate how risk-aware RL agents can play a decisive role in critical situations such as the treatment of sepsis patients, a situation acerbated due to the COVID-19 pandemic (Martineau 2020). In addition, we emphasize the tractability of the methodology and the learning behavior while addressing some criticisms of the previous work (Komorowski et al. 2018) on this topic.
引用
收藏
页数:18
相关论文
共 50 条
  • [21] Favorable Outcomes of Anticoagulation With Unfractioned Heparin in Sepsis-Induced Coagulopathy: A Retrospective Analysis of MIMIC-III Database
    Peng, Jiang-Chen
    Nie, Fang
    Li, Yu-Jie
    Xu, Qiao-Yi
    Xing, Shun-Peng
    Li, Wen
    Gao, Yuan
    FRONTIERS IN MEDICINE, 2022, 8
  • [22] The relationship between admission Braden score and poor prognosis in Sepsis patients: evidence from the MIMIC-III database
    Tingting Ding
    Lei Zhao
    Ben Hu
    Xing Wei
    Yongsheng Wang
    Yan Wang
    BMC Infectious Diseases, 25 (1)
  • [23] Impact of Pulmonary Arterial Hypertension on Systemic Inflammation, Cardiac Injury and Hemodynamics in Sepsis: A Retrospective Study From MIMIC-III
    He, Wencheng
    Zhang, Weixing
    An, Youzhong
    Huang, Lei
    Luo, Hua
    AMERICAN JOURNAL OF THE MEDICAL SCIENCES, 2022, 363 (04): : 311 - 321
  • [24] Non Linear Relationship between BMI and Sepsis among ICU Patients: Analysis of the MIMIC-III Real World Database
    Lintu, M. K.
    Puranik, Amitha
    Karun, Kalesh M.
    Micheal, David Raj
    Kamath, Asha
    JOURNAL OF CLINICAL AND DIAGNOSTIC RESEARCH, 2023, 17 (04) : 6 - 10
  • [25] ASSOCIATION OF SEX WITH CLINICAL OUTCOME IN CRITICALLY ILL SEPSIS PATIENTS: A RETROSPECTIVE ANALYSIS OF THE LARGE CLINICAL DATABASE MIMIC-III
    Xu, Jinghong
    Tong, Li
    Yao, Jiyou
    Guo, Zilu
    Lui, Ka Yin
    Hu, XiaoGuang
    Cao, Lu
    Zhu, Yanping
    Huang, Fa
    Guan, Xiangdong
    Cai, Changjie
    SHOCK, 2019, 52 (02): : 146 - 151
  • [26] Mapping Patient Trajectories using Longitudinal Extraction and Deep Learning in the MIMIC-III Critical Care Database
    Beaulieu-Jones, Brett K.
    Orzechowski, Patryk
    Moore, Jason H.
    PACIFIC SYMPOSIUM ON BIOCOMPUTING 2018 (PSB), 2018, : 123 - 132
  • [27] Hospital-acquired dysmagnesemia and mortality in critically ill patients: data from MIMIC-III database
    Zhang, Meng-Meng
    Ji, Mei-Jing
    Wang, Xiao-Ming
    Wang, Si-Qiong
    Sun, Jing
    Ma, Chun-Ming
    MAGNESIUM RESEARCH, 2021, 34 (02) : 64 - 73
  • [28] Development of a Nomogram to Predict 28-Day Mortality of Patients With Sepsis-Induced Coagulopathy: An Analysis of the MIMIC-III Database
    Lu, Zongqing
    Zhang, Jin
    Hong, Jianchao
    Wu, Jiatian
    Liu, Yu
    Xiao, Wenyan
    Hua, Tianfeng
    Yang, Min
    FRONTIERS IN MEDICINE, 2021, 8
  • [29] An empirical evaluation of deep learning for ICD-9 code assignment using MIMIC-III clinical notes
    Huang, Jinmiao
    Osorio, Cesar
    Sy, Luke Wicent
    COMPUTER METHODS AND PROGRAMS IN BIOMEDICINE, 2019, 177 : 141 - 153
  • [30] Prediction of acute kidney injury in patients with liver cirrhosis using machine learning models: evidence from the MIMIC-III and MIMIC-IV
    Tian, Jia
    Cui, Rui
    Song, Huinan
    Zhao, Yingzi
    Zhou, Ting
    INTERNATIONAL UROLOGY AND NEPHROLOGY, 2024, 56 (01) : 237 - 247