Explainable machine learning model for predicting furosemide responsiveness in patients with oliguric acute kidney injury

Background Although current guidelines didn’t support the routine use of furosemide in oliguric acute kidney injury (AKI) management, some patients may benefit from furosemide administration at an early stage. We aimed to develop an explainable machine learning (ML) model to differentiate between fu...

Full description

Saved in:
Bibliographic Details
Main Authors: Meng Jiang, Chun-qiu Pan, Jian Li, Li-gang Xu, Chang-li Li
Format: Article
Language:English
Published: Taylor & Francis Group 2023-12-01
Series:Renal Failure
Subjects:
Online Access:https://www.tandfonline.com/doi/10.1080/0886022X.2022.2151468
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1850040047936471040
author Meng Jiang
Chun-qiu Pan
Jian Li
Li-gang Xu
Chang-li Li
author_facet Meng Jiang
Chun-qiu Pan
Jian Li
Li-gang Xu
Chang-li Li
author_sort Meng Jiang
collection DOAJ
description Background Although current guidelines didn’t support the routine use of furosemide in oliguric acute kidney injury (AKI) management, some patients may benefit from furosemide administration at an early stage. We aimed to develop an explainable machine learning (ML) model to differentiate between furosemide-responsive (FR) and furosemide-unresponsive (FU) oliguric AKI.Methods From Medical Information Mart for Intensive Care-IV (MIMIC-IV) and eICU Collaborative Research Database (eICU-CRD), oliguric AKI patients with urine output (UO) < 0.5 ml/kg/h for the first 6 h after ICU admission and furosemide infusion ≥ 40 mg in the following 6 h were retrospectively selected. The MIMIC-IV cohort was used in training a XGBoost model to predict UO > 0.65 ml/kg/h during 6–24 h succeeding the initial 6 h for assessing oliguria, and it was validated in the eICU-CRD cohort. We compared the predictive performance of the XGBoost model with the traditional logistic regression and other ML models.Results 6897 patients were included in the MIMIC-IV training cohort, with 2235 patients in the eICU-CRD validation cohort. The XGBoost model showed an AUC of 0.97 (95% CI: 0.96–0.98) for differentiating FR and FU oliguric AKI. It outperformed the logistic regression and other ML models in correctly predicting furosemide diuretic response, achieved 92.43% sensitivity (95% CI: 90.88–93.73%) and 95.12% specificity (95% CI: 93.51–96.3%).Conclusion A boosted ensemble algorithm can be used to accurately differentiate between patients who would and would not respond to furosemide in oliguric AKI. By making the model explainable, clinicians would be able to better understand the reasoning behind the prediction outcome and make individualized treatment.
format Article
id doaj-art-1c5b152e128843be80a2f7b520350515
institution DOAJ
issn 0886-022X
1525-6049
language English
publishDate 2023-12-01
publisher Taylor & Francis Group
record_format Article
series Renal Failure
spelling doaj-art-1c5b152e128843be80a2f7b5203505152025-08-20T02:56:11ZengTaylor & Francis GroupRenal Failure0886-022X1525-60492023-12-0145110.1080/0886022X.2022.2151468Explainable machine learning model for predicting furosemide responsiveness in patients with oliguric acute kidney injuryMeng Jiang0Chun-qiu Pan1Jian Li2Li-gang Xu3Chang-li Li4Emergency and Trauma Center, The First Affiliated Hospital, Zhejiang University School of Medicine, Hangzhou, ChinaDepartment of Emergency Medicine, Nanfang Hospital, Southern Medical University, Guangzhou, ChinaDepartment of Traumatic Surgery, Tongji Hospital, Tongji Medical College, Huazhong University of Science and Technology, Wuhan, ChinaDepartment of Critical Care Medicine, Wuhan Central Hospital, Tongji Medical College, Huazhong University of Science and Technology, Wuhan, ChinaDepartment of FSTC Clinic of The First Affiliated Hospital, Zhejiang University School of Medicine, Hangzhou, ChinaBackground Although current guidelines didn’t support the routine use of furosemide in oliguric acute kidney injury (AKI) management, some patients may benefit from furosemide administration at an early stage. We aimed to develop an explainable machine learning (ML) model to differentiate between furosemide-responsive (FR) and furosemide-unresponsive (FU) oliguric AKI.Methods From Medical Information Mart for Intensive Care-IV (MIMIC-IV) and eICU Collaborative Research Database (eICU-CRD), oliguric AKI patients with urine output (UO) < 0.5 ml/kg/h for the first 6 h after ICU admission and furosemide infusion ≥ 40 mg in the following 6 h were retrospectively selected. The MIMIC-IV cohort was used in training a XGBoost model to predict UO > 0.65 ml/kg/h during 6–24 h succeeding the initial 6 h for assessing oliguria, and it was validated in the eICU-CRD cohort. We compared the predictive performance of the XGBoost model with the traditional logistic regression and other ML models.Results 6897 patients were included in the MIMIC-IV training cohort, with 2235 patients in the eICU-CRD validation cohort. The XGBoost model showed an AUC of 0.97 (95% CI: 0.96–0.98) for differentiating FR and FU oliguric AKI. It outperformed the logistic regression and other ML models in correctly predicting furosemide diuretic response, achieved 92.43% sensitivity (95% CI: 90.88–93.73%) and 95.12% specificity (95% CI: 93.51–96.3%).Conclusion A boosted ensemble algorithm can be used to accurately differentiate between patients who would and would not respond to furosemide in oliguric AKI. By making the model explainable, clinicians would be able to better understand the reasoning behind the prediction outcome and make individualized treatment.https://www.tandfonline.com/doi/10.1080/0886022X.2022.2151468Oliguric acute kidney injuryfurosemide responsivenessmachine learningXGBoost modeling
spellingShingle Meng Jiang
Chun-qiu Pan
Jian Li
Li-gang Xu
Chang-li Li
Explainable machine learning model for predicting furosemide responsiveness in patients with oliguric acute kidney injury
Renal Failure
Oliguric acute kidney injury
furosemide responsiveness
machine learning
XGBoost modeling
title Explainable machine learning model for predicting furosemide responsiveness in patients with oliguric acute kidney injury
title_full Explainable machine learning model for predicting furosemide responsiveness in patients with oliguric acute kidney injury
title_fullStr Explainable machine learning model for predicting furosemide responsiveness in patients with oliguric acute kidney injury
title_full_unstemmed Explainable machine learning model for predicting furosemide responsiveness in patients with oliguric acute kidney injury
title_short Explainable machine learning model for predicting furosemide responsiveness in patients with oliguric acute kidney injury
title_sort explainable machine learning model for predicting furosemide responsiveness in patients with oliguric acute kidney injury
topic Oliguric acute kidney injury
furosemide responsiveness
machine learning
XGBoost modeling
url https://www.tandfonline.com/doi/10.1080/0886022X.2022.2151468
work_keys_str_mv AT mengjiang explainablemachinelearningmodelforpredictingfurosemideresponsivenessinpatientswitholiguricacutekidneyinjury
AT chunqiupan explainablemachinelearningmodelforpredictingfurosemideresponsivenessinpatientswitholiguricacutekidneyinjury
AT jianli explainablemachinelearningmodelforpredictingfurosemideresponsivenessinpatientswitholiguricacutekidneyinjury
AT ligangxu explainablemachinelearningmodelforpredictingfurosemideresponsivenessinpatientswitholiguricacutekidneyinjury
AT changlili explainablemachinelearningmodelforpredictingfurosemideresponsivenessinpatientswitholiguricacutekidneyinjury