Optimizing ICU care: Machine learning and PCA for early prediction of Renal Replacement Therapy requirement

Monira Mahmoud; Mohamed Bader; James McNicholas; Ramazan Esmeli

doi:10.3233/SHTI240553

Optimizing ICU care: Machine learning and PCA for early prediction of Renal Replacement Therapy requirement

Monira Mahmoud, Mohamed Bader, James McNicholas, Ramazan Esmeli

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

Abstract

Forecasting the need for Renal Replacement Therapy (RRT) in intensive care units (ICUs) at an early stage can enhance patient outcomes and optimize resource allocation. The study aimed to develop a model for early prediction of Renal Replacement Therapy (RRT) requirement within 24 hours of ICU admission, utilizing machine learning techniques and SHapley Additive exPlanations (SHAP). It assessed various models including Random Forest (RF), Neural Network (NN), and XGBoost, using data from 34,000 ICU admissions. XGBoost showed superior performance in terms of AUPRC, while RF performed better in AUC-ROC. Results were consistent before and after Principal Component Analysis (PCA) and feature evaluation analysis. The top 10 feature models outperformed the PCA model while using fewer inputs. These findings suggest the potential utility of the developed models in accurately predicting RRT requirement within 24 hours of ICU admission, aiding in efficient critical care delivery.

Original language	English
Title of host publication	Digital Health and Informatics Innovations for Sustainable Health Care Systems
Subtitle of host publication	Proceedings of MIE 2024
Editors	John Mantas, Arie Hasman, George Demiris, Kaija Saranto, Michael Marschollek, Theodoros N. Arvanitis, Ivana Ognjanović, Arriel Benis, Parisis Gallos, Emmanouil Zoulias, Elisavet Andrikopoulou
Publisher	IOS Press
Pages	879-883
Number of pages	5
ISBN (Print)	9781643685335
DOIs	https://doi.org/10.3233/SHTI240553
Publication status	Published - 25 Aug 2024
Event	34th Medical Informatics Europe Conference: Digital Health & Informatics Innovations for Sustainable Health Care Systems - Athens, Greece Duration: 25 Aug 2024 → 29 Aug 2024 https://mie2024.org/

Publication series

Name	Studies in Health Technology and Informatics
Publisher	IOS Press
Volume	316
ISSN (Print)	0926-9630
ISSN (Electronic)	1879-8365

Conference

Conference	34th Medical Informatics Europe Conference
Abbreviated title	MIE 2024
Country/Territory	Greece
City	Athens
Period	25/08/24 → 29/08/24
Internet address	https://mie2024.org/

Keywords

ICU
Machine learning
Prediction
Renal replacement therapy and Acute kidney injury

Access to Document

10.3233/SHTI240553

SHTI-316-SHTI240553Final published version, 182 KBLicence: CC BY-NC

Cite this

Mahmoud, M., Bader, M., McNicholas, J., & Esmeli, R. (2024). Optimizing ICU care: Machine learning and PCA for early prediction of Renal Replacement Therapy requirement. In J. Mantas, A. Hasman, G. Demiris, K. Saranto, M. Marschollek, T. N. Arvanitis, I. Ognjanović, A. Benis, P. Gallos, E. Zoulias, & E. Andrikopoulou (Eds.), Digital Health and Informatics Innovations for Sustainable Health Care Systems: Proceedings of MIE 2024 (pp. 879-883). (Studies in Health Technology and Informatics; Vol. 316). IOS Press. https://doi.org/10.3233/SHTI240553

Mahmoud, Monira ; Bader, Mohamed ; McNicholas, James et al. / Optimizing ICU care : Machine learning and PCA for early prediction of Renal Replacement Therapy requirement. Digital Health and Informatics Innovations for Sustainable Health Care Systems: Proceedings of MIE 2024. editor / John Mantas ; Arie Hasman ; George Demiris ; Kaija Saranto ; Michael Marschollek ; Theodoros N. Arvanitis ; Ivana Ognjanović ; Arriel Benis ; Parisis Gallos ; Emmanouil Zoulias ; Elisavet Andrikopoulou. IOS Press, 2024. pp. 879-883 (Studies in Health Technology and Informatics).

@inproceedings{73007e0022a7409790cb8c4d75ffbae7,

title = "Optimizing ICU care: Machine learning and PCA for early prediction of Renal Replacement Therapy requirement",

abstract = "Forecasting the need for Renal Replacement Therapy (RRT) in intensive care units (ICUs) at an early stage can enhance patient outcomes and optimize resource allocation. The study aimed to develop a model for early prediction of Renal Replacement Therapy (RRT) requirement within 24 hours of ICU admission, utilizing machine learning techniques and SHapley Additive exPlanations (SHAP). It assessed various models including Random Forest (RF), Neural Network (NN), and XGBoost, using data from 34,000 ICU admissions. XGBoost showed superior performance in terms of AUPRC, while RF performed better in AUC-ROC. Results were consistent before and after Principal Component Analysis (PCA) and feature evaluation analysis. The top 10 feature models outperformed the PCA model while using fewer inputs. These findings suggest the potential utility of the developed models in accurately predicting RRT requirement within 24 hours of ICU admission, aiding in efficient critical care delivery.",

keywords = "ICU, Machine learning, Prediction, Renal replacement therapy and Acute kidney injury",

author = "Monira Mahmoud and Mohamed Bader and James McNicholas and Ramazan Esmeli",

year = "2024",

month = aug,

day = "25",

doi = "10.3233/SHTI240553",

language = "English",

isbn = "9781643685335",

series = "Studies in Health Technology and Informatics",

publisher = "IOS Press",

pages = "879--883",

editor = "John Mantas and Arie Hasman and George Demiris and Kaija Saranto and Michael Marschollek and Arvanitis, {Theodoros N.} and Ivana Ognjanovi{\'c} and Arriel Benis and Parisis Gallos and Emmanouil Zoulias and Elisavet Andrikopoulou",

booktitle = "Digital Health and Informatics Innovations for Sustainable Health Care Systems",

address = "Netherlands",

note = "34th Medical Informatics Europe Conference : Digital Health & Informatics Innovations for Sustainable Health Care Systems, MIE 2024 ; Conference date: 25-08-2024 Through 29-08-2024",

url = "https://mie2024.org/",

}

Mahmoud, M, Bader, M, McNicholas, J & Esmeli, R 2024, Optimizing ICU care: Machine learning and PCA for early prediction of Renal Replacement Therapy requirement. in J Mantas, A Hasman, G Demiris, K Saranto, M Marschollek, TN Arvanitis, I Ognjanović, A Benis, P Gallos, E Zoulias & E Andrikopoulou (eds), Digital Health and Informatics Innovations for Sustainable Health Care Systems: Proceedings of MIE 2024. Studies in Health Technology and Informatics, vol. 316, IOS Press, pp. 879-883, 34th Medical Informatics Europe Conference, Athens, Greece, 25/08/24. https://doi.org/10.3233/SHTI240553

Optimizing ICU care: Machine learning and PCA for early prediction of Renal Replacement Therapy requirement. / Mahmoud, Monira; Bader, Mohamed; McNicholas, James et al.
Digital Health and Informatics Innovations for Sustainable Health Care Systems: Proceedings of MIE 2024. ed. / John Mantas; Arie Hasman; George Demiris; Kaija Saranto; Michael Marschollek; Theodoros N. Arvanitis; Ivana Ognjanović; Arriel Benis; Parisis Gallos; Emmanouil Zoulias; Elisavet Andrikopoulou. IOS Press, 2024. p. 879-883 (Studies in Health Technology and Informatics; Vol. 316).

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

TY - GEN

T1 - Optimizing ICU care

T2 - 34th Medical Informatics Europe Conference

AU - Mahmoud, Monira

AU - Bader, Mohamed

AU - McNicholas, James

AU - Esmeli, Ramazan

PY - 2024/8/25

Y1 - 2024/8/25

N2 - Forecasting the need for Renal Replacement Therapy (RRT) in intensive care units (ICUs) at an early stage can enhance patient outcomes and optimize resource allocation. The study aimed to develop a model for early prediction of Renal Replacement Therapy (RRT) requirement within 24 hours of ICU admission, utilizing machine learning techniques and SHapley Additive exPlanations (SHAP). It assessed various models including Random Forest (RF), Neural Network (NN), and XGBoost, using data from 34,000 ICU admissions. XGBoost showed superior performance in terms of AUPRC, while RF performed better in AUC-ROC. Results were consistent before and after Principal Component Analysis (PCA) and feature evaluation analysis. The top 10 feature models outperformed the PCA model while using fewer inputs. These findings suggest the potential utility of the developed models in accurately predicting RRT requirement within 24 hours of ICU admission, aiding in efficient critical care delivery.

AB - Forecasting the need for Renal Replacement Therapy (RRT) in intensive care units (ICUs) at an early stage can enhance patient outcomes and optimize resource allocation. The study aimed to develop a model for early prediction of Renal Replacement Therapy (RRT) requirement within 24 hours of ICU admission, utilizing machine learning techniques and SHapley Additive exPlanations (SHAP). It assessed various models including Random Forest (RF), Neural Network (NN), and XGBoost, using data from 34,000 ICU admissions. XGBoost showed superior performance in terms of AUPRC, while RF performed better in AUC-ROC. Results were consistent before and after Principal Component Analysis (PCA) and feature evaluation analysis. The top 10 feature models outperformed the PCA model while using fewer inputs. These findings suggest the potential utility of the developed models in accurately predicting RRT requirement within 24 hours of ICU admission, aiding in efficient critical care delivery.

KW - ICU

KW - Machine learning

KW - Prediction

KW - Renal replacement therapy and Acute kidney injury

UR - http://www.scopus.com/inward/record.url?scp=85202005223&partnerID=8YFLogxK

U2 - 10.3233/SHTI240553

DO - 10.3233/SHTI240553

M3 - Conference contribution

C2 - 39176934

AN - SCOPUS:85202005223

SN - 9781643685335

T3 - Studies in Health Technology and Informatics

SP - 879

EP - 883

BT - Digital Health and Informatics Innovations for Sustainable Health Care Systems

A2 - Mantas, John

A2 - Hasman, Arie

A2 - Demiris, George

A2 - Saranto, Kaija

A2 - Marschollek, Michael

A2 - Arvanitis, Theodoros N.

A2 - Ognjanović, Ivana

A2 - Benis, Arriel

A2 - Gallos, Parisis

A2 - Zoulias, Emmanouil

A2 - Andrikopoulou, Elisavet

PB - IOS Press

Y2 - 25 August 2024 through 29 August 2024

ER -

Mahmoud M, Bader M, McNicholas J, Esmeli R. Optimizing ICU care: Machine learning and PCA for early prediction of Renal Replacement Therapy requirement. In Mantas J, Hasman A, Demiris G, Saranto K, Marschollek M, Arvanitis TN, Ognjanović I, Benis A, Gallos P, Zoulias E, Andrikopoulou E, editors, Digital Health and Informatics Innovations for Sustainable Health Care Systems: Proceedings of MIE 2024. IOS Press. 2024. p. 879-883. (Studies in Health Technology and Informatics). doi: 10.3233/SHTI240553

Optimizing ICU care: Machine learning and PCA for early prediction of Renal Replacement Therapy requirement

Abstract

Publication series

Conference

Keywords

Access to Document

Fingerprint

Cite this