Federated machine learning for predicting acute kidney injury in critically ill patients: a multicenter study in Taiwan

Health Information Science and Systems - Tập 11 Số 1
Chun-Te Huang1,2, Tsai‐Jung Wang2, Li‐Kuo Kuo3, Ming‐Ju Tsai4, Cong-Tat Cia5, Dung-Hung Chiang6, Pi‐Chen Chang7, Inn‐Wen Chong4, Yi-Shan Tsai8, Fa-Yauh Lee9, Chia‐Jen Liu1, Cheng‐Hsu Chen10, Kai-Chih Pai11, Chieh‐Liang Wu12
1Institute of Emergency and Critical Care Medicine, National Yang-Ming Chiao Tung University, Taipei, Taiwan
2Nephrology and Critical Care Medicine, Department of Internal Medicine and Critical Care Medicine, Taichung Veterans General Hospital, Taichung, Taiwan
3Department of Critical Care Medicine, MacKay Memorial Hospital, Taipei, Taiwan
4Division of Pulmonary and Critical Care Medicine, Department of Internal Medicine, School of Medicine, College of Medicine, Kaohsiung Medical University, Kaohsiung, Taiwan
5Division of Critical Care Medicine, Department of Internal Medicine, National Cheng Kung University Hospital, College of Medicine, National Cheng Kung University, Tainan, Taiwan
6Department of Critical Care Medicine, Taipei Veterans General Hospital, Taipei, Taiwan
7Department of Information Technology, MacKay Memorial Hospital, Taipei, Taiwan
8Department of Diagnostic Radiology, National Cheng Kung University Hospital, College of Medicine, National Cheng Kung University, Tainan, Taiwan
9Department of Information Technology, Taipei Veterans General Hospital, Taipei, Taiwan
10Division of Nephrology, Department of Internal Medicine, Taichung Veterans General Hospital, Taichung, Taiwan
11College of Engineering, Tunghai University, Taichung, Taiwan
12College of Medicine, National Chung Hshin University, Taichung, Taiwan

Tóm tắt

Abstract Purpose To address the contentious data sharing across hospitals, this study adopted a novel approach, federated learning (FL), to establish an aggregate model for acute kidney injury (AKI) prediction in critically ill patients in Taiwan. Methods This study used data from the Critical Care Database of Taichung Veterans General Hospital (TCVGH) from 2015 to 2020 and electrical medical records of the intensive care units (ICUs) between 2018 and 2020 of four referral centers in different areas across Taiwan. AKI prediction models were trained and validated thereupon. An FL-based prediction model across hospitals was then established. Results The study included 16,732 ICU admissions from the TCVGH and 38,424 ICU admissions from the other four hospitals. The complete model with 60 features and the parsimonious model with 21 features demonstrated comparable accuracies using extreme gradient boosting, neural network (NN), and random forest, with an area under the receiver-operating characteristic (AUROC) curve of approximately 0.90. The Shapley Additive Explanations plot demonstrated that the selected features were the key clinical components of AKI for critically ill patients. The AUROC curve of the established parsimonious model for external validation at the four hospitals ranged from 0.760 to 0.865. NN-based FL slightly improved the model performance at the four centers. Conclusion A reliable prediction model for AKI in ICU patients was developed with a lead time of 24 h, and it performed better when the novel FL platform across hospitals was implemented.

Từ khóa


Tài liệu tham khảo

Ronco C, Bellomo R, Kellum JA. Acute kidney injury. Lancet. 2019;394:1949–64.

Hoste EA, Bagshaw SM, Bellomo R, et al. Epidemiology of acute kidney injury in critically ill patients: the multinational AKI-EPI study. Intensive Care Med. 2015;41:1411–23.

Mehta RL, Burdmann EA, Cerda J, et al. Recognition and management of acute kidney injury in the International Society of Nephrology 0by25 global snapshot: a multintional cross-sectional study. Lancet. 2016;387:2017–25.

Flechet M, Falini S, Bonetti C, et al. Machine learning versus physicians’ prediction of acute kidney injury in critically ill adults: a prospective evaluation of the AKIpredictor. Crit Care. 2019;23:282.

Dong J, Feng T, Thapa-Chhetry B, et al. Machine learning model for early prediction of acute kidney injury (AKI) in pediatric critical care. Crit Care. 2021;25:288.

Le S, Allen A, Calvert J, et al. Convolutional neural network model for intensive care unit acute kidney injury prediction. Kidney Int Rep. 2021;6:1289–98.

Song X, Yu ASL, Kellum JA, et al. Cross-site transportability of an explainable artificial intelligence model for acute kidney injury prediction. Nat Commun. 2020;11:5668.

Rieke N, Hancox J, Li W, et al. The future of digital health with federated learning. NPJ Digit Med. 2020;3:119.

Tomasev N, Glorot X, Rae JW, et al. A clinically applicable approach to continuous prediction of future acute kidney injury. Nature. 2019;572:116–9.

Forcier MB, Gallois H, Mullan S, Joly Y. Integrating artificial intelligence into health care through data access: can the GDPR act as a beacon for policymakers? J Law Biosci. 2019;6:317–35.

Oh W, Nadkarni GN. Federated learning in health care using structured medical data. Adv Kidney Dis Health. 2023;30:4–16.

Loftus TJ, Ruppert MM, Shickel B, et al. Federated learning for preserving data privacy in collaborative healthcare research. Digit Health. 2022;8:20552076221134456.

Palevsky PM, Liu KD, Brophy PD, et al. KDOQI US commentary on the 2012 KDIGO clinical practice guideline for acute kidney injury. Am J Kidney Dis. 2013;61:649–72.

Collins GS, Reitsma JB, Altman DG, Moons KG. Transparent reporting of a multivariable prediction model for individual prognosis or diagnosis (TRIPOD): the TRIPOD statement. BMJ. 2015;350: g7594.

Friedman JH. Greedy function approximation: a gradient boosting machine. Ann Stat. 2001;29(5):1189–232.

Clark JW. Neural network modelling. Phys Med Biol. 1991;36(10):1259–317.

Breiman L. Random forests. Mach Learn. 2001;45:5–32.

Huang C, Li SX, Caraballo C, et al. Performance metrics for the comparative analysis of clinical risk prediction models employing machine learning. Circ Cardiovasc Qual Outcomes. 2021;14:e007526.

Vickers AJ, van Calster B, Steyerberg EW. A simple, step-by-step guide to interpreting decision curve analysis. Diagn Progn Res. 2019;3:18.

Pickkers P, Darmon M, Hoste E, et al. Acute kidney injury in the critically ill: an updated review on pathophysiology and management. Intensive Care Med. 2021;47:835–50.

Hoste EA, Kashani K, Gibney N, et al. Impact of electronic-alerting of acute kidney injury: workgroup statements from the 15(th) ADQI consensus conference. Can J Kidney Health Dis. 2016;3:10.

Colpaert K, Hoste EA, Steurbaut K, et al. Impact of real-time electronic alerting of acute kidney injury on therapeutic intervention and progression of RIFLE class. Crit Care Med. 2012;40:1164–70.

Wilson FP, Shashaty M, Testani J, et al. Automated, electronic alerts for acute kidney injury: a single-blind, parallel-group, randomised controlled trial. Lancet. 2015;385:1966–74.

Koyner JL, Carey KA, Edelson DP, Churpek MM. The development of a machine learning inpatient acute kidney injury prediction model. Crit Care Med. 2018;46:1070–7.

Chiofolo C, Chbat N, Ghosh E, Eshelman L, Kashani K. Automated continuous acute kidney injury prediction and surveillance: a random forest model. Mayo Clin Proc. 2019;94:783–92.

Zhang L, Wang Z, Zhou Z, et al. Developing an ensemble machine learning model for early prediction of sepsis-associated acute kidney injury. iScience. 2022;25: 104932.

Churpek MM, Carey KA, Edelson DP, et al. Internal and external validation of a machine learning risk score for acute kidney injury. JAMA Netw Open. 2020;3:e2012892.

Yue S, Li S, Huang X, et al. Machine learning for the prediction of acute kidney injury in patients with sepsis. J Transl Med. 2022;20:215.

Dayan I, Roth HR, Zhong A, et al. Federated learning for predicting clinical outcomes in patients with COVID-19. Nat Med. 2021;27:1735–43.

Dang TK, Lan X, Weng J, Mengling F. Federated learning for electronic health records. ACM Trans Intell Syst Technol. 2022;13:1–17.

Shiri I, Vafaei Sadr A, Akhavan A, et al. Decentralized collaborative multi-institutional PET attenuation and scatter correction using federated deep learning. Eur J Nucl Med Mol Imaging. 2023;50:1034–50.

Pati S, Baid U, Edwards B, et al. Federated learning enables big data for rare cancer boundary detection. Nat Commun. 2022;13:7346.

Ali M, Naeem F, Tariq M, Kaddoum G. Federated learning for privacy preservation in smart healthcare systems: a comprehensive survey. IEEE J Biomed Health Inform. 2022. https://doi.org/10.1109/JBHI.2022.3181823.

Nguyen TV, Dakka MA, Diakiw SM, et al. A novel decentralized federated learning approach to train on globally distributed, poor quality, and protected private medical data. Sci Rep. 2022;12:8888.

Thông tin
Thông tin xuất bản

Health Information Science and Systems

Tập 11 Số 1

Thông tin tác giả