Machine Learning Improves Upon Clinicians' Prediction of End Stage Kidney Disease

Aaron Chuah; Giles Walters; Daniel Christiadi; Krishna Karpe; Alice Kennard; Richard Singer; Girish Talaulikar; Wenbo Ge; Hanna Suominen; T Daniel Andrews; Simon Jiang

doi:10.3389/fmed.2022.837232

Machine Learning Improves Upon Clinicians' Prediction of End Stage Kidney Disease

Front Med (Lausanne). 2022 Mar 16:9:837232. doi: 10.3389/fmed.2022.837232. eCollection 2022.

Authors

Aaron Chuah¹, Giles Walters², Daniel Christiadi², Krishna Karpe², Alice Kennard², Richard Singer², Girish Talaulikar², Wenbo Ge³, Hanna Suominen^{3

4}, T Daniel Andrews^{1

5}, Simon Jiang^{1

2

5}

Affiliations

¹ Department of Immunology and Infectious Disease, John Curtin School of Medical Research, Australian National University (ANU), Canberra, ACT, Australia.
² Department of Renal Medicine, The Canberra Hospital, Garran, ACT, Australia.
³ School of Computing, Australian National University, ACT, Australia.
⁴ Department of Computing, University of Turku, Turku, Finland.
⁵ Centre for Personalised Immunology, Australian National University (ANU), Canberra, ACT, Australia.

Abstract

Background and objectives: Chronic kidney disease progression to ESKD is associated with a marked increase in mortality and morbidity. Its progression is highly variable and difficult to predict.

Methods: This is an observational, retrospective, single-centre study. The cohort was patients attending hospital and nephrology clinic at The Canberra Hospital from September 1996 to March 2018. Demographic data, vital signs, kidney function test, proteinuria, and serum glucose were extracted. The model was trained on the featurised time series data with XGBoost. Its performance was compared against six nephrologists and the Kidney Failure Risk Equation (KFRE).

Results: A total of 12,371 patients were included, with 2,388 were found to have an adequate density (three eGFR data points in the first 2 years) for subsequent analysis. Patients were divided into 80%/20% ratio for training and testing datasets.ML model had superior performance than nephrologist in predicting ESKD within 2 years with 93.9% accuracy, 60% sensitivity, 97.7% specificity, 75% positive predictive value. The ML model was superior in all performance metrics to the KFRE 4- and 8-variable models.eGFR and glucose were found to be highly contributing to the ESKD prediction performance.

Conclusions: The computational predictions had higher accuracy, specificity and positive predictive value, which indicates the potential integration into clinical workflows for decision support.

Keywords: XGBoost (Extreme Gradient Boosting); chronic kidney disease; end stage kidney disease (ESKD); machine learning (ML); prediction model.