Applying stacking ensemble method to predict chronic kidney disease progression in Chinese population based on laboratory information system: a retrospective study

View article
PeerJ

Main article text

 

Introduction

Materials and Methods

Study population

Data collection

Statistical analysis

Machine learning-based model development and evaluation

Results

General characteristics

ML model establishment and evaluation

Performance of the model with different follow-up periods

External validation study

Discussion

Conclusions

Supplemental Information

Critical characteristics in the unmatched and propensity-score matched cohorts.

Values are presented as median (IQR) for continuous variables or n (%) for binary variables, *p < 0.05; **p < 0.01; ***p < 0.001.

DOI: 10.7717/peerj.18436/supp-1

Confusion matrices in training and validation cohort based on three laboratory variables.

DOI: 10.7717/peerj.18436/supp-2

Confusion matrices in training and validation cohort based on six laboratory variables.

DOI: 10.7717/peerj.18436/supp-3

Baseline clinical and biochemical characteristics of patients in external validation cohort.

Values are presented as median (IQR) for continuous variables or n (%) for binary variables, *p < 0.05; **p < 0.01; ***p < 0.001. Abbreviations: BMI, body mass index; estimated glomerular filtration rate (eGFR); 24hrUpr, 24-hour urine protein; Alb, albumin; ChE, cholinesterase; LDL, low density lipoprotein; HDL, high-density lipoprotein; TG, triglyceride; GGT, gamma-glutamyl transpeptidase; ALT, alanine aminotransferase; AST, aspartate amino transferase; Ca, calcium; ALP, alkaline phosphatase; K, potassium; P, phosphorus; CL, chlorine; Mg, magnesium; Na, sodium; UA, Uric Acid; GLU, glucose; PA, prealbumin; TBIL, total bilirubin; DBIL, direct bilirubin; IBIL, indirect bilirubin; TCHO, total cholesterol; TBA, total bile acid; TP, total protein; WBC, white blood cell; RBC, red blood cell; RDW, red blood cell distribution width; MCH, Mean corpuscular hemoglobin content; MCHC, mean corpuscular hemoglobin concentration; MCV, mean corpuscular volume; MPC, mean platelet volume; HGB, hemoglobin; HCT, hematocrit; PCT, platelet hematocrit; PLT, blood platelet count; SD, standard deviation; IQR, interquartile range

DOI: 10.7717/peerj.18436/supp-4

SHAP summary plot of the 6 features of the ensemble models (XGBoost, LightGBM, RF).

(A,C,E) The SHapley Additive exPlanation (SHAP) values. Blue dots represent low risk values of the features and red dots represent high risk values of the features. (B,D,F) Feature importance of model, evaluated by the average absolute SHAP value. Abbreviations: RF, random forest; 24hrUpr, 24-hour urine protein

DOI: 10.7717/peerj.18436/supp-5

Human participant information sheet.

DOI: 10.7717/peerj.18436/supp-6

The cohort included 987 patients with more than 24 months of follow-up.

DOI: 10.7717/peerj.18436/supp-7

Database used for the development of the prediction model based on machine learning.

DOI: 10.7717/peerj.18436/supp-8

External validation cohort.

DOI: 10.7717/peerj.18436/supp-9

Code for machine learning algorithms.

DOI: 10.7717/peerj.18436/supp-10

Additional Information and Declarations

Competing Interests

The authors declare that they have no competing interests.

Author Contributions

Jialin Du conceived and designed the experiments, performed the experiments, analyzed the data, prepared figures and/or tables, authored or reviewed drafts of the article, and approved the final draft.

Jie Gao conceived and designed the experiments, prepared figures and/or tables, and approved the final draft.

Jie Guan conceived and designed the experiments, prepared figures and/or tables, and approved the final draft.

Bo Jin conceived and designed the experiments, prepared figures and/or tables, and approved the final draft.

Nan Duan performed the experiments, authored or reviewed drafts of the article, and approved the final draft.

Lu Pang performed the experiments, authored or reviewed drafts of the article, and approved the final draft.

Haiming Huang analyzed the data, prepared figures and/or tables, and approved the final draft.

Qian Ma performed the experiments, prepared figures and/or tables, and approved the final draft.

Chenwei Huang performed the experiments, analyzed the data, authored or reviewed drafts of the article, and approved the final draft.

Haixia Li conceived and designed the experiments, performed the experiments, prepared figures and/or tables, authored or reviewed drafts of the article, and approved the final draft.

Human Ethics

The following information was supplied relating to ethical approvals (i.e., approving body and any reference numbers):

The Clinical Ethics Review Committee of the Peking University First Hospital (Ethical Application Ref: 2024Yan-237-002).

Data Availability

The following information was supplied regarding data availability:

The raw data and code are available in the Supplemental Files.

Funding

This study was supported by the National Natural Science Foundation of China (Grant No. 82072369), the “Sailing Plan” of Medical Youth Science and Technology Innovation of Peking University (Grant No. BMU2023YFJHPY003), the National High Level Hospital Clinical Research Funding (Scientific and Technological Achievements Transformation Incubation Guidance Fund Project of Peking University First Hospital) (Grant No. 2024CX12), and the National High Level Hospital Clinical Research Funding (Interdisciplinary Clinical Research Proiect of Peking University FirstHospital) (Grant No. 2022CR49). The funders had no role in study design, data collection and analysis, decision to publish, or preparation of the manuscript.

828 Visitors 776 Views 27 Downloads

Your institution may have Open Access funds available for qualifying authors. See if you qualify

Publish for free

Comment on Articles or Preprints and we'll waive your author fee
Learn more

Five new journals in Chemistry

Free to publish • Peer-reviewed • From PeerJ
Find out more