A new hybrid ensemble machine-learning model for severity risk assessment and post-COVID prediction system

被引:15
|
作者
Shakhovska, Natalya [1 ]
Yakovyna, Vitaliy [1 ,2 ]
Chopyak, Valentyna [3 ]
机构
[1] Lviv Polytech Natl Univ, Dept Artificial Intelligence, UA-79013 Lvov, Ukraine
[2] Univ Warmia & Mazury, Fac Math & Comp Sci, PL-10719 Olsztyn, Poland
[3] Danylo Halytskyi Lviv Natl Univ, Dept Clin Immunol & Allergol, UA-79010 Lvov, Ukraine
基金
新加坡国家研究基金会;
关键词
COVID-19; severity prediction; machine learning; ensemble classification; biomarkers; FEATURE-SELECTION;
D O I
10.3934/mbe.2022285
中图分类号
Q [生物科学];
学科分类号
07 ; 0710 ; 09 ;
摘要
Starting from December 2019, the COVID-19 pandemic has globally strained medical resources and caused significant mortality. It is commonly recognized that the severity of SARS-CoV-2 disease depends on both the comorbidity and the state of the patient's immune system, which is reflected in several biomarkers. The development of early diagnosis and disease severity prediction methods can reduce the burden on the health care system and increase the effectiveness of treatment and rehabilitation of patients with severe cases. This study aims to develop and validate an ensemble machine-learning model based on clinical and immunological features for severity risk assessment and post-COVID rehabilitation duration for SARS-CoV-2 patients. The dataset consisting of 35 features and 122 instances was collected from Lviv regional rehabilitation center. The dataset contains age, gender, weight, height, BMI, CAT, 6-minute walking test, pulse, external respiration function, oxygen saturation, and 15 immunological markers used to predict the relationship between disease duration and biomarkers using the machine learning approach. The predictions are assessed through an area under the receiver-operating curve, classification accuracy, precision, recall, and F1 score performance metrics. A new hybrid ensemble feature selection model for a post-COVID prediction system is proposed as an automatic feature cut-off rank identifier. A three-layer high accuracy stacking ensemble classification model for intelligent analysis of short medical datasets is presented. Together with weak predictors, the associative rules allowed improving the classification quality. The proposed ensemble allows using a random forest model as an aggregator for weak repressors' results generalization. The performance of the three-layer stacking ensemble classification model (AUC 0.978; CA 0.920; F1 score 0.921; precision 0.924; recall 0.920) was higher than five machine learning models, viz. tree algorithm with forward pruning; Naive Bayes classifier; support vector machine with RBF kernel; logistic regression, and a calibrated learner with sigmoid function and decision threshold optimization. Aging-related biomarkers, viz. CD3+, CD4+, CD8+, CD22+ were examined to predict post-COVID rehabilitation duration. The best accuracy was reached in the case of the support vector machine with the linear kernel (MAPE = 0.0787) and random forest classifier (RMSE = 1.822). The proposed three -layer stacking ensemble classification model predicted SARS-CoV-2 disease severity based on the cytokines and physiological biomarkers. The results point out that changes in studied biomarkers associated with the severity of the disease can be used to monitor the severity and forecast the rehabilitation duration.
引用
收藏
页码:6102 / 6123
页数:22
相关论文
共 50 条
  • [31] Hybrid Machine-Learning Model for Accurate Prediction of Filtration Volume in Water-Based Drilling Fluids
    Davoodi, Shadfar
    Al-Rubaii, Mohammed
    Wood, David A.
    Al-Shargabi, Mohammed
    Mehrad, Mohammad
    Rukavishnikov, Valeriy S.
    APPLIED SCIENCES-BASEL, 2024, 14 (19):
  • [32] Covid-19 Mortality Risk Prediction Model Using Machine Learning
    Sanchez-Galvez, Alba Maribel
    Sanchez-Galvez, Sully
    Alvarez-Gonzalez, Ricardo
    Rojas-Alarcon, Frida
    COMPUTACION Y SISTEMAS, 2023, 27 (04): : 881 - 888
  • [33] Early Mortality Risk Prediction in Covid-19 Patients Using an Ensemble of Machine Learning Models
    Walia, Harsh
    Jeevaraj, S.
    2021 INTERNATIONAL CONFERENCE ON COMPUTATIONAL PERFORMANCE EVALUATION (COMPE-2021), 2021, : 965 - 970
  • [34] Development and clinical impact assessment of a machine-learning model for early prediction of late-onset sepsis
    van den Berg, Merel
    Medina, O'Jay
    Loohuis, Ingmar
    van der Flier, Michiel
    Dudink, Jeroen
    Benders, Manon
    Bartels, Richard
    Vijlbrief, Daniel
    COMPUTERS IN BIOLOGY AND MEDICINE, 2023, 163
  • [35] The use of machine-learning methods for post-earthquake building usability assessment: A predictive model for seismic-risk impact analyses
    Tocchi, Gabriella
    Misra, Sushreyo
    Padgett, Jamie E. .
    Polese, Maria
    Di Ludovico, Marco
    INTERNATIONAL JOURNAL OF DISASTER RISK REDUCTION, 2023, 97
  • [36] Crash Severity Prediction Using Two-Layer Ensemble Machine Learning Model for Proactive Emergency Management
    Mansoor, Umer
    Ratrout, Nedal T.
    Rahman, Seyd Masiur
    Assi, Khaled
    IEEE ACCESS, 2020, 8 : 210750 - 210762
  • [37] Personalized risk prediction of symptomatic intracerebral hemorrhage after stroke thrombolysis using a machine-learning model
    Wang, Feng
    Huang, Yuanhanqing
    Xia, Yong
    Zhang, Wei
    Fang, Kun
    Zhou, Xiaoyu
    Yu, Xiaofei
    Cheng, Xin
    Li, Gang
    Wang, Xiaoping
    Luo, Guojun
    Wu, Danhong
    Liu, Xueyuan
    Campbell, Bruce C. V.
    Dong, Qiang
    Zhao, Yuwu
    THERAPEUTIC ADVANCES IN NEUROLOGICAL DISORDERS, 2020, 13
  • [38] A machine-learning prediction model to identify risk of firearm injury using electronic health records data
    Zhou, Hui
    Nau, Claudia
    Xie, Fagen
    Contreras, Richard
    Grant, Deborah Ling
    Negriff, Sonya
    Sidell, Margo
    Koebnick, Corinna
    Hechter, Rulin
    JOURNAL OF THE AMERICAN MEDICAL INFORMATICS ASSOCIATION, 2024, 31 (10) : 2173 - 2180
  • [39] A Hybrid Machine Learning Model Architecture with Clustering Analysis and Stacking Ensemble for Real Estate Price Prediction
    Cilgin, Cihan
    Gokcen, Hadi
    COMPUTATIONAL ECONOMICS, 2024,
  • [40] Development and validation of a hybrid deep learning–machine learning approach for severity assessment of COVID-19 and other pneumonias
    Doohyun Park
    Ryoungwoo Jang
    Myung Jin Chung
    Hyun Joon An
    Seongwon Bak
    Euijoon Choi
    Dosik Hwang
    Scientific Reports, 13