A Machine Learning Methodology for Diagnosing Chronic Kidney Disease

被引:89
|
作者
Qin, Jiongming [1 ]
Chen, Lin [2 ]
Liu, Yuhua [1 ]
Liu, Chuanjun [2 ]
Feng, Changhao [1 ]
Chen, Bin [1 ]
机构
[1] Southwest Univ, Coll Elect & Informat Engn, Chongqing Key Lab Nonlinear Circuit & Intelligent, Chongqing 400715, Peoples R China
[2] Kyushu Univ, Grad Sch Informat Sci & Elect Engn, Dept Elect, Fukuoka 8190395, Japan
关键词
Chronic kidney disease; machine learning; KNN imputation; integrated model; PREVALENCE; PREDICTION; MODELS;
D O I
10.1109/ACCESS.2019.2963053
中图分类号
TP [自动化技术、计算机技术];
学科分类号
0812 ;
摘要
Chronic kidney disease (CKD) is a global health problem with high morbidity and mortality rate, and it induces other diseases. Since there are no obvious symptoms during the early stages of CKD, patients often fail to notice the disease. Early detection of CKD enables patients to receive timely treatment to ameliorate the progression of this disease. Machine learning models can effectively aid clinicians achieve this goal due to their fast and accurate recognition performance. In this study, we propose a machine learning methodology for diagnosing CKD. The CKD data set was obtained from the University of California Irvine (UCI) machine learning repository, which has a large number of missing values. KNN imputation was used to fill in the missing values, which selects several complete samples with the most similar measurements to process the missing data for each incomplete sample. Missing values are usually seen in real-life medical situations because patients may miss some measurements for various reasons. After effectively filling out the incomplete data set, six machine learning algorithms (logistic regression, random forest, support vector machine, k-nearest neighbor, naive Bayes classifier and feed forward neural network) were used to establish models. Among these machine learning models, random forest achieved the best performance with 99.75% diagnosis accuracy. By analyzing the misjudgments generated by the established models, we proposed an integrated model that combines logistic regression and random forest by using perceptron, which could achieve an average accuracy of 99.83% after ten times of simulation. Hence, we speculated that this methodology could be applicable to more complicated clinical data for disease diagnosis.
引用
收藏
页码:20991 / 21002
页数:12
相关论文
共 50 条
  • [1] Diagnosing chronic kidney disease
    Glassock, Richard J.
    Winearls, Christopher
    CURRENT OPINION IN NEPHROLOGY AND HYPERTENSION, 2010, 19 (02): : 123 - 128
  • [2] Diagnosing asthma and chronic obstructive pulmonary disease with machine learning
    Spathis, Dimitris
    Vlamos, Panayiotis
    HEALTH INFORMATICS JOURNAL, 2019, 25 (03) : 811 - 827
  • [3] A novel machine learning methodology for the systematic extraction of chronic kidney disease comorbidities from abstracts
    Saghy, Eszter
    Elsharkawy, Mostafa
    Moriarty, Frank
    Kovacs, Sandor
    Wittmann, Istvan
    Zemplenyi, Antal
    FRONTIERS IN DIGITAL HEALTH, 2025, 7
  • [4] Machine learning to predict end stage kidney disease in chronic kidney disease
    Qiong Bai
    Chunyan Su
    Wen Tang
    Yike Li
    Scientific Reports, 12
  • [5] Machine learning to predict end stage kidney disease in chronic kidney disease
    Bai, Qiong
    Su, Chunyan
    Tang, Wen
    Li, Yike
    SCIENTIFIC REPORTS, 2022, 12 (01)
  • [6] Machine learning approaches for predicting and diagnosing chronic kidney disease: current trends, challenges, solutions, and future directions
    Gogoi, Prokash
    Valan, J. Arul
    INTERNATIONAL UROLOGY AND NEPHROLOGY, 2025, 57 (04) : 1245 - 1268
  • [7] Chronic Kidney Disease Prediction Using Machine Learning
    Kaur, Chamandeep
    Kumar, M. Sunil
    Anjum, Afsana
    Binda, M. B.
    Mallu, Maheswara Reddy
    Al Ansari, Mohammed Saleh
    JOURNAL OF ADVANCES IN INFORMATION TECHNOLOGY, 2023, 14 (02) : 384 - 391
  • [8] A Machine Learning Perspective for Predicting Chronic Kidney Disease
    Vanathi, D.
    Ramesh, S. M.
    Sudha, K.
    Tamizharasu, K.
    Sengottaiyan, N.
    Kalyanasundaram, P.
    2ND INTERNATIONAL CONFERENCE ON SUSTAINABLE COMPUTING AND SMART SYSTEMS, ICSCSS 2024, 2024, : 989 - 993
  • [9] Diagnosing and Characterizing Chronic Kidney Disease with Machine Learning: The Value of Clinical Patient Characteristics as Evidenced from an Open Dataset
    Figueroa, Juan
    Etim, Patrick
    Shibu, Adithyan Karanathu
    Berger, Derek
    Levman, Jacob
    ELECTRONICS, 2024, 13 (21)
  • [10] Machine learning models for chronic kidney disease diagnosis and prediction
    Rahman, Md. Mustafizur
    Al-Amin, Md.
    Hossain, Jahangir
    BIOMEDICAL SIGNAL PROCESSING AND CONTROL, 2024, 87