CoChat
Sign Up
Cited by 35Artificial Intelligence in HealthcareExplainable Artificial Intelligence (XAI)Data Mining Algorithms and Applications

Rule extraction from biased random forest and fuzzy support vector machine for early diagnosis of diabetes

Open access
Hao, Jingwei, Luo, Senlin, Pan, Limin·2022·Scientific Reports
DOI 10.1038/s41598-022-14143-8PMC PMC9198101
Open this paper in CoChat — free accountOpen PDF

Abstract

Due to concealed initial symptoms, many diabetic patients are not diagnosed in time, which delays treatment. Machine learning methods have been applied to increase the diagnosis rate, but most of them are black boxes lacking interpretability. Rule extraction is usually used to turn on the black box. As the number of diabetic patients is far less than that of healthy people, the rules obtained by the existing rule extraction methods tend to identify healthy people rather than diabetic patients. To address the problem, a method for extracting reduced rules based on biased random forest and fuzzy support vector machine is proposed. Biased random forest uses the k-nearest neighbor (k-NN) algorithm to identify critical samples and generates more trees that tend to diagnose diabetes based on critical samples to improve the tendency of the generated rules for diabetic patients. In addition, the conditions and rules are reduced based on the error rate and coverage rate to enhance interpretability. Experiments on the Diabetes Medical Examination Data collected by Beijing Hospital (DMED-BH) dataset demonstrate that the proposed approach has outstanding results (MCC = 0.8802) when the rules are similar in number. Moreover, experiments on the Pima Indian Diabetes (PID) and China Health and Nutrition Survey (CHNS) datasets prove the generalization of the proposed method.

The claims and statistics of this paper haven’t been checked yet.

Run the check — free, no account needed. It reads the open-access text and checks the sources it cites.

A few free checks a day · papers already verified open instantly · results are public

Integrity signals

Registry

Crossref · 10.1038/s41598-022-14143-8

Cites

1 of 1 references verified0 citation errors · 0 not checkable

Statistics

Claims the paper makes

The claims and statistics of this paper haven’t been checked yet.

Run the check — free, no account needed. It reads the open-access text and checks the sources it cites.

A few free checks a day · papers already verified open instantly · results are public

Claims other papers make about this one

Each is checked against this paper’s own text: does it say what the citing paper says it does?

  • When combined with Random Forests, fuzzy logic can enhance model performance without sacrificing interpretability.

    “When combined with Random Forests, an ensemble-based machine learning method known for handling non-linear relationships and high-dimensional data, fuzzy logic can enhance model performance without sacrificing interpretability”

    From A hybrid fuzzy logic–Random Forest model to predict psychiatric treatment order outcomes: an interpretable tool for legal decision support (2025) · cites this paper as Hao et al., 2022

    The Introduction describes a fuzzy SVM combined with a biased random forest (BRF) to produce accurate, reduced rules, and the Discussion reports improved performance and interpretability. This supports the central point for the paper’s diabetes-diagnosis method, but the method is not simply fuzzy logic combined with a standard random forest. The cited passages also do not establish the sentence’s description of random forests as handling non-linear relationships and high-dimensional data. (LLM, conf=0.82)

    Experimental — accuracy not yet measured

Self-check

Percentages, sums and reported differences re-computed from the paper’s own numbers.

The self-check needs the paper’s full text.

Cites

Flagged first, then by citations

Research works printed but not linked: 38

  1. [4]Bragg F Holmes MV Iona A Association between diabetes and cause-specific mortality in rural and urban areas of Chine [J] J. Am. Med. Assoc. 2017 317 3 280 289 10.1001/jama.2016.19720 PMC6520233 28114552 · DOI
  2. [6]Montazeri M Montazeri M Montazeri M Machine learning models in breast cancer survival prediction[J] Technol. Health Care 2016 24 1 31 42 10.3233/THC-151071 26409558 · DOI
  3. [7]Książek W Gandor M Pławiak P Comparison of various approaches to combine logistic regression with genetic algorithms in survival prediction of hepatocellular carcinoma[J] Comput. Biol. Med. 2021 134 104431 10.1016/j.compbiomed.2021.104431 34015670 · DOI
  4. [8]Doppalapudi S Qiu RG Badr Y Lung cancer survival period prediction and understanding: Deep learning approaches[J] Int. J. Med. Informatics 2021 148 104371 10.1016/j.ijmedinf.2020.104371 33461009 · DOI
  5. [9]Faura G Boix-Lemonche G Holmeide AK Colorimetric and electrochemical screening for early detection of diabetes mellitus and diabetic retinopathy—application of sensor arrays and machine learning[J] Sensors 2022 22 3 718 10.3390/s22030718 35161465 PMC8839630 · DOI
  6. [10]Choubey DK Tripathi S Kumar P Classification of diabetes by kernel based SVM with PSO[J] Recent Adv. Comput. Sci. Commun. 2021 14 4 1242 1255 10.2174/2213275912666190716094836 · DOI
  7. [11]Dremin V Marcinkevics Z Zherebtsov E Skin complications of diabetes mellitus revealed by polarized hyperspectral imaging and machine learning[J] IEEE Trans. Med. Imaging 2021 40 4 1207 1216 10.1109/TMI.2021.3049591 33406038 · DOI
  8. [13]Tiddi I Schlobach S Knowledge graphs as tools for explainable machine learning: A survey[J] Artif. Intell. 2022 302 103627 10.1016/j.artint.2021.103627 · DOI
  9. [15]Tama BA Rhee KH Tree-based classifier ensembles for early detection method of diabetes: An exploratory study [J] Artif. Intell. Rev. 2019 51 3 355 370 10.1007/s10462-017-9565-3 · DOI
  10. [16]Kumari S Kumar D Mittal M An ensemble approach for classification and prediction of diabetes mellitus using soft voting classifier[J] Int. J. Cognit. Comput. Eng. 2021 2 40 46 10.1016/j.ijcce.2021.01.001 · DOI
  11. [17]Farran B AlWotayan R Alkandari H Use of non-invasive parameters and machine-learning algorithms for predicting future risk of type 2 diabetes: A retrospective cohort study of health data from Kuwait [J] Front. Endocrinol. 2019 10 1 10.3389/fendo.2019.00624 PMC6749017 31572303 · DOI
  12. [18]Hasan MK Alam MA Das D Diabetes prediction using ensembling of different machine learning classifiers[J] IEEE Access 2020 8 76516 76531 10.1109/ACCESS.2020.2989857 · DOI
  13. [19]Singh A Dhillon A Kumar N eDiaPredict: An Ensemble-based framework for diabetes prediction[J] ACM Trans. Multimed. Comput. Commun. Appl. 2021 17 2s 1 26
  14. [20]Singh N Singh P Bhagat D A rule extraction approach from support vector machines for diagnosing hypertension among diabetics [J] Expert Syst. Appl. 2019 130 188 205 10.1016/j.eswa.2019.04.029 · DOI
  15. [21]Thaiyalnayaki K Classification of diabetes using deep learning and svm techniques[J] Int. J. Curr. Res. Rev. 2021 13 01 146 10.31782/IJCRR.2021.13127 · DOI
  16. [22]Jaiswal V Negi A Pal T A review on current advances in machine learning based diabetes prediction[J] Prim. Care Diabetes 2021 15 3 435 443 10.1016/j.pcd.2021.02.005 33642253 · DOI
  17. [23]Almansour NA Syed HF Khayat NR Neural network and support vector machine for the prediction of chronic kidney disease: A comparative study [J] Comput. Biol. Med. 2019 109 101 111 10.1016/j.compbiomed.2019.04.017 31054385 · DOI
  18. [24]Patil BM Joshi RC Toshniwal D Hybrid prediction model for Type-2 diabetic patients [J] Expert Syst. Appl. 2010 37 12 8102 8108 10.1016/j.eswa.2010.05.078 · DOI
  19. [25]Shen L Chen H Yu Z Evolving support vector machines using fruit fly optimization for medical data classification [J] Knowl.-Based Syst. 2016 96 61 75 10.1016/j.knosys.2016.01.002 · DOI
  20. [26]Santhanam T Padmavathi MS Application of K-Means and Genetic Algorithms for Dimension Reduction by Integrating SVM for Diabetes Diagnosis [C] In proceedings of Graph algorithms, High performance implementations and its applications, India 2015 47 76 83
  21. [27]Uzer, M. S., Yilmaz, N., & Inan, O. Feature selection method based on artificial bee colony algorithm and support vector machines for medical datasets classification [J]. Sci. World J. (2013). PMC3745978 23983632
  22. [29]Barakar N Bradley AP Rule extraction from support vector machines: A review [J] Neurocomputing 2010 74 1–3 178 190 10.1016/j.neucom.2010.02.016 · DOI
  23. [30]Núñez, H., Angulo, C., & Català, A. Rule extraction from support vector machines [C]. In proceedings of European Symposium on Artificial Neural Networks, Bruges, Belgium, 2002, 107–112.D
  24. [32]Martens D Baesens B Van Gestel T Comprehensible credit scoring models using rule extraction from support vector machines [J] Eur. J. Oper. Res. 2007 183 3 1466 1476 10.1016/j.ejor.2006.04.051 · DOI · Paper page
  25. [33]Han L Luo S Yu J Rule extraction from support vector machines using ensemble learning approach: An application for diagnosis of diabetes [J] IEEE J. Biomed. Health Inform. 2015 19 2 728 734 10.1109/JBHI.2014.2325615 24860043 · DOI
  26. [34]Liu C Soong R Lee W A predictive model for acute allograft rejection of liver transplantation [J] Expert Syst. Appl. 2018 94 228 236 10.1016/j.eswa.2017.11.003 · DOI
  27. [35]Khanam JJ Foo SY A comparison of machine learning algorithms for diabetes prediction[J] ICT Express 2021 7 4 432 439 10.1016/j.icte.2021.02.004 · DOI
  28. [36]Deshmukh, T., Fadewar, H. S., & Shukla, A. The detection of Prameha (diabetes) in Ayurvedic way with the help of fuzzy deep learning. In International Conference on Intelligent Computing and Communication Technologies, pp. 152–158 (Springer, Singapore, 2019).
  29. [38]Wang Y Wang D Geng N Stacking-based ensemble learning of decision trees for interpretable prostate cancer detection [J] Appl. Soft Comput. J. 2019 77 188 204 10.1016/j.asoc.2019.01.015 · DOI
  30. [39]Hayashi Y Yukita S Rule extraction using Recursive-Rule extraction algorithm with J48graft combined with sampling selection techniques for the diagnosis of type 2 diabetes mellitus in the Pima Indian dataset[J] Inf. Med. Unlocked 2016 2 92 104 10.1016/j.imu.2016.02.001 · DOI
  31. [40]Chakraborty M Biswas SK Purkayastha B Rule extraction from neural network using input data ranges recursively[J] N. Gener. Comput. 2019 37 1 67 96 10.1007/s00354-018-0048-0 · DOI
  32. [41]Bader-El-Den M Teitei E Perry T Biased random forest for dealing with the class imbalance problem [J] IEEE Trans. Neural Netw. Learn. Syst. 2019 30 7 2163 2172 10.1109/TNNLS.2018.2878400 30475733 · DOI
  33. [42]Saeys Y Inza I Larranaga P A review of feature selection techniques in bioinformatics [J] Bioinformatics 2007 23 19 2507 2517 10.1093/bioinformatics/btm344 17720704 · DOI
  34. [43]Jin, X., Xu, A., & Bie, R. Machine learning techniques and Chi-square feature selection for cancer classification using SAGE gene expression profiles [C]. In proceedings of the 1st workshop on Data Mining for Biomedical Applications, Singapore, 106–115.
  35. [44]Brown, G. A new perspective for information theoretic feature selection [C]. In Proceedings of the twelfth international conference on artificial intelligence and statistics (AISTATS), 49–56.
  36. [46]Menze BH Kelm BM Masuch R A comparison of random forest and its Gini importance with standard chemometric methods for the feature selection and classification of spectral data [J] BMC Bioinf. 2009 10 1 1 10.1186/1471-2105-10-213 PMC2724423 19591666 · DOI
  37. [48]Zhang XT Jiang YL Hu WJ A parallel ensemble fuzzy classifier for diabetes diagnosis [J] J. Med. Imaging Health Inf. 2020 10 3 544 551 10.1166/jmihi.2020.2972 · DOI
  38. [49]Hu YX Luo SL Han LF Deep supervised learning with mixture of neural networks [J] Artif. Intell. Med. 2020 102 1 10.1016/j.artmed.2019.101764 31980101 · DOI

Cited by

Sorted by citations

Authors
Hao, J., Luo, S., & Pan, L.
Affiliations
Beijing Institute of Technology (CN)
Corresponding author
Hao, Jingwei
ORCID
Venue
Scientific Reports
Publisher
Springer Science and Business Media LLC
Published
2022-06-14
Volume
12
Issue
1
Pages
9858-9858
ISSN
2045-2322 (ISSN-L)
DOI
10.1038/s41598-022-14143-8
PMC
PMC9198101
OpenAlex
W4282943750
Cited by
35
References
1
Citations by year
2026: 4 · 2025: 12 · 2024: 10 · 2023: 7 · 2022: 2
FWCI
5.80
Type
journal article
Language
en
Open access
Licence
Locations
  • Scientific Reports (publishedVersion, cc-by)
  • PubMed Central (publishedVersion, cc-by)
  • PubMed (publishedVersion)
  • DOAJ (DOAJ: Directory of Open Access Journals) (submittedVersion, cc-by-sa)
Funders
  • the 13th 5-year National Science and Technology Supporting Project, PR China (2018YFC2000302)
  • the Information Security Software Project (2020) of the Ministry of Industry and Information Technology, PR China (CEIEC-2020-ZM02-0134)
Topics
  • Health Sciences › Health Professions › Health Information Management › Artificial Intelligence in Healthcare
  • Physical Sciences › Computer Science › Artificial Intelligence › Explainable Artificial Intelligence (XAI)
  • Physical Sciences › Computer Science › Information Systems › Data Mining Algorithms and Applications
Keywords
rule extraction, fuzzy support vector machine, early detection of diabetes, class imbalance, interpretability, k-nearest neighbors, rule reduction, coverage rate, error rate, Pima Indians diabetes dataset
MeSH terms
Machine Learning, Algorithms, Diabetes Mellitus, Humans, Early Diagnosis, Support Vector Machine

About these checks

Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.

Statistics and arithmetic are recomputed, not judged.

Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.

What counts as a claim ›How we measure confidence ›How we check this ›

Are you an author, or do you see a problem with this page? Request a review