CoChat
Sign Up
Cited by 97Artificial Intelligence in HealthcareRetinal Imaging and AnalysisRough Sets and Fuzzy Logic

Learning ensemble classifiers for diabetic retinopathy assessment

Open access
Saleh, Emran, Błaszczyński, Jerzy, Moreno, Antonio, Valls, Aida, Romero-Aroca, Pedro, de la Riva-Fernández, Sofia, Słowiński, Roman·2018·Artificial Intelligence in Medicine
DOI 10.1016/j.artmed.2017.09.006
Open this paper in CoChat — free accountOpen PDF

Abstract

Diabetic retinopathy is one of the most common comorbidities of diabetes. Unfortunately, the recommended annual screening of the eye fundus of diabetic patients is too resource-consuming. Therefore, it is necessary to develop tools that may help doctors to determine the risk of each patient to attain this condition, so that patients with a low risk may be screened less frequently and the use of resources can be improved. This paper explores the use of two kinds of ensemble classifiers learned from data: fuzzy random forest and dominance-based rough set balanced rule ensemble. These classifiers use a small set of attributes which represent main risk factors to determine whether a patient is in risk of developing diabetic retinopathy. The levels of specificity and sensitivity obtained in the presented study are over 80%. This study is thus a first successful step towards the construction of a personalized decision support system that could help physicians in daily clinical practice.

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 · 10.1016/j.artmed.2017.09.006

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?

  • Saleh et al. reported that a fuzzy RF using retinal images for DR screening yielded an accuracy of 77.32%, sensitivity of 76.89%, and specificity of 77.43% for detecting the presence of DR.

    “the best results yielded an accuracy of 77.32%, sensitivity of 76.89% and specificity of 77.43% for detecting the presence of DR”

    From Artificial intelligence in diabetes management: Advancements, opportunities, and challenges (2023) · cites this paper as Saleh et al.109

    Table 8 (Additional information; page not provided) assigns 77.32% accuracy, 76.89% sensitivity, and 77.43% specificity to DRSA, not the fuzzy random forest (FRF). It reports 80.29%, 80.67%, and 80.18%, respectively, for FRF. The Conclusions (page not provided) describe analysis of retinal photos as a later, still-in-progress stage rather than the input to these classifiers. (LLM, conf=0.92)

    Checked by a reasoning model — may be wrong.

    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: 35

  1. Alghadyan, A. A. (2011). Diabetic retinopathy-an update. Saudi Journal of Ophthalmology, 25 , 99-111.
  2. Alickovic, E., & Subasi, A. (2016). Medical decision support system for diagnosis of heart arrhythmia using DWT and random forests classifier. Journal of medical systems, 40 , 1-12.
  3. Blasco, H., B laszczyński, J., Billaut, J., Nadal-Desbarats, L., Pradat, P.-F., Devos, D., Moreau, C., Andres, C. R., Emond, P., Corcia, P. et al. (2015). Comparative analysis of targeted metabolomics: Dominance- based rough set approach versus orthogonal partial least square-discriminant analysis. Journal of biomed- ical informatics, 53 , 291-299.
  4. B laszczyński, J., Greco, S., S lowiński, R., & Szelkag, M. (2009). Monotonic variable consistency rough set approaches. International journal of approximate reasoning, 50 , 979-999.
  5. B laszczyński, J., S lowiński, R., & Susmaga, R. (2011a). Rule-based estimation of attribute relevance. In International Conference on Rough Sets and Knowledge Technology (pp. 36-44). Springer.
  6. Cadenas, J. M., Garrido, M. C., Martínez, R., Pelta, D., & Bonissone, P. P. (2016). Gene priorization for tumor classification using an embedded method. In Computational Intelligence (pp. 363-380). Springer.
  7. Chandrakumar, T., & Kathirvel, R. (2016). Classifying diabetic retinopathy using deep learning architecture. International Journal of Engineering Research and Technology, 5 .
  8. Cvetković, B., Janko, V., Romero, A. E., Kafalı, Ö., Stathis, K., & Luštrek, M. (2016). Activity recognition for diabetic patients using a smartphone. Journal of Medical Systems, 40 , 256.
  9. Escorcia-Gutiérrez, J., Torrents-Barrena, J., Romero-Aroca, P., Valls, A., & Puig, D. (2016). Interactive optic disk segmentation ia discrete convexity shape knowledge using high-order functionals. In Artificial Intelligence Research and Development: Proceedings of the 19th International Conference of the Catalan Association for Artificial Intelligence, Barcelona, Catalonia, Spain, October 19-21, 2016 (p. 39). IOS Press volume 288.
  10. Gardiner, E. J., & Gillet, V. J. (2015). Perspectives on knowledge discovery algorithms recently introduced in chemoinformatics: Rough set theory, association rule mining, emerging patterns, and formal concept analysis. Journal of chemical information and modeling, 55 , 1781-1803.
  11. Greco, S., Matarazzo, B., & S lowiński, R. (2001). Rough sets theory for multicriteria decision analysis. European journal of operational research, 129 , 1-47.
  12. Haloi, M. (2015). Improved microaneurysm detection using deep neural networks. arXiv preprint arXiv:1505.04424 , . · arXiv
  13. IDF (2015). International Diabetes Federation. Diabetes Atlas 7th edition, 2015 , .
  14. Jiang, R., Bouridane, A., Crookes, D., Celebi, M. E., & Wei, H.-L. (2016). Privacy-protected facial biometric verification using fuzzy forest learning. IEEE Transactions on Fuzzy Systems, 24 , 779-790.
  15. Kafali, Ö. ., Schaechtle, U., & Stathis, K. (2014). Hydra: A hybrid diagnosis and monitoring architecture for diabetes. In 2014 IEEE 16th International Conference on e-Health Networking, Applications and Services (Healthcom) (pp. 531-536). doi:10.1109/HealthCom.2014.7001898. · DOI
  16. Khan, A., & Revett, K. (2004). Data mining the pima dataset using rough set theory with a special emphasis on rule reduction. In Multitopic Conference, 2004. Proceedings of INMIC 2004. 8th International (pp. 334-339). IEEE.
  17. Kovacs, W., Liu, C.-Y., Summers, R. M., & Yao, J. (2016). Differentiation of fat, muscle, and edema in thigh MRIs using random forest classification. In SPIE Medical Imaging (pp. 978507-978507). International Society for Optics and Photonics.
  18. Kulkarni, V. Y., & Sinha, P. K. (2013). Random forest classifiers: a survey and future research directions. International Journal of Advanced Computing, 36 , 1144-1153.
  19. La Torre, J. d., Valls, A., & Puig, D. (2016). Diabetic retinopathy detection hrough image analysis using deep convolutional neural networks. In Artificial Intelligence Research and Development: Proceedings of the 19th International Conference of the Catalan Association for Artificial Intelligence, Barcelona, Catalonia, Spain, October 19-21, 2016 (p. 58). IOS Press volume 288.
  20. Marsala, C. (2009). A fuzzy decision tree based approach to characterize medical data. In Fuzzy Systems, 2009. FUZZ-IEEE 2009. IEEE International Conference on (pp. 1332-1337). IEEE.
  21. Nakayama, H., Hattori, Y., & Ishii, R. (1999). Rule extraction based on rough set theory and its application to medical data analysis. In Systems, Man, and Cybernetics, 1999. IEEE SMC'99 Conference Proceedings. 1999 IEEE International Conference on (pp. 924-929). IEEE volume 5.
  22. Napierala, K., & Stefanowski, J. (2016). Types of minority class examples and their influence on learning classifiers from imbalanced data. Journal of Intelligent Information Systems, 46 , 563-597.
  23. Olafsdottir, E., & Stefansson, E. (2007). Biennial eye screening in patients with diabetes without retinopathy: 10-year experience. British journal of ophthalmology, 91 , 1599-1601.
  24. Popescu, D., & Ichim, L. (2015). Computeraided localization of the optic disc based on textural features. In Advanced Topics in Electrical Engineering (ATEE), 2015 9th International Symposium on (pp. 307-312).
  25. Romero-Aroca, P., de la Riva-Fernandez, S., Valls-Mateu, A., Sagarra-Alamo, R., Moreno-Ribas, A., & Soler, N. (2016). Changes observed in diabetic retinopathy: eight-year follow-up of a spanish population. British Journal of Ophthalmology, 100 , 1366-1371. URL: http://bjo.bmj.com/content/100/10/1366. doi:10.1136/bjophthalmol-2015-307689. · DOI
  26. Saleh, E., Valls, A., Moreno, A., Romero-Aroca, P., de la Riva-Fernandez, S., & Sagarra-Alamo, R. (2016). Diabetic retinopathy risk estimation using fuzzy rules on electronic health record data. In Modeling Decisions for Artificial Intelligence (pp. 263-274). Springer.
  27. Sanromà, S., Moreno, A., Valls, A., Romero, P., de la Riva, S., & Sagarra, R. (2016). Assessment of diabetic retinopathy risk with random forests. In 24th European Symposium on Artificial Neural Networks, Computational Intelligence and Machine Learning (ESANN 2016) (pp. 313-318).
  28. Skevofilakas, M., Zarkogianni, K., Karamanos, B. G., & Nikita, K. S. (2010). A hybrid decision support system for the risk assessment of retinopathy development as a long term complication of type 1 diabetes mellitus. In Engineering in Medicine and Biology Society (EMBC), 2010 Annual International Conference of the IEEE (pp. 6713-6716). IEEE.
  29. S lowiński, R., Greco, S., & Matarazzo, B. (2014). Rough-set-based decision support. In Search Methodologies (pp. 557-609). Springer.
  30. S lowiński, R., Greco, S., & Matarazzo, B. (2015). Rough set methodology for decision aiding. In Springer Handbook of Computational Intelligence (pp. 349-370). Springer.
  31. Stepaniuk, J. (1999). Rough set data mining of diabetes data. Foundations of Intelligent Systems, (pp. 457-465).
  32. Wang, X., Yeung, D. S., & Tsang, E. C. C. (2001). A comparative study on heuristic algorithms for generating fuzzy decision trees. IEEE Transactions on Systems, Man, and Cybernetics, Part B: Cybernetics, 31 , 215-226.
  33. Yao, Y., Greco, S., & S lowiński, R. (2015). Probabilistic rough sets. In Springer Handbook of Computational Intelligence (pp. 387-411). Springer.
  34. Zhang, L., Wei, H., Zhu, J., de la Cruz, J., Gonzalez, H. J., & Yadegar, J. (2012). An ontology-based multi- class terrain surface classification system for aerial imagery. In Emerging Signal Processing Applications (ESPA), 2012 IEEE International Conference on (pp. 95-98). IEEE.
  35. Zhang, W., Liu, H., Al-Shabrawey, M., Caldwell, R. W., & Caldwell, R. B. (2011). Inflammation and diabetic retinal microvascular complications. Journal of cardiovascular disease research, 2 , 96-103.

Cited by

Sorted by citations

Authors
Saleh, E., Błaszczyński, J., Moreno, A., Valls, A., Romero-Aroca, P., de la Riva-Fernández, S., & Słowiński, R.
Affiliations
  • Universitat Rovira i Virgili (ES)
  • Poznań University of Technology (PL)
ORCID
Venue
Artificial Intelligence in Medicine
Publisher
Elsevier BV
Published
2018-04
Volume
85
Pages
50-63
ISSN
0933-3657 (ISSN-L)
DOI
10.1016/j.artmed.2017.09.006
OpenAlex
W2764302726
Cited by
97
References
1
Citations by year
2026: 3 · 2025: 9 · 2024: 11 · 2023: 16 · 2022: 15 · 2021: 12 · 2020: 9 · 2019: 17 · 2018: 4 · 2017: 1
FWCI
11.67
Type
journal article
Language
en
Open access
Licence
Locations
  • Artificial Intelligence in Medicine (publishedVersion)
  • PubMed (publishedVersion)
  • Rovira & Virgili repository (submittedVersion, cc-by)
Funders
  • Spanish research projects (PI15/01150, PI12/01535)
  • URV (2015PFR-URV-B2-60, 2016PFR-URV-B2-60)
  • Martí-Franquès URV research fellowship programme (2016PMF-PIPF-24)
  • Polish National Science Center (DEC-2013/11/B/ST6/00963)
Topics
  • Health Sciences › Health Professions › Health Information Management › Artificial Intelligence in Healthcare
  • Health Sciences › Medicine › Radiology, Nuclear Medicine and Imaging › Retinal Imaging and Analysis
  • Physical Sciences › Computer Science › Computational Theory and Mathematics › Rough Sets and Fuzzy Logic
Keywords
diabetic retinopathy, risk prediction, ensemble classifiers, dominance-based rough set approach, clinical decision support, risk factors
MeSH terms
Clinical Decision-Making, Machine Learning, Decision Support Techniques, Decision Trees, Diabetes Mellitus, Type 1, Diabetes Mellitus, Type 2, Diabetic Retinopathy, Humans, Predictive Value of Tests, Prognosis, Risk Factors, Time Factors, Reproducibility of Results, Fuzzy Logic, Risk Assessment, Decision Support Systems, Clinical, Electronic Health Records

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