Research Article
BibTex RIS Cite

Plazma Glukoz Konsantrasyonu, Serum Insülin Direnci ve Diastolik Kan Basıncı Göstergeleri ile Makine Öğrenme Yöntemleri Kullanılarak Diyabet Hastalığının Erken Tanısı

Year 2022, Volume: 4 Issue: 2, 191 - 5, 01.05.2022

Mehmet Kıvrak

https://doi.org/10.37990/medr.1021148

Abstract

Amaç: Diyabetin sıklıkla arttığı ve bir çok farklı hastalığı tetiklediği bilinen bir gerçektir. Bu nedenle hastalığın erken teşhisi önemlidir. Bu çalışmada plazma glukoz konsantrasyonu, serum insülin direnci ve diyastolik kan basıncı göstergelerinden, makine öğrenmesi yöntemlerine göre hastalığın erken teşhisi öngörülmeye çalışılmıştır.
Materyal ve Metot: Çalışmada, bir web sitesinden alınan halka açık veri seti 768 örnek ve dokuz değişkenden oluşmaktadır. Diyabetin erken teşhisinde üç farklı makine öğrenme stratejisi kullanıldı (Destek Vektör Makineleri, Çok Katmanlı Algılayıcılar ve Stokastik Gradyan Artırma). Hiper parametre optimizasyonu için 3 tekrarlı 10 kat tekrarlı çapraz doğrulama yöntemi kullanıldı. Modellerin performansı doğruluk, seçicilik, duyarlılık, karışıklık matrisi, pozitif tahmin değeri (kesinlik), negatif tahmin değeri ve AUC (ROC eğrisi altında kalan alan) temel alınarak değerlendirilmiştir.
Bulgular: Deneysel sonuçlara göre (doğruluk (0.79), duyarlılık (0.57), özgüllük (0.91), pozitif tahmin değeri (0.79), negatif tahmin değeri (0.80) ve AUC (0.74) kriterleri), Destek Vektör Makineleri diğer yöntemlere göre daha başarılı çıkmıştır.
Sonuç: Diyabet hastalığının erken tanısında plazma glukoz konsantrasyonu, serum insülin direnci ve diastolik kan basinci belirteçleri önemli göstergelerdir. Bu çalışmada da bu belirteçlerin diyabetin erken tanısında önemli katkı sağladığı görülmüştür. Ancak tek başlarına bu göstergelerin hastalığın erken tanısında yeterli olmayacağı özellikle yaş, beden kitle indeksi ve gebeliğin de önemli derecede katkı sağladığı görülmüştür. 

Keywords

Diyabet hastalığı plazma glukoz konsantrasyonu serum insülin direnci diyastolik kan basıncı makine öğrenme

Thanks

İnönü Üniversitesi Tıp Fakültesi Biyoistatistik ve Tıp Bilişimi Anabilim Dalı Öğretim Üyelerine sonsuz teşekkürlerimi sunarım

References

  • 1. Said G. Diabetic neuropathy-A Review. Nat Clin Prac Neurol. 2007;3:331-340.
  • 2. Albers JW. Diabetic Neuropathy: Mechanisms, Emerging Treatments and Subtypes. Curr Neurol Neurosci Rep. 2014;14:473.
  • 3. Charnogursky G. Neurological Complications of diabetes. Curr Neurol Neurosci Rep. 2014;14:457.
  • 4. Prima Indians Diabetes Database (PIDD), accessed 11.5.2021 (ttps://www.kaggle.com/saurabh00007/diabetescsv)
  • 5. Platt J. Probabilistic outputs for support vector machines and comparisons to regularized likelihood methods. Advances in large margin classifiers 1999, 10(3): 61-74.6. Birjandi SM, Khasteh SH. A survey on data mining techniques used in medicine. Journal of Diabetes & Metabolic Disorders. 2021:1-17.
  • 6. Nitze I, Schulthess U, Asche H. Comparison of machine learning algorithms random forest, artificial neural network and support vector machine to maximum likelihood for supervised crop type classification. Proc. of the 4th GEOBIA 2012, 35.
  • 7. Cortes C, Vapnik V. Support-vector networks. Machine learning 1995, 20(3): 273-97.
  • 8. Ayhan S, Erdoğmuş Ş. Destek vektör makineleriyle sınıflandırma problemlerinin çözümü için çekirdek fonksiyonu seçimi. Eskişehir Osmangazi Üniversitesi İktisadi ve İdari Bilimler Dergisi 2014, 9(1): 175-201.
  • 9. Arslan A, Şen B. Detection of non-coding RNA's with optimized support vector machines. 23nd Signal Processing and Communications Applications Conference (SIU) IEEE. 2015:1668-71.
  • 10. Schapire R.E. The Boosting Approach to Machine Learning: An Overview, Nonlinear Estimation and Classification. Springer (2003), pp. 149-171.
  • 11. Friedman J.H. Stochastic gradient boosting Comput. Stat. Data Anal., 38 (2002), pp. 367-378.
  • 12. Ridgeway G. gbm: Generalized Boosted Regression Models, R Package Version, vol. 1
  • 13. Rosenblatt, F. Two theorems of statistical separability in the perceptron. United States Department of Commerce. 1958.
  • 14. Yaşar, Ş., Arslan, A., Colak, C. and Yoloğlu, S. (2020). A Developed Interactive Web Application for Statistical Analysis: Statistical Analysis Software. Middle Black Sea Journal of Health Science, 6(2), 227-239.
  • 15. Campbell, M. (2019). RStudio Projects. In Learn RStudio IDE (pp. 39- 48). Apress, Berkeley, CA.

Early Diagnosis of Diabetes Mellitus by Machine Learning Methods According to Plasma Glucose Concentration, Serum Insulin Resistance and Diastolic Blood Pressure Indicators

Year 2022, Volume: 4 Issue: 2, 191 - 5, 01.05.2022

Mehmet Kıvrak

https://doi.org/10.37990/medr.1021148

Abstract

Aim: It is a known fact that diabetes mellitus is increasing frequently and triggering many different diseases. Therefore, early diagnosis of the disease is important. This study was trying to predict the early diagnosis of the disease, according to machine learning methods by measuring plasma glucose concentration, serum insulin resistance, and diastolic blood pressure.
Material and Methods: In the study, the public dataset from a website consists of 768 samples and nine variables. Three different machine learning strategies were used in the early diagnosis of diabetes mellitus (Support Vector Machine, Multilayer Perceptron, and Stochastic Gradient Boosting). 3 repeats and 10 fold cross-validation method was used to optimize the hyperparameters. The model’s performance parameters were evaluated based on accuracy, specificity, sensitivity, confusion matrix, positive predictive value (precision), negative predictive value, and AUC (area under the ROC curve).
Results: According to the experimental results (the criteria of accuracy (0.79), sensitivity (0.57), specificity (0.91), positive predictive value (0.79), negative predictive value (0.80), and AUC (0.74)) the Support Vector Machine was more successful than other methods.Conclusion: Plasma glucose concentration, serum insulin resistance, and diastolic blood pressure markers are important indicators in the early diagnosis of diabetes mellitus. In this study, it was seen that these markers make a significant contribution to the early diagnosis of diabetes mellitus. However, it has been observed that these indicators alone will not be sufficient in the early diagnosis of the disease, especially since age, body mass index and pregnancy contribute significantly. 

Keywords

Diabetes Mellitus Plasma Glucose Concentration Serum Insulin Resistance Diastolic Blood Pressure Machine Learning

References

  • 1. Said G. Diabetic neuropathy-A Review. Nat Clin Prac Neurol. 2007;3:331-340.
  • 2. Albers JW. Diabetic Neuropathy: Mechanisms, Emerging Treatments and Subtypes. Curr Neurol Neurosci Rep. 2014;14:473.
  • 3. Charnogursky G. Neurological Complications of diabetes. Curr Neurol Neurosci Rep. 2014;14:457.
  • 4. Prima Indians Diabetes Database (PIDD), accessed 11.5.2021 (ttps://www.kaggle.com/saurabh00007/diabetescsv)
  • 5. Platt J. Probabilistic outputs for support vector machines and comparisons to regularized likelihood methods. Advances in large margin classifiers 1999, 10(3): 61-74.6. Birjandi SM, Khasteh SH. A survey on data mining techniques used in medicine. Journal of Diabetes & Metabolic Disorders. 2021:1-17.
  • 6. Nitze I, Schulthess U, Asche H. Comparison of machine learning algorithms random forest, artificial neural network and support vector machine to maximum likelihood for supervised crop type classification. Proc. of the 4th GEOBIA 2012, 35.
  • 7. Cortes C, Vapnik V. Support-vector networks. Machine learning 1995, 20(3): 273-97.
  • 8. Ayhan S, Erdoğmuş Ş. Destek vektör makineleriyle sınıflandırma problemlerinin çözümü için çekirdek fonksiyonu seçimi. Eskişehir Osmangazi Üniversitesi İktisadi ve İdari Bilimler Dergisi 2014, 9(1): 175-201.
  • 9. Arslan A, Şen B. Detection of non-coding RNA's with optimized support vector machines. 23nd Signal Processing and Communications Applications Conference (SIU) IEEE. 2015:1668-71.
  • 10. Schapire R.E. The Boosting Approach to Machine Learning: An Overview, Nonlinear Estimation and Classification. Springer (2003), pp. 149-171.
  • 11. Friedman J.H. Stochastic gradient boosting Comput. Stat. Data Anal., 38 (2002), pp. 367-378.
  • 12. Ridgeway G. gbm: Generalized Boosted Regression Models, R Package Version, vol. 1
  • 13. Rosenblatt, F. Two theorems of statistical separability in the perceptron. United States Department of Commerce. 1958.
  • 14. Yaşar, Ş., Arslan, A., Colak, C. and Yoloğlu, S. (2020). A Developed Interactive Web Application for Statistical Analysis: Statistical Analysis Software. Middle Black Sea Journal of Health Science, 6(2), 227-239.
  • 15. Campbell, M. (2019). RStudio Projects. In Learn RStudio IDE (pp. 39- 48). Apress, Berkeley, CA.
There are 15 citations in total.

Details

Primary Language English
Subjects ​Internal Diseases
Journal Section Original Articles
Authors

Mehmet Kıvrak 0000-0002-2405-8552

Publication Date May 1, 2022
Acceptance Date February 25, 2022
Published in Issue Year 2022 Volume: 4 Issue: 2

Cite

AMA Kıvrak M. Early Diagnosis of Diabetes Mellitus by Machine Learning Methods According to Plasma Glucose Concentration, Serum Insulin Resistance and Diastolic Blood Pressure Indicators. Med Records. May 2022;4(2):191-5. doi:10.37990/medr.1021148
 Download Cover Image

17741

Chief Editors

Assoc. Prof. Zülal Öner
Address: İzmir Bakırçay University, Department of Anatomy, İzmir, Türkiye

Assoc. Prof. Deniz Şenol
Address: Düzce University, Department of Anatomy, Düzce, Türkiye

E-mail: medrecsjournal@gmail.com

Publisher:
Medical Records Association (Tıbbi Kayıtlar Derneği)
Address: Düzce / Türkiye

Publication Support:

Effect Publishing & Agency
Phone: + 90 (553) 610 67 80
E-mail: info@effectpublishing.com