The Analysis of Anesthesia Methods Used in Cesarean Section Through Data Mining Techniques

Öz

Aim: The aim of this study is to examine and analyze new patterns of cesarean section anesthesia types and prediction performances of decision trees with data mining techniques. Materials and methods: Classification and clustering analysis were performed to analyze the data of 300 patients. Gini algorithm and C5.0 algorithm were applied to the data set with 24 parameters. These algorithms were also applied to the 16-parameter data set obtained after preprocessing. The estimation performances obtained were compared according to the accuracy criterion. Then, clustering analysis was applied to the 24 and 16 parameter data sets with the K-prototype algorithm. Results: The study revealed that the prediction success of the Gini algorithm was determined as 96.61%, and the prediction success of the pruned decision tree obtained by the Gini algorithm was 94.91%. The prediction success of the C5.0 algorithm was determined as 98.87%.In the clustering analysis performed with the K-prototype algorithm, the number of clusters was determined as 4 and 5 for both data sets, based on expert opinion, and important patterns were observed with these cluster numbers. Conclusion: As a result of the study, it was revealed that the C5.0 algorithm had the highest performance with an accuracy rate of 98.87As a result of the cluster analysis, it was concluded that the age of the patients, the duration of the operation, the type of previous anesthesia, the number of previous cesarean sections, the fear of anesthesia and the previous surgical operations were effective on the type of anesthesia in cesarean section cases.

Anahtar Kelimeler

• Data science
• Anesthesia Types
• Cesarean Section
• K-prototype
• Classification

Sezaryen Ameliyatında Kullanılan Anestezi Yöntemlerinin Veri Madenciliği Yöntemleri İle İncelenmesi

Öz

Amaç: Bu çalışmanın amacı, sezaryen anestezi tiplerinin yeni örüntülerini ve karar ağaçlarının tahmin performanslarını veri madenciliği teknikleri ile incelemek ve analiz etmektir. Gereç ve Yöntemler: 300 hastanın verilerini analiz etmek için sınıflandırma ve kümeleme analizi yapıldı. 24 parametreli veri setine Gini algoritması ve C5.0 algoritması uygulanmıştır. Bu algoritmalar, ön işlemeden sonra elde edilen 16 parametrelik veri setine de uygulanmıştır. Elde edilen tahmin performansları doğruluk kriterine göre karşılaştırılmıştır. Daha sonra K-prototip algoritması ile 24 ve 16 parametreli veri setlerine kümeleme analizi uygulanmıştır. Bulgular: Çalışma, Gini algoritmasının tahmin başarısının %96.61, Gini algoritması ile elde edilen budanmış karar ağacının tahmin başarısının ise %94.91 olduğunu ortaya koydu. C5.0 algoritmasının tahmin başarısı %98,87 olarak belirlenmiştir. K-prototip algoritması ile yapılan kümeleme analizinde uzman görüşüne dayalı olarak her iki veri seti için küme sayısı 4 ve 5 olarak belirlenmiş ve bu küme sayıları ile önemli örüntüler gözlemlenmiştir. Sonuç:Çalışma sonucunda C5.0 algoritmasının %98,87 doğruluk oranı ile en yüksek performansa sahip olduğu ortaya çıkmıştır. Kümeleme analizi sonucunda ise hastaların yaşı, operasyon süresi, önceki anestezi tipi, önceki sezaryen sayısı, anestezi korkusu ve önceki cerrahi operasyonların sezaryen olgularında anestezi türü üzerinde etkili olduğu kanısına varılmıştır.

Anahtar Kelimeler

• Veri bilimi
• Anestezi Türleri
• Sezaryen
• K-prototip

Kaynakça

1. 1. Alagöz A. The Relationship of Data Mining , as a Business Intelligence Technology , with the Accounting Information System. The Journal of Selcuk University Social Sciences Institute. 2014;1–21.
2. 2. World Health Organization. Caesarean section rates continue to rise, amid growing inequalities in access [Internet]. World Health Organization. 2021 [cited 2021 Jun 18]. Available from: https://www.who.int/news/item/16-06-2021-caesarean-section-rates-continue-to-rise-amid-growing-inequalities-in-access
3. 3. OECD. Caesarean sections (indicator). 2024.
4. 4. Altun M. Veri Madenciliği ve Uygulama Alanları. Akdeniz University; 2017.
5. 5. Senthilkumar D, Paulraj S. Prediction of Low Birth Weight Infants and Its Risk Factors Using Data Mining Techniques. Proceedings of the 2015 International Conference on Industrial Engineering and Operations Management Dubai, United Arab Emirates (UAE). 2015;3:186–94.
6. 6. Mehbodniya A, Lazar AJP, Webber J, Sharma DK, Jayagopalan S, Kousalya K, et al. Fetal health classification from cardiotocographic data using machine learning. Expert Systems. 2021;39(6):1–13.
7. 7. Abdar M, Zomorodi-Moghadam M, Das R, Ting I-H. Performance analysis of classification algorithms on early detection of liver disease. Expert Systems with Applications. 2017;67:239–51.
8. 8. Begum A, Parkavi A. Prediction of thyroid Disease Using Data Mining Techniques. In: 2019 5th International Conference on Advanced Computing & Communication Systems (ICACCS). 2019. p. 342–5.

9. 9. Topaloğlu M, Sur H. Decision tree application to reduce incorrect diagnosis in symptoms of jaundice. Nobel Medicus. 2015;11(3):64–73.
10. 10. Şatir E, Azboy F, Aydin A, Arslan H, Haciefendioğlu Ş. Diagnosis of Glaucoma Disease via Data Reduction and Classification Techniques. El-Cezerî Journal of Science and Engineering. 2015;2016(3):485–97.
11. 11. Birnbach DJ, Browne IM. Anesthesia for Obstetrics. In: Miller RD, Eriksson LI, Fleisher LA, Wiener-kronish JP, Young WL, editors. Miller’s Anesthesia. 7th ed. Edinburg: Churchill Livingstone; 2009. p. 2203–10.
12. 12. Purtuloǧlu T, Özkan S, Teksöz E, Dere K, Şen H, Yen T, et al. Comparison of the maternal and fetal effects of general and spinal anesthesia in elective cesarean section. Gulhane Med J. 2008;50(2):91–7.
13. 13. Okafor U V, Ezegwui HU, Ekwazi K. Trends of different forms of anaesthesia for caesarean section in South-eastern Nigeria. Journal of obstetrics and gynaecology : the journal of the Institute of Obstetrics and Gynaecology. 2009 Jul;29(5):392–5.
14. 14. Morgan G, Mikhail M, Murray M. Obstetric Anesthesia. In: Tulunay M, Cuhruk H, editors. Clinical Anaesthesiology. 4th ed. Ankara: Öncü basımevi; 2008. p. 890–921.
15. 15. Abir G, Mhyre J. Maternal mortality and the role of the obstetric anesthesiologist. Best practice & research Clinical anaesthesiology. 2017 ;31(1):91–105.
16. 16. Berrin G, Kadir K. A retrospective seven years audit of mode of deliveries in a tertiary care university hospital of Turkey. ANAESTH, PAIN & INTENSIVE CARE. 2013;17(2):51–4.
17. 17. Haque MF, Sen S, Meftahuzzaman SM, Haque MM. Anesthesia for emergency cesarean section. Mymensingh Med J. 2008;17(2):221–6.
18. 18. Levy D. Anesthesia for Cesarean section. Contin Educ Anaesth Crit Care Pain. 2001;1:171–6.
19. 19. Şahin Ş, Günaydın B, Seyhan TO, Köse A, Yaman F, Ayoğlu H, et al. General Anesthesia Practice Guide for Cesarean Surgery. Turkish Anesthesiology and Reanimation Association. 2015;4–6.
20. 20. Leung TY, Lao TT. Timing of caesarean section according to urgency. Best Pract Res Clin Anesthesiol. 2013;27(2):251–67.