SavedAdd your journal

Journals / Konya Journal of Engineering Sciences / 2017 / Cilt: 5 Sayı: 4

COMPARING VARIOUS MACHINE LEARNING METHODS FOR PREDICTION OF PATIENT REVISIT INTENTION: A CASE STUDY

Yeniden Hastane Tercih Etme Davranışının Tahmini İçin Çeşitli Makine Öğrenmesi Yöntemlerinin Karşılaştırılması: Bir Uygulama

Osman DEMİRDÖĞEN
Hamit ERDAL
Ahmet İlker AKBABA
Pages
386–401
Publication Date
2017-12-01
DOI
—
🏛️Bibliographic metadata and full text access for this article are provided via DergiPark.
DergiPark Record ↗
✨

AI Summary & Key Takeaways

AI Insight
⚡ TL;DR(Too Long; Didn't Read)

Experimental results reveal that the C4.5 tree demonstrates to be the most suitable predictive model since it has the highest overall average accuracy (95.24%) and a very low percentage error on both Type I (3.40%) and Type II (23.53%) errors, closely followed by the locally weighted learning (94.44%, 3.43%, 31.58%) and decisionstump (94.05%, 3,85%, 30.00%), whereas the logistic regression and the IBk algorithms appear to be the worst in terms of average accuracy (87.30% and 88.49%, respectively) and Type II error (70.37% and 68.18%, respectively).

📌 3 Key Takeaways

🎯
Objective & Hypothesis:Numerous methods have been suggested for analysis of costumer intention, from surveys to statistical models.
📊
Key Findings & Data:In this paper, it is carried on a comparative evaluation of the performance of ten widely used machine learning methods, (i.e., logistic regression, multilayer perceptron, support vector machines, IBk, KStar, locally weighted learning, decisionstump, C4.5., randomtree and reduced error pruning tree) for the aim of suggesting appropriate machine learning techniques in the context of patient revisit intention prediction problem.
💡
Conclusion & Impact:Experimental results reveal that the C4.5 tree demonstrates to be the most suitable predictive model since it has the highest overall average accuracy (95.24%) and a very low percentage error on both Type I (3.40%) and Type II (23.53%) errors, closely followed by the locally weighted learning (94.44%, 3.43%, 31.58%) and decisionstump (94.05%, 3,85%, 30.00%), whereas the logistic regression and the IBk algorithms appear to be the worst in terms of average accuracy (87.30% and 88.49%, respectively) and Type II error (70.37% and 68.18%, respectively).
🔬Design:Survey & Empirical Study
📍Scope:Comprehensive Sample
⚙️Variables:Yeniden tercih etme davranışı · hastane yönetimi · makine öğrenmesi

Abstract

Numerous methods have been suggested for analysis of costumer intention, from surveys to statistical models. The most recent couple of years, various machine learning methods have effectively been utilized to costumer-centric decision-making problems. The trend of patient revisit intention analysis has an improved reliance on computerized decision making models. Computerized decision-making may never take the place of the hospital managers, but it can provide decision support via a simple questionnaire. In this paper, it is carried on a comparative evaluation of the performance of ten widely used machine learning methods, (i.e., logistic regression, multilayer perceptron, support vector machines, IBk, KStar, locally weighted learning, decisionstump, C4.5., randomtree and reduced error pruning tree) for the aim of suggesting appropriate machine learning techniques in the context of patient revisit intention prediction problem. Experimental results reveal that the C4.5 tree demonstrates to be the most suitable predictive model since it has the highest overall average accuracy (95.24%) and a very low percentage error on both Type I (3.40%) and Type II (23.53%) errors, closely followed by the locally weighted learning (94.44%, 3.43%, 31.58%) and decisionstump (94.05%, 3,85%, 30.00%), whereas the logistic regression and the IBk algorithms appear to be the worst in terms of average accuracy (87.30% and 88.49%, respectively) and Type II error (70.37% and 68.18%, respectively). Besides the randomtree (6.36%) and the IBk (6.09%) algorithms appear to be the worst in terms of type I error. As a result, this study has demonstrated the promising attempt of incorporating sentiment classification into patient revisit intention.

Özet

Müşteri davranışının analizi amacıyla anketlerden, istatistiksel modellere kadar pek çok yöntem önerilmiştir. Son birkaç yılda çeşitli makine öğrenmesi yöntemleri, müşteriye odaklı karar verme problemlerine etkili bir biçimde uygulanmıştır. Yeniden hastane tercih etme davranışının analizi, bilgisayar destekli karar verme modellerine daha fazla bağımlılık gösterme eğilimi içerisindedir. Bilgisayar destekli karar verme, hiçbir zaman hastane yöneticilerinin yerini alamaz ancak basit bir anket yoluyla karar desteği sağlayabilir. Bu çalışmada, yeniden hastane tercih etme davranışının tahmini problemi için uygun makine öğrenmesi yöntemlerinin belirlenmesi amacıyla yaygın olarak kullanılan on adet makine öğrenmesi yönteminin (lojistik regresyon, yapay sinir ağları, destek vektör makineleri, IBk algoritması, KStar algoritması, lokal ağırlıklandırılmış öğrenme algoritması, decisionstump karar ağacı, C4.5. karar ağacı, rastgele ağaç algoritması ve indirgenmiş hata budama karar ağacı) performansları karşılaştırmalı olarak incelenmiştir. Deney sonuçlarına göre C4.5. karar ağacı, en yüksek ortalama doğruluk oranı (95.24%) ile çok düşük Tip-I ve Tip-II hata oranları elde edilmesi nedeniyle en uygun tahminleme modeli olarak belirlenmiştir. C4.5. karar ağacının hemen ardından, sırasıyla, lokal ağırlıklandırılmış öğrenme algoritması (94.44%, 3.43%, 31.58%) ve decisionstump karar ağacı (94.05%, 3,85%, 30.00%) en uygun tahminleme modelleri olarak belirlenirken, lojistik regresyon ve IBk algoritması hem ortalama doğruluk oranına (sırasıyla, 87.30% ve 88.49%) göre, hemde Tip-II hata oranına (sırasıyla, 70.37% ve 68.18%) göre en kötü tahminleme modelleri olarak belirlenmiştir. Bunun yanında rastgele ağaç ve IBk algoritmaları Tip-I hata oranına göre (sırasıyla, 6.36% ve 6.09%) en kötü tahminleme modelleri olarak belirlenmiştir. Sonuç olarak, bu çalışmada yeniden hastane tercih etme davranışının sınıflandırması için umut vadeden sonuçlar ortaya koyulmuştur.

🔖

Cite This Article

DEMİRDÖĞEN, O., ERDAL, H., AKBABA, A. İ. (2017). COMPARING VARIOUS MACHINE LEARNING METHODS FOR PREDICTION OF PATIENT REVISIT INTENTION: A CASE STUDY. Konya Journal of Engineering Sciences, Cilt: 5 Sayı: 4, 386–401. https://ajindex.com/articles/909346

📄 Full Text PDF Viewer

📄

PDF görüntüleyici hazırlanıyor...

References (12)

  1. Al-Refaie, A., 2011, “A Structural Model to Investigate Factors Affect Patient Satisfaction and Revisit Intention in Jordanian Hospitals”, International Journal of Artificial Life Research, Vol. 2(4), pp. 43-56.
  2. Al Snousy, M. B., El-Deeb, H. M., Badran, K., Al Khlil, I. A., 2011, “Suite of Decision Tree-based Classification Algorithms on Cancer Gene Expression Data”, Egyptian Informatics Journal, Vol. 12(2), pp. 73-82.
  3. Aliman, N. K., Mohamad, W. N. (2013). “Perceptions of Service Quality and Behavioral Intentions: A Mediation Effect of Patient Satisfaction in the Private Health Care in Malaysia”, International Journal of Marketing Studies, Vol. 5(4), pp. 15-29.
  4. Anbarasi, M., Anupriya, E., Iyengar, N. C. S. N., 2010, “Enhanced Prediction of Heart Disease with Feature Subset Selection using Genetic Algorithm”, International Journal of Engineering Science and Technology, Vol. 2(10), pp. 5370-5376.
  5. Arif, M., Ishihara, T., Inooka, H., 2001, “Incorporation of Experience in Iterative Learning Controllers using Locally Weighted Learning”, Automatica, Vol. 37(6), pp. 881-888.
  6. Aydogmus, H.Y., Ekinci, A., Erdal, H.İ., Erdal, H., 2015, “Optimizing the Monthly Crude Oil Price Forecasting Accuracy via Bagging Ensemble Models”, Journal of Economics and International Finance, Vol. 7(5), pp. 127-136.
  7. Aydogmus, H.Y., Erdal, H.İ., Karakurt, O., Namli, E., Turkan, Y.S., Erdal, H., 2015, “A Comparative Assessment of Bagging Ensemble Models for Modeling Concrete Slump Flow”, Computers and Concrete, Vol. 16(5), pp. 741-757.
  8. Aydogmus, H.Y., Turkan, Y.S., 2016, “Passenger Demand Prediction for Fast Ferries Based on Neural Network and Support Vector Machine”, Uluslararası Alanya İşletme Fakültesi Dergisi, Vol. 8(1), pp. 209-216.
  9. Boshoff, C., Gray, B., 2004, “The Relationships Between Service Quality, Customer Satisfaction and Buying Intentions in The Private Hospital Industry”, South African Journal of Business Management, Vol. 35(4), pp. 27-37.
  10. Brown, I., Mues, C., 2012, “An Experimental Comparison of Classification Algorithms for Imbalanced Credit Scoring Data Sets”, Expert Systems with Applications, Vol. 39(3), pp. 3446-3453.
  11. Bushinak, H., AbdelGaber, S., AlSharif, F. K., 2011, “Recognizing The Electronic Medical Record Data from Unstructured Medical Data Using Visual Text Mining Techniques”, International Journal of Computer Science and Information Security, Vol. 9(6), pp. 25-35.
  12. Caouette, J., Altman, E., Narayanan, P., Nimmo, R., 2008, Managing Credit Risk: The Great Challenge