Research Article
BibTex RIS Cite

The Comparison of Artificial Neural Network Approach and Response Surface Model for Evaluation Upper Limb Performance in Patients with Chronic Neck Pain

Year 2021, Volume: 33 Issue: 1, 150 - 158, 30.01.2021
https://doi.org/10.7240/jeps.748256

Abstract

Response surface model (RSM) is used to detect the variable values that make the response variable maximum or minimum. Besides, the effect of exploratory variables on the response variable is determined. Thus, this method can be referred as a combination of regression analysis and optimization. RSM is mostly used in many fields such as industry and chemistry. However, it has limited application in the field of health. The upper limb performance assessment is a two-stage assessment of upper limb contributions to task performance. In this study, the upper limb performance of chronic neck pain patients is examined on 63 patients. The upper extremity functional index (UEFI-20) identifying the performance of upper limb is assigned as response variable. Input variables are taken as the variables related the pain-rating scales of patients at rest or in activity. The central composite model is implemented to estimate the model. The artificial neural network (ANN) approach is also applied to upper limb performance data. The mean absolute error, correlation coefficients, standard error of prediction are obtained from evaluating the experimental and predicted values of both models. The comparative analysis for both models is made on the prediction accuracy.

References

  • Akın Takmaz, S. (2017). Kronik bel-boyun ağrılı hastaya yaklaşım ve değerlendirme yöntemleri. TOTBID Dergisi, 16(2), 81–88.
  • Gilroy, A.M. (2015). Anatomi temel ders kitabı, (çev: C. Denk), 1. baskı, Palme Yayıncılık, Ankara, 21-39&234-240.
  • Jaspers, E., Desloovere, K., Bruyninckx, H., Klingels, K., Molenaers, G., Aertbeliën, E., Van Gestel, L. and Feys, H. (2011). Three-dimensional upper limb movement characteristics in children with hemiplegic cerebral palsy and typically developing children. Res Dev Disabil, 32(6), 2283–2294.
  • Barela, A.M.F., Almeida, G.L. (2006). Control of voluntary movements in the non-affected upper limb of spastic hemiplegic cerebral palsy patients. Braz J Phys Ther, 10(3), 325–332.
  • Huisstede, B.M.A., Bierma-Zeinstra, S.M.A., Koes, B.W. and Verhaar, J.A.N. (2006). Incidence and prevalence of upper-extremity musculoskeletal disorders. A systematic appraisal of the literature, BMC Musculoskelet Disord., 7, 1–7.
  • Box, G.E.P. and Draper, Norman. (2007). Response surfaces, mixtures, and ridge analyses, Second edition [of Empirical Model-Building and Response Surfaces, 1987], Wiley.
  • Baş, C. (2010). Cevap yüzeyi tasarımları ve sinir ağları yaklaşımı. Doktora Tezi, Ankara Üniversitesi, Türkiye, pp. 6-51.
  • Cornell, J. (2002). Experiments with mixtures: designs, models, and the analysis of mixture data (third ed.), Wiley.
  • Khuri, A.I. and Cornell, J.A. (1996). Response surfaces, Second edition. Dekker, New York.
  • Öztemel, E. (2003). Yapay sinir ağları, Papatya Yayıncılık, İstanbul, pp. 29-57.
  • Ahire, J.B. (2018). The Artificial Neural Networks Handbook: Part 4, https://medium.com/@jayeshbahire/the-artificial-neural-networks-handbook-part-4-d2087d1f583e, (January 2020).
  • Özsoy, H. (2019). Kronik boyun ağrılı bireylerde boyun ağrı ve özür şiddeti ile üst ekstemite performansı arasındaki ilişkinin incelenmesi. Yüksek Lisans Tezi, Ankara Yıldırım Beyazıt Üniversitesi, Türkiye, 26-31.
  • Stratford, P.W., Binkley, J.M. and Stratford, D.M. (2001). Development and initial validation of the Upper Extremity Functional Index. Physiother Can, 53(4), 259–267.
  • Cavlak, U., Baş Aslan U., Yagci, N. and Altuğ F. (2015). Kronik muskuloskeletal ağrının fizyoterapi-rehabilitasyon ile yönetimi, Turkiye Klinikleri J Physiother Rehabil-Special Topics, 1(1), 70-90.
  • Jordan A., Manniche C., Mosdal C. and Hindsberger C. (1998). The Copenhagen Neck Functional Disability Scale: a study of reliability and validity. J Manipulative Physiol Ther, 21(8), 520 – 527.
  • Kiran, M.D., Shrikant, A.S., Parag, S.S., Lele, S.S. and Rekha S.S. (2008). Comparison of artificial neural network (ANN) and response surface methodology (RSM) in fermentation media optimization: Case study of fermentative production of scleroglucan. Biochemical Engineering Journal, 41(3), 266-273.
  • Lou, W. and Nakai, S. (2001). Application of artificial neural networks for predicting the thermal inactivation of bacteria: a combined effect of temperature, pH and water activity, Food Res. Int., 34, 573–591.
  • Bourquin, J., Schmidli, H., Hoogevest, P. V. and Leuenberger, H. (1998). Advantages of artificial neural networks (ANNs) as alternative modeling technique for data sets showing non-linear relationships using data from a galenical study on a solid dosage form, Eur. J. Pharm. Sci., 7, 5–16.
  • Agatonovic-Kustrin, S., Zecevic, M., Zivanovic, L.J. and Tucker, I. G. (1998). Application of artificial neural networks in HPLC method development. J. Pharm. Biomed. Anal., 17, 69–76.
  • Baş, D. and Boyacı, I. (2007). Modeling and optimization II. Comparison of estimation capabilities of response surface methodology with artificial neural networks in a biochemical reaction, J. Food Eng., 78, 846–854.

Kronik Boyun Ağrısı Olan Hastalarda Üst Ekstremite Performansının Değerlendirilmesi için Yapay Sinir Ağları Yaklaşımı ve Yanıt Yüzeyi Modelinin Karşılaştırılması

Year 2021, Volume: 33 Issue: 1, 150 - 158, 30.01.2021
https://doi.org/10.7240/jeps.748256

Abstract

Yanıt yüzey modeli (YYM), yanıt değişkenini maksimum veya minimum yapan değişken değerleri tespit etmek için kullanılır. Ayrıca, açıklayıcı değişkenlerin cevap değişkeni üzerindeki etkisi belirlenir. Dolayısıyla, bu yöntem, regresyon analizi ve optimizasyonun bir kombinasyonu olarak adlandırılabilir. YYM, çoğunlukla sanayi ve kimya gibi birçok alanda kullanılmaktadır. Ancak, sağlık alanında sınırlı bir uygulamaya sahiptir. Üst ekstremite performans değerlendirmesi, üst ekstremite ve onun görev performansı olarak iki aşamalı bir değerlendirmedir. Bu çalışmada, kronik boyun ağrılı hastaların üst ekstremite performansı 63 hastada incelenmiştir. Üst ekstremitenin performansını tanımlayan üst ekstremite fonksiyonel indeksi(UEFI-20) cevap değişkeni olarak belirlenmiştir. Girdi değişkenleri, istirahatte veya etkin durumdaki hastaların ağrı derecelendirme ölçekleriyle ilgili değişkenler olarak alınmıştır. Merkezi kompozit model, modeli tahmin etmek için uygulanmıştır. Yapay Sinir Ağı yaklaşımı da üst ekstremite performans verilerine uygulanmıştır. Hata kareler ortalaması, korelasyon katsayıları, standart hatası, her iki modelin de deneysel ve öngörülen değerleri değerlendirilerek elde edilmiştir. Her iki model için karşılaştırmalı analiz, tahminlerin doğrulukları üzerinden yapılmıştır.

References

  • Akın Takmaz, S. (2017). Kronik bel-boyun ağrılı hastaya yaklaşım ve değerlendirme yöntemleri. TOTBID Dergisi, 16(2), 81–88.
  • Gilroy, A.M. (2015). Anatomi temel ders kitabı, (çev: C. Denk), 1. baskı, Palme Yayıncılık, Ankara, 21-39&234-240.
  • Jaspers, E., Desloovere, K., Bruyninckx, H., Klingels, K., Molenaers, G., Aertbeliën, E., Van Gestel, L. and Feys, H. (2011). Three-dimensional upper limb movement characteristics in children with hemiplegic cerebral palsy and typically developing children. Res Dev Disabil, 32(6), 2283–2294.
  • Barela, A.M.F., Almeida, G.L. (2006). Control of voluntary movements in the non-affected upper limb of spastic hemiplegic cerebral palsy patients. Braz J Phys Ther, 10(3), 325–332.
  • Huisstede, B.M.A., Bierma-Zeinstra, S.M.A., Koes, B.W. and Verhaar, J.A.N. (2006). Incidence and prevalence of upper-extremity musculoskeletal disorders. A systematic appraisal of the literature, BMC Musculoskelet Disord., 7, 1–7.
  • Box, G.E.P. and Draper, Norman. (2007). Response surfaces, mixtures, and ridge analyses, Second edition [of Empirical Model-Building and Response Surfaces, 1987], Wiley.
  • Baş, C. (2010). Cevap yüzeyi tasarımları ve sinir ağları yaklaşımı. Doktora Tezi, Ankara Üniversitesi, Türkiye, pp. 6-51.
  • Cornell, J. (2002). Experiments with mixtures: designs, models, and the analysis of mixture data (third ed.), Wiley.
  • Khuri, A.I. and Cornell, J.A. (1996). Response surfaces, Second edition. Dekker, New York.
  • Öztemel, E. (2003). Yapay sinir ağları, Papatya Yayıncılık, İstanbul, pp. 29-57.
  • Ahire, J.B. (2018). The Artificial Neural Networks Handbook: Part 4, https://medium.com/@jayeshbahire/the-artificial-neural-networks-handbook-part-4-d2087d1f583e, (January 2020).
  • Özsoy, H. (2019). Kronik boyun ağrılı bireylerde boyun ağrı ve özür şiddeti ile üst ekstemite performansı arasındaki ilişkinin incelenmesi. Yüksek Lisans Tezi, Ankara Yıldırım Beyazıt Üniversitesi, Türkiye, 26-31.
  • Stratford, P.W., Binkley, J.M. and Stratford, D.M. (2001). Development and initial validation of the Upper Extremity Functional Index. Physiother Can, 53(4), 259–267.
  • Cavlak, U., Baş Aslan U., Yagci, N. and Altuğ F. (2015). Kronik muskuloskeletal ağrının fizyoterapi-rehabilitasyon ile yönetimi, Turkiye Klinikleri J Physiother Rehabil-Special Topics, 1(1), 70-90.
  • Jordan A., Manniche C., Mosdal C. and Hindsberger C. (1998). The Copenhagen Neck Functional Disability Scale: a study of reliability and validity. J Manipulative Physiol Ther, 21(8), 520 – 527.
  • Kiran, M.D., Shrikant, A.S., Parag, S.S., Lele, S.S. and Rekha S.S. (2008). Comparison of artificial neural network (ANN) and response surface methodology (RSM) in fermentation media optimization: Case study of fermentative production of scleroglucan. Biochemical Engineering Journal, 41(3), 266-273.
  • Lou, W. and Nakai, S. (2001). Application of artificial neural networks for predicting the thermal inactivation of bacteria: a combined effect of temperature, pH and water activity, Food Res. Int., 34, 573–591.
  • Bourquin, J., Schmidli, H., Hoogevest, P. V. and Leuenberger, H. (1998). Advantages of artificial neural networks (ANNs) as alternative modeling technique for data sets showing non-linear relationships using data from a galenical study on a solid dosage form, Eur. J. Pharm. Sci., 7, 5–16.
  • Agatonovic-Kustrin, S., Zecevic, M., Zivanovic, L.J. and Tucker, I. G. (1998). Application of artificial neural networks in HPLC method development. J. Pharm. Biomed. Anal., 17, 69–76.
  • Baş, D. and Boyacı, I. (2007). Modeling and optimization II. Comparison of estimation capabilities of response surface methodology with artificial neural networks in a biochemical reaction, J. Food Eng., 78, 846–854.
There are 20 citations in total.

Details

Primary Language English
Journal Section Research Articles
Authors

Leyla Bakacak Karabenli 0000-0001-8968-7221

Serpil Aktaş 0000-0003-3364-6388

Publication Date January 30, 2021
Published in Issue Year 2021 Volume: 33 Issue: 1

Cite

APA Bakacak Karabenli, L., & Aktaş, S. (2021). The Comparison of Artificial Neural Network Approach and Response Surface Model for Evaluation Upper Limb Performance in Patients with Chronic Neck Pain. International Journal of Advances in Engineering and Pure Sciences, 33(1), 150-158. https://doi.org/10.7240/jeps.748256
AMA Bakacak Karabenli L, Aktaş S. The Comparison of Artificial Neural Network Approach and Response Surface Model for Evaluation Upper Limb Performance in Patients with Chronic Neck Pain. JEPS. January 2021;33(1):150-158. doi:10.7240/jeps.748256
Chicago Bakacak Karabenli, Leyla, and Serpil Aktaş. “The Comparison of Artificial Neural Network Approach and Response Surface Model for Evaluation Upper Limb Performance in Patients With Chronic Neck Pain”. International Journal of Advances in Engineering and Pure Sciences 33, no. 1 (January 2021): 150-58. https://doi.org/10.7240/jeps.748256.
EndNote Bakacak Karabenli L, Aktaş S (January 1, 2021) The Comparison of Artificial Neural Network Approach and Response Surface Model for Evaluation Upper Limb Performance in Patients with Chronic Neck Pain. International Journal of Advances in Engineering and Pure Sciences 33 1 150–158.
IEEE L. Bakacak Karabenli and S. Aktaş, “The Comparison of Artificial Neural Network Approach and Response Surface Model for Evaluation Upper Limb Performance in Patients with Chronic Neck Pain”, JEPS, vol. 33, no. 1, pp. 150–158, 2021, doi: 10.7240/jeps.748256.
ISNAD Bakacak Karabenli, Leyla - Aktaş, Serpil. “The Comparison of Artificial Neural Network Approach and Response Surface Model for Evaluation Upper Limb Performance in Patients With Chronic Neck Pain”. International Journal of Advances in Engineering and Pure Sciences 33/1 (January 2021), 150-158. https://doi.org/10.7240/jeps.748256.
JAMA Bakacak Karabenli L, Aktaş S. The Comparison of Artificial Neural Network Approach and Response Surface Model for Evaluation Upper Limb Performance in Patients with Chronic Neck Pain. JEPS. 2021;33:150–158.
MLA Bakacak Karabenli, Leyla and Serpil Aktaş. “The Comparison of Artificial Neural Network Approach and Response Surface Model for Evaluation Upper Limb Performance in Patients With Chronic Neck Pain”. International Journal of Advances in Engineering and Pure Sciences, vol. 33, no. 1, 2021, pp. 150-8, doi:10.7240/jeps.748256.
Vancouver Bakacak Karabenli L, Aktaş S. The Comparison of Artificial Neural Network Approach and Response Surface Model for Evaluation Upper Limb Performance in Patients with Chronic Neck Pain. JEPS. 2021;33(1):150-8.