Ölçüm teknikleri arasındaki uyumun belirlenmesinde kullanılan grafiksel yöntemlerin ve regresyon modellerinin bir uygulama ile incelenmesi

Amaç: Bu çalışmada, iki ölçüm tekniği arasındaki ilişkisel vemutlak uyumun incelenmesinde kullanılan grafiksel (Bland Altman ve Mountain Plot) ve metodolojik (Passing-Bablok ve Deming regresyon analizleri) yöntemlerin bir uygulama veri setiyardımı ile gösterilmesi amaçlanmıştır.Gereç ve Yöntem: Uygulama materyalini alanında uzman biraraştırmacının temin ettiği toplam 84 adet timus dokusu örneğioluşturmaktadır. Bu doku örneklerine ilişkin bloklardan alınankesitlere TUNEL (Yöntem 1) ve Caspase 3 immunohistokimyateknikleri (Yöntem 2) uygulanmış ve tespit sonrası her iki yöntem ile de apoptozise uğrayan hücrelerin sayımı yapılmıştır. İkiölçüm yönteminin uyumunun incelenmesinde ise Bland Altmanve Mountain Plot grafiksel yöntemleri ile Passing-Bablok ve Deming regresyon analizlerinden yararlanılmıştır.Bulgular: İki ölçüm yöntemi arasında sistematik olarak sabitbir hatanın (yanlılığın) bulunduğu ve TUNEL yönteminin Caspase 3 immunohistokimya yöntemine göre ortalama 4,11 birimdaha yüksek sonuç verdiği bulunmuştur. Ancak iki teknik arasında orantısal bir yanlılığın bulunmadığı tespit edilmiştir. İkiyöntem arasında pozitif yönlü orta derecede bir uyum olduğubulunmuştur (ρc=0,51 %95GA: 0,41-0,60).Öneri: Metot karşılaştırılmasında kullanılan hatalı yaklaşımlartartışılarak, bunlara alternatif olabilecek, daha sağlıklı sonuçlarelde edilmesinde kullanılabilecek yöntemler bir uygulama ilesunulmuştur.

Evaluation of concordance between measurement techniques using graphical methods and regression models with an application

Aim: The aim of this study was to introduce the graphical (Bland Altman and Mountain Plot) and methodogical (Passing- Bablok and Deming Regression analysis) methods which are used to evaluate the rational and absolute agreement between two measurement techniques with the help of an application data set. Materials and Methods: A total of 84 thymus tissue specimens provided by a researcher in the field were included in the study. TUNEL (Method 1) and Caspase 3 immunohistochemistry techniques (Method 2) were applied to the sections taken from the blocks of these tissue samples. The apoptotic cells in the tissue samples were counted using both methods. Bland Altman and Mountain Plot graphical methods and Passing-Bablok and Deming regression analyzes were used to examine the concordance of the two measurement methods. Results: Results showed that there was a systematic constant error (bias) between the two measurement methods and the TUNEL method gave an average of 4.11 units higher than the Caspase 3 immunohistochemistry method. However, it was determined that there was no proportional bias between the two techniques. Also, there was a moderate positive correlation between the two methods (ρc =0.51, 95%CI: 0.41-0.60). Conclusion: Erroneous approaches used in method comparison studies were discussed and alternative methods were presented with an application that can be used to obtain unbiased results.

PDF

___

Altman DG, Bland JM,1983. Measurement in medicine: the analysis of method comparison studies. The Statistician, 32, 307-317.
Atkinson G, Nevill A, 1997. Comment on the use of concordance correlation to assess the agreement between two variables. Biometrics, 53(2), 775-777.
Bland JM, Altman DG,1986. Statistical method for assessing agreement between two methods of clinical measurement. The Lancet, 307-310.
Bland JM, Altman DG, 1995.Comparing two methods of clinical measurement: A personal history. International Journal of Epidemiology, 24(1), 7-14.
Barnhart H, Haber B, Lin L, 2007. An overview on assessing agreement with continuous measurement. J Biopharm Stat., 17, 529-569.
Ceylan A, Alabay B, 2017. Ultrastructure of apoptotic T lymphocytes and thymicepithelial cells in early postnatal pig thymus. Turkish Journal of Veterinary and Animal Sciences, 41(5), 613-620.
Cornbleet PJ, Gochman N, 1979. Incorrect least-squares regression coefficients in method-comparison analysis. Clinical Chemistry, 25, 432-438.
Deming WE, 1943. Statistical adjustment of data. Wiley, NY, Dover Publications Edition, 1985.
Gasljevic V, 2010. Method validation and measurement uncertainty. Biochem Med, 20, 57-63
Genç Y, Sertkaya D, Demirtaş S, 2003. Statistical methods for assessing agreement between two measurement technique in clinical research. Ankara Üniversitesi Tıp Fakültesi Mecmuası, 56(1), 1-6.
Giavarina D, 2015. Understanding Bland Altman analysis. Biochemia Medica, 25, 141–151.
Gorczyca W, Traganos F, Jesıonowska H, Darzynkıewıcz Z, 1993. Presence of DNA strand breaks and increased sensitivity of DNA in situ to denaturation in abnormal human sperm cells: analogy to apoptosis of somatic cells. Exp Cell Res, 207, 202–205
Güllü Ö, Tekindal MA, Gökçe İ, Köse SK, Türkölmez K, 2014. Nomogramlar ile istatistiksel modellerin yaşam olasılıklarını belirlemedeki performanslarının metot karşılaştırma yöntemleri ile değerlendirilmesi: mesane kanseri örneği. Turkiye Klinikleri J Biostat, 6(1), 42-52
Hasegawa S, Suzuki N, Sakuramoto K, 2015. Performance of Deming and Passing-Balbok regression analysis in detecting proportionality in the stock recruitment relationship. Asian Fisheries Science, 28, 102-116.
Krouwer JS, Monti KL, 1995. A simple, graphical method to evaluate laboratory assays. Eur J Clin Chem Clin Biochem, 33, 525-527
Linnet K, 1993. Evaluation of regression procedures for methods comparision studies. Clinical Chemistry, 39, 424-432
Linnet K, 1998. Performance of Deming regression analysis in case of misspecified analytical error ratio in method comparision studies. Clinical Chemistry, 44, 1024-1031.
Linnet K, Boyd JC, 2012, Selection and analytical evaluation of methods - with statistical techniques. In Burtis CA, Ashwood ER, Bruns DE (eds). Tietz Textbook of Clinical Chemistry and Molecular Diagnostics (5th edn). Elsevier Saunders, St Louis, MO, pp. 201-228.
Ludbrook J, 2010. Linear regression analysis for comparing two measures or methods of measurement: but which regression? Clinical and Experimental Pharmacology & Physiology 37, 692-699
Mantha S, Roizen M, Fleisher L, 2000. Comparing methods of clinical measurement: Reporting standards for Bland and Altman analysis. Anesth Analg, 90, 593-602.
Passing H, Bablok W, 1983. A new biometrical procedure for testing the equality of measurements from two different analytical methods. Application of linear regression procedures for method comparison studies in Clinical Chemistry, Part I. J Clin Chem Clin Biochem, 21, 709-20.
Passing H, Bablok W, 1984. Comparison of several regression procedures for method comparison studies and determination of sample sizes. Application of linear regression procedures for method comparison studies in Clinical Chemistry, Part II. Journal of Clinical Chemistry & Clinical Biochemistry 22, 431-445.
Payne RB, 1997. Method comparison: evaluation of least squares, Deming and Passing/Bablok regression procedures using computer simulation. Ann Clin Biochem, 34, 319-320.
Resendes AR, Majo N, Segales J, Espadamala J, Mateu E, Chianini F, Nofrarias M, Domingo M, 2004. Apoptosis in normal lymphoid organs from healthy normal, conventional pigs at different ages detected by TUNEL and cleaved caspase-3 immunohistochemistry in paraffin embedded tissues. Veterinary Immunology and Immunopathology, 99, 203-213.
Saraçlı S, Doğan İ, Doğan N, 2009. Medikal metod karşılaştırma çalışmalarında deming regresyon tekniği. Türkiye Klinikleri J Biostat, 1(1), 9-15.