Mostafa EİSSA, Engy RASHED, Dalia Essam EISSA

Uzun Vadeli Veri Trendinin İstatistiksel Müdahalesi Kullanılarak Sağlık Ürünlerinin Rutin Muayenesi ve Kontrolünde Kalite İyileştirme

Piyasalardaki ticari ürünler, kullanım amacına uygun olarak kabul edilebilir olması için düzenleyici ve kalite kontrol kriterlerini karşılamalıdır. Her ürün serisinin spesifikasyon limitlerini karşılaması zorunlu olmakla birlikte, uzun vadede stabilite ve verimlilik hafife alınmaktadır. Bu çalışma, korelasyon matrisi ve çok değişkenli analiz içeren istatistiksel bir yazılım paketi kullanılarak bir sağlık ürününün kronolojik eğilimi üzerinde yürütülmüştür. Araştırılan kalite özellikleri, bir kimyasal koruyucuya ek olarak, ortalama dolum ağırlığı, bağıl yoğunluk, pH ve üç aktif bileşenin bağıl gücüydü. Veritabanı bir Excel sayfasında işlendi ve tanımlayıcı istatistiksel genel bakışa, histogram grafiğine, kutu grafiğine, zaman serisi grafiğine, korelasyon matrisi tablosuna ve Temel Bileşen Analizine tabi tutuldu. Araştırma, tüm serilerin kalite kontrol testlerini başarıyla geçmesine rağmen, tüm kalite ölçümlerinde gözlemlenebilen aykırı değerlerle birlikte istikrarsızlık, dalgalanmalar veya salınımlar ve sapmalar olduğunu gösterdi. Parametrik olmayan korelasyon, bazı denetim karakteristik göstergeleri arasında bir düzeyde ilişki olduğunu göstermiştir. PCA, veri kümesinin gruplandırılmasına rehberlik eden incelenen kalite belirteçleri arasındaki ana değişkenlik etkileyicisini ve kümelenme eğilimini gösterdi. Çalışma, ürün istikrarını, verimliliğini ve kalitesini sağlamak için gereken iyileştirmeyi belirledi.

Anahtar Kelimeler:

Kutu Grafiği, Histogram, Normallik testi, Matris Grafiği, Aykırı, Temel bileşenler analizi

Quality Improvement in Routine Inspection and Control of Healthcare Products Using Statistical Intervention of Long-Term Data Trend

Commercial products in markets must meet the regulatory and quality control criteria to be acceptable for the intended use. While it is mandatory that each product batch must meet specification limits, the stability and efficiency over the long term are underestimated. The present study was conducted on the chronological trend of a healthcare product using a statistical software package, including correlation matrix and multivariate analysis. The investigated quality characteristics were the average filling weight, relative density, pH and the relative potency of three active components, in addition to a chemical preservative. The database was processed in an Excel sheet and was subjected to descriptive statistical overview, histogram plot, box plot diagram, time series plot, correlation matrix table and Principal Component Analysis. The investigation showed that despite all batches passed quality control tests successfully yet there were signs of instability, fluctuations or oscillations and drifts in all quality metrics, with outlier values that could be observed. Non-parametric correlation demonstrated some level of association between some inspection characteristic indicators. PCA illustrated the major variability influencer and clustering tendency among studied quality markers that guided the grouping of the dataset. The study pinpointed the improvement needed to ensure product stability, efficiency and quality.

Keywords:

Box plot, Histogram, Normality test, Matrix plot, Outlier, Principal component analysis,

PDF

___

Y. Christopher, Inadvertent ingestion exposure in the workplace. Edimbourg, Royaume-Uni: Health and safety executive, 2007.
OECD, Improving Healthcare Quality in Europe: Characteristics, Effectiveness and Implementation of Different Strategies. OECD Publishing, 2019.
World Health Organization (WHO), Quality Assurance of Pharmaceuticals 2016. Geneva: World Health Organization, 2016.
C. Yang, The Evolution of Quality Concepts and the Related Quality Management, Quality Control and Assurance - An Ancient Greek Term Re-Mastered. London, UK: Intech Open, 2017.
M. Nguyen, A. Phan and Y. Matsui, "Contribution of Quality Management Practices to Sustainability Performance of Vietnamese Firms", Sustainability, vol. 10, no. 2, pp. 375-385, 2018, doi: 10.3390/su10020375.
M. Eissa, "Rare event control charts in drug recall monitoring and trend analysis of data record: A multidimensional study", Global Journal on Quality and Safety in Healthcare, vol. 2, no. 2, pp. 34-39, 2019. Available: 10.4103/jqsh.jqsh_3_19.
Food & Drug Administration, Guidance for Industry Q9 Quality Risk Management. (2006). Accessed: Feb. 21, 2021. [Online]. Available: https://www.fda.gov/media/71543/download.
G. Sonnemann and M. Margni, Life Cycle Management. LCA Compendium – The Complete World of Life Cycle Assessment, (2015). Accessed: Feb. 22, 2021. [Online]. Available: 10.1007/978-94-017-7221-1.
J. Nielsen, Microsoft Official Academic Course Microsoft Excel 2016. (2016). Accessed: Feb. 20, 2021. [Online]. Available: https://www.dit.ie/media/ittraining/msoffice/MOAC_Excel_2016_Core.pdf.
J. Kim, K. Lee, U. Jerng and G. Choi, "Global Comparison of Stability Testing Parameters and Testing Methods for Finished Herbal Products", Evidence-Based Complementary and Alternative Medicine, vol. 2019, pp. 1-14, 2019. Available: 10.1155/2019/7348929 [Accessed:22 February 2021].
SCCS Members & External experts, The Sccs Notes Of Guidance For The Testing Of Cosmetic Ingredients And Their Safety Evaluation. (2015). Accessed: Feb. 19, 2021. [Online]. Available: https://ec.europa.eu/health/scientific_committees/consumer_safety/docs/sccs_o_190.pdf.
S. Gad, Pharmaceutical manufacturing handbook: Production & Processes. Hoboken, N.J.: Wiley-Interscience, 2008.
Natural Resources Biometrics, Chapter 1: Descriptive Statistics and the Normal Distribution | Natural Resources Biometrics. (2021). Accessed: Feb. 18, 2021. [Online]. Available: https://courses.lumenlearning.com/suny-natural-resources-biometrics/chapter/chapter-1-descriptive-statistics-and-the-normal-distribution/.
A. Sleeper, Minitab Demystified. New York: McGraw-Hill Education, 2011.
C. Steele, An Easy Data Set to Summarize with Minitab's Assistant. (2015). Accessed: Feb. 16, 2021. [Online]. Available: https://blog.minitab.com/en/statistics-and-quality-improvement/an-easy-data-set-to-summarize-with-minitabs-assistant.
H. Motulsky, GraphPad Prism. San Diego, Calif.: GraphPad Software, 2003.
H. Motulsky, Analyzing data with graphPad prism. San Diego: GraphPad Software Inc., 1999.
H. Pham, Springer Handbook of Engineering Statistics. New York: Springer, 2007.
L. Ngo, How to read PCA biplots and scree plots - BioTuring's Blog. (2018). Accessed: Feb. 15, 2021. [Online]. Available: https://blog.bioturing.com/2018/06/18/how-to-read-pca-biplots-and-scree-plots/.
R. Wicklin, What are biplots?. (2019). Accessed: Feb. 16, 2021. [Online]. Available: https://blogs.sas.com/content/iml/2019/11/06/what-are-biplots.html.
J. Fish, Outliers Episode 3: Detecting outliers using the Mahalanobis distance (and T2). (2021). Accessed: Feb. 14, 2021. [Online]. Available: https://community.jmp.com/t5/JMP-Blog/Outliers-Episode-3-Detecting-outliers-using-the-Mahalanobis/ba-p/351183.
P. Python, PCA: Practical Guide to Principal Component Analysis in R & Python. (2016). Accessed: Feb. 1, 2021. [Online]. Available: https://www.analyticsvidhya.com/blog/2016/03/pca-practical-guide-principal-component-analysis-python/.
Kassambara, PCA - Principal Component Analysis Essentials - Articles – STHDA. (2021). Accessed: Feb. 2, 2021. [Online]. Available: http://www.sthda.com/english/articles/31-principal-component-methods-in-r-practical-guide/112-pca-principal-component-analysis-essentials/.
WHO Technical Report Series, No. 957, WHO good practices for pharmaceutical quality control laboratories. (2010). Accessed: Feb. 5, 2021. [Online]. Available: https://www.who.int/medicines/areas/quality_safety/quality_assurance/Goodpractices PharmaceuticalQualityControlLaboratoriesTRS957Annex1.pdf.
S. Kulkarni, Total Quality Management. (2021). Accessed: Feb. 6, 2021. [Online]. Available: http://hsit.ac.in/e-learning/mechanical%20engineering/ vi%20semester/total%20quality%20management(17me664)/tqm%20 notes.pdf.
C. Berardinelli and L. Yerian, Run Charts: A Simple and Powerful Tool for Process Improvement. (2021). Accessed: Feb. 7, 2021. [Online]. Available: https://www.isixsigma.com/tools-templates/control-charts/run-charts-a-simple-and-powerful-tool-for-process-improvement/.
M. Eissa and A. Abid, "Application of statistical process control for spotting compliance to good pharmaceutical practice", Brazilian Journal of Pharmaceutical Sciences, vol. 54, no. 2, 2018. Available: 10.1590/s2175-97902018000217499.
J. Bland and D. Altman, "Statistics notes: Measurement error", BMJ, vol. 312, no. 7047, pp. 1654-1654, 1996. Available: 10.1136/bmj.312.7047.1654 [Accessed: 25 Feb. 2021].
A. Bhattacherjee, Social science research. Tampa, FL: University of South Florida, 2012.
M. Essam Eissa, "Investigation of Microbiological Quality of Water from the Feed Source to the Terminal Application in the Healthcare Facility: A Case Study", Health Research, vol. 2, no. 1, pp. 16, 2018. Available: 10.31058/j.hr.2018.21002 [Accessed: 25 Feb.2021].
N. Balakrishnan, V. Barnett and T. Lewis, "Outliers in Statistical Data.", Biometrics, vol. 51, no. 1, pp. 381, 1995. Available: 10.2307/2533352.
J. Frost, Guidelines for Removing and Handling Outliers in Data - Statistics By Jim. (2021). Accessed: Feb. 24, 2021. [Online]. Available: https://statisticsbyjim.com/basics/remove-outliers/.
A. Monnappa, Common Cause Variation vs Special Cause Variation. (2021). Accessed: Feb. 8, (2021). [Online]. Available: https://www.simplilearn.com/common-vs-special-cause-of-variance-article.
M. Eissa, "Application of Laney control chart in assessment of microbiological quality of oral pharmaceutical filterable products", Bangladesh Journal of Scientific and Industrial Research, vol. 52, no. 3, pp. 239-246, 2017. Available: 10.3329/bjsir.v52i3.34160 [Accessed: 25 February 2021].
S. Wachs, Process Stability vs. Capability Explained | WinSPC.com. (2021). Accessed: Feb. 9, 2021. [Online]. Available: https://www.winspc.com/what-is-the-relationship-between-process-stability-and-process-capability/.
İ. K. Keser, İ. D. Kocakoç and A. Şehirlioğlu, "A New Descriptive Statistic for Functional Data: Functional Coefficient of Variation", Alphanumeric Journal, vol. 4, no. 2, 2016. Available: 10.17093/aj.2016.4.2.5000185408 [Accessed: 25 February 2021].
B. Illowsky and S. Dean, Outliers. (2021). Accessed: Feb. 10, 2021. [Online]. Available: https://opentextbc.ca/introstatopenstax/chapter/outliers/.
Department of Statistics Online Programs, 7.7 - Polynomial Regression | STAT 462. (2021). Accessed: Feb. 11, 2021. [Online]. Available: https://online.stat.psu.edu/stat462/node/158/.
S. Nickolas, What Do Correlation Coefficients Positive, Negative, and Zero Mean?. (2021). Accessed: Feb. 12, 2021. [Online]. Available: https://www.investopedia.com/ask/answers/032515/what-does-it-mean-if-correlation-coefficient-positive-negative-or-zero.asp.
B. C. Cronk, How to Use SPSS, Fifth Edition. (2021). Accessed: Jan. 31, 2021. [Online]. Available: http://www.xysfxy.cn/wcm.files/upload/null/201604/2016041309440 20 .pdf.
D. Bartholomew, International Encyclopedia of Education | ScienceDirect. (2010). Accessed: Jan. 30, 2021. [Online]. Available: https://www.sciencedirect.com/referencework/9780080448947/international-encyclopedia -of-education.
I. Jolliffe and J. Cadima, "Principal component analysis: a review and recent developments", Philosophical Transactions of the Royal Society A: Mathematical, Physical and Engineering Sciences, vol. 374, no. 2065, 2016. Available: 10.1098/rsta.2015.0202 [Accessed: 25 February 2021].
M. Patel, PCA. (2016). Accessed: Jan. 29, 2021. [Online]. Available: https://rstudio-pubs-static.s3.amazonaws.com/231900_91fafc24d70943f19b1c016987c886d9.html.
P. Tan, M. Steinbach and V. Kumar, Introduction to Data Mining - Instructor’s Solution Manual. (2006). Accessed: Jan. 28, 2021. [Online]. Available: https://www-users.cs.umn.edu/~kumar001/dmbook/sol.pdf.
K. Hartmann, J. Krois and B. Waske, SOGA. (2018). Accessed: Jan. 26, 2021. [Online]. Available: https://www.geo.fu-berlin.de/en/v/soga/index.html.
S. Serneels and T. Verdonck, "Principal component analysis for data containing outliers and missing elements", Computational Statistics & Data Analysis, vol. 52, no. 3, pp. 1712-1727, 2008. Available: 10.1016/j.csda.2007.05.024.
C. Rao, J. Miller and D. Rao, Essential statistical methods for medical statistics. Amsterdam: Elsevier, 2011.
screeplot — Scree plot of eigenvalues. (2021). Accessed: Jan. 25, 2021. [Online]. Available: https://www.stata.com/manuals/mvscreeplot.pdf.