مروری بر مفاهیم معنی‌داری آماری و بالینی: استفاده و تفسیر حدود اطمینان

نوع مقاله : مقاله مروری

نویسندگان

1 استادیار، گروه آمار زیستی و اپیدمیولوژی، دانشکده‌ی بهداشت، دانشگاه علوم پزشکی بابل، بابل، ایران

2 دانشجوی کارشناسی ارشد، گروه آمار زیستی و اپیدمیولوژی، دانشکده‌ی بهداشت، دانشگاه علوم پزشکی بابل، بابل، ایران

چکیده

مقاله مروری




مقدمه: کاربرد و تفسیر معنی‌داری آماری برای اثبات اثربخشی یک مداخله و یا وجود رابطه‌ی بین دو متغیر، یک اصل اساسی و ضروری در مطالعات است. بطور سنتی تجزیه و تحلیل داده‌های یک مطالعه با استفاده از آزمون فرضیه و گزارش p-value انجام می‌شود. بسیاری از پژوهشگران در حیطه‌ی علوم پزشکی، یافته‌های مطالعه‌ی خویش را صرفأ به معنی‌داری و یا غیرمعنی‌داری آماری خلاصه می‌نمایند. آزمون فرضیه و صرف گزارش p-value، نمی‌تواند بزرگی اثر و دقت آن را بدست دهد. در حال حاضر قریب به اتفاق مجلات معتبر علوم پزشکی؛ گزارش تنهای معنی‌داری آماری را نپذیرفته و گزارش همزمان شاخص اندازه‌ی اثر، حدود اطمینان و معنی‌داری بالینی را الزامی کرده‌اند. اما استفاده و گزارش معنی‌داری آماری و بالینی در مجلات علوم پزشکی یک‌دست نبوده، دستورالعمل واحدی در مورد کاربرد عملی، تفسیر آماری و بالینی یافته‌ها وجود ندارد و تناقضات آشکاری در مجلات مشاهده می‌شود. هدف نویسندگان این مقاله، ارائه‌ی یک دستورالعمل صحیح و یکپارچه به پژوهشگران و متخصصین بالینی، به جهت گزارش صحیح معنی‌داری آماری و بالینی یافته‌ها بر اساس اهداف و طراحی مطالعات در علوم پزشکی با رویکرد تخمین (گزارش Confidence interval) بود.

کلیدواژه‌ها


عنوان مقاله [English]

An Overview of Statistical and Clinical Concepts: The Use and Interpretation of Confidence Interval

نویسندگان [English]

  • Mahdi Sepidarkish 1
  • Zahra Mohammadi-Pirouz 2
1 Assistant Professor, Department of Biostatistics and Epidemiology, School of Public Health, Babol University of Medical Sciences, Babol, Iran
2 MSc Student, Department of Biostatistics and Epidemiology, School of Public Health, Babol University of Medical Sciences, Babol, Iran
چکیده [English]

Application and interpretation of statistical significance of association are the basic and necessary principle in medical research. Traditionally, hypothesis testing and reporting p-values have been extensively utilized to quantify the statistical significance of observed results. The majority of published research that involves statistical inference seems to make exclusive use of hypothesis testing, and summarize their findings only to statistical significance. Most importantly, p-value fail to provide two crucial pieces of information: (1) the magnitude of an effect of interest, and (2) the precision of the estimate of the magnitude of that effect. Currently, most of the reputable journals no longer accept statistical significance alone; and there has been increasing attention focused on the Effect size index, confidence limits along with clinical significant. However, there is no single guideline for reporting statistical and clinical significance, and there are inconsistencies between journals. The aim of this paper is to provide a correct and integrated instruction for reporting statistical and clinical significance in medical sciences employing an estimation approach (reporting confidence interval).

کلیدواژه‌ها [English]

  • Confidence interval
  • Data interpretation
  • Effect size
  • Estimation
  • Statistics
  1. McShane BB, Gal D, Gelman A, Robert C, Tackett JL. Abandon statistical significance. Am Stat 2019; 73(S1): 235-45.
  2. Wagenmakers EJ. A practical solution to the pervasive problems of p values. Psychon Bull Rev 2007; 14(5): 779-804.
  3. Nakagawa S, Cuthill IC. Effect size, confidence interval and statistical significance: a practical guide for biologists. Biol Rev Camb Philos Soc 2007; 82(4): 591-605.
  4. Ferguson CJ. An effect size primer: a guide for clinicians and researchers. Prof Psychol Res Pr 2016; 40(5): 532-8.
  5. Figueiredo Filho DB, Paranhos R, Rocha ECd, Batista M, Silva Jr JAd, Santos MLWD, et al. When is statistical significance not significant? Bras Political Sci Rev 2013; 7(1): 31-55.
  6. Wellek S. A critical evaluation of the current “p‐value controversy”. Biom J 2017; 59(5): 854-72.
  7. Frérot M, Lefebvre A, Aho S, Callier P, Astruc K, Aho Glélé LS. What is epidemiology? Changing definitions of epidemiology 1978-2017. PloS One 2018; 13(12): e0208442.
  8. Samani RO, Almasi-Hashiani A, Vesali S, Shokri F, Cheraghi R, Torkestani F, et al. Tehran survey of potential risk factors for multiple births. Int J Fertil Steril 2017; 11(3): 220-5.
  9. Pirjani R, Hosseini R, Soori T, Rabiei M, Hosseini L, Abiri A, et al. Maternal and neonatal outcomes in COVID-19 infected pregnancies: a prospective cohort study. J Travel Med 2020; 27(7): taaa158.
  10. Karimi E, Khorvash F, Arab A, Sepidarkish M, Saadatnia M, Amani R. The effects of royal jelly supplementation on oxidative stress, inflammatory mediators, mental health, cognitive function, quality of life, and clinical outcomes of patients with ischemic stroke: study protocol for a randomized controlled trial. BMC Nutr 2023; 9(1): 32.
  11. Heshmati J, Moini A, Sepidarkish M, Morvaridzadeh M, Salehi M, Palmowski A, et al. Effects of curcumin supplementation on blood glucose, insulin resistance and androgens in patients with polycystic ovary syndrome: A randomized double-blind placebo-controlled clinical trial. Phytomedicine 2021; 80: 153395.
  12. Zhao L, Tian L, Cai T, Claggett B, Wei LJ. Effectively selecting a target population for a future comparative study. J Am Stat Assoc 2013; 108(502): 527-39.
  13. Altman DG, Bland JM. Uncertainty and sampling
    BMJ 2014; 349: g7064.
  14. Sedgwick PM. What is sampling error? BMJ 2012; 344: e4285.
  15. Nakagawa S, Cuthill IC. Effect size, confidence interval and statistical significance: a practical guide for biologists. Biol Rev Camb Philos Soc 2007; 82(4): 591-605.
  16. Borenstein M, Cooper H, Hedges L, Valentine J. Effect sizes for continuous data. In Cooper H, Hedges LV, Valentine JC, editors. The handbook of research synthesis and meta-analysis. Manhattan, NY: Russell Sage Foundation; 2009. p. 221-35.
  17. Lee DK. Alternatives to P value: confidence interval and effect size. Korean J Anesthesiol 2016; 69(6): 555-62.
  18. Xie Mg, Singh K. Confidence distribution, the frequentist distribution estimator of a parameter: A review. Int Stat Rev 2013; 81(1): 3-39.
  19. Fleischmann M, Vaughan B. Commentary: Statistical significance and clinical significance-A call to consider patient reported outcome measures, effect size, confidence interval and minimal clinically important difference (MCID). J Bodyw Mov Ther 2019; 23(4): 690-4.
  20. Martínez-Ezquerro JD, Riojas-Garza A, Rendón-Macías ME. Clinical significance vs statistical significance. How to interpret the confidence interval at 95%. Rev Alerg Mex 2017; 64(4): 477-86.
  21. Quertemont E. How to statistically show the absence of an effect. Psychologica Belgica 2011; 51(2): 109-27.
  22. Guyatt G, Jaeschke R, Heddle N, Cook D, Shannon H, Walter S. Basic statistics for clinicians: 2. Interpreting study results: confidence intervals. CMAJ 1995; 152(2): 169-73.
  23. Brahman LE. Confidence intervals assess both clinical significance and statistical significance. ACP 1991; 114(6): 515-7.
  24. Prentice RL. Discussion: On the role and analysis of secondary outcomes in clinical trials. Control Clin Trials 1997; 18(6): 561-7.
  25. Ferreira JC, Patino CM. Types of outcomes in clinical research. J Bras Pneumol 2017; 43(1): 5.
  26. Norton EC, Dowd BE, Maciejewski ML. Odds ratios-current best practice and use. JAMA 2018; 320(1): 84-5.
  27. Sedgwick P, Joekes K. Interpreting hazard ratios. BMJ 2015; 351: h4631.
  28. Alizadeh Khatir A, Sepidarkish M, Rajabalizadeh MR, Alizadeh Moghaddam S, Aghapour S, Mehravar S, et al. Case-control study to assess the association between epilepsy and toxocara Infection/Exposure. Microorganisms 2021; 9(10): 2091.
  29. Akhavan S, Ghahghaei-Nezamabadi A, Modaresgilani M, Mousavi AS, Sepidarkish M, Tehranian A, et al. Impact of diabetes mellitus on epithelial ovarian cancer survival. BMC Cancer 2018; 18(1): 1246.
  30. Schouten BC, Meeuwesen L. Cultural differences in medical communication: a review of the literature. Patient Educ Couns 2006; 64(1-3): 21-34.
  31. Bowling A, Ebrahim S. Measuring patients' preferences for treatment and perceptions of risk. Qual Health Care 2001; 10(Suppl 1): i2-8.
  32. Guyatt GH, Haynes RB, Jaeschke RZ, Cook DJ, Green L, Naylor CD, et al. Users' guides to the medical literature: XXV. Evidence-based medicine: principles for applying the users' guides to patient
    JAMA 2000; 284(10): 1290-6.
  33. McColl A, Smith H, White P, Field J. General practitioners' perceptions of the route to evidence based medicine: a questionnaire survey. BMJ 1998; 316(7128): 361-5.
  34. Emanuel EJ, Emanuel LL. Four models of the physician-patient relationship. JAMA 1992; 267(16): 2221-6.
  35. Stewart MA. Effective physician-patient communication and health outcomes: a review. CMAJ 1995; 152(9): 1423-33.
  36. Swift JK, Callahan JL. The impact of client treatment preferences on outcome: A meta‐ J Clin Psychol 2009; 65(4): 368-81.
  37. Siminoff LA. Incorporating patient and family preferences into evidence-based medicine. BMC Med Inform Decis Mak 2013; 13(Suppl 3): S6.