森林圖繪製的探討應用：以MS-Excel繪製為例

Feasibility of using Microsoft Excel to draw forest plots

10.6288/TJPH.201902_38(1).107108

蔡崇煌(CHUNG-HUANG TSAI)；蔡濬莉(JUN-LI TSAI)；王俊堯(JIUN-YAO WANG)

森林圖 ； 刺胳針 ； 統合分析 ； 新英格蘭醫學雜誌 ； forest plot ； Lancet ； meta-analysis ； N Engl J Med

台灣公共衛生雜誌

38卷1期（2019 / 02 / 22）

102 - 110

繁體中文

目標：免費之RevMan 5.3套裝軟體所畫之森林圖不易做修改，本研究嘗試用微軟Excel 2016重新製作常用統合分析軟體的分析結果及新英格蘭醫學雜誌（NEJM）發表的文獻森林圖。方法：以PubMed搜尋題目關鍵詞為“Excel＂AND＂meta analysis或meta-analysis＂、“Excel＂AND＂forest plot＂，中文資料由思博網中文電子期刊服務搜尋，關鍵字同上。並在Google搜索引擎搜尋關鍵詞為“森林圖或forest plot＂作圖法。已發表文獻所呈現的森林圖，主要參考NEJM、刺胳針等期刊的森林圖呈現法。結果：共找到4篇文獻，皆是探討如何使用Excel計算效應量及95% CI，畫森林圖皆非其重點。由期刊上搜尋到的圖形、多元迴歸分析及統合分析套裝軟體計算的結果，皆可用Excel直接畫出，且無論在線條或標記形狀，皆具有極大的修改自由性，更重要為Excel相對較常見，且不難學習。結論：使用Excel製作森林圖可以符合國際學術期刊的呈現法，且容易修改，適合研究及教學的統計實際應用。

Objectives: Forest plots drawn using the free software package RevMan 5.3 are difficult to modify. This study sought to recreate forest plots from the results of meta-analyses in published articles of the New England Journal of Medicine (NEJM) by using Microsoft Excel 2016. Methods: The topic keywords ＂Excel AND meta-analysis OR meta-analysis＂ and ＂Excel AND forest plot＂ were searched for in PubMed and a Chinese-language electronic journal service. In addition, the keyword ＂forest plot＂ was searched for using Google. Example forest plots were collected from journals such as the NEJM and Lancet. Results: Four articles were found, all of which explored how to use Excel to calculate the effect size and 95% confidence interval without particular focus on drawing forest plots. All forest plots found in the journal search could be plotted using Excel; furthermore, Excel could be used to calculate the results of the multivariate regressions in the meta-analyses. Excel provides great freedom to modify forest plots regardless of the line or shape required and is a commonly used piece of software that is easy to learn. Conclusions: Excel can be used to draw forest plots that are consistent with presentations used in journals; moreover, such plots are easily modifiable and are therefore suitable for practical application in medical research and by teaching personnel.

1. 張文蓓, WP,陳淑芬, SF(2017)。薑對癌症病人因化學藥物治療引起噁心與嘔吐之控制成效－系統性回顧暨統合分析。腫瘤護理雜誌，17，11-20。
   連結：
2. Brown, S,Hutton, B,Clifford, T(2014).A Microsoft-Excel-based tool for running and critically appraising network meta-analyses -- an overview and application of NetMetaXL.Syst Rev,3,110.
3. Look AHEAD Research Group,Wing, RR,Bolin, P(2013).Cardiovascular effects of intensive lifestyle intervention in type 2 diabetes.N Engl J Med,369,145-154.
4. Neal, B,Perkovic, V,Mahaffey, KW(2017).Canagliflozin and cardiovascular and renal events in type 2 diabetes.N Engl J Med,377,644-657.
5. Neyeloff, JL,Fuchs, SC,Moreira, LB(2012).Meta-analyses and forest plots using a microsoft excel spreadsheet: step-by-step guide focusing on descriptive data analysis.BMC Res Notes,5,52.
6. Nissen, SE,Wolski, K(2007).Effect of rosiglitazone on the risk of myocardial infarction and death from cardiovascular causes.N Engl J Med,356,2457-2471.
7. Singh, AK,Singh, R(2017).Recent cardiovascular outcome trials of antidiabetic drugs: a comparative analysis.Indian J Endocrinol Metab,21,4-10.
8. Tobias, A,Catala-Lopez, F,Roque, M(2014).Development of an Excel spreadsheet for meta-analysis of indirect and mixed treatment comparisons.Rev Esp Salud Publica,88,5-15.
9. Wanner, C,Inzucchi, SE,Lachin, JM(2016).Empagliflozin and progression of kidney disease in type 2 diabetes.N Engl J Med,375,323-334.
10. Zhang, CH,Huang, DS,Shen, D(2016).Association between serum uric acid levels and atrial fibrillation risk.Cell Physiol Biochem,38,1589-1595.
11. Zoungas, S,Arima, H,Gerstein, HC(2017).Effects of intensive glucose control on microvascular outcomes in patients with type 2 diabetes: a meta-analysis of individual participant data from randomised controlled trials.Lancet Diabetes Endocrinol,5,431-437.
12. 王峰娟, FJ,陳青山, QS,鍾倩紅, QH,李曉珍, XZ(2010)。應用Excel完成計數資料的Meta分析。循證醫學，10，115-119。
13. 張紹勳, SS(2016).Meta分析實作：使用Excel與CMA程式.台北=Taipei:五南=Wu-Nan Book Inc..

1. 蔡崇煌,林彥廷,林正介(2021)。辛普森悖論解決之道：以新英格蘭醫學雜誌之羅格列酮統合分析為例。台灣家庭醫學雜誌，31(4)，245-257。