{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,16]],"date-time":"2026-07-16T17:28:04Z","timestamp":1784222884690,"version":"3.55.0"},"reference-count":23,"publisher":"BMJ","issue":"11","license":[{"start":{"date-parts":[[2021,11,9]],"date-time":"2021-11-09T00:00:00Z","timestamp":1636416000000},"content-version":"unspecified","delay-in-days":8,"URL":"http:\/\/creativecommons.org\/licenses\/by-nc\/4.0\/"}],"content-domain":{"domain":["bmj.com"],"crossmark-restriction":true},"short-container-title":["BMJ Open"],"accepted":{"date-parts":[[2021,10,13]]},"published-print":{"date-parts":[[2021,11]]},"abstract":"<jats:sec>\n                  <jats:title>Introduction and motivation<\/jats:title>\n                  <jats:p>Many health studies measure a continuous outcome and compare means between groups. Since means for biological data are often difficult to interpret clinically, it is common to dichotomise using a cut-point and present the \u2018percentage abnormal\u2019 alongside or in place of means. Examples include birthweight where \u2018abnormal\u2019 is defined as &lt;2500 g (low birthweight), systolic blood pressure with abnormal defined as &gt;140 mm Hg (high blood pressure) and lung function with varying definitions of the \u2018limit of normal\u2019. In vulnerable populations with low means, for example, birthweight in a population of preterm babies, a given difference in means between two groups will represent a larger difference in the percentage with low birthweight than in a general population of babies where most will be full term. Thus, in general, the difference in percentage of patients with abnormal values for a given difference in means varies according to the reference population\u2019s mean value. This phenomenon leads to challenges in interpreting differences in means in vulnerable populations and in defining an outcome-specific minimal clinically important difference (MCID) in means since the proportion abnormal, which is useful in interpreting means, is not constant\u2014it varies with the population mean. This has relevance for study power calculations and data analyses in vulnerable populations where a small observed difference in means may be difficult to interpret clinically and may be disregarded, even if associated with a relatively large difference in percentage abnormal which is clinically relevant.<\/jats:p>\n               <\/jats:sec>\n               <jats:sec>\n                  <jats:title>Methods<\/jats:title>\n                  <jats:p>To address these issues, we suggest both difference in means and difference in percentage (proportion) abnormal are considered when choosing the MCID, and that both means and percentages abnormal are reported when analysing the data.<\/jats:p>\n               <\/jats:sec>\n               <jats:sec>\n                  <jats:title>Conclusions<\/jats:title>\n                  <jats:p>We describe a distributional approach to analyse proportions classified as abnormal that avoids the usual loss of precision and power associated with dichotomisation.<\/jats:p>\n               <\/jats:sec>","DOI":"10.1136\/bmjopen-2021-052338","type":"journal-article","created":{"date-parts":[[2021,11,9]],"date-time":"2021-11-09T11:32:26Z","timestamp":1636457546000},"page":"e052338","update-policy":"https:\/\/doi.org\/10.1136\/crossmarkpolicy","source":"Crossref","is-referenced-by-count":13,"title":["Minimal clinically important difference in means in vulnerable populations: challenges and solutions"],"prefix":"10.1136","volume":"11","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-0310-2518","authenticated-orcid":false,"given":"Janet L","family":"Peacock","sequence":"first","affiliation":[{"name":"Department of Epidemiology, Geisel School of Medicine at Dartmouth, Hanover, New Hampshire, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jessica","family":"Lo","sequence":"additional","affiliation":[{"name":"Centre for Healthy Brain Ageing, University of New South Wales, Sydney, New South Wales, Australia"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Judith R","family":"Rees","sequence":"additional","affiliation":[{"name":"Department of Epidemiology, Geisel School of Medicine at Dartmouth, Hanover, New Hampshire, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1029-8846","authenticated-orcid":false,"given":"Odile","family":"Sauzet","sequence":"additional","affiliation":[{"name":"Epidemiology and International Public Health, Bielefeld School of Public Health, Bielefeld University, Bielefeld, Germany"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"239","published-online":{"date-parts":[[2021,11,9]]},"reference":[{"key":"2025101813453213000_11.11.e052338.1","doi-asserted-by":"publisher","DOI":"10.1016\/0197-2456(89)90005-6"},{"key":"2025101813453213000_11.11.e052338.2","doi-asserted-by":"publisher","DOI":"10.1016\/j.jpain.2007.09.005"},{"key":"2025101813453213000_11.11.e052338.3","doi-asserted-by":"publisher","DOI":"10.1097\/00005650-200305000-00004"},{"key":"2025101813453213000_11.11.e052338.4","doi-asserted-by":"publisher","DOI":"10.1081\/COPD-200051363"},{"key":"2025101813453213000_11.11.e052338.5","doi-asserted-by":"publisher","DOI":"10.1111\/jep.12629"},{"key":"2025101813453213000_11.11.e052338.6","unstructured":"Cohen J . Statistical power analysis for the behavioral sciences. 2nd ed. Hillsdale, N.J: L. Erlbaum Associates, 1988."},{"key":"2025101813453213000_11.11.e052338.7","doi-asserted-by":"publisher","DOI":"10.1136\/bmj.298.6676.795"},{"key":"2025101813453213000_11.11.e052338.8","doi-asserted-by":"publisher","DOI":"10.1093\/ije\/14.1.32"},{"key":"2025101813453213000_11.11.e052338.9","doi-asserted-by":"publisher","DOI":"10.1183\/09031936.00080312"},{"key":"2025101813453213000_11.11.e052338.10","doi-asserted-by":"publisher","DOI":"10.1056\/NEJMoa020432"},{"key":"2025101813453213000_11.11.e052338.11","doi-asserted-by":"publisher","DOI":"10.1164\/rccm.200310-1425OC"},{"key":"2025101813453213000_11.11.e052338.12","doi-asserted-by":"publisher","DOI":"10.1136\/adc.2005.079632"},{"key":"2025101813453213000_11.11.e052338.13","doi-asserted-by":"publisher","DOI":"10.1056\/NEJMoa1309220"},{"key":"2025101813453213000_11.11.e052338.14","doi-asserted-by":"publisher","DOI":"10.1002\/sim.5354"},{"key":"2025101813453213000_11.11.e052338.15","doi-asserted-by":"crossref","DOI":"10.1186\/s12874-015-0028-8","article-title":"Dichotomisation using a distributional approach when the outcome is skewed","volume":"15","author":"Sauzet","year":"2015","journal-title":"BMC Med Res Methodol"},{"key":"2025101813453213000_11.11.e052338.16","doi-asserted-by":"crossref","first-page":"4547","DOI":"10.1002\/sim.6255","article-title":"Estimating dichotomised outcomes in two groups with unequal variances: a distributional approach","volume":"33","author":"Sauzet","year":"2014","journal-title":"Stat Med"},{"key":"2025101813453213000_11.11.e052338.17","doi-asserted-by":"crossref","DOI":"10.1186\/s12982-016-0050-2","article-title":"A distributional approach to obtain adjusted comparisons of proportions of a population at risk","volume":"13","author":"Sauzet","year":"2016","journal-title":"Emerg Themes Epidemiol"},{"key":"2025101813453213000_11.11.e052338.18","doi-asserted-by":"crossref","DOI":"10.1186\/2046-4053-3-63","article-title":"Dichotomisation of a continuous outcome and effect on meta-analyses: illustration of the distributional approach using the outcome birthweight","volume":"3","author":"Ofuya","year":"2014","journal-title":"Syst Rev"},{"key":"2025101813453213000_11.11.e052338.19","doi-asserted-by":"crossref","first-page":"880","DOI":"10.1177\/1536867X1601600405","article-title":"Distributional estimates for the comparison of proportions of a Dichotomized continuous outcome","volume":"16","author":"Sauzet","year":"2016","journal-title":"Stata J"},{"key":"2025101813453213000_11.11.e052338.20","doi-asserted-by":"publisher","DOI":"10.1164\/rccm.201310-1863PP"},{"key":"2025101813453213000_11.11.e052338.21","doi-asserted-by":"crossref","unstructured":"Cook J , Hislop J , Adewuyi T , et al . Assessing methods to specify the target difference for a randomised controlled trial: delta (difference elicitation in trials) review. Health Technol Assess 2014;18.doi:10.3310\/hta18280","DOI":"10.3310\/hta18280"},{"key":"2025101813453213000_11.11.e052338.22","doi-asserted-by":"crossref","DOI":"10.1186\/s13063-014-0526-8","article-title":"Specifying the target difference in the primary outcome for a randomised controlled trial: guidance for researchers","volume":"16","author":"Cook","year":"2015","journal-title":"Trials"},{"key":"2025101813453213000_11.11.e052338.23","doi-asserted-by":"crossref","DOI":"10.1186\/s13063-018-2884-0","article-title":"Delta2 guidance on choosing the target difference and undertaking and reporting the sample size calculation for a randomised controlled trial","volume":"19","author":"Cook","year":"2018","journal-title":"Trials"}],"container-title":["BMJ Open"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/syndication.highwire.org\/content\/doi\/10.1136\/bmjopen-2021-052338","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,10,18]],"date-time":"2025-10-18T20:45:37Z","timestamp":1760820337000},"score":1,"resource":{"primary":{"URL":"https:\/\/bmjopen.bmj.com\/lookup\/doi\/10.1136\/bmjopen-2021-052338"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021,11]]},"references-count":23,"journal-issue":{"issue":"11","published-online":{"date-parts":[[2021,11,9]]},"published-print":{"date-parts":[[2021,11]]}},"alternative-id":["10.1136\/bmjopen-2021-052338"],"URL":"https:\/\/doi.org\/10.1136\/bmjopen-2021-052338","relation":{},"ISSN":["2044-6055","2044-6055"],"issn-type":[{"value":"2044-6055","type":"print"},{"value":"2044-6055","type":"electronic"}],"subject":[],"published":{"date-parts":[[2021,11]]}}}