Evidence Based Medicine on FHIR Implementation Guide, published by HL7 International / Clinical Decision Support. This guide is not an authorized publication; it is the continuous build for version 2.0.0-ballot built by the FHIR (HL7® FHIR® Standard) CI Build. This version is based on the current content of https://github.com/HL7/ebm/ and changes regularly. See the Directory of published versions
<Evidence xmlns="http://hl7.org/fhir">
<id value="179683"/>
<meta>
<versionId value="22"/>
<lastUpdated value="2024-12-13T20:14:59.240Z"/>
<profile
value="http://hl7.org/fhir/uv/ebm/StructureDefinition/endpoint-analysis-plan"/>
</meta>
<text>
<status value="empty"/>
<div xmlns="http://www.w3.org/1999/xhtml"><p>[No data.]</p></div>
</text>
<url value="https://fevir.net/resources/Evidence/179683"/>
<identifier>
<type>
<coding>
<system value="http://terminology.hl7.org/CodeSystem/v2-0203"/>
<code value="ACSN"/>
<display value="Accession ID"/>
</coding>
<text value="FEvIR Object Identifier"/>
</type>
<system value="urn:ietf:rfc:3986"/>
<value value="https://fevir.net/FOI/179683"/>
<assigner>
<display value="Computable Publishing LLC"/>
</assigner>
</identifier>
<name
value="ADAS_Cog11_EndpointAnalysisPlan_from_PHUSE_Lilly_Redacted_Protocol_EBMonFHIR_IG_Version"/>
<title
value="ADAS-Cog(11) EndpointAnalysisPlan from PHUSE Lilly Redacted Protocol - EBMonFHIR IG Version"/>
<status value="active"/>
<publisher value="Computable Publishing LLC"/>
<contact>
<telecom>
<system value="email"/>
<value value="support@computablepublishing.com"/>
</telecom>
</contact>
<author>
<name value="Brian S. Alper"/>
</author>
<useContext>
<code>
<system value="https://fevir.net/resources/CodeSystem/179423"/>
<code value="evidence-communication"/>
<display value="Evidence Communication"/>
</code>
<valueCodeableConcept>
<coding>
<system value="https://fevir.net/resources/CodeSystem/179423"/>
<code value="EndpointAnalysisPlan"/>
<display value="EndpointAnalysisPlan"/>
</coding>
</valueCodeableConcept>
</useContext>
<copyright value="https://creativecommons.org/licenses/by-nc-sa/4.0/"/>
<relatedArtifact>
<type value="cite-as"/>
<citation
value="ADAS-Cog(11) EndpointAnalysisPlan from PHUSE Lilly Redacted Protocol - EBMonFHIR IG Version [Database Entry: FHIR Evidence Resource]. Contributors: Brian S. Alper [Authors/Creators]. In: Fast Evidence Interoperability Resources (FEvIR) Platform, FOI 179683. Revised 2024-11-16. Available at: https://fevir.net/resources/Evidence/179683. Computable resource at: https://fevir.net/resources/Evidence/179683#json."/>
</relatedArtifact>
<relatedArtifact>
<type value="supported-with"/>
<display value="Protocol attachment in associated Evidence Resource"/>
<resourceReference>🔗
<reference value="Evidence/179691"/>
<type value="Evidence"/>
<display
value="Example EndpointAnalysisPlan from PHUSE Lilly Redacted Protocol - EBMonFHIR IG Version"/>
</resourceReference>
</relatedArtifact>
<description
value="An example of an EndpointAnalysisPlan Profile which uses intended='true' and include-if extensions within Evidence.statistic.modelCharacteristic elements."/>
<note>
<text
value="Approximately 100 patients will be randomized to each of the 3 treatment groups (high dose, low dose, and placebo). Previous experience with the oral formulation of xanomeline suggests that this sample size has 90% power to detect a 3.0 mean treatment difference in ADAS-Cog (p<.05, twosided), based on a standard deviation of 6.5.
Group mean changes from baseline in the primary efficacy parameters will serve as efficacy criteria.
The primary analysis of efficacy will include only the data obtained up to and including the visit of discontinuation of study drug. Furthermore, the primary analysis will not include efficacy data obtained at any visit where the study drug was not administered in the preceding three days. Analyses that include the retrieved dropouts are considered secondary. In general, all patients will be included in all analyses of efficacy if they have a baseline measurement and at least one postrandomization measurement.
The primary analysis of ADAS-Cog (11) and CIBIC+ will be the 24-week endpoint, which is defined for each patient and variable as the last measurement obtained postrandomization (prior to protocol defined reduction in dose). a last-observation-carried-forward (LOCF). Note that the LOCF analysis at 24 weeks is the same as the endpoint analysis described previously.
The primary method to be used for the primary efficacy variables will be analysis of covariance (ANCOVA). Effects in the ANCOVA model will be the corresponding baseline score, investigator, and treatment. Investigator-by-treatment interaction will be tested in a full model prior to conducting the primary ANCOVA (see description below). Because 3 treatment groups are involved, the primary analysis will be the test for linear dose response in the ANCOVA model described in the preceding paragraph. The result is then a single p-value for ADAS-Cog.
Investigator-by-treatment interaction will be tested in a full ANCOVA or ANOVA model, which takes the models described above, and adds the interaction term to the model. Interaction will be tested at α = .10 level. When the interaction is significant at this level, the data will be examined for each individual investigator to attempt to identify the source of the significant interaction. When the interaction is not significant, this term will be dropped from the model as described above, to test for investigator and treatment main effects. By doing so, all ANCOVA and ANOVA models will be able to validly test for treatment differences without weighting each investigator equally, which is what occurs when using Type III sums of squares (cell means model) with the interaction term present in the model. This equal weighting of investigators can become a serious problem when sample sizes are dramatically different between investigators.
For all ANOVA and ANCOVA models, data collected from investigators who enrolled fewer than 3 patients in any one treatment group will be combined prior to analysis. If this combination still results in a treatment group having fewer than 3 patients in any one treatment group, then this group of patients will be combined with the next fewestenrolling investigator. In the event that there is a tie for fewest-enrolling investigator, one of these will be chosen at random by a random-number generator.
The inherent assumption of normally distributed data will be evaluated by generating output for the residuals from the full ANCOVA and ANOVA models, which include the interaction term, and by testing for normality using the Shapiro-Wilk test from PROC UNIVARIATE. In the event that the data are predominantly nonnormally distributed, analyses will also be conducted on the ranked data. This rank transformation will be applied by ranking all the data for a particular variable, across all investigators and treatments, from lowest to highest. Integer ranks will be assigned starting at 1; mean ranks will be assigned when ties occur.
All comparisons between xanomeline and placebo with respect to efficacy variables should be one-sided. The null hypothesis is that the drug is equal or worse than placebo. The alternative
hypothesis is that the drug has greater efficacy than placebo.
Different regulatory agencies require different type I error rates. Treatment differences that are significant at the .025 α-level will be declared to be “statistically significant.” When a computed p-value falls between .025 and .05, the differences will be described as “marginally statistically significant.” This approach satisfies regulatory agencies who have accepted a one-sided test at the .05 level, and other regulatory agencies who have requested a two-sided test at the .05 level, or equivalently, a one-sided test at the .025 level. In order to facilitate the review of the final study report, two-sided p-values will be presented in addition to the one-sided p-values."/>
</note>
<variableDefinition>
<description
value="high dose xanomeline vs. low dose xanomeline vs. placebo"/>
<variableRole value="exposure"/>
<comparatorCategory value="placebo"/>
<observed>🔗
<reference value="EvidenceVariable/179689"/>
<type value="EvidenceVariable"/>
<display
value="GroupAssignment: high dose xanomeline vs. low dose xanomeline vs. placebo"/>
</observed>
</variableDefinition>
<variableDefinition>
<description value="ADAS-Cog(11) at 24 weeks"/>
<variableRole value="outcome"/>
</variableDefinition>
<statistic>
<statisticType>
<coding>
<system value="http://terminology.hl7.org/CodeSystem/statistic-type"/>
<code value="0000457"/>
<display value="Mean Difference"/>
</coding>
<text value="(mean treatment difference)"/>
</statisticType>
<attributeEstimate>
<description value="p value for one-sided test"/>
<type>
<coding>
<system value="https://fevir.net/resources/CodeSystem/181513"/>
<code value="STATO:0000661"/>
<display value="p-value for one-sided test"/>
</coding>
<text value="p value for one-sided test"/>
</type>
</attributeEstimate>
<attributeEstimate>
<description value="p value for two-sided test"/>
<type>
<coding>
<system value="https://fevir.net/resources/CodeSystem/181513"/>
<code value="STATO:0000662"/>
<display value="p-value for two-sided test"/>
</coding>
<text value="p value for two-sided test"/>
</type>
</attributeEstimate>
<modelCharacteristic>
<code>
<coding>
<system value="https://fevir.net/resources/CodeSystem/181513"/>
<code value="TBD:participant-inclusion-criteria-for-analysis"/>
<display value="participant inclusion criteria for analysis"/>
</coding>
<text value="participant inclusion criteria for analysis"/>
</code>
<valueCodeableConcept>
<text
value="In general, all patients will be included in all analyses of efficacy if they have a baseline measurement and at least one postrandomization measurement."/>
</valueCodeableConcept>
<intended value="true"/>
</modelCharacteristic>
<modelCharacteristic>
<code>
<coding>
<system value="https://fevir.net/resources/CodeSystem/181513"/>
<code value="TBD:data-inclusion-criteria-for-analysis"/>
<display value="data inclusion criteria for analysis"/>
</coding>
<text value="data inclusion criteria for analysis"/>
</code>
<valueCodeableConcept>
<coding>
<system value="https://fevir.net/resources/CodeSystem/179423"/>
<code value="defined-in-text"/>
<display value="defined in text"/>
</coding>
<text
value="The primary analysis of efficacy will include only the data obtained up to and including the visit of discontinuation of study drug. Furthermore, the primary analysis will not include efficacy data obtained at any visit where the study drug was not administered in the preceding three days."/>
</valueCodeableConcept>
<intended value="true"/>
</modelCharacteristic>
<modelCharacteristic>
<code>
<coding>
<system value="https://fevir.net/resources/CodeSystem/181513"/>
<code value="TBD:handling-of-missing-endpoint-data"/>
<display value="handling of missing endpoint data"/>
</coding>
<text value="handling of missing endpoint data"/>
</code>
<valueCodeableConcept>
<coding>
<system value="https://fevir.net/resources/CodeSystem/181513"/>
<code value="TBD:single-imputation-by-LOCF"/>
<display
value="single imputation by last-observation-carried-forward (LOCF)"/>
</coding>
<text
value="single imputation by last-observation-carried-forward (LOCF)"/>
</valueCodeableConcept>
<intended value="true"/>
</modelCharacteristic>
<modelCharacteristic>
<code>
<coding>
<system value="https://fevir.net/resources/CodeSystem/181513"/>
<code value="TBD:data-inclusion-criteria-for-secondary-analysis"/>
<display value="data inclusion criteria for secondary analysis"/>
</coding>
<text value="data inclusion criteria for secondary analysis"/>
</code>
<valueCodeableConcept>
<coding>
<system value="https://fevir.net/resources/CodeSystem/179423"/>
<code value="defined-in-text"/>
<display value="defined in text"/>
</coding>
<text
value="The primary analysis of efficacy will include only the data obtained up to and including the visit of discontinuation of study drug. Furthermore, the primary analysis will not include efficacy data obtained at any visit where the study drug was not administered in the preceding three days. Analyses that include the retrieved dropouts are considered secondary."/>
</valueCodeableConcept>
<intended value="true"/>
</modelCharacteristic>
<modelCharacteristic>
<code>
<coding>
<system value="https://fevir.net/resources/CodeSystem/181513"/>
<code value="STATO:0000286"/>
<display value="one-tailed test"/>
</coding>
</code>
<intended value="true"/>
</modelCharacteristic>
<modelCharacteristic>
<code>
<coding>
<system value="https://fevir.net/resources/CodeSystem/181513"/>
<code value="TBD:0000081"/>
<display value="alpha setting"/>
</coding>
</code>
<valueQuantity>
<value value="0.025"/>
</valueQuantity>
<intended value="true"/>
</modelCharacteristic>
<modelCharacteristic>
<code>
<coding>
<system value="https://fevir.net/resources/CodeSystem/179423"/>
<code value="defined-in-text"/>
<display value="defined in text"/>
</coding>
<text value="threshold for marginal statistical significance"/>
</code>
<valueRange>
<low>
<value value="0.025"/>
</low>
<high>
<value value="0.05"/>
</high>
</valueRange>
<intended value="true"/>
</modelCharacteristic>
<modelCharacteristic>
<code>
<coding>
<system value="https://fevir.net/resources/CodeSystem/181513"/>
<code value="STATO:0000057"/>
<display value="null hypothesis"/>
</coding>
<text value="null hypothesis"/>
</code>
<valueCodeableConcept>
<coding>
<system value="https://fevir.net/resources/CodeSystem/179423"/>
<code value="defined-in-text"/>
<display value="defined in text"/>
</coding>
<text value="xanomeline is equal or worse than placebo"/>
</valueCodeableConcept>
<intended value="true"/>
</modelCharacteristic>
<modelCharacteristic>
<code>
<coding>
<system value="https://fevir.net/resources/CodeSystem/181513"/>
<code value="STATO:0000208"/>
<display value="alternative hypothesis"/>
</coding>
<text value="alternative hypothesis"/>
</code>
<valueCodeableConcept>
<coding>
<system value="https://fevir.net/resources/CodeSystem/179423"/>
<code value="defined-in-text"/>
<display value="defined in text"/>
</coding>
<text value="xanomeline has greater efficacy than placebo"/>
</valueCodeableConcept>
<intended value="true"/>
</modelCharacteristic>
<modelCharacteristic>
<code>
<coding>
<system value="https://fevir.net/resources/CodeSystem/181513"/>
<code value="TBD:statistical-software-package"/>
<display value="statistical software package"/>
</coding>
<text value="statistical software package"/>
</code>
<valueCodeableConcept>
<coding>
<system value="https://fevir.net/resources/CodeSystem/179423"/>
<code value="defined-in-text"/>
<display value="defined in text"/>
</coding>
<text value="SAS"/>
</valueCodeableConcept>
<intended value="true"/>
</modelCharacteristic>
<modelCharacteristic>
<code>
<coding>
<system value="https://fevir.net/resources/CodeSystem/181513"/>
<code value="TBD:sample-size"/>
<display value="Sample size estimation"/>
</coding>
<text
value="Sample Size/Power Calculation ~ 90% power to detect a 3.0 mean treatment difference in ADAS-Cog (p<.05, twosided), based on a standard deviation of 6.5 and sample size of 100 patients in each of 3 groups"/>
</code>
<intended value="true"/>
<attribute>
<description value="90% power"/>
<type>
<coding>
<system value="https://fevir.net/resources/CodeSystem/181513"/>
<code value="STATO:0000200"/>
<display value="Power"/>
</coding>
<text value="power"/>
</type>
<quantity>
<value value="90"/>
<unit value="%"/>
<system value="http://unitsofmeasure.org"/>
<code value="%"/>
</quantity>
</attribute>
<attribute>
<description value="minimally detectable threshold value 3.0"/>
<type>
<coding>
<system value="https://fevir.net/resources/CodeSystem/181513"/>
<code value="TBD:checkIfInSTATOtesting-margin"/>
<display value="Hypothesis testing margin"/>
</coding>
<text value="minimally detectable threshold value"/>
</type>
<quantity>
<value value="3"/>
</quantity>
</attribute>
<attribute>
<description value="p<.05"/>
<type>
<coding>
<system value="https://fevir.net/resources/CodeSystem/181513"/>
<code value="TBD:0000081"/>
<display value="alpha setting"/>
</coding>
</type>
<quantity>
<value value="0.05"/>
</quantity>
</attribute>
<attribute>
<description value="standard deviation of 6.5"/>
<type>
<coding>
<system value="https://fevir.net/resources/CodeSystem/181513"/>
<code value="STATO:0000237"/>
<display value="Standard deviation"/>
</coding>
</type>
<quantity>
<value value="6.5"/>
</quantity>
</attribute>
<attribute>
<description value="sample size of 100 patients in each of 3 groups"/>
<type>
<coding>
<system value="https://fevir.net/resources/CodeSystem/181513"/>
<code value="TBD:sample-size-per-group"/>
<display value="sample size per group"/>
</coding>
</type>
<quantity>
<value value="100"/>
</quantity>
</attribute>
<attribute>
<description value="two-tailed test"/>
<type>
<coding>
<system value="https://fevir.net/resources/CodeSystem/181513"/>
<code value="STATO:0000287"/>
<display value="two-tailed test"/>
</coding>
</type>
</attribute>
<attribute>
<description
value="sample permutation testing - Because there will be roughly 300!/(3 * 100!) possible permutations of the data, random data permutations will be sampled (10,000 random permutations). -- distribution assumption for comparison if random"/>
<type>
<coding>
<system value="https://fevir.net/resources/CodeSystem/181513"/>
<code value="TBD:prospective-sample-permutation-testing"/>
<display value="prospective sample permutation testing"/>
</coding>
<text value="prospective sample permutation testing"/>
</type>
<attributeEstimate>
<type>
<coding>
<system value="https://fevir.net/resources/CodeSystem/181513"/>
<code value="TBD:number-of-permutations-sampled"/>
<display value="number of permutations sampled"/>
</coding>
<text value="number of permutations sampled"/>
</type>
<quantity>
<value value="10000"/>
</quantity>
</attributeEstimate>
<attributeEstimate>
<type>
<coding>
<system value="https://fevir.net/resources/CodeSystem/179423"/>
<code value="defined-in-text"/>
<display value="defined in text"/>
</coding>
<text value="allocation ratio 1:1:1"/>
</type>
</attributeEstimate>
</attribute>
</modelCharacteristic>
<modelCharacteristic>
<code>
<coding>
<system value="https://fevir.net/resources/CodeSystem/181513"/>
<code value="TBD:primary-analytic-method"/>
<display value="primary analytic method"/>
</coding>
<text value="Primary analytic method"/>
</code>
<valueCodeableConcept>
<coding>
<system value="https://fevir.net/resources/CodeSystem/181513"/>
<code value="TBD:ANCOVA"/>
<display value="ANCOVA"/>
</coding>
<text value="analysis of covariance (ANCOVA)"/>
</valueCodeableConcept>
<intended value="true"/>
<variable>
<variableDefinition>
<display value="baseline ADAS-Cog(11) score"/>
</variableDefinition>
<handling value="continuous"/>
</variable>
<variable>
<variableDefinition>🔗
<reference value="EvidenceVariable/159673"/>
<type value="EvidenceVariable"/>
<display value="investigator"/>
</variableDefinition>
<handling value="polychotomous"/>
</variable>
<variable>
<variableDefinition>
<display value="treatment"/>
</variableDefinition>
<handling value="ordinal"/>
<valueCategory>
<text value="high dose xanomeline"/>
</valueCategory>
<valueCategory>
<text value="low dose xanomeline"/>
</valueCategory>
<valueCategory>
<text value="placebo"/>
</valueCategory>
</variable>
<variable>
<extension
url="http://hl7.org/fhir/uv/ebm/StructureDefinition/statistic-model-include-if">
<extension url="attribute">
<valueCodeableConcept>
<text value="p value for F test"/>
</valueCodeableConcept>
</extension>
<extension url="value">
<valueQuantity>
<value value="0.1"/>
<comparator value="<"/>
</valueQuantity>
</extension>
</extension>
<variableDefinition>🔗
<reference value="EvidenceVariable/156673"/>
<type value="EvidenceVariable"/>
<display value="Investigator-by-treatment interaction"/>
</variableDefinition>
<handling value="polychotomous"/>
</variable>
</modelCharacteristic>
<modelCharacteristic>
<extension
url="http://hl7.org/fhir/uv/ebm/StructureDefinition/statistic-model-include-if">
<extension url="attribute">
<valueCodeableConcept>
<text value="Defined by Expression"/>
</valueCodeableConcept>
</extension>
<extension url="value">
<valueExpression>
<description
value="When the Investigator-by-treatment interaction (p value for F test) is significant at the 0.1 level"/>
<language value="TBD-rewrite in CQL or FHIRPath"/>
<expression
value="Evidence[id='156984'].statistic[statisticType='F test'].attributeEstimate[type='p value'].quantity < 0.1"/>
</valueExpression>
</extension>
</extension>
<code>
<coding>
<system value="https://fevir.net/resources/CodeSystem/179423"/>
<code value="defined-in-text"/>
<display value="defined in text"/>
</coding>
<text value="additional investigation"/>
</code>
<valueCodeableConcept>
<coding>
<system value="https://fevir.net/resources/CodeSystem/181513"/>
<code value="TBD:identify-source-of-interaction"/>
<display value="identify source(s) of significant interaction"/>
</coding>
<text
value="the data will be examined for each individual investigator [EvidenceVariable/159673] to attempt to identify the source of the significant interaction."/>
</valueCodeableConcept>
<intended value="true"/>
<variable>
<variableDefinition>🔗
<reference value="EvidenceVariable/159673"/>
<type value="EvidenceVariable"/>
<display value="investigator"/>
</variableDefinition>
<handling value="polychotomous"/>
</variable>
</modelCharacteristic>
<modelCharacteristic>
<extension
url="http://hl7.org/fhir/uv/ebm/StructureDefinition/statistic-model-include-if">
<extension url="attribute">
<valueCodeableConcept>
<text value="Defined by Expression"/>
</valueCodeableConcept>
</extension>
<extension url="value">
<valueExpression>
<description
value="residuals are nonnormally distributed using the Shapiro-Wilk test from PROC UNIVARIATE"/>
<language value="TBD-rewrite in CQL or FHIRPath"/>
<expression
value="(Evidence[id='168845'].statistic[statisticType='Shapiro-Wilk test'].attributeEstimate[type='p value'].quantity < 0.05), using SAS PROC UNIVARIATE"/>
</valueExpression>
</extension>
</extension>
<code>
<coding>
<system value="https://fevir.net/resources/CodeSystem/181513"/>
<code value="TBD:rank-based-analytic-method"/>
<display value="rank-based analytic method"/>
</coding>
</code>
<valueCodeableConcept>
<text
value="Analyses will also be conducted on the ranked data. This rank transformation will be applied by ranking all the data for a particular variable, across all investigators and treatments, from lowest to highest. Integer ranks will be assigned starting at 1; mean ranks will be assigned when ties occur.."/>
</valueCodeableConcept>
<intended value="true"/>
</modelCharacteristic>
</statistic>
</Evidence>