Use of days alive without life support and similar count outcomes in randomised clinical trials - an overview and comparison of methodological choices and analysis methods
© 2023. The Author(s)..
BACKGROUND: Days alive without life support (DAWOLS) and similar outcomes that seek to summarise mortality and non-mortality experiences are increasingly used in critical care research. The use of these outcomes is challenged by different definitions and non-normal outcome distributions that complicate statistical analysis decisions.
METHODS: We scrutinized the central methodological considerations when using DAWOLS and similar outcomes and provide a description and overview of the pros and cons of various statistical methods for analysis supplemented with a comparison of these methods using data from the COVID STEROID 2 randomised clinical trial. We focused on readily available regression models of increasing complexity (linear, hurdle-negative binomial, zero-one-inflated beta, and cumulative logistic regression models) that allow comparison of multiple treatment arms, adjustment for covariates and interaction terms to assess treatment effect heterogeneity.
RESULTS: In general, the simpler models adequately estimated group means despite not fitting the data well enough to mimic the input data. The more complex models better fitted and thus better replicated the input data, although this came with increased complexity and uncertainty of estimates. While the more complex models can model separate components of the outcome distributions (i.e., the probability of having zero DAWOLS), this complexity means that the specification of interpretable priors in a Bayesian setting is difficult. Finally, we present multiple examples of how these outcomes may be visualised to aid assessment and interpretation.
CONCLUSIONS: This summary of central methodological considerations when using, defining, and analysing DAWOLS and similar outcomes may help researchers choose the definition and analysis method that best fits their planned studies.
TRIAL REGISTRATION: COVID STEROID 2 trial, ClinicalTrials.gov: NCT04509973, ctri.nic.in: CTRI/2020/10/028731.
Medienart: |
E-Artikel |
---|
Erscheinungsjahr: |
2023 |
---|---|
Erschienen: |
2023 |
Enthalten in: |
Zur Gesamtaufnahme - volume:23 |
---|---|
Enthalten in: |
BMC medical research methodology - 23(2023), 1 vom: 14. Juni, Seite 139 |
Sprache: |
Englisch |
---|
Beteiligte Personen: |
Granholm, Anders [VerfasserIn] |
---|
Links: |
---|
Themen: |
Analysis methods |
---|
Anmerkungen: |
Date Completed 16.06.2023 Date Revised 20.06.2023 published: Electronic ClinicalTrials.gov: NCT04509973 CTRI: CTRI/2020/10/028731 Citation Status MEDLINE |
---|
doi: |
10.1186/s12874-023-01963-z |
---|
funding: |
|
---|---|
Förderinstitution / Projekttitel: |
|
PPN (Katalog-ID): |
NLM35818388X |
---|
LEADER | 01000naa a22002652 4500 | ||
---|---|---|---|
001 | NLM35818388X | ||
003 | DE-627 | ||
005 | 20231226074213.0 | ||
007 | cr uuu---uuuuu | ||
008 | 231226s2023 xx |||||o 00| ||eng c | ||
024 | 7 | |a 10.1186/s12874-023-01963-z |2 doi | |
028 | 5 | 2 | |a pubmed24n1193.xml |
035 | |a (DE-627)NLM35818388X | ||
035 | |a (NLM)37316785 | ||
040 | |a DE-627 |b ger |c DE-627 |e rakwb | ||
041 | |a eng | ||
100 | 1 | |a Granholm, Anders |e verfasserin |4 aut | |
245 | 1 | 0 | |a Use of days alive without life support and similar count outcomes in randomised clinical trials - an overview and comparison of methodological choices and analysis methods |
264 | 1 | |c 2023 | |
336 | |a Text |b txt |2 rdacontent | ||
337 | |a ƒaComputermedien |b c |2 rdamedia | ||
338 | |a ƒa Online-Ressource |b cr |2 rdacarrier | ||
500 | |a Date Completed 16.06.2023 | ||
500 | |a Date Revised 20.06.2023 | ||
500 | |a published: Electronic | ||
500 | |a ClinicalTrials.gov: NCT04509973 | ||
500 | |a CTRI: CTRI/2020/10/028731 | ||
500 | |a Citation Status MEDLINE | ||
520 | |a © 2023. The Author(s). | ||
520 | |a BACKGROUND: Days alive without life support (DAWOLS) and similar outcomes that seek to summarise mortality and non-mortality experiences are increasingly used in critical care research. The use of these outcomes is challenged by different definitions and non-normal outcome distributions that complicate statistical analysis decisions | ||
520 | |a METHODS: We scrutinized the central methodological considerations when using DAWOLS and similar outcomes and provide a description and overview of the pros and cons of various statistical methods for analysis supplemented with a comparison of these methods using data from the COVID STEROID 2 randomised clinical trial. We focused on readily available regression models of increasing complexity (linear, hurdle-negative binomial, zero-one-inflated beta, and cumulative logistic regression models) that allow comparison of multiple treatment arms, adjustment for covariates and interaction terms to assess treatment effect heterogeneity | ||
520 | |a RESULTS: In general, the simpler models adequately estimated group means despite not fitting the data well enough to mimic the input data. The more complex models better fitted and thus better replicated the input data, although this came with increased complexity and uncertainty of estimates. While the more complex models can model separate components of the outcome distributions (i.e., the probability of having zero DAWOLS), this complexity means that the specification of interpretable priors in a Bayesian setting is difficult. Finally, we present multiple examples of how these outcomes may be visualised to aid assessment and interpretation | ||
520 | |a CONCLUSIONS: This summary of central methodological considerations when using, defining, and analysing DAWOLS and similar outcomes may help researchers choose the definition and analysis method that best fits their planned studies | ||
520 | |a TRIAL REGISTRATION: COVID STEROID 2 trial, ClinicalTrials.gov: NCT04509973, ctri.nic.in: CTRI/2020/10/028731 | ||
650 | 4 | |a Randomized Controlled Trial | |
650 | 4 | |a Journal Article | |
650 | 4 | |a Research Support, Non-U.S. Gov't | |
650 | 4 | |a Analysis methods | |
650 | 4 | |a Count outcomes | |
650 | 4 | |a Days alive out of hospital | |
650 | 4 | |a Days alive without life support | |
650 | 4 | |a Statistical models | |
700 | 1 | |a Kaas-Hansen, Benjamin Skov |e verfasserin |4 aut | |
700 | 1 | |a Lange, Theis |e verfasserin |4 aut | |
700 | 1 | |a Munch, Marie Warrer |e verfasserin |4 aut | |
700 | 1 | |a Harhay, Michael O |e verfasserin |4 aut | |
700 | 1 | |a Zampieri, Fernando G |e verfasserin |4 aut | |
700 | 1 | |a Perner, Anders |e verfasserin |4 aut | |
700 | 1 | |a Møller, Morten Hylander |e verfasserin |4 aut | |
700 | 1 | |a Jensen, Aksel Karl Georg |e verfasserin |4 aut | |
773 | 0 | 8 | |i Enthalten in |t BMC medical research methodology |d 2001 |g 23(2023), 1 vom: 14. Juni, Seite 139 |w (DE-627)NLM111431921 |x 1471-2288 |7 nnns |
773 | 1 | 8 | |g volume:23 |g year:2023 |g number:1 |g day:14 |g month:06 |g pages:139 |
856 | 4 | 0 | |u http://dx.doi.org/10.1186/s12874-023-01963-z |3 Volltext |
912 | |a GBV_USEFLAG_A | ||
912 | |a GBV_NLM | ||
951 | |a AR | ||
952 | |d 23 |j 2023 |e 1 |b 14 |c 06 |h 139 |