Your English writing platform
Discover LudwigExact(6)
Standardized mortality risk ratios ranged from 1.59 for the full categorization to 1.66 for the dichotomized categorization; RR c values ranged from 1.14 under the full categorization to 1.09 under the dichotomized categorization.
This process yielded four categorizations of the comorbidity index; the full categorization plus three orders of collapsed categorization (eg, Table 1).
In all three scenarios we demonstrate the impact of collapsing upper categories of the comorbidity index on the inferences obtained under full categorization.
Under full categorization, an investigator would conclude that there was substantial confounding by comorbidity, and would choose to retain it as an adjustment or stratification variable.
Effect measure modification (modification of the RR) equaled 0.43 under full categorization, indicating that the RR associating age and mortality in the highest comorbidity stratum was 57% lower than the corresponding RR in the no-comorbidity stratum.
This value might lead an investigator to conclude that older age and comorbidity had interacted to increase mortality risk by four cases per 100 persons over the follow-up period – a measure five-fold lower in magnitude and of opposite sign to that obtained under full categorization.
Similar(53)
The three highest categories were too sparsely populated to be considered independently (together they comprised ∼1% of the persons at risk); we therefore defined our full index categorization as 0, 1, 2, 3, or ≥4 comorbidities.
Beginning with this full index categorization, comorbidity categories were sequentially collapsed by adding counts from the highest and next-highest levels, until comorbidity was ultimately categorized dichotomously (≥1 or 0 comorbidities).
The full and collapsed categorizations were applied to analyses of (1) the association between comorbidity and all-cause mortality, wherein comorbidity was the exposure; (2) the association between older age and all-cause mortality, wherein comorbidity was a candidate confounder or effect modifier.
This requires a structural similarity search methodology, which rather than looking for global topological agreement (more appropriate for categorization of full proteins or domains), identifies detailed geometric matches.
Among the theatrical offerings are "The Only Friends We Have," a comedy involving a bedbug infestation, and "StellYY," about the first child created from the genetic material of two men, and "The Last Hurrah of the Clementines," which, with prime-number mysteries, original music, eggs and an aquarium full of white yarn, eludes categorization.
Write better and faster with AI suggestions while staying true to your unique style.
Since I tried Ludwig back in 2017, I have been constantly using it in both editing and translation. Ever since, I suggest it to my translators at ProSciEditing.

Justyna Jupowicz-Kozak
CEO of Professional Science Editing for Scientists @ prosciediting.com