Higher admission activated partial thromboplastin time, neutrophil-lymphocyte ratio, serum sodium, and anticoagulant use predict in-hospital COVID-19 mortality in people with Diabetes: Findings from Two University Hospitals in the U.K

Abstract

This is a PDF file of an article that has undergone enhancements after acceptance, such as the addition of a cover page and metadata, and formatting for readability, but it is not yet the definitive version of record. This version will undergo additional copyediting, typesetting and review before it is published in its final form, but we are providing this version to give early visibility of the article. Please note that, during the production process, errors may be discovered which could affect the content, and all legal disclaimers that apply to the journal pertain.

COVID-19 mortality risk assessments for individuals with and without diabetes mellitus: Machine learning models integrated with interpretation framework

“…The two categorical variables NLRL (neutrophils-lymphocytes ratio labelled) and APTTL (activated partial thromboplastin time labelled), shown in Table 3 , were created and added to the feature set by binning corresponding numerical variables. A previous study confirmed the association between these two characteristics and in-hospital COVID-19 mortality in DM patients [ 9 ]. For generating the NLRL feature, NLR values less than eight were labelled as ‘low’, while those greater than eight were labelled as ‘high’.…”

“…A comprehensive description of the dataset alongside a detailed explanation of the data collection process can be found in Ref. [ 9 ]. In line with previous COVID-19 research on individuals with DM [ 9 ], in this study, patients with type 1 and type 2 DM were combined in one cohort (DM cohort) and those without diabetes in another cohort (non-DM cohort).…”

“…[ 9 ]. In line with previous COVID-19 research on individuals with DM [ 9 ], in this study, patients with type 1 and type 2 DM were combined in one cohort (DM cohort) and those without diabetes in another cohort (non-DM cohort). Table 1 summarises admission outcomes for DM and non-DM cohorts.…”

“…A comprehensive statistical analysis of the data presented in the table can be found in Ref. [ 9 ]. The current study leverages ML techniques to determine in-hospital COVID-19 mortality risk.…”

“…Such studies aim to identify distinctive characteristics of COVID-19 patients with DM, thereby advancing our understanding of their increased vulnerability. In this respect, several comparative risk assessment studies in COVID-19 patients with and without DM have been conducted [ [8] , [9] , [10] ]. These studies effectively distinguished risk predictions and risk factors for COVID-19 patients with and without DM, primarily through standard statistical analysis.…”