# Clinical outcomes and predictive modeling in COVID-19 patients with type 2 diabetes mellitus: a multicenter retrospective cohort study

## TL;DR

This study shows that type 2 diabetes worsens outcomes in COVID-19 patients and creates a model to predict ICU admission.

## Contribution

A predictive model for ICU admission in T2DM patients with COVID-19 using neutrophil count and lactate dehydrogenase.

## Key findings

- T2DM patients had higher inflammatory markers and ICU admission rates.
- Neutrophil count and lactate dehydrogenase are independent risk factors for ICU admission.
- The predictive model offers clinical utility for managing T2DM-COVID-19 patients.

## Abstract

This study aimed to assess the influence of type 2 diabetes mellitus (T2DM) on clinical features and adverse outcomes in COVID-19 patients and to develop a predictive model for adverse outcomes in this population.

A retrospective analysis was conducted from December 2022 to February 2023, involving 1058 COVID-19 inpatients at two hospitals. Patients were divided into T2DM (n = 363) and non-T2DM (n = 695) groups. Demographic and laboratory data were collected, and univariate analyses were performed. Logistic regression analysis was employed to identify risk factors associated with ICU admission, and a predictive model was constructed and validated using ROC curves.

T2DM patients exhibited higher levels of certain inflammatory and biochemical markers and a greater incidence of ICU admission compared to non-T2DM patients. Neutrophil count and lactate dehydrogenase were identified as independent risk factors for ICU admission.

T2DM is associated with increased levels of inflammatory and biochemical markers and a higher risk of ICU admission in COVID-19 patients. The predictive model, incorporating neutrophil count and lactate dehydrogenase, offers clinical utility. The study’s findings can inform clinical strategies for managing COVID-19 patients with T2DM, particularly in predicting and mitigating adverse outcomes.