Related Experiment Video
Updated: Oct 23, 2025
A High-Throughput Multiplexed Screening for Type 1 Diabetes, Celiac Diseases, and COVID-19
Published on: July 5, 2022
Data-driven identification of temporal glucose patterns in a large cohort of nondiabetic patients with COVID-19 using
Sejal Mistry1, Ramkiran Gouripeddi1, Julio C Facelli1
1Department of Biomedical Informatics, University of Utah, Salt Lake City, Utah, USA.
Insights
This study analyzed blood glucose in nondiabetic COVID-19 patients, revealing distinct glucose patterns. These patterns indicate subclinical dysfunction and increased risk for new-onset diabetes following infection.
Area of Science:
- Endocrinology
- Infectious Diseases
- Data Science
Background:
- Hyperglycemia is a known complication of coronavirus disease 2019 (COVID-19).
- It remains unclear if these glycemic changes are specific to certain patient groups or persist after COVID-19 recovery.
- The role of COVID-19 in diabetes pathogenesis requires further investigation.
Purpose of the Study:
- To characterize longitudinal random blood glucose levels in a large cohort of nondiabetic patients diagnosed with COVID-19.
- To identify distinct patterns of glucose trajectories following COVID-19 infection.
- To explore associations between glucose patterns and clinical factors.
Main Methods:
- Utilized de-identified electronic medical records of 7502 nondiabetic COVID-19 patients.
- Extracted glucose measurements, demographics, and clinical data before, during, and after COVID-19 diagnosis.
- Applied unsupervised time-series clustering to identify glucose trajectory clusters and analyzed their associations with clinical variables.
Main Results:
- Time-series clustering identified distinct glucose trajectory patterns.
- Cluster membership significantly correlated with mortality, COVID-19 severity, and glucose levels.
- In a more complex model, clusters also differed by age, sex, and new-onset diabetes mellitus.
Conclusions:
- Identified distinct longitudinal blood glucose changes in nondiabetic COVID-19 patients.
- Findings suggest subclinical glucose dysfunction and an increased incidence of new-onset diabetes.
- Highlights the utility of data-driven approaches in understanding COVID-19's impact on glycemic control and potential role in diabetes pathogenesis.
Objective:
Hyperglycemia has emerged as an important clinical manifestation of coronavirus disease 2019 (COVID-19) in diabetic and nondiabetic patients. Whether these glycemic changes are specific to a subgroup of patients and persist following COVID-19 resolution remains to be elucidated. This work aimed to characterize longitudinal random blood glucose in a large cohort of nondiabetic patients diagnosed with COVID-19.
Materials And Methods:
De-identified electronic medical records of 7502 patients diagnosed with COVID-19 without prior diagnosis of diabetes between January 1, 2020, and November 18, 2020, were accessed through the TriNetX Research Network. Glucose measurements, diagnostic codes, medication codes, laboratory values, vital signs, and demographics were extracted before, during, and after COVID-19 diagnosis. Unsupervised time-series clustering algorithms were trained to identify distinct clusters of glucose trajectories. Cluster associations were tested for demographic variables, COVID-19 severity, glucose-altering medications, glucose values, and new-onset diabetes diagnoses.
Results:
Time-series clustering identified a low-complexity model with 3 clusters and a high-complexity model with 19 clusters as the best-performing models. In both models, cluster membership differed significantly by death status, COVID-19 severity, and glucose levels. Clusters membership in the 19 cluster model also differed significantly by age, sex, and new-onset diabetes mellitus.
Discussion And Conclusion:
This work identified distinct longitudinal blood glucose changes associated with subclinical glucose dysfunction in the low-complexity model and increased new-onset diabetes incidence in the high-complexity model. Together, these findings highlight the utility of data-driven techniques to elucidate longitudinal glycemic dysfunction in patients with COVID-19 and provide clinical evidence for further evaluation of the role of COVID-19 in diabetes pathogenesis.
